Prediksi Kenaikan Awan Di Wisata Lolai Berbasis Machine Learning

Abstract

The increase in cloud cover is an important indicator in predicting upcoming weather. However, manual observations of cloud cover are still limited and time-consuming. Therefore, this research aims to develop a cloud cover classification model based on measurement data in Lolai using the Naive Bayes machine learning method. In this study, data on cloud cover, temperature, and humidity measurements were collected directly in Lolai for 30 days and using online BMKG data. Then, the data was processed and divided into training and testing datasets. The Naive Bayes model was applied to the training data and its accuracy was tested on the testing data. The research results show that the cloud cover classification model based on Naive Bayes has varying accuracy levels depending on the data source. For direct measurement data, the model achieved an accuracy rate of 63%, while for online BMKG data, the model achieved an accuracy rate of 80%. In testing on the testing data, the model successfully classified cloud cover based on temperature and humidity data. This research contributes to identifying the relationship between temperature, humidity, and cloud conditions and evaluates the performance of the Naive Bayes model in determining the influence of air temperature and humidity on cloud conditions. It is expected that this research can serve as a basis for the development of weather prediction systems in the future.