Effective management of water resources amidst global climate change necessitates advancements in runoff simulation techniques. This study introduces a novel methodology that integrates a spatial element dynamic model with a neural network designed for satellite precipitation product (SPP) and remote sensing data to address the complex dynamics of precipitation-runoff processes. Implemented in the Songhua River basin of China, the methodology features a runoff estimation module that operates across both high-resolution and SPP grid scales. This module synergizes spatial attributes with fuzzy classification for refined confluence optimization, and yielding simulations through long short-term memory network. The results indicate that the proposed multi-scale production-confluence scheme achieved Nash-Sutcliffe efficiency (NSE) scores of 0.87 and 0.84 during calibration (2011–2015) and validation (2017 and 2018) periods, respectively, representing an 8.15% improvement in peak percentage error (PPE10%) over conventional hydrologic models. Additionally, the scheme demonstrated superior simulation performance at tributary sites set compared to main channel sites set, with differences of 0.08 and 0.07 in NSE and Kling-Gupta efficiency (KGE), respectively. The introduction of the surface Ⅱ operator for adjusting precipitation intensity effectively improved runoff estimation accuracy, reducing the average error by 25.48% across both site sets. This study provides a scientific foundation for applying SPP in hydrological modeling and offers decision support for managing water resources.
Read full abstract