SWOT Observations Reveal Basin‐Scale Reservoir Operating Patterns

Abstract

The construction and operation of reservoirs have fundamentally modified the natural hydrograph globally. However, complex seasonal operating patterns remain opaque due to data scarcity, limiting the accuracy of hydrological modeling and water management. Here we show that the Surface Water and Ocean Topography satellite overcomes these challenges by providing full‐coverage water surface elevation measurements for a basin‐wide network of small reservoirs. Applying a two‐step framework to 305 reservoirs (>0.5 km2) in the Ganjiang River Basin (Yangtze), we found that single‐cycle regulation (33.4%) and dual‐cycle regulation (40.3%) patterns are dominant. Coupled with TimesNet deep learning, we predicted reservoir primary functions with an 86.0% accuracy and successfully disentangled multi‐purpose facilities. Our methodology characterizes reservoir regimes in data‐scarce basins, offering high‐resolution insights critical for understanding anthropogenic impacts on the global water cycle and supporting effective management.