Untangling hybrid hydrological models with explainable artificial intelligence
H2Open Journal · 01.01.2021 · 4 (1) · 13-28
DOI: 10.2166/h2oj.2021.066 ↗Kurz gefasst
Fachartikel in der Zeitschrift H2Open Journal, online erschienen am 08.03.2021. Verfasst von Daniel Althoff und 2 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Hydrological models are valuable tools for developing streamflow predictions in unmonitored catchments to increase our understanding of hydrological processes. A recent effort has been made in the development of hybrid (conceptual/machine learning) models that can preserve some of the hydrological processes represented by conceptual models and can improve streamflow predictions. However, these studies have not explored how the data-driven component of hybrid models resolved runoff routing. In this study, explainable artificial intelligence (XAI) techniques are used to turn a ‘black-box’ model into a ‘glass box’ model. The hybrid models reduced the root-mean-square error of the simulated streamflow values by approximately 27, 50, and 24% for stations 17120000, 27380000, and 33680000, respectively, relative to the traditional method. XAI techniques helped unveil the importance of accounting for soil moisture in hydrological models. Differing from purely data-driven hydrological models, the inclusion of the production storage in the proposed hybrid model, which is responsible for estimating the water balance, reduced the short- and long-term dependencies of input variables for streamflow prediction. In addition, soil moisture controlled water percolation, which was the main predictor of streamflow. This finding is because soil moisture controls the underlying mechanisms of groundwater flow into river streams.
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
Althoff, D., Bazame, H. C., & Nascimento, J. G. (2021). Untangling hybrid hydrological models with explainable artificial intelligence. H2Open Journal, 4(1), 13-28. https://doi.org/10.2166/h2oj.2021.066
Vancouver
Althoff D, Bazame HC, Nascimento JG. Untangling hybrid hydrological models with explainable artificial intelligence. H2Open Journal. 2021;4(1):13-28. doi:10.2166/h2oj.2021.066
BibTeX
@article{Althoff2021,
author = {Althoff, Daniel and Bazame, Helizani Couto and Nascimento, Jessica Garcia},
title = {Untangling hybrid hydrological models with explainable artificial intelligence},
journal = {H2Open Journal},
year = {2021},
volume = {4},
number = {1},
pages = {13--28},
doi = {10.2166/h2oj.2021.066}
}
EUVIMED