Abstract
The Revised Universal Soil Loss Equation, Version 2 (RUSLE2), is the primary water erosion prediction tool used by the USDA National Resources Conservation Service (NRCS) for conservation planning across the United States. Despite its widespread adoption, RUSLE2’s current reliance on a personal computer-based model constrains its capacity for large-scale, dynamic applications. This research addresses these limitations by developing a novel cloud-based platform to host and enhance RUSLE2, enabling server-based computations, geospatial data integration, and scalable modeling capabilities. Built on Amazon Web Services (AWS), the platform incorporates web-based user interfaces, spatial databases, and geoprocessing tools to streamline soil erosion modeling. It integrates historical data on soil properties, climate, and land management to support precise assessments of rill and interrill erosion. A redesigned database architecture ensures computational efficiency, reliability, and security while fostering collaborative software development. Scientific advancements in RUSLE2 include quantifying the impacts of rainfall and land management practices on the spatiotemporal variability of dynamic soil properties. Leveraging advanced laboratory and field methods, remote sensing, and machine learning, this platform refines the measurement of soil erodibility and soil loss across diverse U.S. agricultural landscapes. These enhancements enable improved predictions of soil erosion risks under varying climate scenarios and support adaptive land management strategies. This transformative cloud-based platform promotes sustainable agriculture and conservation planning by delivering innovative tools for best management practices. Through the integration of cutting-edge technologies and data-driven approaches, this research addresses critical gaps in soil erosion science and contributes to food security, environmental conservation, and resilience to climate change.