Support Vector Regression modelling for rainfall prediction in dry season based on Southern Oscillation Index and NINO3.4

Author

Adhani, Gita ; Buono, Andrea ; Faqih, Akhmad

Author_Institution

Dept. of Comput. Sci., Bogor Agric. Univ., Bogor, Indonesia

fYear

2013

fDate

28-29 Sept. 2013

Firstpage

315

Lastpage

320

Abstract

Various climate disasters in Indonesia are mostly related to the El Nino Southern Oscillation (ENSO) phenomenon. The variability of climate especially rainfall is strongly related to this phenomenon. Southern Oscillation Index (SOI) and sea surface temperature anomaly (SSTA) at Nino3.4 region are two common indicators used to monitor phenomenon of El Nino and La Nina. Furthermore, SOI and NINO SSTA can be the indicator to find the rainfall probability in a particular season, related to the existing condition of climate irregularities. This research was conducted to estimate the rainfall during dry season at Indramayu district. The basic method used in this study was Support Vector Regression (SVR). Predictors used were SOI and NINO3.4 sea surface temperature (SST) data. The experiments were conducted by comparing the model performance and prediction results. The training set was clustered in advance and then SVR model was generated using RBF kernel based on their clustering result. This research obtained an SVR model with correlation coefficient of 0.76 and NRMSE error value of 1.73.

Keywords

El Nino Southern Oscillation; atmospheric movements; climatology; disasters; geophysics computing; ocean temperature; radial basis function networks; rain; regression analysis; support vector machines; El Nino Southern Oscillation phenomenon; Indonesia; Indramayu district; La Nina; NINO3.4 sea surface temperature data; NRMSE error value; Nino3.4 region; RBF kernel; Southern Oscillation Index; climate disasters; climate irregularities; climate variability; correlation coefficient; dry season; model performance; rainfall probability; sea surface temperature anomaly; support vector regression modelling; training set; Correlation coefficient; Data models; Kernel; Meteorology; Ocean temperature; Sea surface; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Computer Science and Information Systems (ICACSIS), 2013 International Conference on

Conference_Location

Bali

Type

conf

DOI

10.1109/ICACSIS.2013.6761595

Filename

6761595