Journal of

Marine Science
and Engineering

Review
Sustainable Maritime Transport: A Review of Intelligent
Shipping Technology and Green Port Construction Applications
Guangnian Xiao 1 , Yiqun Wang 1 , Ruijing Wu 2, *, Jinpei Li 3 and Zhaoyun Cai 4

1 School of Economics and Management, Shanghai Maritime University, Shanghai 201306, China;
[email protected] (G.X.); [email protected] (Y.W.)
2 School of International Business Administration, Shanghai International Studies University,
Shanghai 200083, China
3 School of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, China;
[email protected]
4 Department of Industrial and Manufacturing Systems Engineering, The University of Hong Kong,
Hong Kong SAR, China; [email protected]
* Correspondence: [email protected]

Abstract: With the global economy’s relentless growth and heightened environmental conscious-
ness, sustainable maritime transport emerges as a pivotal development trajectory for the shipping
sector. This study systematically analyzes 478 publications searched in the Web of Science Core
Collection, from 2000 to 2023, utilizing bibliometric methods to investigate the application areas
in sustainable development within the shipping industry. This study begins with an analysis of
annual publication trends, which reveals a substantial expansion in research endeavors within this
discipline over recent years. Subsequently, a comprehensive statistical evaluation of scholarly jour-
nals and a collaborative network assessment are conducted to pinpoint the foremost productive
journals, nations, organizations, and individual researchers. Furthermore, a keyword co-occurrence
methodology is applied to delineate the core research themes and emerging focal points within this
domain, thereby outlining potential research directions for future research. In addition, drawing
on the keyword co-occurrence analysis, the advancements in intelligent shipping technologies and
green port construction applications within sustainable maritime transport are discussed. Finally,
the review discusses the existing challenges and opportunities of sustainable maritime transport
Citation: Xiao, G.; Wang, Y.; Wu, R.;
from a theoretical and practical perspective. The research shows that, in terms of intelligent shipping
Li, J.; Cai, Z. Sustainable Maritime
technology, data security and multi-source data are the focus that people need to pay attention to in
Transport: A Review of Intelligent
the future; a trajectory prediction for different climates and different ship types is also an area for
Shipping Technology and Green Port
future research. In terms of green ports, Cold Ironing (CI) is one of the key points of the green port
Construction Applications. J. Mar. Sci.
Eng. 2024, 12, 1728. https://doi.org/
strategy, and how to drive stakeholders to build sustainable green ports efficiently and economically
10.3390/jmse12101728 is the future developmental direction. This review serves to enhance researchers’ comprehension
of the current landscape and progression trajectory of intelligent shipping technologies, thereby
Academic Editor: Mihalis Golias
fostering the continued advancement and exploration in this vital domain.
Received: 22 July 2024
Revised: 21 September 2024 Keywords: bibliometric analysis; sustainability; maritime transport; trajectory prediction; green port
Accepted: 23 September 2024
Published: 1 October 2024

1. Introduction
Copyright: © 2024 by the authors.
Shipping, the lifeblood of the global economy, carrying nearly 90% of the world’s trade
Licensee MDPI, Basel, Switzerland. in goods, is the most cost-effective and energy efficient mode of transport, and a key pillar
This article is an open access article of sustainable economic development worldwide [1]. Its main business is to undertake
distributed under the terms and the transport of the subject goods on the basis of trade demand, and transport the subject
conditions of the Creative Commons matter from the port of departure to the port of arrival [2]. With the continuous growth
Attribution (CC BY) license (https:// of global trade and the vigorous development of the marine economy, the importance of
creativecommons.org/licenses/by/ maritime transport as an important link to connect the world is self-evident. However,
4.0/). while bringing economic benefits, traditional maritime transport is also accompanied

J. Mar. Sci. Eng. 2024, 12, 1728. https://doi.org/10.3390/jmse12101728 https://www.mdpi.com/journal/jmse

J. Mar. Sci. Eng. 2024, 12, 1728 2 of 27

by environmental pollution, high energy consumption, and low operational efficiency,

which brings challenges to the marine ecological environment and global sustainable
development. Therefore, the sustainable development of maritime transport has become
an urgent problem to be solved.
In the literature search sources of this review, the literature reviews on sustainable
maritime transport are increasing year by year; the number of reviews in 2023 was nine.
It can be found that the research field mainly focuses on maritime traffic safety issues
and maritime transport emission reduction technologies. Shi et al. (2017) conducted a
comprehensive review of papers published in 19 transport journals between 2000 and
2014, and listed the research topics, research methods, and data analysis techniques of
maritime transport respectively [3]. Tian et al. (2017) reviewed the application research of
the Internet of Vehicles (IoV) in the field of shipping, discussed how IoV technology can
improve the level of ship intelligence, operational efficiency and navigation safety, and
pointed out the technical obstacles to the application of ad hoc network technology in the
ocean environment and the shortcomings of the existing research in solving long-distance
communication problems [4]. Parhamfar et al. (2023) mainly explored the economic advan-
tages of offshore wind in green ports compared to other renewable energy technologies,
and outlined a variety of renewable energy technologies that are compatible with ports [5].
Huang et al. (2023) comprehensively reviewed various decarbonization technologies, and
by comparing the emission reduction potential and the economic feasibility of various
technologies, they showed that alternative fuels and hybrid power systems have great
potential in reducing carbon emissions and improving sustainability, and the emission
reduction potential can be further improved by combining alternative fuels with hybrid
power systems with high control flexibility [6]. Employing 491 articles on marine accidents,
Cao et al. (2023) demonstrated that human factor analyses of remote control ships and
accident prevention in Arctic waters have become research hotspots, while innovative
methodologies like machine learning and big data mining have also shown substantial
insights in elucidating marine accident causation [7]. Xu et al. (2023) directed their atten-
tion towards the domain of maritime transport safety management and crisis response,
discovering that technologies driven by data or intelligence, including scenario modeling,
digital replicas, and data-based simulations, held the potential to bolster the development
of resilient maritime transport systems [8].
In this context, with the increasing importance of globalization and environmental
sustainability, the sustainable development of maritime transport as a major mode of
international trade is particularly important [9]. At the same time, the two directions of
intelligent shipping technology and green port construction have also become the key
driving forces to promote the sustainable development of maritime transport. This study
aims to review the application status, technical characteristics and future developmental
trend of intelligent shipping technology and green port construction in sustainable maritime
transport. By systematically combing and analyzing academic literature in related fields, we
can better understand the important role of intelligent shipping technology and green port
construction in maritime transport; we can also provide valuable references for relevant
policy formulation, technology research and development, and industrial development.
The rest of this study is organized as follows: Section 2 provides an overview of data
collection and research methods. Section 3 introduces the bibliometric analysis and research
results. Based on the analysis results of bibliometric methods, Section 4 summarizes and an-
alyzes the hot research areas of intelligent shipping technology and green port construction.
Section 5 presents the challenges and opportunities for the future of sustainable maritime
transport, taking into account current technological trends and market demands. Section 6
provides conclusions.
J. Mar. Sci. Eng. 2024, 12, x FOR PEER REVIEW 3 of 27
J. Mar. Sci. Eng. 2024, 12, 1728 3 of 27

2. Research Methods and Data Collection

2. Research Methods and Data Collection
2.1. Bibliometric Method
2.1. Bibliometric Method
The
Thebibliometrics
bibliometricsmethod,
method,originally
originallyconceptualized
conceptualizedby byPritchard
Pritchardin in1969,
1969,serves
servesas asaa
literature evaluation method utilizing statistical means to undertake
literature evaluation method utilizing statistical means to undertake a thorough quanti- a thorough quantita-
tive assessment
tative assessment of of
thetheresearch
research articles
articlespublished
publishedwithinwithina aparticular
particulardiscipline
discipline[10]. [10].ByBy
visualizing
visualizing massive data sets and enabling the visualization of broad data collections,this
massive data sets and enabling the visualization of broad data collections, this
review
reviewmakes
makesititeasier
easierto tomap
mapthethepresent
presentstate,
state,subjects,
subjects,and andboundaries
boundariesfor forthe
theareaareaofof
study, and helps academics understand the discipline’s dynamic attributes
study, and helps academics understand the discipline’s dynamic attributes and structural and structural
framework
framework [11].
[11]. In comparison to
In comparison toalternative
alternativeliterature
literaturereview
reviewmethodologies,
methodologies, thethe ad-
advan-
vantage of bibliometrics lies in its capacity to yield more impartial and
tage of bibliometrics lies in its capacity to yield more impartial and trustworthy outcomes, trustworthy out-
comes,
therebythereby furnishing
furnishing researchersresearchers with a comprehensive
with a comprehensive understanding
understanding of the ad-
of the advancements
vancements within
within a specific a specific
domain [12].domain [12]. Ashas
As shipping shipping
grownhas moregrown
slowlymore
thanslowly
otherthan other
transport
transport systems
systems like like airplanes,
airplanes, railroads,railroads,
and cars,and cars, application
application research forresearch
marine forintelligent
marine intelli-
trans-
gent
porttransport
systems in systems
shipping in shipping
likewise likewise began
began later thanlater than
other other transport
transport systems.systems. Bibli-
Bibliometrics
ometrics can to
can be used be gain
usedatomore gaincomprehensive
a more comprehensive understanding
understanding of the research
of the research status and status
the
and the impending developmental trajectory within this field. This review
impending developmental trajectory within this field. This review constructs a comprehen- constructs a com-
prehensive analytical
sive analytical framework framework to analyze
to analyze and visualize
and visualize sustainable
sustainable maritime maritime
transport transport
research
research
published published
from 2000from 2000astoshown
to 2023, 2023, inas Figure
shown1.inInFigure 1. In this
this review, review, bibliometric
bibliometric analysis will
analysis
includewill
the include
following theaspects:
following (1)aspects:
annual (1) annual publication
publication trends; (2)trends;
source(2) source journals
journals analysis;
analysis; (3) collaboration
(3) collaboration networknetworkanalysis;analysis; (4) keyword
(4) keyword co-occurrence
co-occurrence analysis.analysis.

Figure 1. The integrated analysis framework.

Figure 1. The integrated analysis framework.
2.2. Data Collection
Web of Science (WoS), a cutting-edge information service platform managed by Clari-
vate, includes the world’s most important and groundbreaking research projects, and has
J. Mar. Sci. Eng. 2024, 12, 1728 4 of 27

become a widely recognized leading search tool for scientific metrics and evaluation [13].
We used SSCI and SCI-Expanded data from the WoS core collection as our data sources for
this review.

2.3. Information Retrieval

The review endeavor centers around the application of intelligent shipping technology
and green port construction within the context of sustainable maritime transport. Conse-
quently, the delimitation of inquiry topics is imperative, encompassing the key domains
of “maritime transport”, “shipping technology”, and “green port.” Regarding the subject
search term “maritime transport”, it does not necessarily encompass the entire spectrum of
pivotal technologies, as evidenced by the research findings presented by Ahmed et al. [14],
so that this review selects some keywords closely related to maritime transport (such as
intelligent, big data, artificial intelligence, automatic, efficiency, sustainability, emissions,
ports, clean energy, etc.) to improve the breadth of the retrieved data.
To ensure the transparency and comprehensiveness of this research, a detailed expla-
nation of the selection of this series of keyword searches is given below.
(1) Core basic keywords: “maritime” and “shipping” directly point to the field of mar-
itime transportation, covering all activities of maritime transportation, and can ensure
the direct relevance of the search scope, excluding other unrelated topics.
(2) Topic keywords: “maritime transport” is directly related to the core research field and
serves as the basic background of the review. In addition, “shipping transportation”
or “maritime transportation” as a synonym for “maritime transport”, further expands
the search to include a wider range of shipping-related literature.
(3) Keywords related to intelligent shipping technology: The terms “intelligent” and “au-
tomatic” accurately encapsulate the fundamentals of intelligent shipping technology
and will concurrently serve as benchmarks for the future development of sustainable
maritime transport. Furthermore, “big data” and “artificial intelligence” pinpoint the
pivotal technologies enabling intelligent shipping, ensuring that the latest research
and application cases of artificial intelligence-related intelligent ship technology, such
as automated ship operation and ship trajectory prediction, can be searched during
the retrieval process.
(4) Keywords related to green port construction: The terms “sustainability” and “effi-
ciency” emphasize the research focus on sustainable shipping, environmental friendli-
ness, and resource efficiency, which is in line with the prevailing trends in the shipping
industry. In addition, “ports”, “emissions”, and “clean energy” directly address the
second large part of the paper, green port construction, by emphasizing environmental
goals of reducing greenhouse gas emissions and encouraging the use of clean energy
sources, such as solar and wind, thereby broadening the literature search related to
the green port Initiative.
The specified literature types encompass “articles” and “review”, with a preference
for those published in the English language, and spanning the years 2000 through 2023.
This selection was deliberate, as articles undergo rigorous peer review, ensuring their
academic rigor and quality, while reviews offer valuable insights into the contemporary
landscape and evolving trends within the research domain [15]. English serves as the
primary medium for international scholarly discourse, enhancing the quality and credibility
of literature, thereby fostering global research collaboration and exchange. On the one
hand, the time frame of “2000–2023” facilitates a focus on recent research advancements,
offering contemporary insights, and ensuring the timeliness and scientific rigor of literature
reviews. Conversely, given the publication lag in journals, publications in 2024 might not
yet be available, thus excluding them from the search criteria [16]. Ultimately, a total of
478 publications were identified, comprising 438 articles and 40 reviews. The definitive
search parameters are outlined in Table 1.
J. Mar. Sci. Eng. 2024, 12, 1728 5 of 27

Table 1. Search parameters.

