Search

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 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. Highlights • We present the first use of machine learning-based model combination applied to a global hydrological model ensemble. • The multi-model combination (MMC) performs in most cases better than any individual input model and the ensemble mean. • MMC is not always able to out-perform model combination based on multiple linear regression. • The physical interpretation of the MMC solutions is limited by the complexity of their non-linear weighting schemes. [ABSTRACT FROM AUTHOR]

This paper traces two decades of neural network rainfall-runoff and streamflow modelling, collectively termed ‘river forecasting’. The field is now firmly established and the research community involved has much to offer hydrological science. First, however, it will be necessary to converge on more objective and consistent protocols for: selecting and treating inputs prior to model development; extracting physically meaningful insights from each proposed solution; and improving transparency in the benchmarking and reporting of experimental case studies. It is also clear that neural network river forecasting solutions will have limited appeal for operational purposes until confidence intervals can be attached to forecasts. Modular design, ensemble experiments, and hybridization with conventional hydrological models are yielding new tools for decision-making. The full potential for modelling complex hydrological systems, and for characterizing uncertainty, has yet to be realized. Further gains could also emerge from the provision of an agreed set of benchmark data sets and associated development of superior diagnostics for more rigorous intermodel evaluation. To achieve these goals will require a paradigm shift, such that the mass of individual isolated activities, focused on incremental technical refinement, is replaced by a more coordinated, problem-solving international research body. [ABSTRACT FROM PUBLISHER]

Summary: The decision sequence which guides the selection of a preferred data-driven modelling solution is usually based solely on statistical assessment of fit to a test dataset, and lacks the incorporation of essential contextual knowledge and understanding included in the evaluation of conventional empirical models. This paper demonstrates how hydrologic insight and knowledge of data quality issues can be better incorporated into the sediment-discharge data-driven model assessment procedure: by the plotting of datasets and modelled relationships; and from an understanding and appreciation of the hydrologic context of the catchment being modelled. DAMP: a four-point protocol for evaluating the hydrologic soundness of data-driven single-input single-output sediment rating curve solutions is presented. The approach is adopted and exemplified in an evaluation of seven explicit sediment-discharge models that are used to predict daily suspended sediment concentration values for a small tropical catchment on the island of Puerto Rico. Four neurocomputing counterparts are compared and contrasted against a set of traditional log–log linear sediment rating curve solutions and a simple linear regression model. The statistical assessment procedure provides one indication of the best model, whilst graphical and hydrologic interpretation of the depicted datasets and models challenge this overly-simplistic interpretation. Traditional log–log sediment rating curves, in terms of soundness and robustness, are found to deliver a superior overall product – irrespective of their poorer global goodness-of-fit statistics. [Copyright &y& Elsevier]

A correction is presented to the article "A comparison of changes in river runoff from multiple global and catchment-scale hydrological models under global warming scenarios of 1°C, 2°C and 3°C" which appeared in the December 9, 2016 issue.