Klasifikasi Curah Hujan di Kota Semarang Menggunakan Machine Learning

Abstract

The erratic distribution of rainfall greatly affects people's daily activities, especially in the Semarang City. Therefore, it is necessary to predict rainfall in Semarang City. Correct prediction of rainfall can improve community preparedness in dealing with various natural disasters caused by rain. Machine learning algorithms and data mining have been widely used in research for rainfall data in various regions. The main purpose of this study is to obtain predictions of rainfall in the city of Semarang using machine learning algorithms and to find out the best algorithm for classifying. The dataset used was obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) which is the daily rainfall data in Semarang City. From the dataset, three machine learning algorithms will be classified, namely Logistic Regression, Random Forest, and Gradient Boosting. To measure the performance of the machine learning algorithm, the classification accuracy of each algorithm is measured. From the research results, the performance of the Gradient Boosting algorithm is better than other algorithms, with an accuracy value of 71.6%.

Keywords: Machine Learning, Logistic Regression, Random Forest, Gradient Boosting, Rainfall Prediction