Parameter Content
Database SCI-Expanded and SSCI
Time range 2000–2023
Document type Article or Review
Language English
TS = ((“maritime”) AND (“shipping”) AND (“maritime transportation” OR “maritime transport” OR
Search formula “shipping transportation”) AND (“intelligent” OR “automatic” OR “big data” OR “artificial intelligence” OR
“sustainability” OR “efficiency” OR “ports” OR “clean energy” OR “emissions”))

3. Results and Literature Analysis

This segment may be organized under various subheadings and aimed at providing vi-
sual analysis results, and a concise and accurate description of the experimental conclusion.

3.1. Annual Publication Trends

This study reviews the literatures published from 2000 to 2023 on the application
of intelligent shipping technology and green port construction in sustainable maritime
transport, analyzing the annual publication trends to provide insights into the evolution of
research and potential future developmental trends within this domain [17,18]. Figure 2
shows a statistical graph of published research works since 2010. At the dawn of the 21st
century, due to the sluggish progression of artificial intelligence technology, there were few
research studies on intelligent shipping technology and green port construction in sustain-
able maritime transport. As can be seen from Figure 2, the number of published papers was
relatively flat from 2010 to 2016. Despite the modest annual number of publications within
this domain, there has been a consistent yearly escalation in the number of publications,
surpassing the preceding year’s count. Since 2016, the applied research has been in a rapid
growth stage, and the number of relevant publications has increased year by year, reaching
the peak in 2023. Notably, publications from the past three years comprise an impressive
55%
J. Mar. Sci. Eng. 2024, 12, x FOR PEER of the total publications reviewed herein, suggesting a heightened interest among
REVIEW 6 of 27
scholars in recent years towards the research pertaining to sustainable maritime transport.

Figure2.2.Annual
Figure Annualpublication
publicationstatistics
statisticstrends
trendsfrom
from2010
2010to
to2023.
2023.

3.2. Statistical
This growth Analysis
trendofprimarily
Source Journals
stems from the international demand for sustainable
development and the rapidreview
This comprehensive evolution and integrated
encompassed application of
478 publications advanced
dispersed technologies.
across 149 dis-
tinct journals. For clarity and emphasis, Table 2 presented a list of the 15 most prolific
journals, collectively contributing 49% of the total articles under examination in this re-
view. Among them, Sustainability has the highest production, with 37 publications. It was
followed by Transportation Research Part D: Transport and Environment (27 publica-
tions) and Maritime Policy & Management (25 publications). Publications in these three
J. Mar. Sci. Eng. 2024, 12, 1728 6 of 27

Firstly, with the increasing global emphasis on environmental protection and sustainable
development, the maritime transport sector, as a crucial pillar of international trade, has
seen its green transformation and intelligent development become an international consen-
sus. Governments, international organizations, and research institutions worldwide have
intensified their investments in this domain, fostering the development and application
of relevant technologies, thereby promoting the prosperity of related academic research.
Secondly, the rapid advancements in technologies, such as artificial intelligence, big data,
and the Internet of Things, have provided robust technical support for intelligent shipping
and green port construction. The continuous breakthroughs and integrated applications of
these advanced technologies have not only enhanced the efficiency and safety of maritime
transport, but propelled the deep-seated implementation of green and low-carbon concepts
within the shipping industry.

3.2. Statistical Analysis of Source Journals

This comprehensive review encompassed 478 publications dispersed across 149 dis-
tinct journals. For clarity and emphasis, Table 2 presented a list of the 15 most prolific
journals, collectively contributing 49% of the total articles under examination in this review.
Among them, Sustainability has the highest production, with 37 publications. It was fol-
lowed by Transportation Research Part D: Transport and Environment (27 publications)
and Maritime Policy & Management (25 publications). Publications in these three respected
journals account for approximately 18.6% of the publications searched in this review, in-
dicating their critical influence in the field of sustainable maritime transport, providing
valuable benchmarks and important references for academic work in the field.

Table 2. Most productive journals.

Journal Name Publications Percentage (%) H-Index

Sustainability 37 7.74 12
Transportation Research Part D: Transport and Environment 27 5.65 19
Maritime Policy & Management 25 5.23 14
Journal of Marine Science and Engineering 24 5.02 7
Transportation Research Part E: Logistics and Transportation Review 20 4.18 15
Maritime Economics & Logistics 16 3.35 9
Ocean Engineering 16 3.35 10
Marine Policy 12 2.51 7
Transport Policy 11 2.30 8
Journal of Cleaner Production 10 2.09 9
Ocean & Coastal Management 10 2.09 8
Applied Sciences-Basel 8 1.67 5
International Journal of Shipping and Transport Logistics 7 1.46 5
Energies 6 1.26 3
Transportation Research Part B: Methodological 6 1.26 6

From the H-index of journal influence in Table 2, the Transportation Research journals
series (Parts B, D, E) feature prominently in the list, showing that these journals have
attracted many high-quality publications, and have a high academic influence and research
quality in the field of intelligent shipping technology and green port construction, which
has promoted the rapid development of the field. Among them, Transportation Research
Part D: Transport and Environment and Transportation Research Part E: Logistics and
Transportation Review ranked the top with an H-index of 19 and 15, respectively. As
technology continues to advance, sustainable maritime transport will continue to evolve in
a more efficient, intelligent, and environmentally friendly direction. Future research will
pay more attention to technological innovation and integration, promote interdisciplinary
cooperation, and improve the overall research level.
Many journals related to environmental protection such as Sustainability, the Journal
of Cleaner Production, Applied Sciences-Basel, and Energies are also listed in Table 2,
J. Mar. Sci. Eng. 2024, 12, 1728 7 of 27

indicating that sustainable development and environmental protection are current research
hotspots and future research trends. These journals not only focus on technological innova-
tion, but emphasize the environmental benefits and social responsibility of technological
applications. Finally, it can be found that the number of Maritime Policy & Management
publications ranks third in the statistics, while Marine Policy and Transport Policy rank
eighth and ninth, respectively. It shows that the formulation and introduction of a series
of maritime and transport policies have gradually played an important role in shipping.
The effective implementation and steady promotion of policies also provide strong sup-
port for the rapid development of technology, which can more efficiently promote the
transformation and application of research results.

3.3. Analysis of Collaboration Network

3.3.1. Author Collaboration Analysis
Scrutinizing the authorship of the paper can help researchers gain insights into the
utilization of intelligent shipping advancements and environmentally friendly port devel-
opment within the realm of sustainable maritime transport [19]. Table 3 presents the most
influential authors in this application area. The top 15 authors all published more than
four papers, of which Shuaian Wang owned the most publications, with 20, H-index 13.
According to the results of the analysis, 5 of the top 15 authors in the field of sustainable
maritime transport are from China. This reason is inseparable from China’s specific pol-
icy drivers in the field of shipping. Over the past decade, the Chinese government has
recognized the importance of sustainable maritime transport strategies and implemented
policies such as financial incentives and research project grants to support research in
this area, which has facilitated the output of academic works by Chinese researchers. At
the same time, China’s academic culture, which emphasizes collective achievement and
competition between research teams, also drives researchers to strive to contribute to the
country’s efforts in advancing maritime transport technology.

Table 3. Most productive authors.

Author Publications Percentage (%) H-Index

Shuaian Wang 20 4.18 13
Elizabeth Lindstad 14 2.93 12
Zaili Yang 12 2.51 8
Kjetil Fagerholt 10 2.09 7
Harilaos Psaraftis 9 1.88 9
Kum Fai Yuen 8 1.67 7
Cesar Ducruet 8 1.67 8
Xueqin Wang 6 1.26 6
Qiang Meng 6 1.26 6
Jukka-Pekka Jalkanen 6 1.26 4
Kevin Li 6 1.26 6
Thalis Zis 6 1.26 6
Yiik Diew Wong 5 1.05 5
Lu Zhen 5 1.05 3
Jasmine Siu Lee Lam 4 0.84 4

To examine the collaborative efforts among authors in the realm of intelligent shipping
technology and green port construction applications within maritime transportation, we
built an author collaboration network using VOSviewer software version 1.6.20 [20]. The
detailed steps of the algorithm are shown in Table 4. Figure 2 shows the collaborative
network among authors, with at least 22 documents containing 67 projects, 72 links, and
27 clusters. Each author is associated with an article, with the size depicting the total
count of publications. The links between projects signify the collaboration among authors,
where the line thickness reflects the intensity of their collaboration. The coloration of
the items represents the outcome of the clustering analysis, indicating that items sharing
 J. Mar. Sci. Eng. 2024, 12, x FOR PEER REVIEW 9 of

J. Mar. Sci. Eng. 2024, 12, 1728 8 of 27

energy issues in 2019 and 2021, respectively [46,47]. This observation may stem from t
nascent stage of research in sustainable maritime transport, where collaborations are p
the same hue (i.e.,confined
marily authors)to arewithin
affiliated with the
individual same research
research group. As depicted
teams. Consequently, in
cooperation acro
Figure 3, because of the academic collaboration between the authors, multiple
teams remains an underdeveloped area requiring further exploration, resulting in limit research
teams wereinter-team
established around the [48].
collaboration application of smart shipping technology and green
port construction in sustainable maritime transport. Furthermore, the clustering pattern
exhibited in Figure
Table 3 underscores
4. Search theon
request based prevalence of intra-cluster
the collaboration network ofconnections
authors. over inter-
cluster ones.
Step Search Request
Table 4. Search request
1 based on the collaboration
Choose type of data network of authors.
as ‘Create a map based on bibliographic data’.
2 Choose data source as ‘Read data from bibliographic database files’.
Step Search Request
3 Select the file set as ‘Web of Science’.
1 Choose type of data Setasthe
‘Create
typeaofmap based as
analysis on ‘Co-authorship’,
bibliographic data’.the unit of analysis as ‘Authors’ an
2 Choose data4source as ‘Read data from bibliographic database files’.
3 Select the file set as ‘Web ofcounting
Science’. method as ‘Full counting’.
4 The minimum number
Set the type of analysis as ‘Co-authorship’, the unit of analysis as ‘Authors’ and of documents of anasauthor
counting method is set to three;
‘Full counting’.
5
5
The minimum number of documentsThe minimum number of citations of an author is set to zero.
of an author is set to three;
The minimum
6 number of citations of an author is set
Select alltoconnected
zero. items.
6 Select all connected items.

Figure 3. Collaboration network of authors.

