Determining Salt Production Season Based on Rainfall Forecasting Using Weighted Fuzzy Time Series
Isnaini Muhandhis, Heri Agus Susanto, Ully Asfari · Journal of Applied Computer Science & Mathematics/Journal of Applied Computer Science · 2020
Most of the salt production in Indonesia uses the solar evaporation method, so salt production is very dependent on the weather. As one of the salt production centers in Indonesia, rainfall forecasting on the Sumenep Regency is very important to prepare salt production as soon as possible and to prevent crop failure. This study aims to predict rainfall to determine the beginning and end of the dry season using the weighted fuzzy time series method. The weighted fuzzy time series assign different weights in trends of the fuzzy relationships process to improve forecasting accuracy. The results showed that the weighted fuzzy time series method is able to predict rainfall with good accuracy with a MAPE value of 5.64% and RMSE 33.64. The beginning and end of dry season testing results have a small error value of about 1.5 periods. Therefore, the weighted fuzzy time series method has good accuracy for determining the dry season on the Sumenep Regency