A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran

This study compared two machine learning techniques, support vector machines (SVM), and artificial neural network (ANN) in modeling monthly precipitation fluctuations. The SVM and ANN approaches were applied to the monthly precipitation data of two synoptic stations in Hamadan (Airport and Nojeh), the west of Iran. To avoid overfitting, the data were divided into two parts of training (70 %) and test sets (30 %). Then, monthly data from July 1976 to June 2001 and data from April 1961 to November 1996 were considered as training set for the Hamadan and Nojeh stations, respectively, and the remaining were used as test set. The results of the SVM model were compared with those of the ANN based on the root mean square errors, mean absolute errors, determination coefficient, and efficiency coefficient criteria. Based on the comparison, it was found that the SVM model outperformed the ANN, and the estimated precipitation values were in good agreement with the corresponding observed values.

[1]  Nitin K. Tripathi,et al.  An artificial neural network model for rainfall forecasting in Bangkok, Thailand , 2008 .

[2]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[3]  Rouslan A. Moro,et al.  Support Vector Machines (SVM) as a Technique for Solvency Analysis , 2008 .

[4]  Ahmed El-Shafie,et al.  Artificial neural network technique for rainfall forecasting applied to Alexandria, Egypt , 2011 .

[5]  Charles A. Doswell,et al.  Precipitation Forecasting Using a Neural Network , 1999 .

[6]  Ozgur Kisi,et al.  Comparison of two different data-driven techniques in modeling lake level fluctuations in Turkey , 2009 .

[7]  Supawadee Ingsriswang,et al.  Machine Learning Techniques for Short-Term Rain Forecasting System in the Northeastern Part of Thailand , 2008 .

[8]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[9]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[10]  Deg-Hyo Bae,et al.  Monthly dam inflow forecasts using weather forecasting information and neuro-fuzzy technique , 2007 .

[11]  Ajay Kalra,et al.  Estimating annual precipitation for the Colorado River Basin using oceanic‐atmospheric oscillations , 2012 .

[12]  Karim Solaimani,et al.  A study of rainfall forecasting models based on artificial neural network. , 2009 .

[13]  Yu-Min Wang,et al.  Using artificial neural networks for modeling suspended sediment concentration , 2008 .

[14]  I-Fan Chang,et al.  Support vector regression for real-time flood stage forecasting , 2006 .

[15]  K. Chau,et al.  Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques , 2010 .

[16]  Upmanu Lall,et al.  Support vector machines for nonlinear state space reconstruction: Application to the Great Salt Lake time series , 2005 .

[17]  N. J. Ferreira,et al.  Artificial neural network technique for rainfall forecasting applied to the São Paulo region , 2005 .

[18]  MohammadSajjad Khan,et al.  Application of Support Vector Machine in Lake Water Level Prediction , 2006 .

[19]  Junbin Gao,et al.  A Probabilistic Framework for SVM Regression and Error Bar Estimation , 2002, Machine Learning.

[20]  Luis A. Bastidas,et al.  Multiobjective analysis of chaotic dynamic systems with sparse learning machines , 2006 .

[21]  Luis A. Bastidas,et al.  Downscaling and Forecasting of Evapotranspiration Using a Synthetic Model of Wavelets and Support Vector Machines , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Daily Precipitation Prediction in Isparta Station by Artificial Neural Network , 2010 .

[23]  Y. Radhika,et al.  Atmospheric Temperature Prediction using Support Vector Machines , 2009 .

[24]  Ozgur Kisi,et al.  River Flow Modeling Using Artificial Neural Networks , 2004 .