Figure 3. Collaboration network of authors.
These include key authors Harilaos Psaraftis and Lu Zhen working with industry
leaders such as Shuaian
3.3.2. Wang Collaboration
Organization and Yan Ran on the challenges of maritime transportation,
Analysis
optimization of shipping emissions, and carbon emissions [21–23]. Elizabeth Lindstad
The 478
and Kjetil Fagerholt publications
from included
the Norwegian in the review
University were published
of Science by 635 diverse
and Technology, who organiz
have worked together six times, on ship lifetime fuel and power system selection in engag
tions. Table 5 compiles the leading organizations that exhibit the most vigorous
mentrespectively,
2022 and 2023, in the realminof
thesustainable maritime transport
journal Transportation Researchresearch.
Part D: The top 10and
Transport organizatio
Environment [24,25]. Moreover, Zaili Yang from the University of Liverpool, has conducted two fro
contribute nearly 46% of academic publications, four of which are from China,
Norway,
in-depth research onand most ofand
modeling the analysis
rest are from universities
of sustainable in coastal
transport cities. Among
networks these orga
and ship
zations, theand
trajectory prediction, Hong
hasKong Polytechnic
also made University andinthe
great achievements Norwegian
a series of newUniversity
methods of Scien
and technologies, such as Bayesian networks and deep learning methods [26–28]. Harilaos
J. Mar. Sci. Eng. 2024, 12, 1728 9 of 27

Psaraftis has also worked with Christos Kontovas 11 times on green ship routes and
balancing the economics and environment of maritime transportation [29–31]. As you
can see in Figure 3, the orange cluster on the left is mainly the collaboration of Kum Fai
Yuen, Yiik Diew Wong from Nanyang Technological University, and Xueqin Wang from the
University of Science and Technology of China, who have collaborated 63 times on research
areas such as maritime logistics and sustainable shipping; Kevin Li has also cooperated with
Kum Fai Yuen 23 times [32–35]. Cesar Ducruet of the French National Centre for Scientific
Research has done some work on the structure of space networks and port cities [36–38].
Qiang Meng is a professor in the Department of Civil and Environmental Engineering at the
National University of Singapore, whose outstanding contributions to the maritime sector
are mainly shipping and intermodal transport analysis, having worked with Shuaian Wang
48 times on container speed optimization and liner deployment as early as 2011 [39–41].
Jukka-Pekka Jalkanen is the lead developer of the Ship Traffic Emissions Assessment Model
(STEAM) of the Finnish Meteorological Institute, where he conducts in-depth research on
shipping emissions and air pollution, mainly in the Baltic Sea [42,43]. Thalis Zis, from
Imperial College London, specializes in ways to decarbonize shipping and reduce emissions
from port operations, and has worked with Harilaos Psaraftis 16 times on ports [44,45]. In
addition, Lam Jasmine Siu Lee from the Technical University of Denmark has also made
remarkable achievements in the shipping field, focusing on the green port economy, port
vessel emissions, and other directions. She has published 16 articles in “Maritime Policy &
Management”, and 8 articles in “International Journal of Shipping and Transport Logistics”
and “Transportation Research Part E: Logistics and Transportation Review”, respectively.
She has also worked with Cagatay Iris six times, and the two conducted review analysis and
operations management studies on port energy issues in 2019 and 2021, respectively [46,47].
This observation may stem from the nascent stage of research in sustainable maritime
transport, where collaborations are primarily confined to within individual research teams.
Consequently, cooperation across teams remains an underdeveloped area requiring further
exploration, resulting in limited inter-team collaboration [48].

3.3.2. Organization Collaboration Analysis

The 478 publications included in the review were published by 635 diverse organiza-
tions. Table 5 compiles the leading organizations that exhibit the most vigorous engagement
in the realm of sustainable maritime transport research. The top 10 organizations contribute
nearly 46% of academic publications, four of which are from China, two from Norway,
and most of the rest are from universities in coastal cities. Among these organizations, the
Hong Kong Polytechnic University and the Norwegian University of Science and Tech-
nology tied for the top spot with 24 publications, followed by Dalian Maritime University
(23 publications), and Shanghai Maritime University (19 publications). This highlights
China’s key role in advancing sustainable maritime research and application. SINTEF is
one of the largest independent research organizations in Europe, with multidisciplinary
expertise in the fields of technology, natural sciences, and social sciences. Its aim is to
contribute to the development of society by conducting research in the natural sciences,
technology (including architecture and civil engineering), and health and social sciences in
cooperation with the Norwegian University of Science and Technology.
To analyze the collaboration between organizations in the application field of in-
telligent shipping technology and green port construction, VOSviewer software version
1.6.20 is used to build an organization collaboration network. The specific search steps
are shown in Table 6. Figure 3 illustrates a collaborative network among organizations,
with a minimum document count of 5, consisting of 29 projects, 5 clusters, 72 links, and a
total link strength of 111. As depicted in Figure 4, each project serves as a representation
of an organization, with the proportional size of each symbol reflecting the quantity of
published articles emanating from that particular entity. The connections between projects
indicate collaboration between organizations, and the thickness of the links signifies the
strength of the collaboration between organizations. In terms of project scale and the
 J. Mar. Sci. Eng. 2024, 12, 1728 10 of 27

number of collaborations, the Hong Kong Polytechnic University plays a key role as a
bridge in the collaborative network, with 10 universities working with it. As the chal-
lenges of sustainable maritime transport become more complex and interconnected, many
universities are placing greater emphasis on research investment and talent attraction in
maritime related research, and further collaboration between these top organizations is
expected. This includes not only academic partnerships, but a close collaboration with
industry, governments and non-governmental organizations, which can work to translate
research findings into practical technologies in the future.

Table 5. Most productive organizations.

Organizations Publications Percentage (%)

Hong Kong Polytechnic University 24 5.02
Norwegian University of Science and Technology (NTNU) 24 5.02
Dalian Maritime University 23 4.81
Shanghai Maritime University 19 3.97
Nanyang Technological University 16 3.35
Technical University of Denmark 14 2.93
Wuhan University of Technology 14 2.93
Liverpool John Moores University 13 2.72
SINTEF 13 2.72
University of Lisbon 11 2.30

Table 6. Search request based on the collaboration network of organizations.

Step Search Request

1 Choose type of data as ‘Create a map based on bibliographic data’.
2 Choose data source as ‘Read data from bibliographic database files’.
3 Select the file set as ‘Web of Science’.
4 Set the type of analysis as ‘Co-authorship’, the unit of analysis as ‘Organizations’ and counting method as ‘Full counting’.
J. Mar. Sci. Eng. 2024, 12, x FOR PEER REVIEW
The minimum number of documents of an organization is set to five; 11 of 27
5
The minimum number of citations of an organization is set to zero.
6 Select the largest set of connected items instead of all items.

Figure
Figure 4. Collaboration network
Collaboration network of of organizations.
organizations.

3.3.3. Country Collaboration Analysis

3.3.3. Country Collaboration Analysis
Analyzing the country information in this review can understand the research contri-
Analyzing
butions of variousthe country
countries in information in thistechnology
intelligent shipping review can andunderstand the research con-
green port construction,
tributions of various
as well as the exchanges countries in intelligent
and cooperation among shipping technology
them. Between 2000 andand green
2023, port construc-
65 countries
tion, as well as the exchanges and cooperation among them. Between 2000 and
have contributed to the study of the field of sustainable maritime transport through publi-2023, 65
cations in have
countries SCI core databases. to
contributed Table
the7 study
shows ofthethe
top field
10 countries ranked bymaritime
of sustainable the number transport
of publications.
through China contributes
publications in SCI corethe most papers
databases. in this
Table application
7 shows the top field, with a totalranked
10 countries of by
141 publications. Following closely behind are England (46 publications),
the number of publications. China contributes the most papers in this application field,the United States
(42 publications), and Norway (39 publications). In addition, China accounts for nearly
with a total of 141 publications. Following closely behind are England (46 publications),
30% of all publications in the field of sustainable shipping, far more than other countries,
the Unitedthat
indicating States
China(42provides
publications), and Norway
a great impetus (39 publications).
for the development In addition,
of the field. China ac-
The signifi-
counts forofnearly
cant lead China 30% of all
in terms of publications in the
publication output field
can of sustainable
be primarily shipping,
attributed far more than
to macro-level
other
factors. Firstly, the Chinese government has placed great importance on the strategy of of the
countries, indicating that China provides a great impetus for the development
field. The asignificant
becoming lead and
maritime power of China in terms
sustainable of publication
development output
goals in recent can Through
years. be primarily
a at-
tributed to macro-level factors. Firstly, the Chinese government has placed great im-
portance on the strategy of becoming a maritime power and sustainable development
goals in recent years. Through a series of policy guidance and support, it has provided a
strong impetus for the research and development of marine technology and environmen-
J. Mar. Sci. Eng. 2024, 12, 1728 11 of 27

series of policy guidance and support, it has provided a strong impetus for the research
and development of marine technology and environmental protection technologies. Driven
by “the Belt and Road” Initiative, in particular, China has been committed to enhancing the
intelligence and greenness of global port facilities, which has directly promoted academic
research and practical applications in related fields. Secondly, as the world’s second-largest
economy, China boasts a vast market demand and industrial foundation. Both state-owned
and private enterprises, in collaboration with major universities, have actively responded
to national calls while pursuing economic benefits and scientific research needs. They
have increased investment in scientific research, promoted technological innovation and
experience-sharing, and made significant contributions to China’s research in the field of
sustainable maritime transport.

Table 7. Most productive countries.

Country Publications Percentage (%)

China 141 29.50
England 46 9.62
the United States 42 8.79
Norway 39 8.16
Spain 36 7.53
France 31 6.49
Sweden 29 6.07
Singapore 28 5.86
Germany 25 5.23
South Korea 25 5.23

To elucidate on country-to-country collaborations, we employ the VOSviewer software

version 1.6.20 to construct a collaborative network map. The specific search steps are shown
in Table 8. Figure 5 shows the collaborative network between countries with at least four
papers, with 36 projects, 163 links, and a total link strength of 322. The size of the projects
indicates that China is the leading country in terms of publications. Among them, China
has collaborated with 23 countries, contributing to a total link strength of 91. Following
China are England (21 collaborating countries, with a total link strength of 51) and Norway
(19 collaborating countries, with a total link strength of 35). The thickness of the links
shows that the cooperation between China and England is the closest, with a link strength
of 16. This is followed by cooperation between China and Singapore (link strength 14) and
the United States (link strength 10).

Table 8. Search request based on the collaboration network of countries.

Step Search Request

1 Choose type of data as ‘Create a map based on bibliographic data’.
2 Choose data source as ‘Read data from bibliographic database files’.
3 Select the file set as ‘Web of Science’.
4 Set the type of analysis as ‘Co-authorship’, the unit of analysis as ‘Countries’ and counting method as ‘Full counting’.
The minimum number of documents of a country is set to four;
5
The minimum number of citations of a country is set to zero.
6 Select all connected items.

However, we can also see from Figure 5 that some countries have fewer publications,
less intensive cooperation with other countries, and numerous countries are absent from
this collaborative network. On the one hand, this may be attributed to the fact that
cooperation among countries in the field of sustainable maritime transport often involves
the sharing of intellectual property rights and the distribution of benefits, and the inability
to reach a consensus may hinder the development of such cooperation. On the other hand,
disparate countries might hold diverse interpretations and necessitate varying standards
 tion in sustainable maritime transport.

Table 8. Search request based on the collaboration network of countries.

Step Search Request

J. Mar. Sci. Eng. 2024, 12, 1728 1 12 of 27 data’.
Choose type of data as ‘Create a map based on bibliographic
2 Choose data source as ‘Read data from bibliographic database files’.
3 Select the file set as ‘Web of Science’.
and norms pertaining to sustainable maritime transport,
Set the type of analysis as thereby posing
‘Co-authorship’, potential
the unit barriers
of analysis as ‘Countrie
4
to collaborative research endeavors across national borders. Significant differences in
counting method as ‘Full counting’.
technical standards and norms among countries may lead to incompatibility, thereby
The minimum number of documents of a country is set to four;
increasing the difficulty
5 of collaborative research among nations. Therefore, for the purpose
The minimum number of citations of a country is set to zero.
of future research, further enhancement of international academic cooperation is imperative
6 Select all connected
in the application of human intelligent shipping technology items.
and green port construction in
sustainable maritime transport.

Figure 5.
Figure 5. Collaboration Collaboration
network network of countries.
of countries.

