Mapping Paddy Cropland in Guntur District using Machine Learning and Google Earth Engine utilizing Images from Sentinel-1 and Sentinel-2

Abstract

Ensuring global food security necessitates vigilant monitoring of crop quantity and quality. Therefore, the reliable classification of croplands and diverse Land Covers (LC) becomes pivotal in fostering sustainable agricultural progress and safeguarding national food security. The Seasonal Crop Inventory (SCI) emerges as a strong asset. In this study, Sentinel-1 (S1) and Sentinel-2 (S2) image data were used to show varied land uses and paddy crops in Guntur district, Andhra Pradesh, India, during the 2021 growing season. Employing a technologically advanced space-based remote sensing approach, this study exploited the Google Earth Engine (GEE) and a range of classification techniques, including Random Forest (RF) and Classification Regression Trees (CART), to generate pixel-based SCI tailored to the area under investigation. The results underscored the reliability of GEE-based cropland mapping in the region, demonstrating a satisfactory level of classification accuracy, surpassing 97% across distinct time intervals in overall accuracy values, Kappa coefficients, and F1-Score.