Robert J. Abrahart

HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts

This paper presents details of an open access web site that can be used by hydrologists and other scientists to evaluate time series models. There is at present a general lack of consistency in the way in which hydrological models are assessed that handicaps the comparison of reported studies and hinders the development of superior models. The HydroTest web site provides a wide range of objective metrics and consistent tests of model performance to assess forecasting skill. This resource is designed to promote future transparency and consistency between reported models and includes an open forum that is intended to encourage further discussion and debate on the topic of hydrological performance evaluation metrics. It is envisaged that the provision of such facilities will lead to the creation of superior forecasting metrics and the development of international benchmark time series datasets.

Detection of conceptual model rainfall—runoff processes inside an artificial neural network

Abstract The internal behaviour of an artificial neural network rainfall—runoff model is examined and it is demonstrated that specific architectural features can be interpreted with respect to the quasi-physical dynamics of a parsimonious water balance model. Neural network solutions were developed for daily discharge series simulated by a conceptual rainfall—runoff model given observed daily precipitation totals and evaporation rates for the Test River basin in southern England. Neural outputs associated with each hidden node, produced from the output node after all other hidden nodes had been deleted, were then compared with state variables and internal fluxes of the conceptual model (including soil moisture, percolation, groundwater recharge and baseflow). Correlation analysis suggests that hidden nodes in the neural network correspond to dominant processes within the conceptual model. In particular, different hidden nodes are associated with distinct “quickflow” and “baseflow” components, as well as a threshold state in the soil moisture accounting. The results also demonstrate that, for this river basin, a neural network with seven inputs and three hidden nodes can emulate the gross behaviour of the conceptual model.

Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting

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.

Multi-model data fusion for hydrological forecasting

This paper outlines some simple data fusion strategies for continuous river level forecasting where data fusion is defined as the amalgamation of information from different data sources. The objective of data fusion is to provide a better solution than could otherwise be achieved from the use of single-source data alone. In this paper, the simplest data-in/data-out fusion architecture was used to combine neural network, fuzzy logic, statistical, and persistence forecasts using four different experimental strategies to produce a single predicted output. In the first two experiments, mean and median values were calculated from the individual forecasts and used as the final forecasts. These types of approaches can be effective when the individual model residuals follow a consistent pattern of over and under prediction. In the other two experiments, amalgamation was performed with a neural network, which provided a more flexible solution based on function approximation. The four individual model outputs were input to a one hidden layer, feed-forward network that had been trained to produce a single final forecast. The second network was similar to the first, except that differenced values were used as inputs and outputs. These various data fusion strategies were implemented using hydrological data for the River Ouse gauge at Skelton, above York, in Northern England. Neither the mean nor the median produced improved results, whereas the two neural network data fusion approaches produced substantial gains with respect to their single solution components. The potential to obtain more accurate forecasts using data fusion methodologies could therefore have significant implications for the design and construction of automated flood forecasting and flood warning systems.

Timing error correction procedure applied to neural network rainfall—runoff modelling

Abstract Several studies have observed that neural network models will often produce phase-shift errors or timing lags in their output results. This paper investigates a potential solution to the timing error problem through the application of a procedure first applied in sunspot prediction. This procedure was applied to two neural network hydrological forecasting models for the River Ouse, in northern England, using a neuro-evolution toolbox. Models were optimised on a combination of root mean squared error and a timing correction factor. The application of this correction procedure produced timing improvements of up to about six hours on average over shorter forecasting horizons, whereas longer horizons showed little or no overall improvement in timing. The correction procedure also produced improved lower-magnitude estimates at the expense of higher-magnitude events over shorter forecasting horizons and, more significantly, improved higher-magnitude estimates at the expense of lower-magnitude events over longer forecasting horizons.

