Long-term rainfall forecasting using deep neural network coupling with input variables selection technique: A case study of Ping River Basin, Thailand

Main Article Content

Uruya Weesakul
Krisada Chaiyasarn
Shekhar Mahat

Abstract

Long-term rainfall forecast is essential for water resources planning and management. Various approaches for forecasting have been developed, however, the accuracy of the forecast is still not satisfied for real engineering practice, particularly for monthly rainfall forecast with leading time of one-year ahead. This study aims to investigate the capability of the machine learning approach in the forecasting of monthly rainfall by using Deep Learning Neural Network (DNN) as a tool for calculation. Ping river basin, situated in the northern part of Thailand, was selected as a study area due to its availability of long time series of rainfall data. Six rainfall stations, distributed over the river basin, were selected for analysis using monthly rainfall from 1975 to 2018. The stochastic efficiency (SE) and correlation coefficient (r) were used for evaluation of model performance. Based on previous studies in this area, it has been revealed that 24 large-scale atmospheric variables (LAV), which were used as predictors in the DNN model, have correlations with seasonal rainfall over the Ping river basin. The result of the first simulation using all 24 LAV during the validation period (2009-2018) in predicting monthly rainfall for six rainfall stations for one-year ahead indicates that DNN is capable of forecasting with an accuracy of the forecast ranging from 58% to 72% with correlation coefficient from 0.59 to 0.82. Further improvement of the forecast was also conducted by the input selection technique resulting in a reduction of input LAV from 24 to 13 LAV. The second simulation of DNN with the input selection technique reveals that DNN provides better accuracy of the forecast for one-year ahead with the stochastic efficiency of the forecast ranging from 69% to 78%, with correlation coefficient from 0.75 to 0.82 for all stations.

Article Details

How to Cite
Weesakul, U., Chaiyasarn, . K., & Mahat, S. (2021). Long-term rainfall forecasting using deep neural network coupling with input variables selection technique: A case study of Ping River Basin, Thailand. Engineering and Applied Science Research, 48(2), 209–220. Retrieved from https://ph01.tci-thaijo.org/index.php/easr/article/view/241620
Section
ORIGINAL RESEARCH

References

Yu PS, Yang TC, Chen SY, Kuo CM, Tseng HW. Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting. J Hydrol. 2017;552:92-104.

Abdourahamane ZS, Acar R, Serkan Ş. Wavelet–copula-based mutual information for rainfall forecasting applications. Hydrolog Process. 2019;33(7):1127-42.

Mekanik F, Imteaz MA, Talei A. Seasonal rainfall forecasting by adaptive network-based fuzzy inference system (ANFIS) using large scale climate signals. Clim Dynam. 2016;46(9-10):3097-111.

Acharya R, Pal J, Das D, Chaudhuri S. Long‐range forecast of Indian summer monsoon rainfall using an artificial neural network model. Meteorol Appl. 2019;26(3):347-61.

Mishra N, Soni HK, Sharma S, Upadhyay AK. Development and analysis of artificial neural network models for rainfall prediction by using time-series data. Int J Intell Syst Appl. 2018;10(1):16-23.

Khalili N, Khodashenas SR, Davary K, Baygi MM, Karimaldini F. Prediction of rainfall using artificial neural networks for synoptic station of Mashhad: a case study. Arab J Geosci. 2016;9(13):624.

Babel MS, Badgujar GB, Shinde VR. Using the mutual information technique to select explanatory variables in artificial neural networks for rainfall forecasting. Meteorol Appl. 2015;22(3):610-6.

Alotaibi K, Ghumman AR, Haider H, Ghazaw YM, Shafiquzzaman M. Future predictions of rainfall and temperature using GCM and ANN for arid regions: a case study for the Qassim Region, Saudi Arabia. Water. 2018;10(9):1260.

Beheshti Z, Firouzi M, Shamsuddin SM, Zibarzani M, Yusop Z. A new rainfall forecasting model using the CAPSO algorithm and an artificial neural network. Neural Comput Appl. 2016;27(8):2551-65.

Singh P, Borah B. Indian summer monsoon rainfall prediction using artificial neural network. Stoch Environ Res Risk Assess. 2013;27:1585-99.

Hung NQ, Babel MS, Weesakul S, Tripathi NK. An artificial neural network model for rainfall forecasting in Bangkok, Thailand. Hydrol Earth Syst Sci. 2009;13:1413-25.

