Short-Term Forecasting of Weekly Dengue Cases in Singapore Using ARIMA and Fourier-ARIMA Models
DOI:
https://doi.org/10.54097/a21c4j25Keywords:
Dengue, time series, ARIMA, Fourier-ARIMA, public health surveillance.Abstract
Dengue remains a recurring public health issue in Singapore, where sudden weekly increases in reported cases can create pressure on surveillance, healthcare response, and vector-control planning. This study builds a short-term forecasting framework using official weekly dengue surveillance data from 2012-W01 to 2026-W17. The dataset was reorganized into a continuous epidemiological-week time series, and total dengue cases were defined by combining dengue fever and dengue hemorrhagic fever cases. Because the raw series contains outbreak spikes and unstable variance, the log transformation was used before model fitting. The analysis then applied ACF/PACF inspection, differencing, ARIMA search, Fourier-ARIMA comparison, residual diagnostics, and chronological train-test validation. The first 673 weeks were used for training, and the final 75 weeks were used for one-week-ahead testing. Results indicate that ARIMA(4,1,0)+Fourier(2) offers the strongest balance between prediction accuracy, residual adequacy, and model simplicity. The model should be understood as a practical surveillance baseline rather than a complete explanation of dengue transmission.
Downloads
References
[1] Shi Yuan, Liu Xu, et al. Three-month real-time dengue forecast models: An early warning system for outbreak alerts and policy decision support in Singapore. Environmental Health Perspectives, 2016, 124(9): 1369-1375. DOI: https://doi.org/10.1289/ehp.1509981
[2] Tian Na, Zheng Jin-Xin, et al. Precision prediction for dengue fever in Singapore: A machine learning approach incorporating meteorological data. Tropical Medicine and Infectious Disease, 2024, 9(4): 72. DOI: https://doi.org/10.3390/tropicalmed9040072
[3] Government of Singapore. Weekly Infectious Disease Bulletin Cases. data.gov.sg, 2026.
[4] Communicable Diseases Agency Singapore. Weekly Infectious Diseases Bulletin 2023. Communicable Diseases Agency Singapore, 2023.
[5] Communicable Diseases Agency Singapore. Weekly Infectious Diseases Bulletin 2024. Communicable Diseases Agency Singapore, 2024.
[6] Communicable Diseases Agency Singapore. Weekly Infectious Diseases Bulletin 2025. Communicable Diseases Agency Singapore, 2025.
[7] Communicable Diseases Agency Singapore. Weekly Infectious Diseases Bulletin 2026. Communicable Diseases Agency Singapore, 2026.
[8] Hii Yien Ling, Zhu Huaiping, et al. Forecast of dengue incidence using temperature and rainfall. PLOS Neglected Tropical Diseases, 2012, 6(11): e1908. DOI: https://doi.org/10.1371/journal.pntd.0001908
[9] Leung Xing Yu, Islam Rakibul M., et al. A systematic review of dengue outbreak prediction models: Current scenario and future directions. PLOS Neglected Tropical Diseases, 2023, 17(2): e0010631. DOI: https://doi.org/10.1371/journal.pntd.0010631
[10] Ong Song Quan, Isawasan Pradeep, et al. Predicting dengue transmission rates by comparing different machine learning models with vector indices and meteorological data. Scientific Reports, 2023, 13(1): 19129. DOI: https://doi.org/10.1038/s41598-023-46342-2
[11] Earnest Arul, Tan Say Beng, et al. Comparing statistical models to predict dengue fever notifications. Computational and Mathematical Methods in Medicine, 2012, 2012-758674. DOI: https://doi.org/10.1155/2012/758674
[12] Zhao Ning, Charland Katelyn, et al. Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. PLOS Neglected Tropical Diseases, 2020, 14(9): e0008056. DOI: https://doi.org/10.1371/journal.pntd.0008056
[13] Colon-Gonzalez Felipe J., Soares Bastos Leonardo, et al. Probabilistic seasonal dengue forecasting in Vietnam: A modelling study using superensembles. PLOS Medicine, 2021, 18(3): e1003542. DOI: https://doi.org/10.1371/journal.pmed.1003542
[14] Nguyen Van H., Tuyet-Hanh Thi Tuyet, et al. Deep learning models for forecasting dengue fever based on climate data in Vietnam. PLOS Neglected Tropical Diseases, 2022, 16(6): e0010509. DOI: https://doi.org/10.1371/journal.pntd.0010509
[15] Zhao Xinxing, Li Kainan, et al. A deep learning based hybrid architecture for weekly dengue incidences forecasting. Chaos, Solitons & Fractals, 2023, 168: 113170. DOI: https://doi.org/10.1016/j.chaos.2023.113170
[16] Panja Madhurima, Chakraborty Tanujit, et al. An ensemble neural network approach to forecast dengue outbreak based on climatic condition. Chaos, Solitons & Fractals, 2023, 167: 113124. DOI: https://doi.org/10.1016/j.chaos.2023.113124
[17] Sebastianelli Alessandro, Spiller Dario, et al. A reproducible ensemble machine learning approach to forecast dengue outbreaks. Scientific Reports, 2024, 14: 3807. DOI: https://doi.org/10.1038/s41598-024-52796-9
[18] Chen Xuan, Moraga Paula. Assessing dengue forecasting methods: A comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil. Tropical Medicine and Health, 2025, 53: 52. DOI: https://doi.org/10.1186/s41182-025-00723-7
[19] Chen Xuan, Moraga Paula. Forecasting dengue across Brazil with LSTM neural networks and SHAP-driven lagged climate and spatial effects. BMC Public Health, 2025, 25: 973. DOI: https://doi.org/10.1186/s12889-025-22106-7
[20] Hyndman Rob J., Athanasopoulos George. Dynamic harmonic regression. Forecasting: Principles and Practice, 2021.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

