Articles | Volume 26, issue 3
https://doi.org/10.5194/hess-26-795-2022
https://doi.org/10.5194/hess-26-795-2022
Research article
 | 
14 Feb 2022
Research article |  | 14 Feb 2022

Evaluation and interpretation of convolutional long short-term memory networks for regional hydrological modelling

Sam Anderson and Valentina Radić

Model code and software

andersonsam/cnn_lstm_era: First release (Version v1.0.0) S. Anderson https://doi.org/10.5281/zenodo.5181175

Download
Short summary
We develop and interpret a spatiotemporal deep learning model for regional streamflow prediction at more than 200 stream gauge stations in western Canada. We find the novel modelling style to work very well for daily streamflow prediction. Importantly, we interpret model learning to show that it has learned to focus on physically interpretable and physically relevant information, which is a highly desirable quality of machine-learning-based hydrological models.