2006 Special issue: Symbiotic adaptive neuro-evolution applied to rainfall-runoff modelling in northern England

This paper uses a symbiotic adaptive neuro-evolutionary algorithm to breed neural network models for the River Ouse catchment. It advances on traditional evolutionary approaches by evolving and optimising individual neurons. Furthermore, it is ideal for experimentation with alternative objective functions. Recent research suggests that sum squared error may not result in the most appropriate models from a hydrological perspective. Models are bred for lead times of 6 and 24 hours and compared with conventional neural network models trained using backpropagation. The algorithm is also modified to use different objective functions in the optimisation process: mean squared error, relative error and the Nash-Sutcliffe coefficient of efficiency. The results show that at longer lead times the evolved neural networks outperform the conventional ones in terms of overall performance. It is also shown that the sum squared error objective function does not result in the best performing model from a hydrological perspective.

Data-driven modelling approaches for socio-hydrology: opportunities and challenges within the Panta Rhei Science Plan

ABSTRACT “Panta Rhei – Everything Flows” is the science plan for the International Association of Hydrological Sciences scientific decade 2013–2023. It is founded on the need for improved understanding of the mutual, two-way interactions occurring at the interface of hydrology and society, and their role in influencing future hydrologic system change. It calls for strategic research effort focused on the delivery of coupled, socio-hydrologic models. In this paper we explore and synthesize opportunities and challenges that socio-hydrology presents for data-driven modelling. We highlight the potential for a new era of collaboration between data-driven and more physically-based modellers that should improve our ability to model and manage socio-hydrologic systems. Crucially, we approach data-driven, conceptual and physical modelling paradigms as being complementary rather than competing, positioning them along a continuum of modelling approaches that reflects the relative extent to which hypotheses and/or data are available to inform the model development process. EDITOR D. Koutsoyiannis; ASSOCIATE EDITOR not assigned

Software, Data and Modelling News: HydroTest: Further development of a web resource for the standardised assessment of hydrological models

Hydro Test is an open access web resource that was established in 2005. This site offers a wide range of statistical metrics for the testing and evaluation of hydrological modelling outputs. In providing computational support to the international scientific community the authors are aiming to ensure that reported studies are based on consistent and accurate evaluations expressed in terms of recognised global standards. This article reports a number of recent improvements to the resource. These developments include a fresh user interface, additional statistical measures of model performance, a graphing facility, and an option to perform the simultaneous analysis of multiple model outputs. Through continuing development of this open access resource the authors are attempting to share and promote: the latest analytical procedures; discussions on current thinking; and a dynamic hydrological modelling tool that is evolving in parallel with its associated application domain.

Hydroinformatics: computational intelligence and technological developments in water science applications—Editorial

LINDA SEE, DIMITRI SOLOMATINE, ROBERT ABRAHART & ELENA TOTH 1School of Geography, University of Leeds, Leeds LS2 9JT, UK geolms@leeds.ac.uk 2UNESCO-IHE Institute for Water Education, PO Box 3015, 2601 DA Delft, The Netherlands d.solomatine@unesco-ihe.org 3School of Geography, University of Nottingham, Nottingham NG7 2RD, UK bob.abrahart@nottingham.ac.uk 4DISTART, Faculty of Engineering, University of Bologna, Bologna, Italy elena.toth@mail.ing.unibo.it

Use of Gene Expression Programming for Multimodel Combination of Rainfall-Runoff Models

AbstractThis paper deals with the application of an innovative method for combining estimated outputs from a number of rainfall-runoff models using gene expression programming (GEP) to perform symbolic regression. The GEP multimodel combination method uses the synchronous simulated river flows from four conventional rainfall-runoff models to produce a set of combined river flow estimates for four different catchments. The four selected models for the multimodel combinations are the linear perturbation model (LPM), the linearly varying gain factor model (LVGFM), the soil moisture accounting and routing (SMAR) model, and the probability-distributed interacting storage capacity (PDISC) model. The first two of these models are black-box models, the LPM exploiting seasonality and the LVGFM employing a storage-based coefficient of runoff. The remaining two are conceptual models. The data of four catchments with different geographical locations and hydrological and climatic conditions are used to test the perfor...