Extreme Gradient Boosting pada Peramalan Pola Curah Hujan Bulanan Kabupaten Banyuwangi

Ana Fauziah; Hermanto Hermanto; Mita Akbar Sukmarini

doi:10.53863/kst.v6i02.1154

Authors

Ana Fauziah Universitas Bakti Indonesia, Banyuwangi, Indonesia
Hermanto Hermanto Universitas Bakti Indonesia, Banyuwangi, Indonesia
Mita Akbar Sukmarini Universitas Bakti Indonesia, Banyuwangi, Indonesia

DOI:

https://doi.org/10.53863/kst.v6i02.1154

Keywords:

Rainfall, Forecast, Ensemble Learning, XGBoost, Banyuwangi

Abstract

Long-term meteorological data is very useful for identifying signs of climate change phenomena. The phenomenon refers to long-term changes in the physical conditions of the Earth's atmosphere, such as temperature and weather patterns. This has a huge impact, especially in Banyuwangi, which is one of the largest rice production areas in East Java. Predicting monthly rainfall trends is important to anticipate crop failures due to extreme weather and natural disasters such as floods and landslide. This research uses weather parameters on a global scale, such as temperature, rain, evaporation, surface humidity, and sea level pressure, while for local-scale information, it uses monthly rainfall data in the Banyuwangi area from 2011 to 2023.The extreme gradient boosting (XGBoost) method will be used to predict monthly rainfall in an ensemble learning model based on the boosting approach. In particular, this study emphasizes its ability to build predictive models on limited time series and the impact of data splitting on model performance. The best results were shown by the model with a data split ratio of 1:12, or covering 80% of the data as training data. The model accuracy achieved a MAE of 72.579 mm in training and 80.777 mm in testing. In addition, the RMSE was 95.940 mm in training and 95.775 mm in testing. The results of this study are expected to be a reference for building a more optimal long-term weather forecast model.

References

Bagirov, A.M., Mahmood, A., & Barton, A. (2017). Prediction of monthly rainfall in Victoria, Australia: clusterwise linear regressionapproach. Atmospheric Research ,188,20-29. https://doi.org/10.1016/j.atmosres.2017.01.003

BMKG Banyuwangi. (2024). [Web application]. https://www.bmkg.go.id/tag/?tag=stasiun-meteorologi-banyuwangi&lang=ID

bmkg-sebut-fenomena-iklim-di-indonesia-kian-tak-pasti-dan-cepat-berubah-ini-sebabnya

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable Tree Boosting System. KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. https://doi.org/10.1145/2939672.2939785

Gu, J., Liu, S., Zhou,Z., Chalov, S.R., & Zhuang, Q. (2022). A Stacking Ensemble Learning Model for Monthly Rainfall Prediction in the Taihu Basin, China [Special section]. Water, 14(3), 492.

He, R., Zhang, L., & Chew, A.W.Z. (2024). Data-driven multi-step prediction and analysis of monthly rainfall using explainable deep learning. Expert Systems with Applications, 235(121160). https://doi.org/10.1016/j.eswa.2023.121160

Helmi, I. (2022, Maret 23). BMKG Sebut Fenomena Iklim di Indonesia Kian Tak Pasti dan Cepat Berubah, Ini Sebabnya. Kompas TV. https://www.kompas.tv/nasional/273138/

Jhonson, R.A. & Wichern, D.W. (2007). Applied multivariate statistical analysis. Pearson Prentice Hill.

KNMI climate explorer. (2022). [Web application]. https://climexp.knmi.nl/start.cgi?id=

Latif, S.D., Hazrin, N.A.B., koo, C.H., Lin Ng, J., Chaplot, B., Huang, Y.F., El-Shafie, A., & Ahmed, A.N. (2023). Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches. Alexandria Engineering Journal, 82, 16-25. https://doi.org/10.1016/j.aej.2023.09.060

Li, S., Xu, C., Su, M., Lu, W., Chen, Q., Huang, Q., & Teng Y.(2024). Downscaling of environmental indicators: A review. Science of The Total Environment, 916. https://doi.org/10.1016/j.scitotenv.2024.170251

Munandar, D., Ruchjana, B.N., & Abdullah, A.S. (2022). Principal component analysis-vector autoregressive integrated (PCA-VARI) model using data mining approach to climate data in the west java region. Jurnal Ilmu Matematika dan Terapan, 16(1), 099-112. https://doi.org/10.30598/barekengvol16iss1pp099-112

Najafi, M.R., Hamid, M., & Wherry, S.A. (2009). A procedure for statistical downscaling of precipitation with an objective method for predictor selection. Journal of Hydrologic Engineering. 16(8). https://doi.org/10.1061/(ASCE)HE.1943-5584.0000355

Nurdin. (2011). Antisipasi perubahan iklim untuk keberlanjutan ketahanan pangan [Srikpsi]. Universitas Negeri Gorontalo. https://repository.ung.ac.id/karyailmiah/show/20/antisipasi-perubahan-iklim-untuk-keberlanjutan-ketahanan-pangan.html#

Pathan, M.S., Nag, A., & Dev, S. (2022, Juli 17-22). Efficient rainfall prediction using a dimensionality reduction method. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing [Symposium]. Kuala Lumpur, Malaysia. https://doi.org/10.1109/IGARSS46834.2022.9884849

Pour, S.H., shahid, S., Chung, E.S., & Wang, X.J. (2018). Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh. Atmospheric Research, 213, 149-163. https://doi.org/10.1016/j.atmosres.2018.06.006

Raymer, M.L., Punch, W.F., Goodman, E.D., Khun, L.A., & Jain, A.K. (2000). Dimensionality reduction using genetic algorithms. IEEE Transactions on Evolutionary Computation, 4(2), 164-171. https://corescholar.libraries.wright.edu/knoesis/9

Robock, A., Turco, R.P., Harwell, M.A., Ackerman, T.P., Andressen,R., Chang,H.S., & Sivakumar,M.V.K. (1993). Use of general circulation model output in the creation of climate change scenarios for impact analysis. Climatic Change, 23, 293-335. https://link.springer.com/article/10.1007/BF01091621

Sachindra, D.A., Ahmed, K., Rashid, M.M., Shahid, S., & Perera, B.J.C (2018). Statistical downscaling of precipitation using machine learning techniques. Atmospheric Research, 212, 240-248. https://doi.org/10.1016/j.atmosres.2018.05.022

Salathe, E. P., Jr., Mote, P. W., & Wiley, M. W. (2007). Review of scenario selection and downscaling methods for the assessment of climate change impacts on hydrology in the United States pacific northwest. Int. J. Climatol, 27(12), 1611–1621. https://doi.org/10.1002/joc.1540

Siregar, A.M., Tukino, Faisal, S., Fauzi, A., & Kadori, I. (2020). Klasifikasi untuk prediksi cuaca menggunakan esemble learning. Jurnal Pengkajian dan Penerapan Teknik Informatika, 13, 138-147. DOI:https://doi.org/10.33322/petir.v13i2.998

Thara, D.K. Prema, P.S., & Xiong, F. (2019). Auto-detection of epileptic seizure events using deep neural network with different feature scaling techniques. Pattern Recognition Letters, 128, 544-550. https://doi.org/10.1016/j.patrec.2019.10.029

Vieira, V.M. (2012). Permutation tests to estimate significances on Principal Components Analysis. Computational Ecology and Software, 2, 103-123. http://www.iaees.org/publications/journals/ces/articles/2012-2(2)/permutation-tests-to-estimate-significances.pdf