Proceedings of the International Conference on Mathematics, Geometry, Statistics, and Computation (IC-MaGeStiC 2021)

Naive Bayes Classifier (NBC) for Forecasting Rainfall in Banyuwangi District Using Projection Pursuit Regression (PPR) Method

Authors
Ana Ulul Azmi1, Alfian Futuhul Hadi2, Yuliani Setia Dewi2, I Made Tirta2, Firdaus Ubaidillah2, Dian Anggraeni2, *
1Master Student of Mathematics Department, Faculty of Mathematics and Natural Science, University of Jember
2Department of Mathematics, Faculty of Mathematics and Natural Science, University of Jember
*Corresponding author. Email: dian_a.fmipa@unej.ac.id
Corresponding Author
Dian Anggraeni
Available Online 8 February 2022.
DOI
10.2991/acsr.k.220202.036How to use a DOI?
Keywords
General Circulation Model (GCM); Statistical Downscaling (SDs); Projection Pursuit Regression (PPR); Classification; Naive Bayes Classifier (NBC)
Abstract

Rainfall is one of the climates that has a big influence on life, such as aviation, plantations, and agriculture. Remote areas like Banyuwangi Regency are most likely to lack information on weather and climate data. Rainfall information in the future is also very decisive for the community in carrying out their daily lives, therefore prediction models or rainfall forecasting are very necessary for the community. This situation has encouraged the development of various models of approaches for forecasting rainfall. One approach for forecasting rainfall is the use of Global Circulation Model (GCM) data. GCM resolution is too low to predict local climate which is influenced by topography and land use, but it is still possible to use GCM to obtain local scale information if Statistical Downscaling (SDs) technique is used. SDs is a technique that connects GCM output as a predictor variable with local rainfall in Banyuwangi Regency as a response variable with an intermediary functional model. As for the GCM output response variable, there are three variables used in this study, namely rainfall, sea level pressure, and air temperature with a domain of 3×3 to 10×10. Forecasting rainfall in Banyuwangi Regency is carried out using the Projection Pursuit Regression (PPR) method. At the modeling stage with PPR, the optimum domain and many functions will be determined, where the chosen domain is the 6×6 domain and the optimum number of functions is m=6 with RMSEP value of 89.79. Furthermore, a process is needed to represent the forecasting results in simpler way, such as classification. The classification method used in this study is the Naive Bayes Classifier (NBC). Evidently, NBC uses PPR as a model produces forecasts classification with correct values for 18 months out of a total of 24 months with 75% of accuracy.

Copyright
© 2022 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Mathematics, Geometry, Statistics, and Computation (IC-MaGeStiC 2021)
Series
Advances in Computer Science Research
Publication Date
8 February 2022
ISBN
978-94-6239-529-9
ISSN
2352-538X
DOI
10.2991/acsr.k.220202.036How to use a DOI?
Copyright
© 2022 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Ana Ulul Azmi
AU  - Alfian Futuhul Hadi
AU  - Yuliani Setia Dewi
AU  - I Made Tirta
AU  - Firdaus Ubaidillah
AU  - Dian Anggraeni
PY  - 2022
DA  - 2022/02/08
TI  - Naive Bayes Classifier (NBC) for Forecasting Rainfall in Banyuwangi District Using Projection Pursuit Regression (PPR) Method
BT  - Proceedings of the  International Conference on Mathematics, Geometry, Statistics, and Computation (IC-MaGeStiC 2021)
PB  - Atlantis Press
SP  - 190
EP  - 195
SN  - 2352-538X
UR  - https://doi.org/10.2991/acsr.k.220202.036
DO  - 10.2991/acsr.k.220202.036
ID  - Azmi2022
ER  -