Predicting Rainfall Intensity using Naïve Bayes and Information Gain Methods (Case Study: Sleman Regency)

Sena, I Gede Wiarta and Dillak, J W and Leunupun, P. and Santoso, Albertus Joko (2020) Predicting Rainfall Intensity using Naïve Bayes and Information Gain Methods (Case Study: Sleman Regency). In: The 2nd 2019 ICERA: International Conference on Electronics Representation and Algorithm "Innovation and Transformation for Best Practices in Global Community" 12-13 December 2019, Yogyakarta, Indonesia. Journal of Physics: Conference Series, Yogyakarta, pp. 1-6.

Preview

Text (I G W Sena, J W Dillak, P Leunupun and A J Santoso) 29. Predicting Rainfall Intensity using Naive Bayes and Information Gain Methods.pdf Download (1MB) | Preview

Abstract

Climate change, which has an impact on environmental problems in tropical countries, is still a severe problem, and efforts to prevent and manage it are continuously pursued. Indonesia, as a tropical country with topographical conditions and strategic geographical position, causes Indonesia to have different weather and climate patterns. Climatologically there are significant differences between the rainy season and the dry season. Both these seasons can bring blessings but also disasters if not appropriately handled, flooding in the rainy season and drought in the dry season. High rainfall can cause floods and landslides, whereas if using excess water in the rainy season can be a solution for water shortages in the dry season. The purpose of this study is to predict the rainfall intensity with the Naïve Bayes method and what parameters are considered the most dominant causes of heavy rainfall using the information gain method. The source of the data in this study came from BMKG data, which was during the rainy season between October to March from 2016 - 2019 in the Sleman Regency. The results of this study showed that the Naïve Bayes method could be used to predict rainfall intensity in Sleman Regency. Also, the most influential parameter on rainfall intensity is the average temperature with an information gain value of 0.047811028.

Actions (login required)

View Item