Classification of Disaster Impact Severity in North Maluku Using Random Forest Based on Spatial-Temporal Characteristics
DOI:
https://doi.org/10.63581/JoCPES.v6i2.04Keywords:
Disaster, Disaster Classification, Principal Component Analysis, Severity Index, Random ForestAbstract
Disaster impact severity is typically assessed only after casualty and damage data have been collected, even though the spatial-temporal characteristics of an event are known from the outset. This study aims to construct a disaster severity index using multi-component Principal Component Analysis (PCA) and to classify it using only spatial-temporal characteristics, deliberately excluding impact variables as predictors to avoid target leakage. The dataset comprises 239 disaster events in North Maluku Province (2021-2025) sourced from DIBI-BNPB. The severity index was built through log1p transformation, standardization, KMO (0.757) and Bartlett's Test (chi- square=1010.81; p<0.001), and Kaiser-criterion PCA yielding four principal components (cumulative variance 64.44%). The severity class was divided into four quartile-based classes and validated through a monotonic relationship with mean affected/displaced victims and a significant ANOVA test (F=17.574; p<0.001). Classification used five spatial-temporal features (year, month, week, regency/city, disaster type) under a temporal split scheme, comparing Random Forest, XGBoost, and a Dummy Classifier. Random Forest achieved the best performance with a Macro-F1 of 0.146 on the 2025 test set, outperforming the baseline (0.041) though the absolute value remains low. An ablation test revealed that a temporal-only feature scenario achieved the highest Macro-F1 (0.180), indicating limitations in the categorical encoding scheme. Sensitivity analysis confirmed the results are robust to changes in the class scheme (Macro-F1 difference of 0.047). The main contribution of this study is a validated severity-index construction methodology and early empirical evidence on the limitations of spatial- temporal features for early disaster severity classification.
References
[1] Badan Nasional Penanggulangan Bencana (BNPB), “Data dan Informasi Bencana Indonesia (DIBI),” http://dibi.bnpb.go.id/, 2025 (accessed Aug. 20, 2026).
[2] N. Haris, A. C. Furqan, A. Kahar, and F. Karim, “Disaster risk index on disaster management budgeting: Indonesia’s national data set,” Jàmbá: J. Disaster Risk Stud., vol. 15, no. 1, Art. no. a1365, 2023, doi: 10.4102/jamba.v15i1.1365.
[3] R. Djalante, “A systematic literature review of research trends and authorships on natural hazards, disasters, risk reduction and climate change in Indonesia,” Nat. Hazards Earth Syst. Sci., vol. 18, no. 6, pp. 1785–1810, 2018, doi: 10.5194/nhess-18-1785-2018.
[4] N. Zhang, H. Huang, B. Su, J. Zhao, and B. Zhang, “Information dissemination analysis of different media towards the application for disaster pre-warning,” PLoS ONE, vol. 9, no. 5, Art. no. e98649, 2014, doi: 10.1371/journal.pone.0098649.
[5] K. Schwarz, D. A. Aranda, and M. Hartmann, “Towards automated situational awareness reporting for disaster management—a case study,” Sustainability, vol. 15, no. 10, Art. no. 7968, 2023, doi: 10.3390/su15107968.
[6] S. P. Adi, V. B. Adishesha, K. V. Bharadwaj, and A. Narayan, “Earthquake damage prediction using random forest and gradient boosting classifier,” Am. J. Biol. Environ. Stat., vol. 6, no. 3, pp. 58–63, 2020, doi: 10.11648/j.ajbes.20200603.14.
[7] R. L. Puspasari, D. Yoon, H. Kim, and K.-W. Kim, “Machine learning for flood prediction in Indonesia: Providing online access for disaster management control,” Econ. Environ. Geol., vol. 56, no. 1, pp. 65–73, 2023, doi: 10.9719/eeg.2023.56.1.65.
[8] F. Grady, J. K. Tarigan, J. R. Wahidiyat, and A. Prasetyo, “Classification of flood alert in Jakarta with random forest,” in 2022 IEEE 7th Int. Conf. Inf. Technol. Digit. Appl. (ICITDA), Yogyakarta, Indonesia, 2022, pp. 1–6, doi: 10.1109/ICITDA55840.2022.9971411.
[9] S. Kaufman, S. Rosset, C. Perlich, and O. Stitelman, “Leakage in data mining: Formulation, detection, and avoidance,” ACM Trans. Knowl. Discov. Data, vol. 6, no. 4, Art. no. 15, 2012, doi: 10.1145/2382577.2382579.
[10] H. F. Kaiser, “The application of electronic computers to factor analysis,” Educ. Psychol. Meas., vol. 20, no. 1, pp. 141–151, 1960, doi: 10.1177/001316446002000116.
[11] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[12] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
[13] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 785–794, doi: 10.1145/2939672.2939785.
[14] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” arXiv:1705.07874, 2017, doi: 10.48550/arXiv.1705.07874.
[15] M. Loecher, “From unbiased MDI feature importance to explainable AI for trees,” arXiv:2003.12043, 2020, doi: 10.48550/arXiv.2003.12043.
Downloads
Published
Data Availability Statement
The disaster event data supporting the findings of this study are openly available in the Indonesian Disaster Data and Information (DIBI) system managed by the National Disaster Management Authority (BNPB), accessible at http://dibi.bnpb.go.id/. The processed dataset and analysis code used to generate the severity index and classification results are available from the corresponding author upon reasonable request.
Issue
Section
License
Copyright (c) 2026 Firman Almaliky Gapi Amra (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright and License
Copyright © The Author(s). Authors retain copyright and full publishing rights to their work. Publication in the Journal of Computation Physics and Earth Science (JoCPES) does not transfer copyright to the journal or publisher. Authors grant JoCPES a non-exclusive right of first publication.
All articles published by JoCPES are licensed under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).
Under this license, users are permitted to share, copy, redistribute, adapt, remix, transform, and build upon the published material for any purpose, including commercial use, provided that appropriate credit is given to the original author(s) and source, a link to the license is provided, and any changes made are indicated.
If the material is remixed, transformed, or built upon, the resulting work must be distributed under the same CC BY-SA 4.0 license. No additional legal terms or technological measures may be applied that restrict others from exercising the rights permitted by the license.
For complete license terms, please refer to the Creative Commons Attribution-ShareAlike 4.0 International License:
https://creativecommons.org/licenses/by-sa/4.0/
