Geographically Weighted Machine Learning Model for Untangling Spatial Heterogeneity of Dengue Incidence in West Java
Keywords:
Dengue, Random forest regression, Geographically weighted random forest, Spatial analysis, West JavaAbstract
Dengue hemorrhagic fever continues to pose a significant public health challenge, particularly in West Java Province, Indonesia, which consistently reports the highest incidence rates in the country. This study examined the factors influencing dengue fever incidence using Random Forest Regression (RFR) and Geographically Weighted Random Forest (GWRF) methodologies. Utilizing secondary data from 2022 to 2024 across 27 districts/cities, the data from 2022 to 2023 served as training data, while the 2024 data were used for testing. The findings revealed that the optimal RFR model, with ntree = 1000 and mtry = 1, achieved an RMSE of 1796.409, a MAPE of 0.482, and an of 0.685. Conversely, the GWRF model, which employed an adaptive kernel and an optimal bandwidth of 45 nearest neighbors, exhibited superior performance, with an RMSE of 1,756.713, MAPE of 0.466, and of 0.700. This enhancement in the model performance suggests that spatial weighting improves the model's capacity to capture spatial heterogeneity. In addition, variations in local feature importance indicate spatial non-stationarity across regions. These results imply that the GWRF is more effective in modeling dengue fever outbreaks and can inform the development of region-specific public health interventions.References
[1] Y. Chen, Y. Liao, K. Yuan, A. Wu, and L. Liu, “HLA-A, -B, -DRB1 Alleles as Genetic Predictive Factors for Dengue Disease: A Systematic Review and Meta-Analysis,” Viral Immunol., vol. 32, no. 3, pp. 121–130, 2019, doi: 10.1089/vim.2018.0151.
[2] M. Kanan et al., “Genetic variants associated with dengue hemorrhagic fever. A systematic review and meta-analysis,” J. Infect. Public Health, vol. 17, no. 4, pp. 579–587, 2024, doi: 10.1016/j.jiph.2024.02.001.
[3] Y. Liu et al., “Trends and insights in dengue virus research globally : a bibliometric analysis ( 1995 – 2023 ),” J. Transl. Med., vol. 22, no. 1, p. 818, 2024.
[4] R. Yousuf, M. W. Salam, S. Akter, S. Sinha, and M. Haque, “Dengue Dynamics : A Global Update,” Advances in Human Biology, vol. 14, no. December, pp. 5–10, 2023, doi: 10.4103/aihb.aihb_135_23.
[5] A. M. Tejo, D. T. Hamasaki, L. M. Menezes, and Y. Ho, “Severe dengue in the intensive care unit,” Journal of Intensive Medicine, vol. 4, no. September 2023, pp. 16–33, 2024, doi: 10.1016/j.jointm.2023.07.007.
[6] W. C. Ng et al., “A natural human cell-adapted dengue type 3 virus strain,” Microbiol. Spectr., vol. 12, no. 7, pp. 10–13, 2024, doi: 10.1128/spectrum.00701-24.
[7] B. A. Ajlan, M. M. Alafif, M. M. Alawi, N. A. Akbar, E. K. Aldigs, and T. A. Madani, “Assessment of the new World Health Organization’s dengue classification for predicting severity of illness and level of healthcare required,” PLoS Negl. Trop. Dis., vol. 13, no. 8, p. p.516229, 2019, doi: 10.1371/journal.pntd.0007144.
[8] Ministry of Health of the Republic of Indonesia, “Indonesia Health Profile 2024,” 2025.
[9] WHO, “Dengue - Global situation,” World Health Organization. Accessed: Apr. 21, 2026. [Online]. Available: https://www.who.int/emergencies/disease-outbreak-news/item/2023-DON498
[10] T. C. N. Monintja, A. A. Arsin, R. Amiruddin, and M. Syafar, “Analysis of temperature and humidity on dengue hemorrhagic fever in Manado Municipality ଝ,” Gac. Sanit., vol. 35, no. 2, pp. S330–S333, 2021, doi: 10.1016/j.gaceta.2021.07.020.
