Challenges in Applying Machine Learning Models for Hydrological Inference: A Case Study for Flooding Events Across Germany

Machine learning (ML) 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 ML algorithms. Despite advances in their predictive accuracy, the usefulness o...

Full description

Saved in:
Bibliographic Details
Published in:Water resources research Vol. 56; no. 5
Main Authors: Schmidt, Lennart, Heße, Falk, Attinger, Sabine, Kumar, Rohini
Format: Journal Article
Language:English
Published: Washington John Wiley & Sons, Inc 01.05.2020
Subjects:
Accuracy
Algorithms
Artificial neural networks
case studies
Computer applications
data collection
Datasets
Environment models
Environmental modeling
Flood predictions
Flooding
Floods
Germany
Heterogeneity
Hydrologic models
Hydrology
Inference
Learning algorithms
Machine learning
Model accuracy
Modelling
Neural networks
prediction
Regression analysis
water
Germany
ISSN:0043-1397, 1944-7973
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning (ML) 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 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 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 modeling also exists for ML 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. Key Points We investigate the use of machine learning methods for flood forecasting Predictive accuracy of ML methods is generally very high Using ML methods for inference, however, is very elusive and potentially error prone
Bibliography:ObjectType-Case Study-2
SourceType-Scholarly Journals-1
content type line 14
ObjectType-Feature-4
ObjectType-Report-1
ObjectType-Article-3
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0043-1397
1944-7973
DOI:10.1029/2019WR025924