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.
1.Univ Nottingham, Sch Geog, Sir Clive Granger Bldg, Nottingham NG7 2RD, England 2.Met Off, FitzRoy Rd, Exeter EX1 3PB, Devon, England 3.Univ Kassel, Ctr Environm Syst Res, Wilhelmshoher Allee 47, D-34109 Kassel, Germany 4.Potsdam Inst Climate Impact Res, D-14473 Potsdam, Germany 5.Humboldt Univ, Dept Geog, D-10099 Berlin, Germany 6.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Water Cycle & Related Land Surface Proc, Beijing, Peoples R China 7.Hirosaki Univ, Bunkyocho 3, Hirosaki, Aomori 0368561, Japan 8.Goethe Univ Frankfurt, Inst Phys Geog, Altenoferallee 1, D-60438 Frankfurt, Germany 9.Senckenberg Biodivers & Climate Res Ctr SBiK F, Senckenberganlage 25, D-60325 Frankfurt, Germany 10.IIASA, Schlosspl 1, A-2361 Laxenburg, Austria 11.Norwegian Inst Bioecon Res, POB 115, N-1431 As, Norway
Recommended Citation:
Zaherpour, Jamal,Mount, Nick,Gosling, Simon N.,et al. Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models[J]. ENVIRONMENTAL MODELLING & SOFTWARE,2019-01-01,114:112-128