Open AccessNaive bayes methods for rainfall prediction classification in Banyuwangi
Author(s) -
Aida Azmi,
Alfian Futuhul Hadi,
Dian Anggraeni,
Abduh Riski
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1872/1/012028
Subject(s) - naive bayes classifier , wet season , agriculture , dry season , java , meteorology , environmental science , geography , computer science , machine learning , cartography , support vector machine , archaeology , programming language
Banyuwangi is the largest district in East Java with an area of 5,782.50 km 2 . It has a long coastline of about 175.8 km which stretches along the southern eastern boundary of Banyuwangi Regency, and there are 10 islands. The BMKG estimates that the dry season in the Banyuwangi area is due to the appearance of the beach having hot weather and rarely rains. Banyuwangi also predicts that the dry season is due to the slight influence of cloud growth. Rainfall is a factor of the rainy season which has a big influence on life such as aviation, plantations and agriculture. Agriculture and plantations in Banyuwangi are mostly located in remote areas. Remote areas are likely to lack weather and climate data information. climate elements of a region cannot be ignored, especially rainfall. Based on data from BMKG (Meteorology, Climatology and Geophysics), the weather data used needs to be classified. Rainfall classification can be categorized into three, namely, light, normal and heavy. There are quite a lot of classification methods, there are several new methods that are quite good such as Naive Bayes (NB). Naive Bayes Classifier (NBC) is an algorithm in data mining techniques that is used to determine the probability of a member of a group. Large and irrelevant datasets can be solved using the Naive Bayes Classifier (NBC) method. The rainfall data used is known first, observed then identified to form a training dataset. Determining the accuracy of rainfall with the Naive Bayes Classifier (NBC) can use several parameters that have a physical relationship between the atmosphere and rainfall. The parameters used to determine rainfall are humidity, rainfall and precipitation. From this study, from 49 data testing, 47 data were predicted correctly with an accuracy of 96%.