COMPARATIVE ANALYSIS OF MACHINE LEARNING MODELS FOR RAINFALL CLASSIFICATION IN YOGYAKARTA
Abstract
Precise rainfall classification is most important for meteorological forecasting and disaster risk mitigation, particularly in regions such as Yogyakarta, which are vulnerable to extreme weather events. Although previous studies have examined rainfall classification through the lens of meteorological variables, a notable lack of research has systematically evaluated the effectiveness of diverse machine learning algorithms for categorizing rainfall types within this specific locale. This study aims to rectify this gap by incorporating essential weather variables, specifically temperature, humidity, atmospheric pressure, and precipitation, into predictive models that utilize K-Nearest Neighbors (KNN), decision trees, and logistic regression techniques. Among the evaluated models, the decision tree demonstrated the highest degree of accuracy across both training and testing datasets. An examination of feature significance indicated that precipitation emerged as the most pivotal variable, aligning with the fundamental physical mechanisms associated with rainfall. This study contributes significantly to the evolving field of weather informatics by illustrating the utility of machine learning approaches in classifying regional rainfall. However, the parameters of this research are limited to specific meteorological variables and do not account for spatial or temporal variations, which could potentially influence the model’s broader applicability. Future research endeavors could augment this framework by integrating remote sensing data and methodologies for spatiotemporal modeling.
Downloads
References
S. Scher, “TOWARD DATA‐DRIVEN WEATHER AND CLIMATE FORECASTING: APPROXIMATING A SIMPLE GENERAL CIRCULATION MODEL WITH DEEP LEARNING,” Geophys Res Lett, vol. 45, no. 22, Nov. 2018, doi: https://doi.org/10.1029/2018GL080704.
S. Adebayo, F. O. Aweda, I. A. Ojedokun, and J. A. Agbolade, “METEOROLOGICAL DATA PREDICTION OVER SELECTED STATIONS IN SUB-SAHARA AFRICA: LEVERAGING ON MACHINE LEARNING ALGORITHM,” Ruhuna Journal of Science, vol. 13, no. 2, pp. 129–140, Dec. 2022, doi: https://doi.org/10.4038/rjs.v13i2.120.
K. Naren Athreyas, E. Gunawan, and B. K. Tay, “ESTIMATION OF VERTICAL STRUCTURE OF LATENT HEAT GENERATED IN THUNDERSTORMS USING CLOUDSAT RADAR,” Meteorological Applications, vol. 27, no. 2, Mar. 2020, doi: https://doi.org/10.1002/met.1902.
W. Ghada et al., “STRATIFORM AND CONVECTIVE RAIN CLASSIFICATION USING MACHINE LEARNING MODELS AND MICRO RAIN RADAR,” Remote Sens (Basel), vol. 14, no. 18, p. 4563, Sep. 2022, doi: https://doi.org/10.3390/rs14184563.
W. Ghada, N. Estrella, and A. Menzel, “MACHINE LEARNING APPROACH TO CLASSIFY RAIN TYPE BASED ON THIES DISDROMETERS AND CLOUD OBSERVATIONS,” Atmosphere (Basel), vol. 10, no. 5, p. 251, May 2019, doi: https://doi.org/10.3390/atmos10050251.
H. Jain, R. Dhupper, A. Shrivastava, D. Kumar, and M. Kumari, “LEVERAGING MACHINE LEARNING ALGORITHMS FOR IMPROVED DISASTER PREPAREDNESS AND RESPONSE THROUGH ACCURATE WEATHER PATTERN AND NATURAL DISASTER PREDICTION,” Front Environ Sci, vol. 11, Nov. 2023, doi: https://doi.org/10.3389/fenvs.2023.1194918.
W. Ghada, J. Bech, N. Estrella, A. Hamann, and A. Menzel, “WEATHER TYPES AFFECT RAIN MICROSTRUCTURE: IMPLICATIONS FOR ESTIMATING RAIN RATE,” Remote Sens (Basel), vol. 12, no. 21, p. 3572, Oct. 2020, doi: https://doi.org/10.3390/rs12213572.
P. Asha, A. Jesudoss, S. P. Mary, K. V. S. Sandeep, and K. H. Vardhan, “AN EFFICIENT HYBRID MACHINE LEARNING CLASSIFIER FOR RAINFALL PREDICTION,” J Phys Conf Ser, vol. 1770, no. 1, p. 012012, Mar. 2021, doi: https://doi.org/10.1088/1742-6596/1770/1/012012.
R. S. Lubis, Y. Suzana, F. Syarah, F. Fajriana, F. Rozi, and B. C. Nusantara, “DYNAMICS OF RAINFALL AND TEMPERATURE IN NORTH SUMATRA PROVINCE: COMPREHENSIVE ANALYSIS OF TEMPORAL TRENDS,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 19, no. 1, pp. 215–226, Jan. 2025, doi: https://doi.org/10.30598/barekengvol19iss1pp215-226.
