Performance Comparison of Random Forest, Support Vector Machine, and K-Nearest Neighbors Algorithms in Ten-Minute Rainfall Prediction for Urban Flood Mitigation in South Tangerang
DOI:
https://doi.org/10.30871/jaic.v10i4.10809Keywords:
KNN, Orange, Rainfall, Random Forest, SVMAbstract
Rainfall prediction with very high temporal resolution, such as ten-minute intervals, is of great urgency in urban flood mitigation, especially in densely populated areas such as South Tangerang. Most previous studies still focus on daily or monthly rainfall prediction, so this study attempts to fill this gap by comparing the performance of three machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in predicting ten-minute rainfall. A dataset of 52,703 entries was obtained from an automated weather station (AWS) with predictor variables of temperature, humidity, and air pressure. The analysis process was carried out through preprocessing stages (missing value imputation, Min–Max normalization), data splitting (80:20), and 10-fold cross-validation using Orange Data Mining software. Model performance evaluation used Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R²). The results showed that Random Forest performed best with an RMSE of 0.671 and MAE of 0.090, followed by KNN with an RMSE of 0.683 and MAE of 0.083, while SVM performed significantly lower (RMSE of 2.553 and MAE of 2.511). However, the negative R² values for all models indicate limitations in explaining rainfall data variability, which is likely influenced by skewed data distribution (zero-inflated) and AWS sensor noise. These findings indicate that Random Forest is relatively more reliable than other models, but its accuracy is still not optimal for operational applications. Future research is recommended to adopt a hybrid or deep learning approach (e.g., LSTM), add other meteorological variables such as wind speed and solar radiation, and integrate the models into IoT-based early warning systems to support urban flood mitigation.
Downloads
References
[1] C. Octavia and K. Marko, “Area vulnerability to flooding in Rangkasbitung District and its surroundings, Lebak Regency, Province of Banten,” E3S Web of Conferences, vol. 211, p. 02002, Nov. 2020, doi: 10.1051/e3sconf/202021102002.
[2] M. Wang et al., “Urban Flooding Risk Assessment in the Rural-Urban Fringe Based on a Bayesian Classifier,” Sustainability, vol. 15, no. 7, p. 5740, Mar. 2023, doi: 10.3390/su15075740.
[3] S. M. Toufique, S. U. Bhuiyan, A. Lateef, A. Zaman, J. Bin Islam, and D. Z. Karim, “Implementing Machine Learning Techniques to Forecast Floods in Bangladesh,” in 2024 International Conference on Electrical, Computer and Energy Technologies (ICECET, IEEE, Jul. 2024, pp. 1–6. doi: 10.1109/ICECET61485.2024.10698703.
[4] G. E. P. Воx, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, Fifth. New Jersey: John Wiley & Sons, 2016.
[5] O. V. Petrochenko, “The problem of flooding and analysis of the ways of its solution,” Environmental safety and natural resources, vol. 46, no. 2, pp. 5–22, Jun. 2023, doi: 10.32347/2411-4049.2023.2.5-22.
[6] J. Chen, Y. Li, C. Zhang, Y. Tian, and Z. Guo, “Urban Flooding Prediction Method Based on the Combination of LSTM Neural Network and Numerical Model,” Int. J. Environ. Res. Public Health, vol. 20, no. 2, p. 1043, Jan. 2023, doi: 10.3390/ijerph20021043.
[7] M. W. Gardner and S. R. Dorling, “Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences,” Atmos. Environ., vol. 32, no. 14–15, pp. 2627–2636, Aug. 1998, doi: 10.1016/S1352-2310(97)00447-0.
[8] F. Yuan et al., “Predicting Road Flooding Risk with Machine Learning Approaches Using Crowdsourced Reports and Fine-grained Traffic Data,” Aug. 2021, [Online]. Available: http://arxiv.org/abs/2108.13265
[9] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
[10] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.
