Sains Malaysiana 46(12)(2017): 2541–2547

http://dx.doi.org/10.17576/jsm-2017-4612-32

 

A Hybrid Climate Model for Rainfall Forecasting based on Combination of Self-Organizing Map and Analog Method

(Model Iklim Hibrid untuk Ramalan Curahan Hujan berdasarkan Gabungan Peta Swaurus dan Kaedah Analog)

 

NATITA WANGSOH1, WIBOONSAK WATTHAYU1* & DUSADEE SUKAWAT2

 

1Department of Mathematics, Faculty of Science, King Mongkut’s University of Technology, Thonburi (KMUTT), 126 Pracha Uthit Rd., Bang Mod, Thung Khru, Bangkok 10140, Thailand

 

2Joint Graduate School of Energy and Environment, KMUTT, 126 Pracha Uthit Rd., Bang Mod, Thung Khru, Bangkok 10140, Thailand

 

Received: 22 November 2016/Accepted: 1 April 2017

 

 

ABSTRACT

A hybrid climate model (HCM) is a novel proposed model based on the combination of self-organizing map (SOM) and analog method (AM). The main purpose was to improve the accuracy in rainfall forecasting using HCM. In combination process of HCM, SOM algorithm classifies high dimensional input data to low dimensional of several disjointed clusters in which similar input is grouped. AM searches the future day that has similar property with the day in the past. Consequently, the analog day is mapped to each cluster of SOM to investigate rainfall. In this study, the input data, geopotential height at 850 hPa from the Climate Forecast System Reanalysis (CFSR) are training set data and also the complete rainfall data at 30-meteorological stations from Thai meteorological department (TMD) are observed. To improve capability of rainfall forecasting, three different measures were evaluated. The experimental results showed that the performance of HCM is better than the traditional AM. It is illustrated that the HCM can forecast rainfall proficiently.

 

Keywords: Analog method; hybrid climate model; rainfall forecasting; self-organizing map

 

ABSTRAK

Model iklim hibrid (HCM) adalah model cadangan novel berdasarkan peta swaurus (SOM) dan kaedah analog (AM). Tujuan utama kajian ialah untuk meningkatkan ketepatan dalam peramalan curahan hujan menggunakan HCM. Dalam proses gabungan HCM, algoritma SOM mengelaskan data input dimensi yang tinggi kepada dimensi rendah daripada beberapa kelompok terputus dengan input yang sama dikumpulkan. AM mencari hari akan datang yang mempunyai sifat yang sama dengan hari pada masa lalu. Oleh yang demikian, hari analog dipetakan kepada setiap kluster SOM untuk mengkaji curahan hujan. Dalam kajian ini, input data, ketinggian geopotensi pada 850 hPa daripada Sistem Iklim Ramalan Analisis Semula (CFSR) adalah data set latihan dan juga data lengkap curahan hujan di 30 stesen meteorologi daripada Jabatan Meteorologi Thailand (TMD) adalah curahan hujan yang dicerap. Untuk memperbaiki keupayaan ramalan curahan hujan, tiga langkah berbeza telah dinilai. Keputusan uji kaji menunjukkan prestasi HCM adalah lebih baik daripada AM tradisi. Ditunjukkan bahawa HCM boleh meramalkan hujan dengan cekap.

 

Kata kunci: Kaedah analog; model hibrid iklim hujan ramalan; peta swaurus

REFERENCES

Allan, H. 2009. A Concise Guide to Clinical Trials. Oxford: John Wiley & Sons, Inc. pp. 205-207.

Andrew, N.C., Bertrand, T., Elodie, F. & Harry, H. 2013. Analog downscaling of seasonal rainfall forecasts in the Murray Darling basin. Monthly Weather Review 141(3): 1099-1117.

Christoph, M., Xuebin, Z., Xiaolan, L.W., Jiafeng, W., Eduardo, Z., Sebastian, W. & Hans, V.S. 2008. Influence of similarity measures on the performance of the analog method for downscaling daily precipitation. Climate Dynamics 30(2): 133-144.

Diego, R., Mario, L., Cintia, B.U. & Max, B. 2011. Forecasting monthly precipitation in central Chile: a self-organizing map approach using filtered sea surface temperature. Theoretical and Applied Climatology 107(1): 1-13.

Eduardo, Z. & Hans, V.S. 1999. The analog method as a simple statistical downscaling techniques: Comparison with more complicated methods. Journal of Climate 12: 2474-2489.

Fredrik, W., Sven, H. & Xu, C-Y. 2005. Statistical precipitation downscaling in central Sweden with analogue method. Journal of Hydrology 306: 174-190.

Ismail, S., Shabir, A. & Samsudin, R. 2012. A hybrid model of self-organizing maps and least square support vector machine for river flow forecasting. Hydrology and Earth System Sciences 16: 4417-4433.

Jiaming, L., Di, Y., Liping, Z., Xia, Z. & Xingyuan, S. 2015. Comparison of three statistical downscaling methods and ensemble downscaling method based on Bayesian model averaging in upper Hanjiang river basin, China. Advances in Meteorology 2016: Article ID. 7463963.

José, A.S., Brígida, R., Arthur, A. & José, R.S. 2012. Recurrent self-organizing map for severe weather patterns recognition. InTech. pp. 151-175.

Lin, G-F. & Wu, M-C. 2009. A hybrid neural network model for typhoon-rainfall forecasting. Journal of Hydrology 375: 450-458.

Mark, N.F., Witold, F.K. & Robert, R.C. 1992. Rainfall forecasting in space and time using a neural network. Journal of Hydrology 137: 1-31.

Pavel, S. & Olga, K. 2011. Influence of learning rates and neighboring functions on self-organizing maps. Advances in Self-Organizing Maps 6731: 141-150.

Rakesh, T. & Tanweer, S.D. 2015. Application of artificial neural network in hydrology-a review. International Journal of Engineering Research & Technology 4(6): 184-188.

Roberto, C., Sergio, L., Javier, S. & Oliver, P. 2015. Statistical-dynamical downscaling of wind fields using self-organizing maps. Applied Thermal Engineering 75: 1201-1209.

Suranjana, S., Shrinivas, M., Xingren, W., Jiande, W., Sudhir, N., Patrick, T., David, B., Yu-Tai, H., Hui-ya, C., Mark, I., Michael, E., Jesse, M., Rongqian, Y., Malaquías, P.M., Huug van den, D., Qin, Z., Wanqiu, W., Mingyue, C. & Emily, B. 2014. The NCEP Climate Forecast System Version 2. Journal of Climate 27: 2185-2208.

Teuvo, K. 1990. The self-organizing map. Proceeding of the IEEE 78(9): 1464-1480.

 

 

*Corresponding author; email: iwibhayu@kmutt.ac.th

 

 

 

 

 

 

previous