1 July 2007 in Environmental Modelling & Software
14 June 2012 in Progress in Physical Geography: Earth and Environment
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.
1 March 2006 in Journal of Hydrology
1 April 2003 in Hydrological Sciences Journal
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 ... Résumé Nous examinons le comportement interne d'un réseau de neurones artificiel à vocation de modélisation pluie—débit et montrons que certaines de ses caractéristiques architecturales peuvent êtr...
31 August 2002 in Hydrology and Earth System Sciences
This paper evaluates six published data fusion strategies for hydrological forecasting based on two contrasting catchments: the River Ouse and the Upper River Wye. The input level and discharge estimates for each river comprised a mixed set of single model forecasts. Data fusion was performed using: arithmetic-averaging, a probabilistic method in which the best model from the last time step is used to generate the current forecast, two different neural network operations and two different soft computing methodologies. The results from this investigation are compared and contrasted using statistical and graphical evaluation. Each location demonstrated several options and potential advantages for using data fusion tools to construct superior estimates of hydrological forecast. Fusion operations were better in overall terms in comparison to their individual modelling counterparts and two clear winners emerged. Indeed, the six different mechanisms on test revealed unequal aptitudes for fixing different categories of problematic catchment behaviour and, in such cases, the best method(s) were a good deal better than their closest rival(s). Neural network fusion of differenced data provided the best solution for a stable regime (with neural network fusion of original data being somewhat similar) — whereas a fuzzified probabilistic mechanism produced a superior output in a more volatile environment. The need for a data fusion research agenda within the hydrological sciences is discussed and some initial suggestions are presented. Keywords: data fusion, fuzzy logic, neural network, hydrological modelling
20 September 2007 in Hydrology and Earth System Sciences
Two recent studies have suggested that neural network modelling offers no worthwhile improvements in comparison to the application of weighted linear transfer functions for capturing the non-linear nature of hydrological relationships. The potential of an artificial neural network to perform simple non-linear hydrological transformations under controlled conditions is examined in this paper. Eight neural network models were developed: four full or partial emulations of a recognised non-linear hydrological rainfall-runoff model; four solutions developed on an identical set of inputs and a calculated runoff coefficient output. The use of different input combinations enabled the competencies of solutions developed on a reduced number of parameters to be assessed. The selected hydrological model had a limited number of inputs and contained no temporal component. The modelling process was based on a set of random inputs that had a uniform distribution and spanned a modest range of possibilities. The initial cloning operations permitted a direct comparison to be performed with the equation-based relationship. It also provided more general information about the power of a neural network to replicate mathematical equations and model modest non-linear relationships. The second group of experiments explored a different relationship that is of hydrological interest; the target surface contained a stronger set of non-linear properties and was more challenging. Linear modelling comparisons were performed against traditional least squares multiple linear regression solutions developed on identical datasets. The reported results demonstrate that neural networks are capable of modelling non-linear hydrological processes and are therefore appropriate tools for hydrological modelling.