3.4. Analysis of Keyword Co-Occurrence

Keywords, which are concise summaries of the core content of a paper, can be utilized
by VOSviewer version 1.6.20 for bibliometric analysis to identify the major research clusters
in the field of sustainable maritime transport [49]. Table 9 lists the top 10 keywords with the
highest frequency, among which “maritime transport” is the most frequently mentioned
keyword, appearing 136 times, followed by its close synonym “maritime transportation”.
It reflects that these keywords are the basic word of research in this field. This is followed
by the high frequency of keywords such as “emissions” and “shipping emissions”, with
researchers increasingly focusing on environmental sustainability in the maritime sector
in recent years. This trend is likely driven by the formal entry into force of international
agreements such as the Paris Agreement in 2016, and the growing public awareness of the
environmental impact of maritime transport [50,51]. The emergence of “model”, “optimiza-
tion” and “speed optimization” indicates that people are interested in using technological
advances such as simulation and prediction to face challenges in various aspects of the
maritime industry. With the rapid development of data accessibility and technology, future
research will explore more sophisticated optimization algorithms, autonomous shipping
technologies, and alternative fuels to further improve the sustainability of shipping. Finally,
the keywords “port” and “management” also appear in Table 6, which shows that ports
are the key nodes of the maritime transportation system, and relevant studies such as
the construction and management of green ports will be crucial to the future maritime
transportation field.
As depicted in Figure 6, an all-keyword co-occurrence network has been constructed.
In this network, each item signifies a keyword whose size indicates the frequency of
occurrence. The concurrent manifestation of two keywords is denoted as keyword co-
occurrence, wherein the spatial proximity between these elements serves as an indicator
J. Mar. Sci. Eng. 2024, 12, 1728 13 of 27

of the intensity of their interconnection, with a diminished separation alluding to a more

pronounced correlation. The color of the items represents the clustering results, with items
of the same color indicating they belong to the same cluster, while those of different colors
belong to distinct clusters. These connections signify the coexistence associations among
keywords, while the density or thickness of these connections serves as a measure of
the robustness of these relationships, thereby reflecting their inherent strength. Figure 6
displays the keyword co-occurrence network, with the minimum occurrence threshold set
at six and the unit of analysis for all keywords. The resulting network diagram contains
136 items, six clusters, 2807 links, and a total link strength of 5061.

Table 9. High-frequency keywords.

Keyword Occurrences Links Average Published Year

Maritime transport 136 131 2020
Maritime transportation 79 98 2019
Emissions 64 103 2021
Model 50 93 2020
Ships 46 97 2021
Shipping emissions 32 74 2021
J. Mar. Sci. Eng. 2024, 12, x FOR PEER REVIEW Ports 31 76 2021 14 of 27
Optimization 31 72 2020
Management 28 76 2019
Speed optimization 28 64 2021

Figure 6.
Figure Keywords co-occurrence
6. Keywords co-occurrence network.
network.

Intelligent transportation
Intelligent transportationoriginated
originatedfrom
from land
landtransportation andand
transportation waswas
laterlater
referenced
refer-
to water transportation, leading to the concept of “intelligent shipping”. An intelligent
enced to water transportation, leading to the concept of “intelligent shipping.” An intelli-
waterway
gent transportation
waterway system
transportation is an
system intelligent
is an intelligent transportation
transportationsystem
systemapplied
applied to the
to the
waterway environment [52]. The shipping system consists of three most basic
waterway environment [52]. The shipping system consists of three most basic elements: elements:
channels, ships,
channels, ships, and
and ports,
ports, along
along with
with the
the various
various support
support and
and security
security systems
systems [53].
[53]. As
As
can be seen from Figure 6, the green cluster and red cluster focus on the application of
can be seen from Figure 6, the green cluster and red cluster focus on the application of
intelligent shipping technology centered on “technology” and “algorithm”. The blue
intelligent shipping technology centered on “technology” and “algorithm.” The blue and
yellow clusters focus on port air pollution and greenhouse gas emissions from ships under
the keyword “port” and “shipping emissions.” These two clusters represent current re-
search hotspots in sustainable maritime transport applications and provide directions for
future research in this field. In addition, the light blue cluster shows the important support
J. Mar. Sci. Eng. 2024, 12, 1728 14 of 27

and yellow clusters focus on port air pollution and greenhouse gas emissions from ships
under the keyword “port” and “shipping emissions”. These two clusters represent current
research hotspots in sustainable maritime transport applications and provide directions for
future research in this field. In addition, the light blue cluster shows the important support
of the maritime supply chain for the management of shipping enterprises in recent years,
which will be the emerging trend and digital technology of the future of maritime transport.
Next, Section 4 will focus on the literature review of the two clusters of intelligent shipping
technology and green port construction.

4. Review and Analysis of Hot Research Areas

4.1. Intelligent Shipping Technology
Intelligent shipping technology is the product of the deep integration of modern
information technology and the shipping industry. The shipping industry has undergone an
intelligent transformation across all aspects through the adoption of advanced technologies,
such as artificial intelligence, big data, and the Internet of Things, thereby enhancing the
efficiency, safety, and environmental sustainability of maritime operations. Ships are the
main carriers of maritime transportation. As a major application of intelligent shipping
technology, intelligent ships enhance navigation safety and operational efficiency through
real-time monitoring, automated navigation, and intelligent collision avoidance. These
functions are enabled by equipping vessels with sensors, radars, and communication
devices [54].
To date, remarkable achievements have been made in autonomous navigation research
and development projects globally. In February 2020, the Japan Shipbuilding Industry
Association funded 3.4 billion yen for over 40 Japanese institutions to form five alliances,
conducting six exploratory autonomous navigation experiments validating the feasibility
of key technologies (e.g., autonomous berthing and unberthing, collision avoidance, target
image processing) for long voyages [32]. This project represents the world’s broadest
autonomous navigation research and development across vessel types. In November 2021,
the Netherlands Forum Smart Shipping (SMASH) released a smart shipping roadmap out-
lining a vision for the development of smart shipping in the Netherlands by 2030, marking
the first systematic framework for smart shipping development in Europe [55]. In June
2022, the Korean Hyundai Heavy Industries Group and SK Corporation collaborated to
complete a 33-day transoceanic autonomous navigation test of “Prism Courage” spanning
5500 nautical miles. The vessel autonomously routed, adjusted speeds, assessed environ-
ments, and executed 100 collision avoidance maneuvers. The test results indicated a 7%
improvement in fuel efficiency and a 5% reduction in greenhouse gas emissions. This marks
the sole reported transoceanic test for an 180,000-cubic-meter ultra-large LNG autonomous
vessel [56]. In China, the concept of intelligent ship navigation was first introduced in the
“Intelligent Ship Regulations” (2015) issued by the China Classification Society (CCS) in
2015. In December 2019, the “Jin Dou Yun” unmanned autonomous cargo ship, jointly
developed by Zhuhai Yunhang Intelligent Technology Co., Ltd., in collaboration with
universities and the government, successfully completed its maiden voyage carrying cargo
autonomously [57].
To guide the standardized and safe development of autonomous marine navigation
technology, a series of regulations have been successively promulgated. The IMO Maritime
Safety Committee’s 105th session endorsed the MASS Code roadmap as the paramount
international rule for intelligent ship navigation, to commence voluntarily from 1 January
2025, and mandate on 1 January 2028, after accumulating implementation experience [58].
Since the establishment of the Smart Shipping Working Group (ISO/TC8/WG10) by the
International Organization for Standardization’s Committee on Ships and Marine Technol-
ogy in 2016, it integrates and manages resources from ISO/TC 8 (including SC6 and SC11)
in the area of smart shipping, which will actively promote and coordinate the widespread
application of smart shipping technologies in the maritime industries of various countries
on an international scale [59].
J. Mar. Sci. Eng. 2024, 12, 1728 15 of 27

Nowadays, the industry and academia have placed an emphasis on intelligent mar-
itime monitoring and ship behavior recognition, a commitment that supports efforts to
enhance maritime safety and reduce accidents [60]. Among these focal points, the accurate
prediction of ship trajectories is a critical challenge in intelligent maritime traffic systems,
serving as a fundamental prerequisite for effective collision detection and risk assessment.
The Automatic Identification System (AIS) provides an important opportunity for realizing
intelligent ship identification and maritime traffic flow supervision, and has been widely
adopted and applied by various countries [61,62]. There are a total of 17 articles on trajec-
tory prediction in the literature sources of this review. Among them, Zhang et al. (2022)
provide a comprehensive review of existing methods for ship trajectory prediction, with a
focus on advanced deep learning techniques and the data sources used. This review article
discusses auxiliary technologies, complexity analyses, benchmark comparisons, perfor-
mance metrics, as well as methods for enhancing model performance. Finally, the article
outlines the current challenges and future research directions in this field [63]. Table 10
summarizes and refines the trajectory prediction methods and specific applications used in
the other 16 papers, providing the latest research direction for ship behavior recognition
and marine traffic detection.

Table 10. Relevant methods and techniques of ship trajectory prediction.

Model/Method Description Applications in Shipping Ref.

Using a maritime dataset collected from the AIS To identify conflicting trajectories
A framework of system, the proposed framework automatically based on the features of maritime
[64]
CCT discovery and unsupervisedly identifies clusters of conflict behavior among ships on the
conflict trajectories. open sea
A CNN-SMMC Training a neural network on labeled AIS data to To label a ship’s movement into three
[65]
architecture effectively accomplish the classification task. types based on AIS data
An integrated approach of Combining machine learning, physical motion
To enhance situation awareness for
vessel trajectory and modeling, and particle filtering to produce [66]
maritime traffic safety management
navigating state prediction reliable forecasting results.
The ARIMA-LSTM model forecasts near-future To maneuver a ship safely by
A hybrid model
ship trajectories using AIS data to aid in considering the estimated risk [67]
(ARIMA-LSTM)
subsequent ship collision avoidance. of collision
A bidirectional Integrating the output results of the To improve the accuracy of ship
data-driven trajectory Encoder-Decoder model, driven by both forward trajectory prediction and reducing the [68]
prediction method and backward data. risk of accidents
Integrating a GRU neural network with the UKF
A multi-ship collision to estimate ship positions at various times and To provide early warning of
[69]
risk model analyze the uncertainty of these positions multi-ship collision risk
over time.
To help manned ships achieve
A deep bi-directional Integrates two bi-directional networks and
high-accuracy predictions and enable
information-empowered optimizing the weights of model units using an [70]
MASS to develop more reasonable
(DBDIE) prediction mode attention mechanism.
operational strategies

Contemporary research results related to ship trajectory prediction are largely based
on the utilization of AIS data. Currently, neural networks have garnered extensive applica-
tion in forecasting the navigational path and operational status of ships, thereby enhancing
predictive capabilities within the maritime domain. Various types of neural networks, in-
cluding Artificial Neural Networks (ANN), neuroevolutionary ANN [71], Backpropagation
(BP) networks [72], and Generalized Regression Neural Networks (GRNN) [73], have been
utilized for predictive tasks. As a prevalent approach, the utilization of ANN technology
excels in the thorough analysis and extraction of historical big data via meticulous model
training. The BP neural network, an exemplar of the multi-layered feedforward network
architecture, stands as a widely embraced ANN variety that undergoes refinement via the
J. Mar. Sci. Eng. 2024, 12, 1728 16 of 27

error backpropagation algorithm. Given appropriate network configuration and intensive

training, this methodology attains remarkable predictive precision, and adeptly models
intricate nonlinear relationships [74]. Chen et al. (2020) designed a Ship Motion Image
Generation and Labeling (SMIGL) algorithm to convert a ship’s AIS trajectory into differ-
ent moving images, thereby fully leveraging the classification capabilities of CNNs. The
findings indicate that the proposed CNN-SMMC exhibits good performance in classifying
AIS data [65].
Additionally, one of the typical deep learning models, the recurrent neural network
(RNN), is commonly used for trajectory prediction applications, including public trans-
portation forecasting, location prediction problems, and destination prediction. A common
issue with RNN is the diminishing or escalating gradient phenomenon across lengthy
sequences, thereby compromising their capacity to grasp long-range dependencies effi-
ciently. The standard RNN model includes Long Short-Term Memory (LSTM) and Gated
Recursive Units (GRUs). The LSTM network, a specialized RNN model, was devised to
mitigate the gradient vanishing issue inherent in traditional RNNs. By virtue of their ability
to capture and sustain long-term dependencies, LSTM networks are well-suited for tack-
ling long-sequence prediction tasks, particularly those involving intricate ship trajectories.
Furthermore, LSTM networks demonstrate flexibility in processing sequences of varying
lengths, accommodating ship trajectories of diverse durations. Another noteworthy RNN
variant, GRU has emerged as a solution to the challenges posed by long-term memory
retention and gradient vanishing during backpropagation. GRU offers advantages in terms
of training simplicity and efficiency enhancement. It achieves this by integrating the forget
and input gates into a unified update gate and merging the hidden layer with the memory
cell into a reset gate. These structural refinements streamline the overall operation and ele-
vate performance [74]. Unlike traditional LSTM, Bi-directional LSTM (Bi-LSTM) networks
use forward and backward information for input sequences. Wu et al. conducted a trajec-
tory prediction model that integrates Convolution LSTM (ConvLSTM) and sequence-based
Seq2Seq models. Experimental findings reveal that this model surpasses two comparative
benchmarks in predicting turn trajectories, and delivers enhanced accuracy for linear move-
ments, significantly boosting overall prediction precision [75]. Li et al. (2024) introduced a
novel predictive method named Deep Bidirectional Information Enabling (DBDIE), which
enhances feature extraction by integrating Bi-LSTM and Bi-directional Gated Recurrent
Unit (Bi-GRU) neural networks. According to experimental results, the new DBDIE model
provides a novel strategy for improving the precision and efficacy of ship trajectory pre-
diction, outperforming all classical methods in delivering the most desirable prediction
outcomes [70]. Bi-LSTM, comprising two distinct LSTMs, possesses the capability to cap-
ture both past and future information. Research has demonstrated that, in the context of
time series forecasting tasks, the Bi-LSTM model surpasses its unidirectional counterpart
in terms of performance. Analogously, the Bi-GRU, as an advancement upon the GRU,
harnesses both forward and backward temporal cues to bolster prediction accuracy.
However, raw AIS data can suffer from data errors, inconsistent data formats, high
latency, coverage limitations, and other issues. These limitations can ultimately result in
inaccurate prediction outcomes. Currently, AIS systems are divided into shore-based and
space-based types. Shore-based AIS systems typically offer restricted, localized coverage,
frequently confined to a radius of approximately 50 nautical miles, thereby limiting their
scope to nearby areas. Correspondingly, space-based AIS networks are emerging to address
these limitations by expanding coverage beyond these local boundaries. However, despite
their broader reach, space-based AIS networks may experience delays of several hours,
indicating that these systems are not without their own challenges [76,77]. Furthermore,
AIS data are prone to several potential error sources. For instance, inaccuracies in satellite
navigation systems can result in erroneous location information. Additionally, AIS ship-
board transponders may be switched on or off, or malfunction during a voyage, introducing
further discrepancies in the data. Moreover, static AIS data elements like Maritime Mobile
J. Mar. Sci. Eng. 2024, 12, 1728 17 of 27

Service Identity (MMSI), ship type, and the captain are predominantly input manually,
which can lead to ambiguities or inaccuracies in the information provided.

