Multiple agricultural cropland products of South Asia developed using Landsat-8 30 m and MODIS 250 m data using machine learning on the Google Earth Engine (GEE) cloud and spectral matching techniques (SMTs) in support of food and water security

Cropland products are of great importance in water and food security assessments, especially South Asia, which is home to nearly 2 billion people 230 million hectares net cropland area. In croplands account for about 90% all human use. extent, cropping intensity, crop watering methods, types important factors that have a bearing on the quantity, quality, location production. Currently, produced using mainly coarse-resolution (250–1000 m) remote sensing data. As multiple needed address challenges, our study was aimed at producing three distinct would be useful overall Asia. The first these, Product 1, meant assess irrigated versus rainfed Asia Landsat 30 m data Google Earth Engine (GEE) platform. second, 2, tailored major Moderate Resolution Imaging Spectroradiometer (MODIS) 250 third, 3, designed intensity (single, double, triple cropping) MODIS For kharif season (the main Jun–Oct), 10 crops (5 crops: rice, soybean, maize, sugarcane, cotton; 5 pulses, sorghum, millet, groundnut) were mapped. rabi (post-rainy season, Nov–Feb), five (three wheat, maize; two chickpea, pulses) product showed an accuracy 79.8% with class providing producer’s 79% 74%. demonstrated by 85.3% accuracies 88%, 85%, 67% single, cropping, respectively. Crop mapped levels ranging from 72% 97%. A comparison crop-type area statistics national explained 63–98% variability. multiple-cropland crucial modeling, mapping, monitoring multiple-satellite sensor big-data, Random Forest (RF) machine learning algorithms coding, processing, computing GEE cloud.