Data-Efficient LSTM Modeling for Climate-based Dengue Early Warning in Lampung, Indonesia
Abstract
We present a data-efficient recurrent framework for climate-informed dengue early warning in Lampung Province. Monthly incidence and climate records are transformed into supervised sequences with 2–3-month lags, consistent with the observed lead–lag structure. Three architectures i.e. single-layer LSTM, stacked LSTM, and Temporal-Attention LSTM (TA-LSTM) are tuned via a compact genetic search under a time-ordered split. Performance improves with longer history; the TA-LSTM (37 units) attains the best accuracy. Permutation feature importance reveals a clear hierarchy: relative humidity and maximum temperature dominate, autoregressive incidence contributes moderately, while rainfall, sunshine, and minimum temperature are secondary; average temperature is largely redundant. The findings indicate that adding meaningful historical context and selective temporal weighting yields robust early-warning capability from coarse, time-limited data, and that humidity–temperature dynamics, together with short-term incidence persistence, are the principal drivers in this provincial setting.
Keywords
References
Y. L. Hii, J. Rocklöv, N. Ng, C. S. Tang, F. Y. Pang, and R. Sauerborn, “Climate variability and increase in intensity and magnitude of dengue incidence in Singapore,” Glob. Health Action, vol. 2, p. 10.3402/gha.v2i0.2036, Nov. 2009, doi: 10.3402/gha.v2i0.2036.
“Dengue.” Accessed: Oct. 18, 2025. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/dengue-and-severe-dengue
Z. Liu et al., “The effect of temperature on dengue virus transmission by Aedes mosquitoes,” Front. Cell. Infect. Microbiol., vol. 13, Sept. 2023, doi: 10.3389/fcimb.2023.1242173.
Y. Wang et al., “Impact of climate change on dengue fever epidemics in South and Southeast Asian settings: A modelling study,” Infect. Dis. Model., vol. 8, no. 3, pp. 645–655, Sept. 2023, doi: 10.1016/j.idm.2023.05.008.
N. Nuraini, I. S. Fauzi, M. Fakhruddin, A. Sopaheluwakan, and E. Soewono, “Climate-based dengue model in Semarang, Indonesia: Predictions and descriptive analysis,” Infect. Dis. Model., vol. 6, pp. 598–611, 2021, doi: 10.1016/j.idm.2021.03.005.
A. Susilawaty, R. Ekasari, L. Widiastuty, D. R. Wijaya, Z. Arranury, and S. Basri, “Climate factors and dengue fever occurrence in Makassar during period of 2011-2017,” Gac. Sanit., vol. 35 Suppl 2, pp. S408–S412, 2021, doi: 10.1016/j.gaceta.2021.10.063.
P. Yushananta and M. Ahyanti, “Pengaruh Faktor Iklim dan Kepadatan Jentik Ae. Aegypti Terhadap Kejadian DBD,” J. Kesehat., vol. 5, no. 1, 2014, doi: 10.26630/jk.v5i1.58.
P. Yushananta, “Dengue Hemorrhagic Fever and Its Correlation with The Weather Factor In Bandar Lampung City: Study From 2009-2018,” J. Aisyah J. Ilmu Kesehat., vol. 6, no. 1, p. 117, Mar. 2021, doi: 10.30604/jika.v6i1.452.
V. G. Ramachandran, P. Roy, S. Das, N. S. Mogha, and A. K. Bansal, “Empirical model for estimating dengue incidence using temperature, rainfall, and relative humidity: a 19-year retrospective analysis in East Delhi,” Epidemiol. Health, vol. 38, p. e2016052, Nov. 2016, doi: 10.4178/epih.e2016052.
A. Anwar and J. Ariati, “Model Prediksi Kejadian Demam Berdarah Dengue (DBD) Berdasarkan Faktor Iklim di Kota Bogor, Jawa Barat,” Indones. Bull. Health Res., vol. 42, no. 4, p. 20092, 2014, doi: 10.22435/bpk.v42i4.
D. Perwitasari and Y. Ariati, “Model Prediksi Demam Berdarah Dengue Dengan Kondisi Iklim Di Kota Yogyakarta,” Indones. J. Health Ecol., vol. 14, no. 2, pp. 124–135, 2015.
“Peringatan Dini DBD – DKI Jakarta | Informasi Iklim BMKG.” Accessed: Oct. 18, 2025. [Online]. Available: https://iklim.bmkg.go.id/id/dbdklim/
“DBDKlim Bali – Stasiun Klimatologi Bali.” Accessed: Oct. 18, 2025. [Online]. Available: https://staklim-bali.bmkg.go.id/?page_id=2708
N. A. Lestari, R. Tyasnurita, R. A. Vinarti, and W. Anggraeni, “Long Short-Term Memory forecasting model for dengue fever cases in Malang regency, Indonesia,” Procedia Comput. Sci., vol. 197, pp. 180–188, Jan. 2022, doi: 10.1016/j.procs.2021.12.131.
A. Sebastianelli et al., “A reproducible ensemble machine learning approach to forecast dengue outbreaks,” Sci. Rep., vol. 14, no. 1, p. 3807, Feb. 2024, doi: 10.1038/s41598-024-52796-9.
Islam Jahirul, Frentiu Francesca D., Devine Gregor J., Bambrick Hilary, and Hu Wenbiao, “A State-of-the-Science Review of Long-Term Predictions of Climate Change Impacts on Dengue Transmission Risk,” Environ. Health Perspect., vol. 133, no. 5, p. 056002, doi: 10.1289/EHP14463.
M. A. Morid, O. R. L. Sheng, and J. Dunbar, “Time Series Prediction Using Deep Learning Methods in Healthcare,” ACM Trans Manage Inf Syst, vol. 14, no. 1, p. 2:1-2:29, Jan. 2023, doi: 10.1145/3531326.
X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W. Wong, and W. Woo, “Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting,” Sept. 19, 2015, arXiv: arXiv:1506.04214. doi: 10.48550/arXiv.1506.04214.
X. Chen and P. Moraga, “Dengue forecasting and outbreak detection in Brazil using LSTM: integrating human mobility and climate factors,” June 19, 2025, medRxiv. doi: 10.1101/2025.03.02.25323168.
S. R. A. Sofian, Sudarti, and R. D. Handayani, “Analisis Korelasi Curah Hujan dan Produktivitas Tanaman Hasil Pertanian Kabupaten Jember,” J. Pendidik. MIPA, vol. 12, no. 2, pp. 287–293, June 2022, doi: 10.37630/jpm.v12i2.612.
M. A. Majeed, H. Z. M. Shafri, Z. Zulkafli, and A. Wayayok, “A Deep Learning Approach for Dengue Fever Prediction in Malaysia Using LSTM with Spatial Attention,” Int. J. Environ. Res. Public. Health, vol. 20, no. 5, p. 4130, Jan. 2023, doi: 10.3390/ijerph20054130.
DOI: http://dx.doi.org/10.30829/zero.v9i2.26192
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Publisher : Department of Mathematics Faculty of Science and Technology Universitas Islam Negeri Sumatera Utara Medan | |
✉️ Email: zero_journal@uinsu.ac.id 📱 WhatsApp:085270009767 (Admin Official) | |
 |  |  |  |  |