4.2. Green Port Construction

A port is an important transportation hub connecting water and land transportation,
plays a key role in international trade and, as a key node of international logistics and
the supply chain, it is also an important position of information construction. As the
need for energy conservation and emission reduction grows, green ports are becoming
increasingly important to maintain the growth of maritime transportation. Initiatives
such as the “Clean Air Action Plan” implemented by the Port of Long Beach and the
Port of Los Angeles (Jelenić, 2016), the “Clean Air Action Program” developed by the
Port of Rotterdam (Mshe, 2012), and the “Clean Air Strategy” for the Port of New York
and New Jersey (Port of NY & NJ, 2009) underscore a global shift towards sustainable
practices. Building on this momentum, China’s recent “Fourteenth Five-Year Plan for Water
Transport Development” (2020–2025) further exemplifies this global commitment. The plan
prioritizes the development of green and low-carbon water transport, integrates advanced
environmental protection technologies, and emphasizes the use of clean energy within port
operations, positioning China at the forefront of sustainable maritime logistics [78].
Governmental concern for port-related environmental pollution has intensified over
time, reflecting a broader understanding of the issues highlighted by numerous studies,
including those by Corbett et al. (2009), which identify stationary vessels and port cargo
handling facilities as primary sources of carbon emissions, contributing to 74% of the
emissions within these zones [79]. This concern has catalyzed the academic and industrial
sectors to explore innovative strategies for managing port emissions effectively. Recent
advancements have introduced comprehensive methodologies that align with operational
efficiency and environmental sustainability to enhance the assessment of carbon emissions
within port operations. Dong et al. proposed a port-centric method for evaluating the
performance of the coal transport chain (PCTC), considering both foreland and hinterland
elements. This approach utilizes real data from China’s coal North–South transportation
corridor to provide decision-making support for shippers and port owners [80]. Following
this, a study on Chinese ports provided a scenario-based forecasting model that analyzes
carbon emissions trends and peak situations under different future scenarios, allowing
ports to plan and adjust strategies accordingly [81]. Additionally, research focused on the
Guangzhou Port examined how government subsidy policies influence carbon emissions
within the port’s collection and distribution network, offering insight into policy impacts
on port emissions [82]. Another tiered approach involved creating detailed emissions
inventories for port vessels by considering various operational modes, which enhances the
granularity and accuracy of emission assessments [83].
Amidst these evolving strategies to tackle port emissions, various innovative models
and technologies have been proposed to enhance the efficiency and sustainability of port
operations. Jiang et al. constructed a mathematical model, which described the complex
issues of ship scheduling and berth allocation in restricted channels, and proposed an adap-
tive, two-population, multi-objective genetic algorithm NSGA-II-DP to solve the problem.
When it comes to port scheduling, the model algorithm outperformed the traditional queu-
ing model, better meeting the goals of efficiency and cost-saving for port management [84].
Further illustrating the application of smart technologies in port operations, Liu et al. (2024)
conducted a study of Tianjin port, highlighting how smart port infrastructures, such as IoT
and AI, can enhance the sustainability and efficiency of port operations through improved
logistics and operational practices [85]. Moreover, the application of Renewable Energy
Technologies (RET) in ports is being increasingly recognized for its potential to mitigate
environmental impacts. Parhamfar et al. (2023) summarized the potential, challenges
and economic aspects of applying RETs in green ports. They discussed how fuel cells
might be used as a backup or primary power source to provide ports with electricity. The
results showed that RETs can play a significant role in helping the marine sector achieve its
J. Mar. Sci. Eng. 2024, 12, 1728 18 of 27

sustainable development objectives and pave the way for the construction of eco-friendly
and more productive ports [5].
Addressing the regulatory landscape, the International Maritime Organization’s (IMO)
Marine Environment Protection Committee (MEPC) has proposed a long-term carbon tax on
ports (IMO, 2005) [86]. To reduce carbon emissions in port areas, operators primarily focus
on optimizing ship berth allocation, improving the loading efficiency of wharf cranes and
utilizing low-sulfur diesel fuel. To address the gap in joint berth and shore crane allocation
under carbon emission tax policies, Wang et al. proposed models for the two tax policies,
respectively, focusing on carbon emission of Quality Control (QC), and developed a series
of equivalent or loose models [87]. In order to reduce berth emissions from ships calling at
ports, Wu et al. investigated the Shore Power Deployment Problem (SPDP) in container
shipping networks, established a framework to capture the complex relationship between
governments, ports and ships, and utilized the proposed labeling algorithm to bring huge
environmental and health benefits to the implementation of subsidy programs [88]. Wang
et al. also explored the integrated issue of berth allocation and QC allocation under carbon
emission tax considerations. They developed a dual-objective integer programming model
aimed at minimizing both the total completion delay of all tasks and the total operating
cost of all quality control [89].
The shipping industry’s move towards shore power represents a cutting-edge ap-
proach to reducing greenhouse gas emissions. In May 2019, the IMO adopted resolution
MEPC.323 (74), entitled “Invitation to Member States to encourage voluntary cooperation
between the port and the shipping sectors to contribute to reducing GHG from ships”. The
resolution advocates for regulatory, technical, operational, and economic actions within the
port sector. Shore power, sometimes referred to as Cold Ironing (CI), Alternative Marine
Power (AMP), or Onshore Power Supply (OPS), is one of the main resolutions supported by
the IMO to reduce greenhouse gas (GHG) emissions. In fact, studies have shown that CI is
effective in reducing shipping emissions both at sea and in ports [90,91]. Daniel et al. (2024)
analyzed the influence of CI on international environmental regulations and incentives
using a bulk carrier case study. Their findings showed that CI can increase the Carbon
Intensity Indicator (CII) by 7.8%, and they proposed policy changes to incorporate CI into
Energy Efficiency Design Index (EEDI) and Energy Efficiency Existing Ship Index (EEXI)
calculations. Currently, CI has the potential to eliminate 100% of emissions from ships at
berth [92].

5. Existing Challenges and Future Opportunities for Sustainable Maritime Transport

The maritime transport industry is at a critical juncture, with the increasing demands
for sustainability and technological innovation driving significant changes. While intel-
ligent shipping technologies and green port construction present new opportunities for
reducing environmental impacts and improving efficiency, numerous challenges, such as
data inaccuracies, network security, equipment failure, regulatory hurdles, high costs, and
international coordination persist. This section explores both the obstacles and opportuni-
ties that lie ahead for achieving sustainable maritime transport, focusing on the integration
of advanced technologies and the development of eco-friendly port construction.

5.1. Intelligent Shipping Technology

With the rapid development of computer technology, artificial intelligence technology
and other scientific and technological fields, significant progress has been made in the
development of intelligent ship technology, but there are still some problems to be solved
in the future. Firstly, the limitation of AIS data will lead to the inaccurate prediction of ship
trajectory. In terms of intelligent shipping technology, many scholars rely on visualization,
simulation, data mining, machine learning, neural network, and other technologies to study
ship historical trajectory based on AIS data. However, the original AIS data may confront
challenges pertaining to restricted coverage area, elevated latency periods, inaccuracies
in data, along with disparities in data formatting, which may hinder its efficacy [63]. In
J. Mar. Sci. Eng. 2024, 12, 1728 19 of 27

addition, there is limited research on the trajectory data under special climatic conditions
and different vessel backgrounds. Taking the tropical cyclone Veronica that occurred in
the northwest waters of Australia in 2019 as an example, a Bayesian network framework
was constructed based on AIS data to study the actual behavior trajectory and delay
characteristics of ships during tropical cyclones [93]. This is one of the future research
directions, such as extreme climate, common accidents at sea, ship type, ship size, deck
crew, sailing status and so on [94,95].
In addition to using only track-related data, various maritime data sources are also
thoroughly explored to help predict ship tracks, including onboard sensor data, meteo-
rological data and port operations data. Before making decisions in complex navigation
scenarios where collision avoidance is required, individual sensors may encounter re-
dundancy, conflicts, and deficiencies in target identification. Additionally, sensors can be
impacted by uncontrollable factors such as severe weather. It is imperative to consider
the uncertainty of data sources and the inconsistency of multi-sensor data to enhance data
reliability. Therefore, another prevailing challenge lies in identifying and integrating multi-
source heterogeneous maritime data to support ship motion pattern recognition. In the
context of future autonomous navigation, the integration of AIS, radar, and GPS data will
be essential for more autonomous and accurate perception of the surrounding navigation
environment. Moreover, the fusion of multi-source shipboard data with intelligent route
planning will be a key area for future research [96].
In addition, the new development model of Shipping 4.0 proposed at the First World
Maritime Science and Technology Conference signifies that people are generating massive
amounts of data at different levels, and utilizing data mining and database programs
to extract information from these data [97]. Among them, data security and privacy
protection will also become important issues of concern. Ensuring that ship data is not
accessed and tampered with unauthorizedly, while protecting the personal privacy of
crew members are crucial issues that need to be addressed in technological development.
Furthermore, equipment failure remains a significant unsolved issue in the maritime
transportation sector. Currently, failure mode and effects analysis (FMEA) is regarded as a
reliable technique for mitigating risks and enhancing shipping safety. Integrating it with
Bayesian networks, generative adversarial networks (GANs), and other methods represents
a promising direction for future research [98,99].
With the in-depth application of machine learning and deep learning algorithms in the
shipping industry, the autonomy of intelligent ships will be significantly enhanced in the
future, thereby reducing operational costs, and improving efficiency and safety. However, it
is noteworthy that in the current research, there exists inconsistency between uncontrollable
navigation environments, dynamic traffic flows, and simulation-based methods. It must
be acknowledged that models, algorithms, and practical operations still cannot achieve a
high degree of accuracy and seamless integration [96]. The primary reason lies in the fact
that the real navigation environment is complex, dynamic, and nonlinear, and conducting
actual tests on ships can be costly. Therefore, the generalization and operability of methods
and models need to be comprehensively evaluated and considered in future research.
In terms of maritime transportation, the potential benefits of blockchain technology for
shipping enterprises are becoming increasingly apparent [100]. In recent years, blockchain
technology has been identified as a potential solution for achieving maritime supply chain
integration and enhancing the efficiency of maritime logistics [101]. A significant research
focus in the future could be on integrating blockchain technology and digital technologies
into shipping supply chains. This integration would involve conducting extensive research
investigations and multiple case studies to test and validate the proposed framework. The
aim is to provide ship management with enhanced decision support, ultimately serving as
a reference for strategic decision-making within enterprises [102].
J. Mar. Sci. Eng. 2024, 12, 1728 20 of 27

