skip to main content

METODE AUTOREGRESSIVE INTEGRATED MOVINGAVERAGE (ARIMA) DAN METODE ADAPTIVE NEURO FUZZY INFERENCE SYSTEM (ANFIS) DALAM ANALISIS CURAH HUJAN

*Rosita Ayu Wulandari  -  Departemen Fisika Fakultas Sains dan Matematika Universitas Diponegoro, Indonesia
Rahmat Gernowo  -  Departemen Fisika Fakultas Sains dan Matematika Universitas Diponegoro, Indonesia

Citation Format:
Abstract

Information of rainfall prediction is important for Indonesian peoples. Many statistical methods can be used in rainfall prediction, they are ARIMA (Autoregressive Integrated Moving Average) and ANFIS (Adaptive Neuro Fuzzy Inference System) methods. The purpose of this study was to compare between ANFIS method and ARIMA method to get rainfall prediction in some periods. The ARIMA method was time series data analysis often used in forecasting. While the ANFIS method was forecasting method based on rarely found time series events that are pure linear or non-linear. Based on this study, the ANFIS method has a good accuracy for time series data analysis compared with the ARIMA method. The ANFIS method has 6.9811 for the result of correlation and 87.29% for the RMSE, while result of correlation for the ARIMA method is 14.037 with 24.92% for RMSE. The ARIMA method is not good for prediction of daily data cases and non-linear data, so that the result is not actual which has a constant and flat for data prediction.

Keywords: ARIMA, ANFIS, time series data, linear, non-linear 
Fulltext View|Download
Keywords: ARIMA, ANFIS, time series data, linear, non-linear

Last update:

No citation recorded.

Last update: 2024-03-28 14:06:23

No citation recorded.