Spatial Products for Crop Monitoring and Sustainable Agriculture


Murali Krishna Gumma

Geospatial and Big Data Sciences, International Crops Research Institute for the Semi-Arid Tropics (ICRISAT), Patancheru, India; Corresponding author email: 

Volume 15(Special Issue), 2022   ;   Click here for Pdf




The spatial cropland products are of great importance in water and food security assessments, especially in India, which is home to nearly 1.4 billion people and 160 million hectares of net cropland area. In India, croplands account for about 90% of all human water use. Cropland extent, cropping intensity, crop watering methods and crop types are important factors that have a bearing on the quantity, quality and location of production. Currently, cropland products are produced using mainly coarse-resolution (250-1000 m) remote sensing data., our study was aimed at producing three distinct spatial products at 30m and 250m resolution that would be useful and needed to address food and water security challenges. The first of these, Product 1, was to assess irrigated versus rainfed croplands in India using Landsat 30 m data in GEE platform. The second, Product 2, was to map major crop types using MODIS 250 m data. The third, Product 3, to map cropping intensity (single, double and triple cropping) using MODIS 250 m data. For the kharif season (the main cropping season in India, Jun-Oct), 9 major crops (5 irrigated crops: rice, soybean, maize, sugarcane, cotton; and 5 rainfed crops: pulses, rice, sorghum, millet, groundnut) were mapped. For the rabi season (post rainy season, Nov-Feb), 5 major crops (3 irrigated crops: rice, wheat, maize; and 2 rainfed crops: chickpea, pulses) were mapped. The irrigated versus rainfed 30 m product showed an overall accuracy of 79.8% with the irrigated cropland class providing a producer’s accuracy of 79% and the rainfed cropland class 74%. The overall accuracy demonstrated by the cropping intensity product was 85.3% with producer’s accuracies of 88%, 85% and 67% for single, double, and triple cropping respectively. Crop types were mapped to accuracy levels ranging from 72% to 97%. A comparison of the crop type area statistics with national statistics explained 63-98% variability. The study highlights production of multiple cropland products to support food security studies using multiple satellite sensor big-data, and RF machine learning algorithm that were coded, processed, and computed.