5.2. Green Port Construction

While green port construction plays a crucial role in advancing maritime sustain-
ability, it continues to face some limitations. Major challenges include the high cost of
infrastructure upgrades and the adoption of new technologies. For instance, implementing
renewable energy sources like solar or wind, modifying equipment to lower emissions,
and introducing smart logistics systems are all expensive initiatives that can strain port
budgets, especially for smaller or developing ports [103]. Furthermore, these upgrades
often require long-term investments that might not yield immediate economic benefits,
making it harder to evaluate them financially [104]. Additionally, building green ports
requires advanced technologies and highly skilled labor, both of which are often in short
supply. The integration of smart systems, such as IoT and AI, to optimize operations
and reduce environmental impacts necessitates extensive technical expertise and training,
which may be lacking in many port regions [105]. This skill gap presents a barrier to
achieving the full potential of green port initiatives.
The lack of standardized regulations across different regions and countries has posed
barriers to implementing green port initiatives as well [106]. Ports operating under different
legal frameworks face difficulties in aligning their green initiatives with international
standards, which creates discrepancies in environmental performance. This inconsistency
often leads to inefficiencies, as ports in countries with stricter regulations may be at a
competitive disadvantage compared to those with more lenient policies [107].
Moreover, operational challenges due to the conflict of goals between efficiency and
emission reduction also pose significant difficulties. Ports must find ways to reduce
emissions without compromising efficiency, which can be a complex and resource-intensive
task [108]. Take the Shanghai port case study as an example. As the port has implemented
greener technologies, it has had to contend with adjusting operational schedules and energy
sources, which initially created inefficiencies [109]. Achieving carbon emission reduction
targets often involves implementing advanced optimization models, but these systems
may not always align with the fast-paced, high-efficiency requirements of busy ports. The
conflict is particularly evident in ports striving to remain competitive while simultaneously
adhering to stringent environmental policies [110].
In terms of future opportunities for green port development, CI stands out as a key
innovation in the electrification of the maritime industry. CI technology, which involves
switching from diesel engines to shore-based electrical power while ships are docked, offers
significant potential for reducing emissions and integrating alternative energy sources into
port operations. Looking forward, CI could be utilized as part of a broader green port
strategy, serving both electric ships and conventional vessels retrofitted to use onshore
power. This technology not only lowers greenhouse gas emissions, but contributes to
energy efficiency and improved air quality in port regions.
Moreover, the integration of CI with RETs presents a promising area for future re-
search and development. By combining RETs such as solar, wind, or hydrogen with
smart port technologies—such as Artificial Intelligence (AI), Internet of Things (IoT), and
blockchain—ports can optimize energy consumption and reduce operational costs. These
digital solutions will enable real-time monitoring and management of energy flows, further
enhancing the environmental performance of green ports. For instance, AI and IoT could
analyze energy usage patterns to improve efficiency, while blockchain could facilitate
transparent carbon accounting and collaboration across the supply chain [111].
In addition to technological advancements, future opportunities lie in the collaboration
among stakeholders, including shipowners, port operators, and policymakers [112]. Joint
efforts in developing standardized regulations and incentivizing sustainable practices will
help accelerate the adoption of CI and other green technologies. As regulatory frameworks
evolve to enforce stricter emission standards, ports will need to invest in cleaner infrastruc-
ture, and the cost of retrofitting ships for CI will become more economically viable through
subsidies or carbon credits [113].
J. Mar. Sci. Eng. 2024, 12, 1728 21 of 27

6. Conclusions
This review summarizes the relevant publications on the application of intelligent
shipping technology and green port construction in the field of sustainable maritime trans-
port and adopts bibliometric methods to collect 462 publications between 2000 and 2023,
based on SCI Expanded, SSCI, and ESCI databases. The research reveals that over the
past 13 years, the literature in the field of sustainable maritime transport applications has
become increasingly extensive, with a rapid growth in the number of publications, par-
ticularly since 2018. Furthermore, the study underscores the preeminent position of the
Journal of Marine Science and Engineering, Ocean Engineering, and IEEE Transactions on
Intelligent Transportation Systems, as evidenced by their substantially higher publication
output in this area compared to other journals. This shows their status as leading publica-
tions within the field, providing researchers with invaluable resources and guidance for
their endeavors.
An analysis of the author collaboration network reveals that, despite certain individu-
als contributing a higher volume of publications, academic cooperation within the field
remains predominantly confined to individual research teams, with limited instances of
cross-team collaboration. For upcoming research endeavors, reinforcing inter-team collabo-
ration holds paramount importance. This collaboration has the potential to expand research
vistas, integrate multifaceted approaches and viewpoints, transcend the limitations posed
by narrow perspectives, and ultimately fortify the trustworthiness of research findings.
According to the analysis of the organizational collaboration network, Wuhan Uni-
versity of Technology, Dalian Maritime University, Hong Kong Polytechnic University,
and Shanghai Maritime University have produced numerous publications in sustainable
maritime transport, significantly contributing to the field’s advancement. However, an
analysis of the organizational collaboration network diagram indicates a lack of intimate
collaboration among these organizations. To propel the field’s growth further, organizations
must enhance their partnerships, foster knowledge and research experience sharing, and
collaboratively facilitate the dissemination and utilization of research outcomes.
According to the country collaboration analysis, China stands as a foremost contributor
within the scholarly corpus of sustainable maritime transport, boasting the largest volume
of publications (190), trailed closely by the United States and England. The VOSviewer-
constructed country collaboration network analysis highlights China’s dominance not
only in publication volume but in the extent and intimacy of international collaborations,
underpinned by the Chinese government’s steadfast commitment to fostering sustainable
maritime transport development. Nevertheless, given shipping’s inherently global nature,
confronting challenges necessitates concerted efforts across nations. Each country harbors
distinct strengths and expertise in shipping, emphasizing the urgency to deepen interna-
tional cooperation and harness complementary knowledge bases to propel the holistic
progress of sustainable maritime transport research.
The analysis of keyword co-occurrence unveils the pivotal research clusters within
the realm of sustainable maritime transport applications. Among the various keywords
identified, AIS data stands out as the most prevalent, constituting a pivotal research
hotspot within this domain. Furthermore, the findings underscore AI technology, trajectory
forecasting, eco-friendly ports, and additional clusters as contemporary focal points of
research within this field. Based on the analysis, it is found that there are two hot areas in
the direction of sustainable maritime transport, namely intelligent shipping technology
and green port construction. Therefore, the research status of these two applications
is described, providing references for researchers in any future exploration in this field.
Finally, the development of intelligent shipping technology and green port construction in
sustainable maritime transport is discussed from two aspects of existing challenges and
future opportunities. As far as intelligent shipping technology is concerned, with the rapid
development of big data and intelligence, data security and data source integration will
become the focus of urgent attention in the future. In ship trajectory prediction, research on
different climates and different ship types will also become the direction for future research.
J. Mar. Sci. Eng. 2024, 12, 1728 22 of 27

In terms of green port construction, in recent years, more scholars have paid attention to
the application of CI in ports, and some studies have also shown that CI has become one of
the indispensable energy sources in the future and is a major focus for future research.
During the inaugural address of the second United Nations Global Sustainable Trans-
port Conference, Xu Lirong, the Chairman and Party Secretary of COSCO Shipping Group,
eloquently remarked: “Maritime transport is a key force to promote the development of
global sustainable transport. We will actively fulfill our social responsibilities, vigorously
promote technological innovation in the industry, actively support and drive the industry to
move towards a green and sustainable direction, and contribute China’s shipping strength
to the sustainable development of global transportation [1]”. The results of this review can
assist scholars in understanding the development trend in the field of sustainable maritime
transport, gaining a better comprehension of the current status in this field and identifying
potential research opportunities.
Furthermore, it must be acknowledged that this review has limitations, and further
in-depth investigation is needed. Firstly, despite conducting a systematic literature review
process, the reliance on a specific database (WoS) for article selection inevitably led to
the potential omission of some significant articles. Furthermore, the selection of search
keywords was limited to the themes of the selected papers and the two focal areas, namely
intelligent shipping technology and green port construction, which constitutes another
limitation of this review. This approach may have overlooked other challenges faced by
the shipping industry in its current state and practice, such as those related to maritime
logistics and transportation accident risks. Therefore, future research should aim to mini-
mize bias by utilizing a wider range of databases to select relevant papers. Additionally,
this review primarily focused on the analysis of scientific papers, neglecting the inclusion
of mandatory regulations, patents, and industry documents, which represents a possible
limitation. To expand the scope and depth of this research, future endeavors should delve
deeper into these aspects. Lastly, this review solely employs bibliometric methods for its
comprehensive analysis. While these methods primarily focus on providing abundant
data support and quantitative analysis, enabling researchers to grasp research trends in
the maritime transportation field from a macro perspective, they inherently fall short in
deeply elucidating the causal relationships between different technologies and strategies,
or evaluating their actual effectiveness. To overcome this limitation, future research could
consider integrating multiple research methodologies, such as case studies and experimen-
tal validations. By comprehensively analyzing data and information from diverse sources,
we can offer more scientific and rational suggestions and guidance for the sustainable
development of the shipping industry.

Author Contributions: Conceptualization, G.X. and Y.W.; methodology, G.X., Y.W., R.W. and Z.C.;
writing—original draft preparation, G.X. and Y.W.; writing—review and editing, G.X., R.W., J.L. and
Z.C.; funding acquisition, G.X. and J.L. All authors have read and agreed to the published version of
the manuscript.
Funding: This research was funded by National Natural Science Foundation of China, grant num-
ber 52472323, Beijing Natural Science Foundation, grant number 9244032, The Ministry of Educa-
tion of Humanities and Social Science project, grant 23YJC630190 and Shanghai Sailing Program,
grant 21YF1445800.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: Readers can access our data by sending an email to the corresponding
author Guangnian Xiao.
Conflicts of Interest: The authors declare no conflicts of interest.
J. Mar. Sci. Eng. 2024, 12, 1728 23 of 27

