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

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 g...

Full description

Bibliographic Details
Main Authors: Zaherpour, Jamal, Mount, Nick J., Gosling, Simon N., Dankers, Rutger, Eisner, Stephanie, Dieter, Gerten, Liu, Xingcai, Masaki, Yoshimitsu, Müller Schmied, Hannes, Tang, Qiuhong, Wada, Yoshihide
Format: Article
Language:English
Published: Elsevier 2019
Subjects:
Online Access:https://eprints.nottingham.ac.uk/55925/
_version_ 1848799239785676800
author Zaherpour, Jamal
Mount, Nick J.
Gosling, Simon N.
Dankers, Rutger
Eisner, Stephanie
Dieter, Gerten
Liu, Xingcai
Masaki, Yoshimitsu
Müller Schmied, Hannes
Tang, Qiuhong
Wada, Yoshihide
author_facet Zaherpour, Jamal
Mount, Nick J.
Gosling, Simon N.
Dankers, Rutger
Eisner, Stephanie
Dieter, Gerten
Liu, Xingcai
Masaki, Yoshimitsu
Müller Schmied, Hannes
Tang, Qiuhong
Wada, Yoshihide
author_sort Zaherpour, Jamal
building Nottingham Research Data Repository
collection Online Access
description 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.
first_indexed 2025-11-14T20:32:31Z
format Article
id nottingham-55925
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:32:31Z
publishDate 2019
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling nottingham-559252020-01-16T04:30:12Z https://eprints.nottingham.ac.uk/55925/ Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models Zaherpour, Jamal Mount, Nick J. Gosling, Simon N. Dankers, Rutger Eisner, Stephanie Dieter, Gerten Liu, Xingcai Masaki, Yoshimitsu Müller Schmied, Hannes Tang, Qiuhong Wada, Yoshihide 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. Elsevier 2019-01-12 Article PeerReviewed application/pdf en cc_by_nc_nd https://eprints.nottingham.ac.uk/55925/1/Exploring%20the%20value%20of%20machine%20learning%20for%20weighted%20multi-model%20combination%20of%20an%20ensemble%20of%20...%20Plus%20SI_Zaherpour%20et%20al._ENVSOFT_2017.pdf Zaherpour, Jamal, Mount, Nick J., Gosling, Simon N., Dankers, Rutger, Eisner, Stephanie, Dieter, Gerten, Liu, Xingcai, Masaki, Yoshimitsu, Müller Schmied, Hannes, 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) Machine Learning; Model Weighting; Gene Expression Programming; Global Hydrological Models; Optimization https://www.sciencedirect.com/science/article/pii/S1364815217309817 doi:10.1016/j.envsoft.2019.01.003 doi:10.1016/j.envsoft.2019.01.003
spellingShingle Machine Learning; Model Weighting; Gene Expression Programming; Global Hydrological Models; Optimization
Zaherpour, Jamal
Mount, Nick J.
Gosling, Simon N.
Dankers, Rutger
Eisner, Stephanie
Dieter, Gerten
Liu, Xingcai
Masaki, Yoshimitsu
Müller Schmied, Hannes
Tang, Qiuhong
Wada, Yoshihide
Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title_full Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title_fullStr Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title_full_unstemmed Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title_short Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
title_sort exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
topic Machine Learning; Model Weighting; Gene Expression Programming; Global Hydrological Models; Optimization
url https://eprints.nottingham.ac.uk/55925/
https://eprints.nottingham.ac.uk/55925/
https://eprints.nottingham.ac.uk/55925/