ML class project for CS 5783 Due to advent and increasing use of Unmanned Aircraft System(UAS) aerial imagery has a potential to be used in multi-disciplinary application. More specially low altitude operation of UAS for surveillance, product delivery and remote sensing. In recent years, UAS equipped with camera sensors and onboard embedded platform for deep learning is being used to classify objects as well as land type during surveillance in real time. In this work, two different Neural Network (NN) has been utilized to classify land type from satellite imagery data. Images were extracted from the National Agriculture Imagery Program (NAIP) data set. The NAIP data set consists of a total of 330,000 scenes spanning the whole of the Continental United States. The imagery is acquired at a ground sample distance of 1 meter and original image tiles are approximately 6000 pixels in width and 7000 pixels in height. The images consist of 4 bands – red, green, blue and Near Infrared (NIR). The data set was labelled manually and downsized to 28X28. This data set known as Sat-4 data and can be found at https://csc.lsu.edu/~saikat/deepsat/. Report can be found at https://drive.google.com/file/d/11wBIjh1m33MKJQIkqTLutEfN9PYAJjlF/view?usp=sharing.