Z. Rustam, R. P. Yuda, H. Alatas, and C. Aroef, “PULMONARY RONTGEN CLASSIFICATION TO DETECT PNEUMONIA DISEASE USING CONVOLUTIONAL NEURAL NETWORKS,” TELKOMNIKA (Telecommunication Computing Electronics and Control), vol. 18, no. 3, p. 1522, Jun. 2020, doi: https://doi.org/10.12928/telkomnika.v18i3.14839.
G. Adhane, M. M. Dehshibi, and D. Masip, “ON THE USE OF UNCERTAINTY IN CLASSIFYING AEDES ALBOPICTUS MOSQUITOES,” IEEE J Sel Top Signal Process, vol. 16, no. 2, pp. 224–233, Feb. 2022, doi: https://doi.org/10.1109/JSTSP.2021.3122886.
S. Kasus et al., “KLASIFIKASI CURAH HUJAN HARIAN MENGGUNAKAN LEARNING VECTOR QUANTIZATION,” Jurnal Ilmu Komputer Indonesia (JIK), vol. 7, no. 2, 2022, [Online]. Available: http://www.ogimet.com,
D. Naidu, B. Majhi, and S. K. Chandniha, “DEVELOPMENT OF RAINFALL PREDICTION MODELS USING MACHINE LEARNING APPROACHES FOR DIFFERENT AGRO-CLIMATIC ZONES,” 2021, pp. 72–94. doi: https://doi.org/10.4018/978-1-7998-6659-6.ch005.
Z. Yang, P. Liu, and Y. Yang, “CONVECTIVE/STRATIFORM PRECIPITATION CLASSIFICATION USING GROUND-BASED DOPPLER RADAR DATA BASED ON THE K-NEAREST NEIGHBOR ALGORITHM,” Remote Sens (Basel), vol. 11, no. 19, p. 2277, Sep. 2019, doi: https://doi.org/10.3390/rs11192277.
T. Herlambang, V. Asy’ari, R. P. Rahayu, A. A. Firdaus, and N. Juniarta, “COMPARISON OF NAÏVE BAYES AND K-NEAREST NEIGHBOR MODELS FOR IDENTIFYING THE HIGHEST PREVALENCE OF STUNTING CASES IN EAST JAVA,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 18, no. 4, pp. 2153–2164, Oct. 2024, doi: https://doi.org/10.30598/barekengvol18iss4pp2153-2164.
J. Gou, H. Ma, W. Ou, S. Zeng, Y. Rao, and H. Yang, “A GENERALIZED MEAN DISTANCE-BASED K-NEAREST NEIGHBOR CLASSIFIER,” Expert Syst Appl, vol. 115, pp. 356–372, Jan. 2019, doi: https://doi.org/10.1016/j.eswa.2018.08.021.
D. M. Ali and H. A.Sadeq, “ROAD POTHOLE DETECTION USING UNMANNED AERIAL VEHICLE IMAGERY AND DEEP LEARNING TECHNIQUE,” Zanco J Pure Appl Sci, vol. 34, no. 6, Dec. 2022, doi: https://doi.org/10.21271/ZJPAS.34.6.12.
G. He, W. Wang, B. Shi, S. Liu, H. Xiang, and X. Wang, “AN IMPROVED YOLO V4 ALGORITHM-BASED OBJECT DETECTION METHOD FOR MARITIME VESSELS,” International Journal of Science and Engineering Applications, vol. 11, no. 04, pp. 50–55, Apr. 2022, doi: https://doi.org/10.7753/IJSEA1104.1001.
M. Mahasin and I. A. Dewi, “COMPARISON OF CSPDARKNET53, CSPRESNEXT-50, AND EFFICIENTNET-B0 BACKBONES ON YOLO V4 AS OBJECT DETECTOR,” International Journal of Engineering, Science and Information Technology, vol. 2, no. 3, pp. 64–72, Sep. 2022, doi: https://doi.org/10.52088/ijesty.v2i3.291.
R. Bhardwaj and V. Duhoon, “WEATHER FORECASTING USING DECISION TREE,” Journal of Engineering Research, Nov. 2021, doi: https://doi.org/10.1155/2021/6758557.
A. Purwanto, M. A. Suprayogi, E. Setiawan, J. F. R. B. Loly, G. A. Rahman, and A. Kurnia, “MULTINOMIAL LOGISTIC REGRESSION MODEL USING MAXIMUM LIKELIHOOD APPROACH AND BAYES METHOD ON INDONESIA’S ECONOMIC GROWTH PRE TO POST COVID-19 PANDEMIC,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 19, no. 1, pp. 51–62, Jan. 2025, doi: https://doi.org/10.30598/barekengvol19iss1pp51-62.
E. García-Portugués, NOTES FOR PREDICTIVE MODELING, Version 5.10.1. https://bookdown.org/egarpor/PM-UC3M/, 2025.
Copyright (c) 2025 Dina Tri Utari, Ghalang Rambu Putera Palage, Faiz Fadhlirobby, Artheta Bimo Nuswantoro

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.