Scalable Forecasting Geoanalytics for Epidemic Dengue Risk in East Java
DOI:
https://doi.org/10.26911/jepublichealth.2026.11.03.05Abstract
Background: Current methods for managing Dengue Hemorrhagic Fever (DHF) in East Java often separate temporal and spatial analyses, hindering proactive public health interventions. To address this limitation, this study develops an integrated spatio-temporal framework that combines multi-model forecasting and geospatial analysis to create localized dengue projections and risk maps.
Subjects and Method: An ecological spatio-temporal design was conducted across 38 districts/ cities in East Java using secondary data from 2013–2023. The dependent variable was annual dengue incidence, while independent variables comprised natural factors (e.g., rainfall, humidity) and social factors (e.g., population density, poverty). Data were analyzed using Geographically Weighted Regression (GWR) for spatial modeling. Time series forecasting for the 2024–2028 period was conducted using Trigonometric seasonality, Box-Cox transformation (TBATS), Autoregressive Integrated Moving Average (ARIMA), Prophet, and Neural NETwork AutoRegression (NNETAR) models, evaluated by Root Mean Square Error (RMSE).
Results: Rainfall demonstrated the strongest natural association (R²=0.49; p=0.022), followed by humidity (R²=0.26; p<0.001). Epidemiologically, population density emerged as the key social determinant (R²=0.50; p=0.005). TBATS achieved the highest forecasting accuracy with the lowest RMSE (47.657), outperforming ARIMA (202.980), Prophet (172.809), and NNETAR (157.653). Spatial risk mapping revealed that high-risk social clusters are heavily concentrated in the eastern 'Tapal Kuda' region and northern coastal metropolitan corridors.
Conclusion: Dengue incidence in East Java is significantly driven by climatic factors and spatially varying social vulnerabilities. The integration of TBATS forecasting and GWR spatial modeling provides a robust framework for anticipating future case burdens and identifying priority intervention areas, thereby supporting highly targeted public health planning.
Keywords:
dengue, forecasting, spatial analysis, population densityHow to Cite
References
Abbasi E. (2025). The impact of climate change on travel-related vector-borne diseases: A case study on dengue virus transmission. Travel Med Infect Dis. 65: 102841. https://doi.org/10.1016/j.tmaid.2025.102841.
Chen Z, Zhang S, Geng W, Ding Y, Jiang X. (2022). Use of Geographically Weighted Regression (GWR) to Reveal Spatially Varying Relationships between Cd Accumulation and Soil Properties at Field Scale. Land. 11(5): 635. https://doi.org/10.3390/-land11050635.
Cunha MS, Coletti, TM Guerra JM, Ponce CC, Fernandes NCCA, Résio RA, Claro IM, et al., (2022). A fatal case of dengue hemorrhagic fever associated with dengue virus 4 (DENV-4) in Brazil: genomic and histopathological findings. Braz J Microbiol. 53(3): 1305–1312. https://doi.org/10.1007/s42770022007844.
Damtew YT, Tong M, Varghesea BM, Anikeevaa O, Hansena A, Dearaet K, al. (2023). Effects of high tempera-tures and heatwaves on dengue fever: a systematic review and meta-analysis. EBioMedicine. 91: 104582. https://doi.org/10.1016/j.ebiom.2023.104582.
de Souza WM, Weaver SC. (2024). Effects of climate change and human acti¬vities on vector-borne diseases. Nature Rev Microbiol. 22(8): 476–491. https://doi.org/10.1038/s41579024010260.
Faridah L, Suroso DSA, Fitriyanto MS, Andari CD, Fauzi I, Kurniawan Y, Watanabe K. (2022). Optimal validated multifactorial climate change risk assessment for adaptation planning and evaluation of infectious disease: A case study of dengue hemorrhagic fever in Indonesia. Trop Med Infect Dis. 7(8): 172. https://doi.org/10.3390/tropicalmed7080172
Fotheringham AS, Yu H, Wolf LJ, Oshan TM, Li Z. (2022). On the notion of ‘bandwidth’ in geographically weighted regression models of spatially varying processes. Int J Geogr Inf Sci. 36(8): 1485–1502. https://doi.org/10.1080/13658816.2022.2034829.
