Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models

Zaherpour, Jamal and Mount, Nick J. and Gosling, Simon N. and Dankers, Rutger and Eisner, Stephanie and Dieter, Gerten and Liu, Xingcai and Masaki, Yoshimitsu and Müller Schmied, Hannes and Tang, Qiuhong and Wada, Yoshihide (2019) Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models. Environmental Modelling and Software . ISSN 1873-6726 (In Press)

[img] PDF - Repository staff only until 16 January 2020. - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Available under Licence Creative Commons Attribution Non-commercial No Derivatives.
Download (30MB)

Abstract

This study presents a novel application of machine learning to deliver optimised, multi-model combinations (MMCs) of Global Hydrological Model (GHM) simulations. We exemplify the approach using runoff simulations from five GHMs across 40 large global catchments. The benchmarked, median performance gain of the MMC solutions is 45% compared to the best performing GHM and exceeds 100% when compared to the EM. The performance gain offered by MMC suggests that future multimodel applications consider reporting MMCs, alongside the EM and intermodal range, to provide endusers of GHM ensembles with a better contextualised estimate of runoff. Importantly, the study highlights the difficulty of interpreting complex, non-linear MMC solutions in physical terms. This indicates that a pragmatic approach to future MMC studies based on machine learning methods is required, in which the allowable solution complexity is carefully constrained.

Item Type: Article
Keywords: Machine Learning; Model Weighting; Gene Expression Programming; Global Hydrological Models; Optimization
Schools/Departments: University of Nottingham, UK > Faculty of Social Sciences > School of Geography
Identification Number: https://doi.org/10.1016/j.envsoft.2019.01.003
Depositing User: Mount, Dr Nick
Date Deposited: 21 Jan 2019 09:25
Last Modified: 21 Jan 2019 09:25
URI: http://eprints.nottingham.ac.uk/id/eprint/55925

Actions (Archive Staff Only)

Edit View Edit View