Neural network modelling of non-linear hydrological relationships

Abstract

Abstract. 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 rainfallrunoff 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 nonlinear hydrological processes and are therefore appropriate tools for hydrological modelling.

An operational dynamical neuro-forecasting model for hydrological disasters

“…That is why, the use of ANN in hydrological modeling, generally characterized by a complex dependence between climatic and topographical variables, has increased since the 90 s and, under certain conditions (Hsu et al 1995;Abrahart and See 2007), it is an option as good as or even better than the traditional physical and conceptual models.…”

Genetic Programming Technique Applied for Flash-Flood Modelling Using Radar Rainfall Estimates

“…These black-box models have the ability to map out existing relationships between a set of input and output variable and have been suggested as efficient instruments for R-R modelling [2], [3] or [4]. The main issue with ANN is given by its black-box nature from which no insight or interpretation can be extracted regarding the underlying mechanisms of the analysed process.…”

Effect of data time interval on real-time flood forecasting

“…Among several artificial intelligence methods artificial neural networks (ANN) hold a vital role and ASCE Task Committee Reports (2000a,b) have accepted ANN as an efficient forecasting and modelling tool. Over the last decade, the artificial neural network has gained great attention and has evolved as the main branch of artificial intelligence that is now a recognised tool for modelling the underlying complexities in many artificial and physical systems including floods (Abrahart & See 2007;Solomatine & Ostfeld 2008). Unlike traditional conceptual and physics-based models, artificial neural networks are able to mimic flow observations, without any mathematical descriptions of the relevant physical processes.…”