Crop Water Productivity Mapping and Benchmarking Using Remote Sensing and Google Earth Engine Cloud Computing

Scarce water resources present a major hindrance to ensuring food security. Crop productivity (WP), embraced as one of the Sustainable Development Goals (SDGs), is playing an integral role in performance-based evaluation agricultural systems and securing sustainable production. This study aims at developing cloud-based model within Google Earth Engine (GEE) based on Landsat -7 -8 satellite imagery facilitate WP mapping regional scales (30-m resolution) analyzing state use efficiency sector means benchmarking its defining local gaps targets spatiotemporal scales. The was tested three districts Lake Urmia Basin (LUB) with respect five crop types, including irrigated wheat, rainfed apples, grapes, alfalfa, sugar beets grown crops. actual evapotranspiration (ET) estimated using geeSEBAL Surface Energy Balance Algorithm for Land (SEBAL) methodology, while yield estimations Monteith’s Light Use Efficiency (LUE) employed. results indicate that LUB below optimum targets, revealing there significant degree work necessary ameliorate LUB. varies between 0.49–0.55 (kg/m3) 0.27–0.34 1.7–2.2 1.2–1.7 5.5–6.2 beets, 0.67–1.08 which could be potentially increased up 80%, 150%, 76%, 83%, 55%, 48%, respectively. spatial variation makes it feasible detect areas best poorest on-farm practices, thereby facilitating better targeting bridge gap through management practices. provides important insights into status potential possible worldwide applications both farm government levels policymakers, practitioners, growers adopt effective policy guidelines improve