Continuous observation and management of agriculture are essential to estimate crop yield and crop failure. Remote sensing is cost-effective, as well as being an efficient solution to monitor agriculture on a larger scale. With high-resolution satellite datasets, the monitoring and mapping of agricultural land are easier and more effective. Nowadays, the applicability of deep learning is continuously increasing in numerous scientific domains due to the availability of high-end computing facilities. In this study, deep learning (U-Net) has been implemented in the mapping of different agricultural land use types over a part of Punjab, India, using the Sentinel-2 data. As a comparative analysis, a well-known machine learning random forest (RF) has been tested. To assess the agricultural land, the major winter season crop types, i.e., wheat, berseem, mustard, and other vegetation have been considered. In the experimental outcomes, the U-Net deep learning and RF classifiers achieved 97.8% (kappa value: 0.9691) and 96.2% (Kappa value: 0.9469), respectively. Since little information exists on the vegetation cultivated by smallholders in the region, this study is particularly helpful in the assessment of the mustard (Brassica nigra), and berseem (Trifolium alexandrinum) acreage in the region. Deep learning on remote sensing data allows the object-level detection of the earth’s surface imagery.

To plan production, the sowing, and harvesting of a particular crop, and the performance of marketing activities information about yields is important for both the traders and producers. In this study, various efforts have been made to extract critical information for agriculture land use classification areas using Sentinel-2 datasets, which was not possible with the help of multi-spectral datasets. As part of the current work, the artificial neural networks (ANN) classifier is combined with the post-classification comparison (PCC), thereby predicting seasonal variability from satellite imagery. The ANN classifier is incorporated into the post-classification comparison procedure, called ANN-based change detection. As part of the demonstration, the datasets were acquired using Sentinel-2 datasets during the period 2017 – 2018 over the agricultural land in Block Khamanon, District Fatehgarh Sahib, Punjab State, India. This process cross-validated the performance of ANN with a conventional maximum likelihood classifier (MLC) for confirmation. In comparison with the conventional PCC-MLC model (classified maps have an average of 86 – 88.8%, and change maps have an average of 83.6 – 84.2%), the PCC-ANN model achieved accuracy (classified maps have an average of 90.4 – 93.4%, and change maps have an average of 87.4 – 90%). In addition to identifying water surfaces, crop types, and man-made features, this study can also help in performing a wide range of land-use patterns.