[11] H. Harapan et al., “Dengue viruses circulating in Indonesia : A systematic review and phylogenetic analysis of data from five decades,” Rev. Med. Virol., no. December 2018, pp. 1–17, 2019, doi: 10.1002/rmv.2037.
[12] I. Saiful Fauzi, N. Nuraini, R. Wahyudyah, R. W. S. Ayu, and B. W. Lestari, “Heliyon Temporal trend and spatial clustering of the dengue fever prevalence in West Java, Indonesia,” Heliyon, vol. 8, no. 8, p. e10350, 2022, doi: 10.1016/j.heliyon.2022.e10350.
[13] I. Suryani, H. Yasin, and P. Kartikasari, “Pemodelan jumlah kasus demam berdarah dengue (dbd) di jawa tengah dengan geographically weighted negative binomial regression (gwnbr),” Gaussian, vol. 10, 2021.
[14] Y. S. Dewi, S. Hastuti, and M. Fatekurohman, “Analysis of stunting in East Java , Indonesia using random forest and geographically weighted random forest regression,” vol. 224, pp. 213–224, 2024, doi: 10.28951/bjb.v42i3.679.
[15] S. Quiñones, A. Goyal, and Z. U. Ahmed, “Geographically weighted machine learning model for untangling spatial heterogeneity of type 2 diabetes mellitus ( T2D ) prevalence in the USA,” Sci. Rep., pp. 1–13, 2021, doi: 10.1038/s41598-021-85381-5.
[16] S. Georganos et al., “Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling,” Geocarto Int., vol. 36, no. 2, pp. 121–136, 2021, doi: 10.1080/10106049.2019.1595177.
[17] Y. Luo, J. Yan, and S. McClure, “Distribution of the environmental and socioeconomic risk factors on COVID-19 death rate across continental USA : a spatial nonlinear analysis,” Environ. Sci. Pollut. Res. Int., vol. 28, no. 6, pp. 6587–6599, 2021, doi: 10.1007/s11356-020-10962-2.
[18] M. Schonlau and R. Y. Zou, “The random forest algorithm for statistical learning,” Stata J., no. 1, pp. 3–29, 2020, doi: 10.1177/1536867X20909688.
[19] S. Astiti, A. W. Aranski, and Darmansah, “Prediction of Potential Fishing Zones Using K-Means Clustering and Random Forest in Batam Waters,” JUITA: Jurnal Informatika, vol. 14, no. 1, pp. 221–230, Mar. 2026, doi: 10.30595/juita.v14i1.29679.
[20] P. Probst, M. N. Wright, and A.-L. Boulesteix, “Hyperparameters and tuning strategies for random forest,” Wires Data Mining And Knowledge Discovery, vol. 9, no. 3, 2019.
[21] Y. Luo, J. Yan, S. C. McClure, and F. Li, “Socioeconomic and environmental factors of poverty in China using geographically weighted random forest regression model,” Environ Sci Pollut Res, vol. 29, pp. 33205–33217, 2022, doi: https://doi.o10.1007/s11356-021-17513-3.
[22] D. N. Gujarati, Basic Econometrics, 4th ed. New York: McGraw-Hill Companies, 2004.
[23] L. Anselin, Spatial Econometrics: Methods and Models. Dordrecht: Kluwer Academic, 1988. doi: 10.1007/978-94-015-7799-1.
[24] U. Grömping, “Variable Importance Assessment in Regression: Linear Regression versus Random Forest,” Am. Stat., vol. 4, no. 63, pp. 308–319, 2012.
[25] L. Feng, Y. Wang, Z. Zhang, and Q. Du, “Geographically and temporally weighted neural network for winter wheat yield prediction,” Remote Sens. Environ., vol. 262, 2021, doi: 10.1016/j.rse.2021.112514.
[26] R. Hartanti, P. Yulianing, S. Astutik, and A. B. Astuti, “Geographically Weighted Random Forest Model for Addressing Spatial Heterogeneity of Monthly Rainfall with Small Sample Size,” Cauchy, vol. 10, no. 1, pp. 442–456, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Auralia Putri Astutiningsih, Gangga Anuraga, Hani Brilianti Rochmanto, Muhammad Athoillah
This work is licensed under a Creative Commons Attribution 4.0 International License.
JUITA: Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.