Gupta G, Khan S, Guleria V, Almjally A, Alabduallah BI, Siddiqui T, Albahlal BM, et al. (2023). DDPM: A Dengue Disease Prediction and Diagnosis Model Using Sentiment Analysis and Machine Learning Algorithms. Diagnostics. 13(6): 1093. https://doi.org/10.3390/diagnostics13061093.
Kontopoulou VI, Panagopoulos AD, Kakkos I, Matsopoulos GK. (2023). A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks. Future Internet. 15(8): 255. https://doi.org/10.3390/fi15080255.
Li J, Guo SX, Ma RL, He J, Zhang XH, Rui DS, Ding YS, et al., (2024). Comparison of the effects of imputation methods for missing data in predictive modelling of cohort study datasets. BMC Med Res Methodol. 24(1): 41. https://doi.org/10.1186/s1287402402173x.
Liu Y, Feng G, Chin KS, Sun S, Wang S (2023). Daily tourism demand fore-casting: the impact of complex seasonal patterns and holiday effects. Curr Issues Tour. 26(10): 1573–1592. https://doi.org/10.1080/13683500.2022.2060067.
Na L, Shi Y, Guo L. (2023). Quantifying the spatial nonstationary response of influencing factors on ecosystem health based on the geographical weighted regression (GWR) model: an example in Inner Mongolia, China, from 1995 to 2020. Environ Sci Pollut Res. 30(29): 73469–73484. https://doi.org/10.1007/s11356023269154.
Oh J, Seong B. (2024). Forecasting with a combined model of ETS and ARIMA. Commun Stat Appl Methods. 31(1): 143–154. https://doi.org/10.29220/CSAM.2024.31.1.143.
Parveen S, Riaz Z, Saeed S, Ishaque U, Sultana M, Faiz Z, Shafqat Z, al., (2023). Dengue hemorrhagic fever: a growing global menace. J Water Health. 21(11): 1632–1650. https://-doi.org/10.2166/wh.2023.114.
Perone G. (2022). Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy. Eur J Health Econ. 23(6): 917–940. https://doi.org/10.1007/s10198021013474.
Riaz M, Harun SNB, Mallhi TH, Khan YH, Butt MH, Husain A, Khan MM, et al., (2024). Evaluation of clinical and laboratory characteristics of dengue viral infection and risk factors of dengue hemorrhagic fever: a multi-center retrospective analysis. BMC Infect Dis. 24(1): 500. https://doi.org/10.1186/s1287902409384z
Sudarmaja IM, Swastika IK, Diarthini LPE, Prasetya IPD, Wirawan IMA (2022). Dengue virus transovarial transmission detection in Aedes aegypti from dengue hemorrhagic fever patients’ residences in Denpasar, Bali. Veterinary World. 1149–1153. https://doi.org/10.14202/vetworld.2022.1149-1153.
Wang H, Huang Z, Guo H, Yin G, Bao Y, Zhou X, Gao Y, et al. (2026). GWR-Boost: A Geographically Weighted Gradient Boosting Framework for Enhanced Explainable Quantification of Spatially Varying Relationships. Ann Am Assoc Geogr. 1–19. https://doi.org/10.1080/24694452.2026.2648327.
Wang Q, Gayed JM. (2026). Effectiveness of large language models in automated evaluation of argumentative essays: finetuning vs. zero-shot prompting. Comput Assist Lang Learn. 39(1–2): 209–237. https://-doi.org/10.1080/09588221.2024.2371395.
Yang W, Deng M, Tang J, Luo L. (2023). Geographically weighted regression with the integration of machine learning for spatial prediction. J Geogr Syst. 25(2): 213–236. https://doi.org/10.1007/s10109022003875.
Zhao D, Zhang H. (2022). The research on TBATS and ELM models for prediction of human brucellosis cases in mainland China: a time series study. BMC Infect Dis. 22(1): 934. https://doi.org/10.1186/s1287902207919w.
1.jpg)
