This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.
Downloads
Authors
Abstract
Machine learning (ML) is a powerful tool for hydrological modelling, forecasting, generation of new datasets, and process discovery. It is widely recognised for its ability to produce skillful predictions and generate insights about physical mechanisms through explainable AI (XAI). This manuscript outlines current progress in the use of ML in hydrology, new tools in XAI, and challenges in these areas. Continued areas of research for ML in hydrology include model interpretability, prediction in data-sparse regions, overcoming hydrology's `cascade of uncertainty', multivariate prediction, and causality.
DOI
https://doi.org/10.31223/X5069W
Subjects
Hydrology
Keywords
hydrology, machine learning, xAI
Dates
Published: 2024-09-09 04:47
License
Additional Metadata
Conflict of interest statement:
None
Data Availability (Reason not available):
Review article; no data.
There are no comments or no comments have been made public for this article.