ANALISIS PREDIKSI CURAH HUJAN DI KOTA METRO DENGAN MENGGUNAKAN METODE FUZZY MARKOV CHAIN

Abstract

Massive global climate change is happening today, resulting in frequent unexpected weather changes. This condition poses a major challenge to various sectors such as aviation, education, and especially the agricultural sector. Metro City as one of the regions in Indonesia that has great potential in the agricultural sector cannot be spared from being an area affected by this natural phenomenon. Therefore, it is necessary to use an effective and accurate prediction method to handle these uncertainties and fluctuations. This study aims to predict rainfall in Metro City using the average-based Fuzzy Time Series Markov Chain method as a prediction method that is known to be effective in analyzing uncertain and fluctuating time series as a decision-making consideration for agricultural actors and the Metro City government. The data used in this study is secondary data in the form of monthly average rainfall data for Metro City for the period April 2020 to March 2025 obtained from the Lampung Province Meteorology, Climatology, and Geophysics Agency (BMKG). The results of the study showed that the Fuzzy Time Series Markov Chain method had a fairly good level of accuracy in making predictions with MAE and MAPE values of 28.61712 and 43%. So it can be concluded that the Fuzzy Time Series Markov Chain method is suitable for predicting rainfall data in Metro City for the next month period.