Peramalan curah hujan menggunakan metode Vector Autoregressive (VAR) di Yogyakarta

Abstract

Rainfall is the amount of rainfall that falls on the surface of the Earth in a certain area within a specific period of time. If the rainfall is high every day, it can be referred to as the rainy season, and if it's the opposite, it can be called the dry season. Rainfall is one of the determining factors for the quality and quantity of agricultural yields in the Yogyakarta region. Considering the unpredictable and increasingly extreme changes in rainfall in D.I. Yogyakarta over the past few years, this irregular condition has made it difficult to accurately predict rainfall. Therefore, rainfall prediction information is needed to support various activities such as in agriculture, water resources, transportation, and others. The purpose of this research is to determine the accuracy of rainfall forecasting using the VAR method in three seasonal zones in D.I. Yogyakarta. The data used in this study is the rainfall data in three seasonal zones of Yogyakarta in the year 2020. The research results show that the rainfall forecasting in the three seasonal zones of D.I. Yogyakarta using the VAR method resulted in a Mean Absolute Percentage Error (MAPE) value of 81.77761%, indicating that the forecasting ability of the VAR method is still categorized as poor.