Rainfall forecasting has been a popular research topic. Precise rainfall prediction can not only assist water management in region of water scarcity, but it can also warn or alleviate the effects of excess or insufficient rainfall. As a result of the advancement in information technology, current prediction methods are more diverse and sophisticated; however they require significant amounts of resources, and time are costly, and the forecast outcomes are still very uncertain. Therefore, this study proposed a novel rainfall forecast model, which combined the proposed integrated non-linear attributes selection method with support vector regression (SVR) to enhance the forecast performance. First, the proposed integrated non-linear attribute selection method was employed to determine the important attributes that affect rainfall in the mountainous region of Taiwan, and then, the selected attribute data were input into the SVR model to train the rainfall forecast model. To assess the prediction performance of the proposed model, this study collected rainfall data from 2005 to 2014 at monitoring stations in the Taiwanese mountains, and compared the proposed model results with those of the listing models. Experimental results show that the proposed model outperforms the listing models in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE).
de CastroT.N., SouzaF, JoséM, PontesR.S, dos ReisL.L and DaherS, Neo-fuzzy neuron model for seasonal rainfall forecast: A case study of Ceara’s eight homogenous regions, Journal of Intelligent and Fuzzy Systems25 (2013), 389–394.
2.
RezaeianzadehM., TabariH., YazdiA.A., IsikS. and KalinL., Flood flow forecasting using ANN, ANFIS and regression models, Neural Computing and Applications25 (2014), 25–37.
3.
HongW.-C., Rainfall forecasting by technological machine learning models, Applied Mathematics and Computation200 (2008), 41–57.
4.
HallM. and HolmesG., Benchmarking attribute selection techniques for discrete class data mining, Knowledge and Data Engineering, IEEE Transactions on15 (2003), 1437–1447.
5.
FanG.-F., PengL.-L., HongW.-C. and SunF., Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression, Neurocomputing173 (2016), 958–970.
6.
CortesC. and VapnikV., Support-vector networks, Machine Learning20 (1995), 273–297.
7.
BasakD., PalS. and PatranabisD.C., Support vector regression, Neural Information Processing-Letters and Reviews11 (2007), 203–224.
8.
BicanB. and YaslanY., A hybrid method for time series prediction using EMD and SVR, in Communications, Control and Signal Processing (ISCCSP), 2014 6th International Symposium on, pp. 2014, 566–569.
9.
GuB., ShengV.S., WangZ., HoD., OsmanS. and LiS., Incremental learning for ν-Support Vector Regression, Neural Networks67 (2015), 140–150.
10.
GuB., ShengV.S., TayK.Y., RomanoW. and LiS., Incremental support vector learning for ordinal regression, IEEE Transactions on Neural Networks and Learning Systems26 (2015), 1403–1416.
11.
HongW.-C., Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm, Neurocomputing74 (2011), 2096–2107.
12.
SpechtD.F., A general regression neural network, Neural Networks, IEEE Transactions on2 (1991), 568–576.
13.
ZhouQ., JiangH., WangJ. and ZhouJ., A hybrid model for PM 2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network, Science of the Total Environment496 (2014), 264–274.
14.
ParzenE., On estimation of a probability density function and mode, pp, The Annals of Mathematical Statistics (1962), 1065–1076.
15.
OnwuboluG.C., Prediction of burr formation during face milling using a hybrid GMDH network model with optimized cutting conditions, The International Journal of Advanced Manufacturing Technology44 (2009), 1083–1093.
16.
ZhangH., LiuX., CaiE., HuangG. and DingC., Integration of dynamic rainfall data with environmental factors to forecast debris flow using an improved GMDH model, Computers & Geosciences56 (2013), 23–31.
17.
AnastasakisL. and MortN., The development of self-organization techniques in modelling: A review of the group method of data handling (GMDH), ACSE Research Report No 813, University of Sheffield, UK, 2001.
18.
SedkiA., OuazarD. and ElE., Mazoudi, Evolving neural network using real coded genetic algorithm for daily rainfall–runoff forecasting, Expert Systems with Applications36 (2009), 4523–4527.
19.
XuY., LiK., HuJ. and LiK., A genetic algorithm for task scheduling on heterogeneous computing systems using multiple priority queues, Information Sciences270 (2014), 255–287.
20.
BenmahdjoubK., AmeurZ. and BoulifaM., Forecasting of rainfall using time delay neural network in tizi-ouzou (Algeria), Energy Procedia36 (2013), 1138–1146.
21.
AbbotJ. and MarohasyJ., Application of artificial neural networks to rainfall forecasting in, Queensland, Australia, Advances in Atmospheric Sciences29 (2012), 717–730.
22.
WuJ., LongJ. and LiuM., Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm, Neurocomputing148 (2015), 136–142.
23.
MercerA., DyerJ. and ZhangS., Warm-season thermodynamically-driven rainfall prediction with support vector machines, Procedia Computer Science20 (2013), 128–133.
24.
TanH. and MathewsJ.A., Identification and analysis of industry cycles, Journal of Business Research63 (2010), 454–462.
25.
CecenA. and XiaoL., Capital flows and current account dynamics in Turkey: A nonlinear time series analysis, Economic Modelling39 (2014), 240–246.
26.
KocadağliO. and AşıkgilB, Nonlinear time series forecasting with Bayesian neural networks, Expert Systems with Applications41 (2014), 6596–6610.
27.
YolcuU., EgriogluE. and AladagC.H., A new linear & nonlinear artificial neural network model for time series forecasting, Decision Support Systems54 (2013), 1340–1347.
28.
WilbyR.L. and WigleyT., Downscaling general circulation model output: A review of methods and limitations, Progress in Physical Geography21 (1997), 530–548.
29.
TsaiC.-F., Feature selection in bankruptcy prediction, Knowledge-Based Systems22 (2009), 120–127.
30.
ZhouX., LiK., ZhouY. and LiK., Adaptive processing for distributed skyline queries over uncertain data, IEEE Transactions on Knowledge and Data Engineering28 (2016), 371–384.
31.
KulkarniS.G., ChaudharyA.K., NandiS., TambeS.S. and KulkarniB.D., Modeling and monitoring of batch processes using principal component analysis (PCA) assisted generalized regression neural networks (GRNN), Biochemical Engineering Journal18 (2004), 193–210.
32.
IvakhnenkoA., Heuristic self-organization in problems of engineering cybernetics, Automatica6 (1970), 207–219.
33.
WangC.-P., LinS.-H., HuangH.-H. and WuP.-C., Using neural network for forecasting TXO price under different volatility models, Expert Systems with Applications39 (2012), 5025–5032.
34.
Omane-AdjepongM., OduroF.T. and OduroS.D., Determining the better approach for short-term forecasting of ghana’s inflation: Seasonal ARIMA Vs holt-winters, International Journal of Business, Humanities and Technology3 (2013), 69–79.
