Using ANFIS and Fuzzy Clustering to Predict Extreme Climate in Indonesian Regions

Using ANFIS and Fuzzy Clustering to Predict Extreme Climate in Indonesian Regions

The Houw Liong2) and Plato M.Siregar1)

ICICI 2007 proceedings
Jl. Ganesha 10
Bandung, 40132 INA

1) Faculty of Earth Science and Mineral Technology, ITB
2) Faculty of Mathematics and Natural Sciences, ITB

Abstract

Extreme climate in Indonesia is influenced by four main quasi periodic cycles: Solar Activity Cycle (Sunspot Numbers Cycle), Galactic Cosmic Ray Cycle, El Nino Southern Oscillation (ENSO) Cycle, and Indian Ocean Dipole Mode (IOD) Cycle. It can be shown that solar activity cycle can be considered as primary cycle that influence other cycles.
In practice eastern Indonesian region is dominantly influenced by ENSO. When the heat pools moves to eastern Indonesian region, then rainfall in this region will be above normal. On the other hand when the heat pool leaves eastern Indonesian region and moves to Pacific Ocean then the rainfall in this region will be below normal.
During a typical Indian Ocean Dipole Mode (IOD) event the weakening and reversal of winds in the central equatorial Indian Ocean lead to the development of unusually warm sea surface temperatures in the western Indian Ocean. IOD negative means wet condition or the rainfall will be above normal along the western Indonesian region.
Precipitation in Pontianak region which represent middle Indonesian region correlated strongly with sunspot numbers cycle (solar activity cycle).
Using ANFIS (Adaptive Neuro Fuzzy Inference System) we are able to predict sunspot numbers cycles so that extreme weather in Indonesian regions can be predicted.
Fuzzy c-means is used to classify regions that are influenced strongly by sunspot numbers (solar activity), IOD, and ENSO cycles. This method is based on fuzzy set as fuzzy c-partition of three cycles above and as cluster center. Fuzzy c-partition matrix for grouping a collection of n data set into c classes.
This study explores the physical of climate predictions and classifications of Indonesian regions and its physical interpretations.

Keywords: ANFIS, fuzzy clustering, climate, solar activity