Improving Streamflow Predictions with Vision Transformers

Accurate streamflow prediction is crucial to understand climate impacts on water resources and develop effective adaption strategies. A global Long Short-Term Memory (LSTM) model, using data from multiple basins, can enhance streamflow prediction, yet acquiring detailed basin attributes remains a challenge. To overcome this, we introduce the Geo-ViT-LSTM model, a novel approach that enriches LSTM predictions by integrating basin attributes derived from remote sensing with a vision transformer. Applied to 531 basins across the United States (US), our method significantly outperforms existing models, showing an 11% increase in prediction accuracy. Geo-ViT-LSTM marks a significant advancement in land surface modeling, providing a more comprehensive and effective tool for managing water resources under climate change.