Deep Learning for Streamflow Regionalization for Ungauged Basins: Application of Long-Short-Term-Memory Cells in Semiarid Regions

Rainfall-runoff modeling in ungauged basins continues to be a great hydrological research challenge. A novel approach is the Long-Short-Term-Memory neural network (LSTM) from the Deep Learning toolbox, which few works have addressed its use for rainfall-runoff regionalization. This work aims to discuss the application of LSTM as a regional method against traditional neural network (FFNN) and conceptual models in a practical framework with adverse conditions: reduced data availability, shallow soil catchments with semiarid climate, and monthly time step. For this, the watersheds chosen were located on State of Ceara, Northeast Brazil. For streamflow regionalization, both LSTM and FFNN were better than the hydrological model used as benchmark, however, the FFNN were quite superior. The neural network methods also showed the ability to aggregate process understanding from different watersheds as the performance of the neural networks trained with the regionalization data were better with the neural networks trained for single catchments.

Automated summary

This study discusses the application of LSTM as a regional method for rainfall-runoff modeling in adverse conditions. The results show that both LSTM and FFNN perform better than traditional hydrological models in streamflow regionalization, with FFNN being superior. Additionally, neural network methods have the ability to aggregate process understanding from different watersheds.