Quantitative and Qualitative Analysis of PCC-based Change detection methods over Agricultural land using Sentinel-2 Dataset

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.