Comparing LSTMs to hybrid deep learning models on generalization capabilities during extreme events.
Abstract
Data-driven techniques have shown the potential to outperform process-based models for rainfall-runoff simulation. Recently, hybrid models, which combine data-driven methods with process-based approaches, have been proposed to leverage the strengths of both methodologies, aiming to enhance simulation accuracy while maintaining certain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions, we test their generalization capabilities for extreme hydrological events, comparing their performance against Long Short-Term Memory (LSTM) networks and process based models. Our results indicate that hybrid models show similar performance as LSTM networks for most cases. However, hybrid models reported slightly lower errors in the most extreme cases, and were able to produce higher peak discharges.
Links
The code repository is available at https://github.com/eduardoAcunaEspinoza/.
Citation
@Article{espinoza2024extreme,
author = {Acuna Espinoza, E. and Loritz, R. and Kratzert, F. and Klotz, D. and Gauch, M. and \'Alvarez Chaves, M. and B\"auerle, N. and Ehret, U.},
title = {Analyzing the generalization capabilities of hybrid hydrological models for extrapolation to extreme events},
journal = {EGUsphere},
volume = {2024},
year = {2024},
pages = {1--17},
doi = {10.5194/egusphere-2024-2147}
}