Rainfall is one of the climate variables that have a significant influence, especially in supporting the activities of various sectors in tropical countries. Climate change is causing rainfall variability in Indonesia. However, the analysis of climate variable patterns is difficult because of the formation of a large matrix. Empirical Orthogonal Function (EOF) analysis can be used to reduce the dimensions of large data by maintaining as much variation as possible from the original data set. The method used in this study is through the Singular Value Decomposition (SVD) approach. The analysis shows that 98.50% of the total rainfall variance can be represented by four EOF modes. Analysis of the spatial pattern of EOF1 shows that rainfall is below average, while the other EOF modes show variations in rainfall.
 A. Domanov, A. Stegeman, L.D. Lathauwer. On the largest multilinear singular values of higher-order tensors. SIAM Journal on Matrix Analysis and Applications, 38 (2017) 1434-1453
 A. Nugroho, B.H. Simanjuntak. ARMA (Autoregressive Moving Average) Model for Prediction of Rainfall in Regency of Semarang – Central Java – Republic of Indonesia. International Journal of Computer Science 11 (2014) 27-32
 A.R. As-syakur, I.W.S. Adnyana, M.S. Mahendra, I.W. Arthana, I.N. Merit, I.W. Kasa, N.W. Ekayansi, I.W. Nuarsa, I.N. Sunarta. Observation of Spatial Patterns on the Rainfall Response to ENSO and IOD over Indonesia using TRMM Multisatellite Precipitation Analysis. International Journal of Climatology 34 (2014) 3825-3839
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.