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

Zaherpour, J.; Mount, N.; Gosling, S. N.; Dankers, R.; Eisner, S.; Gerten, Dieter; Liu, X.; Masaki, Y.; Müller Schmied, H.; Tang, Q.; Wada, Y.

doi:10.1016/j.envsoft.2019.01.003

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben

Zeitschriftenartikel

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

Urheber*innen

Zaherpour, J.
External Organizations;

Mount, N.
External Organizations;

Gosling, S. N.
External Organizations;

Dankers, R.
External Organizations;

Eisner, S.
External Organizations;

/persons/resource/Dieter.Gerten

Gerten, Dieter
Potsdam Institute for Climate Impact Research;

Liu, X.
External Organizations;

Masaki, Y.
External Organizations;

Müller Schmied, H.
External Organizations;

Tang, Q.
External Organizations;

Wada, Y.
External Organizations;

Externe Ressourcen

Es sind keine externen Ressourcen hinterlegt

Volltexte (frei zugänglich)

22997oa.pdf
(Postprint), 2MB

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

Zaherpour, J., Mount, N., Gosling, S. N., Dankers, R., Eisner, S., Gerten, D., Liu, X., Masaki, Y., Müller Schmied, H., Tang, Q., Wada, Y. (2019): Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models. - Environmental Modelling and Software, 114, 112-128.
https://doi.org/10.1016/j.envsoft.2019.01.003

Zitierlink: https://publications.pik-potsdam.de/pubman/item/item_22997

Zusammenfassung

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.