Using global and regional datasets, we compared attention-based models and Long Short-Term Memory (LSTM) models to predict hydrologic variables. Our results show LSTM models perform better in simpler tasks, whereas attention-based models perform better in complex scenarios, offering insights for improved water resource management.

This study explores how combining different model types improves streamflow predictions, especially in data-sparse scenarios. By integrating two highly accurate models with distinct mechanisms and leveraging multiple meteorological datasets, we highlight their unique strengths and set new accuracy benchmarks across spatiotemporal conditions. Our findings enhance the understanding of how diverse models and multi-source data can be effectively used to improve hydrological predictions.

In this study we evaluate the performances of observation-based and climate model-based evapotranspiration estimations and project future changes for evapotranspiration in Australia. Our results show that climate models can provide reasonably accurate estimations, compared to observation-based estimations. This study offers new insights into future water loss and demand changes in Australia with implications for agriculture production, water security, and environmental management.