[11] X. Liu et al., “Influencing Factors and Risk Assessment of Precipitation-Induced Flooding in Zhengzhou, China, Based on Random Forest and XGBoost Algorithms,” Int. J. Environ. Res. Public Health, vol. 19, no. 24, p. 16544, Dec. 2022, doi: 10.3390/ijerph192416544.
[12] Hartanto, S. Humaidi, E. Frida, M. Sinambela, and N. Ananda, “Evaluation of Meteorological Radar Precipitation Forecast in Banten,” in 2023 International Conference on Information Technology and Computing (ICITCOM), IEEE, Dec. 2023, pp. 297–300. doi: 10.1109/ICITCOM60176.2023.10442051.
[13] A. F. Radjab, H. Akib, Rifdan, and Jasruddin, “Partnership in Weather Observation using the Crowdsourcing Method,” IOP Conf. Ser. Earth Environ. Sci., vol. 499, no. 1, p. 012019, Jun. 2020, doi: 10.1088/1755-1315/499/1/012019.
[14] W. C. Skamarock et al., “A Description of the Advanced Research WRF Version 3,” Jun. 2008.
[15] P. Bauer, A. Thorpe, and G. Brunet, “The quiet revolution of numerical weather prediction,” Nature, vol. 525, no. 7567, pp. 47–55, Sep. 2015, doi: 10.1038/nature14956.
[16] S. Talbi, L. Guerzouli, and S. Fezzai, “Flood susceptibility zonation map using remote sensing and XGboost, Random Forest, Nearest neighbor models in GIS: a case study Tebessa city, Algeria.,” Mar. 31, 2023. doi: 10.21203/rs.3.rs-2710595/v1.
[17] Y. Wu, Z. Zhang, X. Qi, W. Hu, and S. Si, “Prediction of flood sensitivity based on Logistic Regression, eXtreme Gradient Boosting, and Random Forest modeling methods,” Water Science & Technology, vol. 89, no. 10, pp. 2605–2624, May 2024, doi: 10.2166/wst.2024.146.
[18] A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Stat. Comput., vol. 14, no. 3, pp. 199–222, Aug. 2004, doi: 10.1023/B:STCO.0000035301.49549.88.
[19] D. Valkenborg, A.-J. Rousseau, M. Geubbelmans, and T. Burzykowski, “Support vector machines,” American Journal of Orthodontics and Dentofacial Orthopedics, vol. 164, no. 5, pp. 754–757, Nov. 2023, doi: 10.1016/j.ajodo.2023.08.003.
[20] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1, pp. 21–27, Jan. 1967, doi: 10.1109/TIT.1967.1053964.
[21] J. Demšar et al., “Orange: Data Mining Toolbox in Python,” Journal of Machine Learning Research, vol. 14, pp. 2349–2353, 2013.
[22] J. Liu et al., “Assessment of Flood Susceptibility Using Support Vector Machine in the Belt and Road Region,” May 25, 2021. doi: 10.5194/nhess-2021-80.
[23] I. E. Mfon, M. C. Oguike, S. U. Eteng, and N. M. Etim, “Causes and Effects of Flooding in Nigeria: A Review,” International Journal of Social Science And Human Research, vol. 05, no. 10, pp. 4526–4533, Oct. 2022, doi: 10.47191/ijsshr/v5-i10-16.
[24] N. Gauhar, S. Das, and K. S. Moury, “Prediction of Flood in Bangladesh using k-Nearest Neighbors Algorithm,” in 2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), IEEE, Jan. 2021, pp. 357–361. doi: 10.1109/ICREST51555.2021.9331199.
[25] K. Rhamadania, M. Makhsun, C. Basir, and N. Ananda, “Imputation of Missing Weather Data in Automatic Weather Station Using the GRU Algorithm,” Journal of Applied Informatics and Computing, vol. 10, no. 2, pp. 1165–1171, Apr. 2026, doi: 10.30871/jaic.v10i2.12301.
[26] L. See, “A review of citizen science and crowdsourcing in applications of pluvial flooding,” Feb. 26, 2019, Frontiers Media S.A. doi: 10.3389/feart.2019.00044.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Tri Nurmayati
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an 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 website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
