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

Abstract

This 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 multi-model 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 multi-model 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 location, hydrological and climatic conditions, are used to test the performance of the GEP combination method.The results of the model using GEP method are compared against original forecasts obtained from the individual models that contributed to the development of the combined model by means of a few global statistics. The findings show that a GEP approach can successfully used as a multi-model combination method. In addition, the GEP combination method also has benefit over other hitherto tested approaches such as an artificial neural network combination method in that its formulation is transparent, can be expressed as a simple mathematical function, and therefore is useable by people who are unfamiliar with such advanced techniques. The GEP combination method is able to combine model outcomes from less accurate individual models and produce a superior river flow forecast.

Fuzzy committees of specialized rainfall-runoff models: further enhancements and tests

“…Further developments are foreseen in improving the weighting schemes involving hydrological states and various combinations of variables influencing the streamflow (for example those presented by Oudin et al, 2006;Kim et al, 2006;Corzo and Solomatine, 2007a, b;Marshall et al, 2007;Jeong and Kim, 2009;Fernando et al, 2012). Combining these approaches will hopefully lead to the techniques for discovering various regimes in the time series representing the modelled system -and this would allow for optimal combination of domain (hydrologic) knowledge incorporated in models with automatic machine learning or time-series analysis routines.…”

Gene Expression Programming Coupled with Unsupervised Learning: A Two-Stage Learning Process in Multi-Scale, Short-Term Water Demand Forecasts

“…The GEP is used in many engineering disciplines [28][29][30][31], and its operating functions are subjected to a vigorous learning process to find the optimum ones to use in the gene structures. As a tool to perform data-driven or self-learning techniques, GEP has some advantages over the conventional predictive models.…”

Real-time error correction method combined with combination flood forecasting technique for improving the accuracy of flood forecasting

“…The multi-model combination approach advocates the synchronous use of the simulated discharges of a number of models to produce an overall integrated result which can be used as an alternative to that produced by a single model (Fernando et al, 2011). Shamseldin et al (1997) first introduced the multi-model combination concept into the hydrologic field.…”

“…Shamseldin et al (1997) first introduced the multi-model combination concept into the hydrologic field. Since then there have been several more studies which have dealt with multi-model combination of hydrological models (Shamseldin and O'Connor, 1999;See and Openshaw, 2000;Xiong et al, 2001;Abrahart and See, 2002;Coulibaly et al, 2005;Ajami et al, 2006;Hsu et al, 2009;Shamseldin et al, 2007;Fernando et al, 2011). Georgakakos et al (2004) indicated that the http://dx.doi.org/10.1016/j.jhydrol.2014.11.053 0022-1694/Ó 2014 Elsevier B.V. All rights reserved.…”