Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions. (January 2015)

• Record Type: Journal Article
• Authors: Wei, Chih-Chiang
• Is Part Of: Environmental modelling & software. Volume 63(2015:Jan.)
• Page Start: 137
• Page End: 155
• Publication Date: 2015-01
• Subjects: Eager learning -- Lazy learning -- Prediction -- Water level -- Basin; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2014.09.026
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: This study developed a methodology for formulating water level models to forecast river stages during typhoons, comparing various models by using lazy and eager learning approaches. Two lazy learning models were introduced: the locally weighted regression (LWR) and the k -nearest neighbor ( k NN) models. Their efficacy was compared with that of three eager learning models, namely, the artificial neural network (ANN), support vector regression (SVR), and linear regression (REG). These models were employed to analyze the Tanshui River Basin in Taiwan. The data collected comprised 50 historical typhoon events and relevant hourly hydrological data from the river basin during 1996–2007. The forecasting horizon ranged from 1 h to 4 h. Various statistical measures were calculated, including the correlation coefficient, mean absolute error, and root mean square error. Moreover, significance, computation efficiency, and Akaike information criterion were evaluated. The results indicated that (a) among the eager learning models, ANN and SVR yielded more favorable results than REG (based on statistical analyses and significance tests). Although ANN, SVR, and REG were categorized as eager learning models, their predictive abilities varied according to various global learning optimizers. (b) Regarding the lazy learning models, LWR performed more favorably than k NN. Although LWR and k NN were categorized as lazy learning models, their predictive abilities were based on diverse local learning optimizers. (c) A comparison of eager and lazy learning models indicated that neither were effective or yielded favorable results, because the distinct approximators of models that can be categorized as either eager or lazy learning models caused the performance to be dependent on individual models. Highlights: Lazy and eager learning models are modeled for water level forecasting in rivers. Lazy learning models, LWR and k NN are presented. Eager learning models, ANN, SVR, and regression are compared with LWR and k NN. The 50 historical typhoons that affected the studied watershed are collected. The distinct approximators of models cause the performance to be dependent on individual models.