TY - JOUR
T1 - Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models
AU - Zaherpour, Jamal
AU - Mount, Nick
AU - Gosling, Simon N.
AU - Dankers, Rutger
AU - Eisner, Stephanie
AU - Gerten, Dieter
AU - Liu, Xingcai
AU - Masaki, Yoshimitsu
AU - Müller Schmied, Hannes
AU - Tang, Qiuhong
AU - Wada, Yoshihide
PY - 2019/4
Y1 - 2019/4
N2 - 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 ensemble mean (EM). The performance gain offered by MMC suggests that future multi-model applications consider reporting MMCs, alongside the EM and intermodal range, to provide end-users 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.
AB - 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 ensemble mean (EM). The performance gain offered by MMC suggests that future multi-model applications consider reporting MMCs, alongside the EM and intermodal range, to provide end-users 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.
KW - Gene expression programming
KW - Global hydrological models
KW - Machine learning
KW - Model weighting
KW - Optimisation
U2 - 10.1016/j.envsoft.2019.01.003
DO - 10.1016/j.envsoft.2019.01.003
M3 - Article
AN - SCOPUS:85060914373
SN - 1364-8152
VL - 114
SP - 112
EP - 128
JO - Environmental Modelling and Software
JF - Environmental Modelling and Software
ER -