Analisis Klasifikasi Curah Hujan Harian Menggunakan Metode Decision Tree (Studi Kasus: Stasiun Pengamatan Radin Inten II Lampung)

Muklas Rivai, Rosni Rosni, Nanda Azzanina, Aldila Nur Indah Berliana Ratam, Bening Zalzabillah Zarrouby, Felicia Perangin Angin, Ikhwan Halim Aqil, Latifah Latifah, Robertus Karlius Laia

Abstract


The role of rainfall in human life is crucial, particularly in fulfilling water needs. However, recent climate changes have made it increasingly difficult for communities to predict rainfall. Therefore, rainfall prediction can support water resource management planning, particularly in the Bandar Lampung area. Classification analysis using the Decision Tree method can provide information on key factors influencing the probability of rainfall occurrence. Hence, rainfall prediction for the upcoming periods can be conducted. The data mining process generated a dataset consisting of relative humidity, dew point, rainfall, total cloud cover, and low cloud cover. The classification analysis stage using the Decision Tree method included data collection, data processing, decision tree construction, and model evaluation. The results of the study show that, in classifying variables influencing rainfall in Bandar Lampung, relative humidity has a significant impact on determining rainfall probability. In addition, dew point and rainfall also contribute to the classification. The decision tree model achieved an accuracy rate of 84.54%. This study contributes to water resource management and helps anticipate potential water shortages.


Keywords


Classification Analysis; Rainfall; Data Mining; Decision Tree Method; Prediction

Full Text:

PDF

References


R. Sulistyiorini, “Alternatif penanganan permasalahan infrastruktur kebutuhan air bersih di Kota Bandar Lampung melalui rain water harvesting,” Journal of Systems Integration, Dec. 2020, doi: 10.23960/JSI.V1I1.3.

N. Dercas, “Editorial to the special issue ‘Drought and water scarcity: Monitoring, modelling and mitigation’,” Hydrology, Jun. 2023, doi: 10.3390/hydrology10060134.

M. Safdar et al., “Drought monitoring with multiple indices and management through various techniques: A review,” Proceedings of the ASECS 2023, Dec. 2023, doi: 10.3390/asec2023-16602.

A. E. Kenawy, S. M. Vicente-Serrano, C. Murphy, and L. Gimeno, “Editorial: Advances in drought analytical tools for better understanding of current and future climate change,” Frontiers in Earth Science, Feb. 2023, doi: 10.3389/feart.2023.1140658.

B. Susilo, “Mengenal Iklim dan Cuaca di Indonesia”. Yogyakarta: DIVA Press, 2021.

P. B. Setio, D. R. Saputro, and B. Winarno, “Klasifikasi dengan pohon keputusan berbasis algoritme C4.5,” Prisma, Prosiding Seminar Nasional Matematika, vol. 3, pp. 65–68, 2020.

R. Oktavia, J. T. Hardinata, and I. Irawan, “Penerapan metode algoritma K-means dalam pengelompokan angka harapan hidup saat lahir menurut provinsi,” Kesatria: Jurnal Penerapan Ilmu dan Teknologi, vol. 1, no. 4, pp. 154–161, Okt. 2020, doi: 10.30645/kesatria.v1i4.41

A. Rodionov and M. Mukhitdinova, “The role of a decision tree as a method of artificial intelligence for the analysis of big data problems,” Economics and Innovative Technologies, vol. 11, no. 2, pp. 400–407, Apr. 2023, doi: 10.55439/eit/vol11_iss2/i39.

K. G. Komarasamy and T. N. Ravishankar, “The application of decision tree method for data mining,” Technoarete Transactions on Intelligent Data Mining and Knowledge Discovery (TTIDMKD), vol. 2, no. 3, Oct. 2022, doi: 10.36647/ttidmkd/02.03.a005.

N. Nurliana, N. Suarna, and W. Prihatono, “Analisis keputusan pembelian produk terhadap promosi dan viral marketing di TikTok Shop menggunakan algoritma C4.5,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 8 no.3, pp. 2871–2872, 2024. 10.36040/jati.v8i3.9583.

U. M. Pratiwi and M. Ibad, “Klasifikasi faktor yang berpengaruh dalam kehamilan tidak diinginkan menggunakan metode algoritma decision tree,” Lebesque, vol. 3, no. 2, pp. 406-416, Agus. 2022, doi: 10.46306/lb.v3i2.129

N. H. Ibrahim dan L. Khikmah, “Perbandingan metode algoritma C4.5, Naïve bayes dan logistic regression untuk penentuan kelayakan penerimaan kredit”. Unipdu, vol. 4. no. 2 pp. 89-93. 2024.

S. Moslehi, N. Rabiei, A. R. Soltanian, and M. Mamani, “Application of machine learning models based on decision trees in classifying the factors affecting mortality of COVID-19 patients in Hamadan, Iran,” BMC Medical Informatics and Decision Making, vol. 22, no. 1, Jul. 2022, doi: 10.1186/s12911-022-01939-x.

Y. Duan et al., “Application of the decision tree method to lithology identification of volcanic rocks-taking the Mesozoic in the Laizhouwan Sag as an example,” Scientific Reports, vol. 10, no. 1, p. 19209, Nov. 2020, doi: 10.1038/s41598-020-76303-y.

S. Samadianfard, F. Mikaeilia and R. Prasad, “Evaluation of classification and decision trees in predicting daily precipitation occurrences,” Water Supply, vol. 22, no. 4, pp. 3879–3895, 2022, doi: 10.2166/ws.2022.017.

A. Nugroho, “Analisa Splitting Criteria pada Decision Tree dan Random Forest untuk Klasifikasi Evaluasi Kendaraan,” JSITIK, vol. 1, no. 1, pp. 41–49, 2022. https://doi.org/10.53624/jsitik.v1i1.154.

E. Muningsih et. al., “Optimized Decision Tree Classification Method for Diabetes Prediction,” TELKOMNIKA Telecommunication, Computing, Electronics and Control, vol. 22, no. 4, pp. 941–948, 2024. doi: 10.12928/TELKOMNIKA.v22i4.25656.

D.T. Larose, Discovering Knowledge in Data: An Introduction to Data Mining, John Wiley and Sons, Inc., New Jersey, 2005.




DOI: https://doi.org/10.15548/jostech.v5i2.12269

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 JOSTECH Journal of Science and Technology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.