Modeling Soil Futures: Integrating Classic and Emerging Approaches to Water Erosion

Soil erosion by water remains one of the most pressing forms of land degradation, undermining agricultural productivity, ecosystem services, and global food security. Over the past decades, diverse modeling approaches have been developed to quantify and predict soil erosion, ranging from classical empirical models to advanced machine learning and hybrid frameworks. This review synthesizes the evolution of erosion modeling, highlighting both the historical foundations and emerging directions. Empirical models such as USLE and RUSLE provided the first standardized and widely adopted methods, while process-based models like WEPP and EUROSEM advanced mechanistic understanding but faced limitations due to extensive data demands. The integration of Geographic Information Systems (GIS) and Remote Sensing (RS) transformed erosion modeling by enabling spatially explicit risk assessments at watershed and regional scales. More recently, machine learning algorithms—including Random Forests, Support Vector Machines, and deep learning architectures—have demonstrated superior predictive power, although challenges of interpretability, transferability, and data dependency remain unresolved. Hybrid and integrated models now represent the state-of-the-art frontier, combining empirical transparency, process-based rigor, and AI-driven adaptability. Future-oriented perspectives, including GeoAI, digital twins, cloud-based platforms, and participatory modeling approaches, offer transformative potential. These innovations are particularly critical under non-stationary conditions driven by climate change and land-use transformations, which demand dynamic, probabilistic, and stakeholder-inclusive frameworks. The review concludes that no single paradigm is sufficient to capture the complexity of water erosion. The way forward lies in integrated, multi-scale, and uncertainty-aware modeling systems that bridge scientific precision with policy relevance, supporting sustainable land management and climate adaptation in the coming decades.