Sulaiman J, Wahab SH. Heavy rainfall forecasting model using artificial neural network for flood prone area. In: Kim K, Kim H, Baek N, editors. IT Convergence and Security 2017. Singapore: Springer; 2018. p. 68-76.

Nourani V, Uzelaltinbulat S, Sadikoglu F, Behfar N. Artificial intelligence based ensemble modeling for multi-station prediction of precipitation. Atmosphere. 2019;10(2):80.

Kumar D, Singh A, Samui P, Jha RK. Forecasting monthly precipitation using sequential modelling. Hydrolog Sci J. 2019;64(6):690-700.

Luo J, Lu W, Ji Y, Ye D. A comparison of three prediction models for predicting monthly precipitation in Liaoyuan city, China. Water Sci Tech Water Supply. 2016;16(3):845-54.

Devi SR, Arulmozhivarman P, Venkatesh C, Agarwal P. Performance comparison of artificial neural network models for daily rainfall prediction. Int J Autom Comput. 2016;13(5):417-27.

Hamidi O, Poorolajal J, Sadeghifar M, Abbasi H, Maryanaji Z, Faridi HR, et al. A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran. Theor Appl Climatol. 2015;119(3-4):723-31.

Ramana RV, Krishna B, Kumar SR, Pandey NG. Monthly rainfall prediction using wavelet neural network analysis. Water Resour Manag. 2013;27(10):3697-711.

Mehr AD, Nourani V, Khosrowshahi VK, Ghorbani MA. A hybrid support vector regression–firefly model for monthly rainfall forecasting. Int J Environ Sci Tech. 2019;16(1):335-46.

Yaseen ZM, Ghareb MI, Ebtehaj I, Bonakdari H, Siddique R, Heddam S, et al. Rainfall pattern forecasting using novel hybrid intelligent model based ANFIS-FFA. Water Resour Manag. 2018;32(1):105-22.

Feng Q, Wen X, Li J. Wavelet analysis-support vector machine coupled models for monthly rainfall forecasting in arid regions. Water Resour Manag. 2015;29(4):1049-65.

Weesakul U, Kaewprapha P, Boonyuen K, Mark O. Deep learning neural network: A machine learning approach for monthly rainfall forecast, case study in eastern region of Thailand. Eng Appl Sci Res. 2018;45(3):203-11.

Weesakul U, Singhrattna N, Viwat H. Identification of large-scale atmospheric predictors for rainfall forecasting of Nan River Basin (Thailand). Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

Weesakul U, Singhrattna N, Luangdilok N. Identification of large-scale atmospheric predictors for rainfall forecasting of Chi River Basin (Thailand). Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

Weesakul U, Singhrattna N, Yodpongpiput P. Statistical relationships between large-scale atmospheric variables and rainfall in Mun River Basin (Thailand). Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

Weesakul N, Singhrattna N, Khetped N. Large-scale atmospheric variables influencing on rainfall in Tapee River Basin (Thailand). Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks: Int J Forecast. 1998;14(1):35-62.

ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. Artificial neural networks in hydrology. I: Preliminary concepts. J Hydrolog Eng. 2000;5(2):115-23.

Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput. 2006;18(7): 1527-54.

Sheela KG, Deepa SN. Review on methods to fix number of hidden neurons in neural networks. Math Probl Eng. 2013;2013:1-11.

Hunter D, Yu H, Pukish, III MS, Kolbusz J, Wilamowski BM. Selection of proper neural network sizes and architectures—a comparative study. IEEE Trans Industr Inform. 2012;8(2):228-40.

Zhang Z, Ma X, Yang Y. Bounds on the number of hidden neurons in three-layer binary neural networks. Neural networks. 2003;16(7):995-1002.

Rumelhart DE, Hintont GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323(6088):533-6.

May R, Dandy G, Maier H. Review of input variable selection methods for artificial neural networks. In: Suzuki K, editor. Artificial neural networks - methodological advances and biomedical applications. Croatia: IntechOpen; 2011. p. 19-44.

Blum AL, Langley L. Selection of relevant features and examples in machine learning. Artif Intell. 1997;97(1-2):245-71.

Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157-82.

Dariane AB, Azimi Sh. Forecasting streamflow by combination of a genetic input selection algorithm and wavelet transforms using ANFIS models. Hydrolog Sci J. 2016;16(3):585-600.

Abbot J, Marohasy J. Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks. Atmos Res. 2014;138: 166-78.