References
1. Ma, S.R. Addressing the climate challenge: Transforming and innovating together the second UN global sustainable transport
conference focuses on the future of the maritime industry. Marit. China 2021, 11, 24–25.
2. Wang, J.Y. Analysing the impact of the worldwide outbreak of new crown on the shipping industry. Pearl River Water Transp.
2020, 82–83. [CrossRef]
3. Shi, W.M.; Li, K.X. Themes and tools of maritime transport research during 2000–2014. Marit. Policy Manag. 2017, 44, 151–169.
[CrossRef]
4. Tian, Z.; Liu, F.; Li, Z.; Malekian, R.; Xie, Y. The development of key technologies in applications of vessels connected to the
Internet. Symmetry 2017, 9, 211. [CrossRef]
5. Parhamfar, M.; Sadeghkhani, I.; Adeli, A.M. Towards the application of renewable energy technologies in green ports: Technical
and economic perspectives. IET Renew. Power Gener. 2023, 17, 3120–3132. [CrossRef]
6. Huang, J.X.; Duan, X.L. A comprehensive review of emission reduction technologies for marine transportation. J. Renew. Sustain.
Energy 2023, 15, 032702. [CrossRef]
7. Cao, Y.; Wang, X.; Yang, Z.; Wang, J.; Wang, H.; Liu, Z. Research in marine accidents: A bibliometric analysis, systematic review
and future directions. Ocean. Eng. 2023, 284, 115048. [CrossRef]
8. Xu, M.; Ma, X.; Zhao, Y.; Qiao, W. A systematic literature review of maritime transportation safety management. J. Mar. Sci. Eng.
2023, 11, 2311. [CrossRef]
9. Wu, X.; Wu, J.; Xu, L. Advanced research on the sustainable maritime transportation. J. Mar. Sci. Eng. 2024, 12, 1104. [CrossRef]
10. Donthu, N.; Kumar, S.; Mukherjee, D.; Pandey, N.; Lim, W.M. How to conduct a bibliometric analysis: An overview and
guidelines. J. Bus. Res. 2021, 133, 285–296. [CrossRef]
11. Ellegaard, O.; Wallin, J.A. The bibliometric analysis of scholarly production: How great is the impact? Scientometrics 2015, 105,
1809–1831. [CrossRef] [PubMed]
12. Wallin, J.A. Bibliometric methods: Pitfalls and possibilities. Basic Clin. Pharmacol. Toxicol. 2005, 97, 261–275. [CrossRef] [PubMed]
13. Zhu, J.; Liu, W. A tale of two databases: The use of Web of Science and Scopus in academic papers. Scientometrics 2020, 123,
321–335. [CrossRef]
14. Ahmed, S.; Alshater, M.M.; Ammari, A.E.; Hammami, H. Artificial intelligence and machine learning in finance: A bibliometric
review. Res. Int. Bus. Financ. 2022, 61, 101646. [CrossRef]
15. Xiao, G.; Yang, D.; Xu, L.; Li, J.; Jiang, Z. The application of artificial intelligence technology in shipping: A bibliometric review. J.
Mar. Sci. Eng. 2024, 12, 624. [CrossRef]
16. Xiao, G.; Chen, L.; Chen, X.; Jiang, C.; Ni, A.; Zhang, C.; Zong, F. A hybrid visualization model for knowledge mapping:
Scientometrics, SAOM, and SAO. IEEE Trans. Intell. Transp. Syst. 2024, 25, 2208–2221. [CrossRef]
17. Adnan, A.R.; Widowati, R.; Nuryakin. Evolution and trends in Indonesian green marketing research: A systematic review
(2018-2023). J. Green Econ. Low-Carbon Dev. 2023, 2, 162–174. [CrossRef]
18. Torku, A.; Chan, A.P.C.; Yung, E.H.K. Age-friendly cities and communities: A review and future directions. Ageing Soc. 2021, 41,
2242–2279. [CrossRef]
19. Xu, C.; Yu, D.; Yang, H.; Yu, S. 20 years of economic corridors development: A bibliometric analysis. J. Appl. Econ. 2021, 24,
173–192. [CrossRef]
20. Waltman, L.; van Eck, N.J.; Noyons, E.C.M. A unified approach to mapping and clustering of bibliometric networks. J. Informetr.
2010, 4, 629–635. [CrossRef]
21. Wang, S.; Zhen, L.; Psaraftis, H.N.; Yan, R. Implications of the EU’s inclusion of maritime transport in the emissions trading
system for shipping companies comment. Engineering 2021, 7, 554–557. [CrossRef]
22. Zhen, L.; Yuan, Y.; Zhuge, D.; Psaraftis, H.N.; Wang, S. Subsidy strategy design for shore power utilization and promotion. Marit.
Policy Manag. 2023, 1–33. [CrossRef]
23. Zhuge, D.; Wang, S.; Zhen, L.; Psaraftis, H.N. Data-Driven modeling of maritime transportation: Key issues, challenges, and
solutions. Engineering 2023, 31, 25–26. [CrossRef]
24. Lagemann, B.; Lagouvardou, S.; Lindstad, E.; Fagerholt, K.; Psaraftis, H.N.; Erikstad, S.O. Optimal ship lifetime fuel and power
system selection under uncertainty. Transp. Res. Part D Transp. Environ. 2023, 119, 103748. [CrossRef]
25. Lagemann, B.; Lindstad, E.; Fagerholt, K.; Rialland, A.; Erikstad, S.O. Optimal ship lifetime fuel and power system selection.
Transp. Res. Part D Transp. Environ. 2022, 102, 103145. [CrossRef]
26. Jiang, M.Z.; Lu, J.; Qu, Z.H.; Yang, Z.L. Port vulnerability assessment from a supply Chain perspective. Ocean. Coast. Manag. 2021,
213, 105851. [CrossRef]
27. Li, H.H.; Jiao, H.; Yang, Z.L. AIS data-driven ship trajectory prediction modelling and analysis based on machine learning and
deep learning methods. Transp. Res. Part E Logist. Transp. Rev. 2023, 175, 103152. [CrossRef]
28. Wang, J.G.; Li, H.H.; Yang, Z.L.; Ge, Y.E. Shore power for reduction of shipping emission in port: A bibliometric analysis. Transp.
Res. Part E Logist. Transp. Rev. 2024, 188, 103639. [CrossRef]
29. Psaraftis, H.N.; Kontovas, C.A. Balancing the economic and environmental performance of maritime transportation. Transp. Res.
Part D Transp. Environ. 2010, 15, 458–462. [CrossRef]
J. Mar. Sci. Eng. 2024, 12, 1728 24 of 27

30. Psaraftis, H.N.; Kontovas, C.A. Speed models for energy-efficient maritime transportation: A taxonomy and survey. Transp. Res.
Part C Emerg. Technol. 2013, 26, 331–351. [CrossRef]
31. Psaraftis, H.N.; Kontovas, C.A. Decarbonization of maritime transport: Is there light at the end of the tunnel? Sustainability 2021,
13, 237. [CrossRef]
32. Chua, J.Y.; Wang, X.Q.; Yuen, K.F. Sustainable shipping management: Definitions, critical success factors, drivers and performance.
Transp. Policy 2023, 141, 72–82. [CrossRef]
33. Wang, X.Q.; Yuen, K.F.; Wong, Y.D.; Li, K.X. How can the maritime industry meet Sustainable Development Goals? An analysis
of sustainability reports from the social entrepreneurship perspective. Transp. Res. Part D Transp. Environ. 2020, 78, 102173.
[CrossRef]
34. Yuen, K.F.; Li, K.X.; Xu, G.Y.; Wang, X.Q.; Wong, Y.D. A taxonomy of resources for sustainable shipping management: Their
interrelationships and effects on business performance. Transp. Res. Part E Logist. Transp. Rev. 2019, 128, 316–332. [CrossRef]
35. Yuen, K.F.; Wang, X.Q.; Wong, Y.D.; Li, K.X. The role of stakeholder participation and sustainability integration in maritime
transport: A structure-conduct-performance analysis. Transp. Policy 2020, 99, 44–53. [CrossRef]
36. Ducruet, C. Port specialization and connectivity in the global maritime network. Marit. Policy Manag. 2022, 49, 1–17. [CrossRef]
37. Mou, N.X.; Xu, H.Q.; Liu, Y.; Li, G.Q.; Zhang, L.X.; Ducruet, C.; Zhang, X.H.; Wang, Y.C.; Yang, T.F. Does the Chinese coastal ports
disruption affect the reliability of the maritime network? Evidence from port importance and typhoon risk. Int. J. Appl. Earth Obs.
Geoinf. 2024, 129, 103846. [CrossRef]
38. Rousset, L.; Ducruet, C. Disruptions in Spatial Networks: A Comparative Study of Major Shocks Affecting Ports and Shipping
Patterns. Netw. Spat. Econ. 2020, 20, 423–447. [CrossRef]
39. Du, Y.Q.; Meng, Q.; Wang, S.A.; Kuang, H.B. Two-phase optimal solutions for ship speed and trim optimization over a voyage
using voyage report data. Transp. Res. Part B Methodol. 2019, 122, 88–114. [CrossRef]
40. Wang, S.A.; Meng, Q. Sailing speed optimization for container ships in a liner shipping network. Transp. Res. Part E Logist. Transp.
Rev. 2012, 48, 701–714. [CrossRef]
41. Wang, S.A.; Meng, Q. Container liner fleet deployment: A systematic overview. Transp. Res. Part C Emerg. Technol. 2017, 77,
389–404. [CrossRef]
42. Aakko-Saksa, P.T.; Lehtoranta, K.; Kuittinen, N.; Järvinen, A.; Jalkanen, J.P.; Johnson, K.; Jung, H.; Ntziachristos, L.; Gagné, S.;
Takahashi, C.; et al. Reduction in greenhouse gas and other emissions from ship engines: Current trends and future options. Prog.
Energy Combust. Sci. 2023, 94, 101055. [CrossRef]
43. Kangasniemi, O.; Simonen, P.; Moldanová, J.; Timonen, H.; Barreira, L.M.F.; Hellén, H.; Jalkanen, J.P.; Majamäki, E.; D’Anna, B.;
Lanzafame, G.; et al. Volatility of a ship’s emissions in the Baltic Sea using modelling and measurements in real-world conditions.
Atmosphere 2023, 14, 1175. [CrossRef]
44. Lagouvardou, S.; Psaraftis, H.N.; Zis, T. Impacts of a bunker levy on decarbonizing shipping: A tanker case study. Transp. Res.
Part D Transp. Environ. 2022, 106, 103257. [CrossRef]
45. Lagouvardou, S.; Psaraftis, H.N.; Zis, T. A literature survey on market-based measures for the decarbonization of shipping.
Sustainability 2020, 12, 3953. [CrossRef]
46. Iris, Ç.; Lam, J.S.L. A review of energy efficiency in ports: Operational strategies, technologies and energy management systems.
Renew. Sustain. Energy Rev. 2019, 112, 170–182. [CrossRef]
47. Iris, Ç.; Lam, J.S.L. Optimal energy management and operations planning in seaports with smart grid while harnessing renewable
energy under uncertainty. Omega 2021, 103, 102445. [CrossRef]
48. Chen, Y.; Wang, W.; Chen, X.M. Bibliometric methods in traffic flow prediction based on artificial intelligence. Expert Syst. Appl.
2023, 228, 120421. [CrossRef]
49. Yu, D.; Xu, Z.; Fujita, H. Bibliometric analysis on the evolution of applied intelligence. Appl. Intell. 2019, 49, 449–462. [CrossRef]
50. Halim, R.A.; Kirstein, L.; Merk, O.; Martinez, L.M. Decarbonization pathways for international maritime transport: A model-based
policy impact assessment. Sustainability 2018, 10, 2243. [CrossRef]
51. Traut, M.; Larkin, A.; Anderson, K.; McGlade, C.; Sharmina, M.; Smith, T. CO2 abatement goals for international shipping. Clim.
Policy 2018, 18, 1066–1075. [CrossRef]
52. Yan, X.P.; Liu, C.G. Review and prospect for intelligent waterway transportation system. CAAI Trans. Intell. Syst. 2016, 11,
807–817. [CrossRef]
53. He, X.H. Research of Structure Frame Designing of Shipping Intelligent Transportation System. Ph.D. Thesis, Tongji University,
Shanghai, China, 2007.
54. Chen, X.; Wu, H.; Han, B.; Liu, W.; Montewka, J.; Liu, R.W. Orientation-aware ship detection via a rotation feature decoupling
supported deep learning approach. Eng. Appl. Artif. Intell. 2023, 125, 106686. [CrossRef]
55. SMASH! SMASH! Launches Roadmap Smart Shipping during Europort. Available online: https://smashnederland.nl/en/news/
smash-launches-roadmap-smart-shipping-during-europort/ (accessed on 3 November 2021).
56. A world first! Very Large LNG Ship Across the Ocean: Half Autonomous, Half Crew Operated! Captain: “Greatly Improve
the Crew’s Working Comfort!”. Available online: https://www.cnss.com.cn/html/sdbd/20220606/346369.html (accessed on 6
June 2022).
J. Mar. Sci. Eng. 2024, 12, 1728 25 of 27

