Performance Analysis of Deep Learning Classification for Agriculture Applications Using Sentinel-2 Data

North Indian states are largely covered with agricultural land which plays an important role in nation’s economy development. Remote sensing offers a cost-effective and efficient solution for sustainable monitoring and mapping of agricultural land. In past, various classification algorithms were developed and implemented for agriculture applications. But the conventional techniques are generally based on machine learning algorithms which are easy to implement but at the same time require human intervention on decision making. Nowadays, deep learning algorithms are becoming more popular due to the presence of trained models and one-time processing. However, the deep learning model required a large amount of computation time and needs to be tested in different regions for different applications. In the present work, the deep learning algorithm has been tested over agricultural land (over a part of Punjab state, India) using Sentinel-2 imagery. The major classes considered in the present analysis are vegetation area, water, and buildup area. For validation purposes, output classified maps are compared with reference datasets which were acquired from field observations for some points. The statistical results have shown that more than 80% of accuracy has been obtained using a deep learning algorithm. This study has many applications in the monitoring and mapping of land use land cover regions using a deep learning algorithm.