Automated analysis of snowmelt from Sentinel-2 imagery to determine variable rate irrigation zones in the American Mountain West

Variable rate irrigation (VRI) is used to save water whilst maintaining crop yields in semiarid regions. A key problem be able inexpensively determine spatial patterns soil moisture so that VRI zones can defined. In Southern Idaho, USA, the annual precipitation low and most falls as winter snow. This research investigates whether snow melt measured using freely available time-series Sentinel 2 imagery from Google Earth Engine define useful for two arable fields (Grace Rexburg). The normalized difference index (NDSI) was computed each 10 m pixel with all images of 2018-2022. NDSI values were ranked within image average ranks calculated month over several years. March similar yield observed previous Zones determined K-means classification mean NDSI. Kruskal Wallis H tests showed consistent significant differences between soil, plant, topographic variables. For Grace site, more their order magnitude than which a labor-intensive method. Rexburg shown better when based on snowmelt data 2018-2022 rather just 2019. It important base years because some there no field March. locations where majority comes snowmelt, basing inexpensive tool deriving meaningful zones. code automatically extract suitable sentinel calculate included practitioners use this approach other locations.