Publication Details

Category Text Publication
Reference Category Journals
DOI 10.1029/2019WR025924
Licence creative commons licence
Title (Primary) Challenges in applying machine learning models for hydrological inference: A case study for flooding events across Germany
Author Schmidt, L.; Heße, F.; Attinger, S.; Kumar, R. ORCID logo
Source Titel Water Resources Research
Year 2020
Department CHS; MET
Volume 56
Issue 5
Page From e2019WR025924
Language englisch
Supplements https://agupubs.onlinelibrary.wiley.com/action/downloadSupplement?doi=10.1029%2F2019WR025924&file=wrcr24608-sup-0001-2019WR025924-ds01.pdf
Keywords Machine‐Learning; Inference; Floods
Abstract Machine learning algorithms are being increasingly used in Earth and Environmental modeling studies owing to the ever‐increasing availability of diverse data‐sets and computational resources as well as advancement in machine learning (ML) algorithms. Despite advances in their predictive accuracy, the usefulness of ML algorithms for inference remains elusive. In this study, we employ two popular ML algorithms, Artificial Neural Networks and Random Forest, to analyze a large data set of flood events across Germany with the goals to analyze their predictive accuracy and their usability to provide insights to hydrologic system functioning. The results of the ML algorithms are contrasted against a parametric approach based on multiple linear regression. For analysis, we employ a model‐agnostic framework named Permuted Feature Importance to derive the influence of a models' predictors. This allows us to compare the results of different algorithms for the first time in the context of hydrology. Our main findings are that 1) the ML‐models achieve higher prediction accuracy than linear regression, 2) the results reflect basic hydrological principles but 3) further inference is hindered by the heterogeneity of results across algorithms. Thus, we conclude that the problem of equifinality as known from classical hydrological modelling also exists for machine‐learning and severely hampers its potential for inference. To account for the observed problems, we propose that when employing ML for inference, this should be made by using multiple algorithms and multiple methods, of which the latter should be embedded in a cross‐validation routine.
Persistent UFZ Identifier https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=23060
Schmidt, L., Heße, F., Attinger, S., Kumar, R. (2020):
Challenges in applying machine learning models for hydrological inference: A case study for flooding events across Germany
Water Resour. Res. 56 (5), e2019WR025924 10.1029/2019WR025924