Genetic programming model for forecast of short and noisy data

Abstract

Abstract:Though forecasting of river flow has received a great deal of attention from engineers and researchers throughout the world, this still continues to be a challenging task owing to the complexity of the process. In the last decade or so, artificial neural networks (ANNs) have been widely applied, and their ability to model complex phenomena has been clearly demonstrated. However, the success of ANNs depends very crucially on having representative records of sufficient length. Further, the forecast accuracy decreases rapidly with an increase in the forecast horizon. In this study, the use of the Darwinian theorybased recent evolutionary technique of genetic programming (GP) is suggested to forecast fortnightly flow up to 4-lead. It is demonstrated that short lead predictions can be significantly improved from a short and noisy time series if the stochastic (noise) component is appropriately filtered out. The deterministic component can then be easily modelled. Further, only the immediate antecedent exogenous and/or non-exogenous inputs can be assumed to control the process. With an increase in the forecast horizon, the stochastic components also play an important role in the forecast, besides the inherent difficulty in ascertaining the appropriate input variables which can be assumed to govern the underlying process. GP is found to be an efficient tool to identify the most appropriate input variables to achieve reasonable prediction accuracy for higher lead-period forecasts. A comparison with ANNs suggests that though there is no significant difference in the prediction accuracy, GP does offer some unique advantages.

Streamflow Modelling: A Primer on Applications, Approaches and Challenges

“…In some cases, the MLP architecture is chosen through trial-and-error (e.g., Jain and Kumar, 2007;Sivapragasam et al, 2007). Others adopt the MLP simply because it is considered to be the norm (e.g., Castellano-Méndez et al, 2004).…”

“…Rainfall-runoff modelling is a popular application of GP, covering a wide range of temporal scales, from sub-hourly to daily and weekly (e.g., Savic et al, 1999;Sivapragasam et al, 2007). GP has also shown promise in the field of downscaling GCM output, though it has not yet been directly applied in hydrological studies (Coulibaly, 2004).…”

“…GP does, however, have the distinct advantage of transparently displaying the relationship between predictors and predictands, whereas this knowledge is hidden in the weights of ANN models. This allows users to gain insight into the physical processes operating in the study watershed Sivapragasam et al, 2007). Comparison of ANNs and GP in daily rainfall-runoff modelling has indicated that the two approaches can yield results of similar quality (Savic et al, 1999;Sivapragasam et al, 2007).…”

“…This allows users to gain insight into the physical processes operating in the study watershed Sivapragasam et al, 2007). Comparison of ANNs and GP in daily rainfall-runoff modelling has indicated that the two approaches can yield results of similar quality (Savic et al, 1999;Sivapragasam et al, 2007). Aytek and Alp (2008) compared Gene Expression Programming (GEP) (Ferreira, 2006), a recent extension of GP, to ANNs and also found similar results between the two methods, indicating that GEP is a promising rainfall-runoff modelling tool.…”

A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series

“…Darwinian theory-based GP approach was suggested for improving fortnightly flow forecast for a 86 short time-series (Sivapragasam et al, 2007). 87…”