57. China’s First Self-Developed Unmanned Cargo Ship Has Completed Its Maiden Voyage. Available online: https://www.
eworldship.com/html/2019/NewShipUnderConstrunction_1215/155317.html (accessed on 15 December 2019).
58. ISOTC8/WG10. International Organization for Standardization Ship and Marine Technology Committee Intelligent Shipping
Working Group (ISOTC8/WG10) 8th Meeting. Available online: http://www.cansi.org.cn/cms/document/17656.html (accessed
on 17 May 2022).
59. Maritime Safety Committee. Maritime Safety Committee (MSC 105), 20–29 April 2022. Available online: https://www.imo.org/
en/MediaCentre/MeetingSummaries/Pages/MSC-105th-session.aspx (accessed on 29 April 2022).
60. Wang, W.; Yang, Y.; Yang, X.; Gayah, V.V.; Wang, Y.; Tang, J.; Yuan, Z. A negative binomial Lindley approach considering
spatiotemporal effects for modeling traffic crash frequency with excess zeros. Accid. Anal. Prev. 2024, 207, 107741. [CrossRef]
61. Enguehard, R.A.; Devillers, R.; Hoeber, O. Comparing interactive and automated mapping systems for supporting fisheries
enforcement activities—A case study on vessel monitoring systems (VMS). J. Coast. Conserv. 2013, 17, 105–119. [CrossRef]
62. Enguehard, R.A.; Hoeber, O.; Devillers, R. Interactive exploration of movement data: A case study of geovisual analytics for
fishing vessel analysis. Inf. Vis. 2013, 12, 65–84. [CrossRef]
63. Zhang, X.; Fu, X.; Xiao, Z.; Xu, H.; Qin, Z. Vessel trajectory prediction in maritime transportation: Current approaches and beyond.
IEEE Trans. Intell. Transp. Syst. 2022, 23, 19980–19998. [CrossRef]
64. Lei, P.-R. Mining maritime traffic conflict trajectories from a massive AIS data. Knowl. Inf. Syst. 2020, 62, 259–285. [CrossRef]
65. Chen, X.; Liu, Y.; Achuthan, K.; Zhang, X. A ship movement classification based on Automatic Identification System (AIS) data
using Convolutional Neural Network. Ocean. Eng. 2020, 218, 108182. [CrossRef]
66. Xiao, Z.; Fu, X.; Zhang, L.; Zhang, W.; Liu, R.W.; Liu, Z.; Goh, R.S.M. Big data driven vessel trajectory and navigating state
prediction with adaptive learning, motion modeling and particle filtering techniques. IEEE Trans. Intell. Transp. Syst. 2022, 23,
3696–3709. [CrossRef]
67. Abebe, M.; Noh, Y.; Kang, Y.-J.; Seo, C.; Kim, D.; Seo, J. Ship trajectory planning for collision avoidance using hybrid ARIMA-LSTM
models. Ocean. Eng. 2022, 256, 111527. [CrossRef]
68. Xiao, Y.; Li, X.; Yao, W.; Chen, J.; Hu, Y. Bidirectional data-driven trajectory prediction for intelligent maritime traffic. IEEE Trans.
Intell. Transp. Syst. 2023, 24, 1773–1785. [CrossRef]
69. Wang, M.; Wang, Y.; Cui, E.; Fu, X. A novel multi-ship collision probability estimation method considering data-driven
quantification of trajectory uncertainty. Ocean. Eng. 2023, 272, 113825. [CrossRef]
70. Li, H.; Xing, W.; Jiao, H.; Yang, Z.; Li, Y. Deep bi-directional information-empowered ship trajectory prediction for maritime
autonomous surface ships. Transp. Res. Part E Logist. Transp. Rev. 2024, 181, 103367. [CrossRef]
71. Liu, R.W.; Liang, M.; Nie, J.; Yuan, Y.; Xiong, Z.; Yu, H.; Guizani, N. STMGCN: Mobile edge computing-empowered vessel
trajectory prediction using spatio-temporal multigraph convolutional network. IEEE Trans. Ind. Inform. 2022, 18, 7977–7987.
[CrossRef]
72. Tu, E.; Zhang, G.; Rachmawati, L.; Rajabally, E.; Huang, G.B. Exploiting AIS data for intelligent maritime navigation: A
comprehensive survey from data to methodology. IEEE Trans. Intell. Transp. Syst. 2018, 19, 1559–1582. [CrossRef]
73. Xu, Y.; Yao, W.; Zheng, X.; Chen, X. An iterative information integration method for multi-level system reliability analysis based
on Bayesian Melding Method. Reliab. Eng. Syst. Saf. 2020, 204, 107201. [CrossRef]
74. Li, H.; Jiao, H.; Yang, Z. Ship trajectory prediction based on machine learning and deep learning: A systematic review and
methods analysis. Eng. Appl. Artif. Intell. 2023, 126, 107062. [CrossRef]
75. Wu, W.; Chen, P.; Chen, L.; Mou, J. Ship trajectory prediction: An integrated approach using ConvLSTM-Based Sequence-to-
Sequence Model. J. Mar. Sci. Eng. 2023, 11, 1484. [CrossRef]
76. Scorzolini, A.; Perini, V.D.; Razzano, E.; Colavolpe, G.; Mendes, S.; Fiori, P.; Sorbo, A. European enhanced space-based AIS system
study. In Proceedings of the 2010 5th Advanced Satellite Multimedia Systems Conference and the 11th Signal Processing for
Space Communications Workshop, Cagliari, Italy, 13–15 September 2010; pp. 9–16.
77. Mazzarella, F.; Arguedas, V.F.; Vespe, M. Knowledge-based vessel position prediction using historical AIS data. In Proceedings of
the 2015 Sensor Data Fusion: Trends, Solutions, Applications (SDF), Bonn, Germany, 6–8 October 2015; pp. 1–6.
78. Ministry of Transport of the People’s Republic of China. Water Transport “14th Five-Year” Development Plan. Available online:
https://xxgk.mot.gov.cn/2020/jigou/zhghs/202204/t20220407_3649837.html (accessed on 29 January 2022).
79. Corbett, J.J.; Wang, H.; Winebrake, J.J. The effectiveness and costs of speed reductions on emissions from international shipping.
Transp. Res. Part D Transp. Environ. 2009, 14, 593–598. [CrossRef]
80. Dong, M.; Li, Y.; Xu, X.; Zha, Y. A practical accessibility evaluation method for port-centric coal transportation chains: Considering
the environment and operational adaptability. Sustainablility 2022, 14, 11619. [CrossRef]
81. Fan, S.; Lu, Z. Research on the peak carbon dioxide emission strategy of Chinese port based on carbonemission estimation. Front.
Environ. Sci. 2022, 9, 789970. [CrossRef]
82. Jiang, L.; Tang, S.; Wang, G.; Yu, T.; Yuan, J. The evaluation of government subsidy policies on carbon emissions in the port
collection and distribution network: A case study of Guangzhou Port. Front. Mar. Sci. 2023, 10, 3389. [CrossRef]
83. Cammin, P.; Yu, J.; Voß, S. Tiered prediction models for port vessel emissions inventories. Flex. Serv. Manuf. J. 2023, 35, 142–169.
[CrossRef]
J. Mar. Sci. Eng. 2024, 12, 1728 26 of 27

84. Jiang, X.; Zhong, M.; Shi, J.; Li, W.; Sui, Y.; Dou, Y. Overall scheduling model for vessels scheduling and berth allocation for ports
with restricted channels that considers carbon emissions. J. Mar. Sci. Eng. 2022, 10, 1757. [CrossRef]
85. Liu, M.; Lai, K.-h.; Wong, C.; Xin, X.; Lun, Y.H. Smart ports for sustainable shipping: Concept and practices revisited through the
case study of China’s Tianjin port. Marit. Econ. Logist. 2024, 1–46. [CrossRef]
86. Zhang, C.; Xiao, G.; Xu, L. Manufacturers’ emission-reduction investments in competing supply chains with Prisoner’s Dilemma:
The economic and environmental impacts of Retailer(s) capital Constraint(s). Transp. Res. Part E Logist. Transp. Rev. 2024,
187, 103602. [CrossRef]
87. Wang, T.; Wang, X.; Meng, Q. Joint berth allocation and quay crane assignment under different carbon taxation policies. Transp.
Res. Part B Methodol. 2018, 117, 18–36. [CrossRef]
88. Wu, L.; Wang, S. The shore power deployment problem for maritime transportation. Transp. Res. Part E Logist. Transp. Rev. 2020,
135, 101883. [CrossRef]
89. Wang, T.; Du, Y.; Fang, D.; Li, Z.-C. Berth allocation and quay crane assignment for the trade-off between service efficiency and
operating cost considering carbon emission taxation. Transp. Sci. 2020, 54, 1307–1331. [CrossRef]
90. Sciberras, E.A.; Zahawi, B.; Atkinson, D.J. Reducing shipboard emissions—Assessment of the role of electrical technologies.
Transp. Res. Part D Transp. Environ. 2017, 51, 227–239. [CrossRef]
91. Yu, J.; Voß, S.; Tang, G. Strategy development for retrofitting ships for implementing shore side electricity. Transp. Res. Part D
Transp. Environ. 2019, 74, 201–213. [CrossRef]
92. Daniel, H.; Trovao, J.P.F.; Williams, D. Shore power as a first step toward shipping decarbonization and related policy impact on a
dry bulk cargo carrier. eTransportation 2022, 11, 100150. [CrossRef]
93. Zhang, C.; Zhao, P.; Huang, Z.; He, Z.; Niu, Y.; Huang, G.; Chen, Y. Assessing vessel transportation delays affected by tropical
cyclones using AIS data and a bayesian network: A case study of veronica in northwestern Australia. Ocean. Eng. 2024,
308, 118385. [CrossRef]
94. Chen, X.; Wei, C.; Xin, Z.; Zhao, J.; Xian, J. Ship detection under low-visibility weather interference via an ensemble generative
adversarial network. J. Mar. Sci. Eng. 2023, 11, 2065. [CrossRef]
95. Chen, X.; Zheng, J.; Li, C.; Wu, B.; Wu, H.; Montewka, J. Maritime traffic situation awareness analysis via high-fidelity ship
imaging trajectory. Multimed. Tools Appl. 2024, 83, 48907–48923. [CrossRef]
96. Zhang, D.; Chu, X.; Liu, C.; He, Z.; Zhang, P.; Wu, W. A review on motion prediction for intelligent ship navigation. J. Mar. Sci.
Eng. 2024, 12, 107. [CrossRef]
97. Soares, C.G. Intelligent shipping technology and development trend. In Proceedings of the first World Conference on Navigation
Science and Technology, Qingdao, China, 17–19 October 2023.
98. Tuncel, A.L.; Sezer, S.I.; Elidolu, G.; Uflaz, E.; Akyuz, E.; Arslan, O. A rule-based Bayesian network modelling under evidential
reasoning theory for risk analysis of anchoring operation in maritime transportation. Ocean. Eng. 2024, 292, 116521. [CrossRef]
99. Yigin, B.; Celik, M. A prescriptive model for failure analysis in ship machinery monitoring using Generative Adversarial Networks.
J. Mar. Sci. Eng. 2024, 12, 493. [CrossRef]
100. Singh, S.; Chakraborty, K.; Pratap, S.; Singh, M.; Zhou, F. Analysing factors influencing the adoption of blockchain technology in
maritime freight enterprises. Enterp. Inf. Syst. 2024, 18, 2326676. [CrossRef]
101. Queiroz, M.M.; Telles, R.; Bonilla, S.H. Blockchain and supply chain management integration: A systematic review of the
literature. Supply Chain. Manag. Int. J. 2020, 25, 241–254. [CrossRef]
102. Shin, S.; Wang, Y.; Pettit, S.; Abouarghoub, W. Blockchain application in maritime supply chain: A systematic literature review
and conceptual framework. Marit. Policy Manag. 2024, 51, 1062–1095. [CrossRef]
103. Puig, M.; Wooldridge, C.; Darbra, R.M. Identification and selection of environmental performance indicators for sustainable port
development. Mar. Pollut. Bull. 2014, 81, 124–130. [CrossRef]
104. Dinwoodie, J.; Tuck, S.; Knowles, H.; Benhin, J.; Sansom, M. Sustainable development of maritime operations in ports. Bus.
Strategy Environ. 2012, 21, 111–126. [CrossRef]
105. Özispa, N.; Arabelen, G. Sustainability issues in ports: Content analysis and review of the literature (1987–2017). SHS Web Conf.
2018, 58, 01022. [CrossRef]
106. Chen, X.; Dou, S.; Song, T.; Wu, H.; Sun, Y.; Xian, J. Spatial-temporal ship pollution distribution exploitation and harbor
environmental impact analysis via large-scale AIS data. J. Mar. Sci. Eng. 2024, 12, 960. [CrossRef]
107. Acciaro, M.; Ghiara, H.; Cusano, M.I. Energy management in seaports: A new role for port authorities. Energy Policy 2014, 71,
4–12. [CrossRef]
108. Lirn, T.-C.; Wu, Y.; Chen, Y. Green performance criteria for sustainable ports in Asia. Int. J. Phys. Distrib. Logist. Manag. 2013, 43,
427–451. [CrossRef]
109. Zeng, Y.; Yuan, X.; Hou, B. Analysis of carbon emission reduction at the port of integrated logistics: The port of Shanghai case
study. Sustainability 2023, 15, 10914. [CrossRef]
110. Peng, Y.; Li, X.; Wang, W.; Li, R. Review on energy saving and emission reduction strategies of green container ports. J. Traffic
Transp. Eng. 2022, 22, 28–46. [CrossRef]
111. Mansoursamaei, M.; Moradi, M.; González-Ramírez, R.G.; Lalla-Ruiz, E. Machine learning for promoting environmental
sustainability in ports. J. Adv. Transp. 2023, 2023, 2144733. [CrossRef]
J. Mar. Sci. Eng. 2024, 12, 1728 27 of 27

112. Xiao, G.; Cui, W. Evolutionary game between government and shipping enterprises based on shipping cycle and carbon quota.
Front. Mar. Sci. 2023, 10, 1132174. [CrossRef]
113. Bakar, N.N.A.; Bazmohammadi, N.; Vasquez, J.C.; Guerrero, J.M. Electrification of onshore power systems in maritime transporta-
tion towards decarbonization of ports: A review of the cold ironing technology. Renew. Sustain. Energy Rev. 2023, 178, 113243.
[CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.