PREDICTION AND MAPPING RAINFALL CLASSIFICATION USING NAIVE BAYES AND SIMPLE KRIGING

Indra Kusuma Yoga
Sri Suryani Prasetyowati
Yuliant Sibaroni


DOI: https://doi.org/10.29100/jipi.v7i4.3264

Abstract


This study discusses the development of a prediction model for the classification of rainfall based on time in Java. The method used in this research is naive Bayes and simple kriging. Naive Bayes is used for classification prediction, while simple kriging is an interpolation method used for mapping. There are two scenarios used, that is building a prediction model for daily and monthly rainfall classification, with data taken from 27 weather stations on the island of Java from 2010 to 2021. The results obtained in the classification process are an accuracy value of 67% for the daily model and 88% for the monthly model. The daily model data uses a spherical semivariogram with an average RMSE of 1,021. For the monthly model data using a Gaussian semivariogram with an average RMSE of 0,34. Then interpolation using simple kriging for mapping rainfall. The results of this study are predictions for the classification and mapping of daily rainfall models from April 1 to April 7 2022 and monthly models from April to September 2022. The contribution of this research is to provide predictive information and mapping of future rainfall so that public people can anticipate more.

Keywords


Naive Bayes; simple kriging; interpolation; classification

Full Text:

PDF

Article Metrics :

References


Y. Andrian and E. Ningsih, Prediksi Curah Hujan Di Kota Medan Menggunakan, Semin. Nas. Inform., pp. 184189, 2014.

D. Eko Nuryanto, KARAKTERISTIK CURAH HUJAN ABAD 20 DI JAKARTA BERDASARKAN KEJADIAN IKLIM GLOBAL, Meteorogi dan Geifisika, p. 11, 2013.

T. D. Mirawati, H. Yasin, and A. Rusgiyono, Prediksi Curah Hujan dengan Metode Kalman Filter (studi kasus di Kota Semarang Tahun 2012), J. Gaussian, vol. 2, no. 3, pp. 239248, 2013, [Online]. Available: https://media.neliti.com/media/publications/137182-ID-prediksi-curah-hujan-dengan-metode-kalma.pdf

i gede aris gunadi, Klasifikasi Curah Hujan di Provinsi Bali Berdasarkan Metode Nave Bayesian, Wahana Mat. dan Sains J. Mat. Sains, dan Pembelajarannya, vol. 12, no. 1, pp. 1415, 2018, [Online]. Available: https://ejournal.undiksha.ac.id/index.php/JPM/article/view/pril2018-2

I. G. W. Sena, J. W. Dillak, P. Leunupun, and A. J. Santoso, Predicting Rainfall Intensity using Nave Bayes and Information Gain Methods (Case Study: Sleman Regency), J. Phys. Conf. Ser., vol. 1577, no. 1, pp. 06, 2020, doi: 10.1088/1742-6596/1577/1/012011.

D. Gupta and U. Ghose, A comparative study of classification algorithms for forecasting rainfall, 2015 4th Int. Conf. Reliab. Infocom Technol. Optim. Trends Futur. Dir. ICRITO 2015, pp. 16, 2015, doi: 10.1109/ICRITO.2015.7359273.

N. W. Zamani and S. S. M. Khairi, A comparative study on data mining techniques for rainfall prediction in Subang, AIP Conf. Proc., vol. 2013, 2018, doi: 10.1063/1.5054241.

D. K. Srivastava, A. K. Sharma, and S. Chaurasia, Supervised Rainfall Learning Model Using Machine Learning Algorithms, Adv. Intell. Syst. Comput., vol. 921, 2020.

M. Sudha and B. Valarmathi, Rainfall forecast analysis using rough set attribute reduction and data mining methods, Agris On-line Pap. Econ. Informatics, vol. 6, no. 4, pp. 145154, 2014.

S. S. Prasetiyowati, Y. Sibaroni, and S. Carolina, Prediction and Mapping of Air Pollution in Bandung Using Generalized Space Time Autoregressive and Simple Kriging, 2020 Int. Conf. Data Sci. Its Appl. ICoDSA 2020, 2020, doi: 10.1109/ICoDSA50139.2020.9212820.

M. Muthmainnah, M. Ashar, I. M. Wirawan, and T. Widiyaningtyas, Time Series Forecast for Rainfall Intensity in Malang City with Naive Bayes Methodology, 3rd Int. Conf. Sustain. Inf. Eng. Technol. SIET 2018 - Proc., pp. 137141, 2018, doi: 10.1109/SIET.2018.8693171.

M. T. Ali Haghpanah Jahromi, A non-parametric mixture of Gaussian naive Bayes classifiers based on local independent features, 2017 Artif. Intell. Signal Process. Conf., no. 1, pp. 134139, 2017.

A. M. Oliver and R. Webster, Basic Steps in Geostatistics:The Variogram and Kriging. 2015.

F. R. Kodong and J. Fajar, Prediction of wind disaster using kriging spatial interpolation and internet of things, IOP Conf. Ser. Mater. Sci. Eng., vol. 620, no. 1, 2019, doi: 10.1088/1757-899X/620/1/012098.

B. Rebholz and M. Almekkawy, Efficacy of Kriging Interpolation in Ultrasound Imaging; Subsample Displacement Estimation, Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2020-July, pp. 21372141, 2020, doi: 10.1109/EMBC44109.2020.9175457.

Y. Z. Ma, Quantitative Geosciences: Data Analytics, Geostatistics, Reservoir Characterization and Modeling. 2019. doi: 10.1007/978-3-030-17860-4