Integrasi Faktor Iklim dan Lingkungan untuk Prediksi Risiko DBD di Kota Palembang Menggunakan Pendekatan GeoAI Berbasis LSTM
DOI:
https://doi.org/10.30865/jurikom.v13i2.9407Keywords:
Dengue Hemorrhagic Fever, GeoAI, LSTM, Risk Index, Spatio-temporal Prediction, PalembangAbstract
Dengue Hemorrhagic Fever (DHF) remains a significant vector-borne disease threat to public health in Palembang. This study aims to analyze the environmental and demographic factors influencing DHF risk and predict risk trends using a GeoAI approach. Four primary variables land surface temperature, rainfall, population density, and residential area were integrated to develop a DHF risk index for the 2020 - 2025 period. The analysis reveals that the risk index consistently falls within the high category across all regions, showing a gradual upward trend from 0.517 in 2020 to 0.527 in 2025. To project future risks, a Long Short-Term Memory (LSTM) model was employed. Model evaluation demonstrated robust performance with a Mean Squared Error (MSE) of 0.0028, a Root Mean Squared Error (RMSE) of 0.052, and a Mean Absolute Error (MAE) of 0.031, indicating low error rates and stable predictive capability. Prediction results suggest that DHF risk is expected to continue increasing through 2029, particularly in sub-districts with high population density and expanding residential areas. This research provides a scientific contribution by developing a predictive model that is more adaptive and precise than conventional statistical approaches. Through the integration of artificial intelligence and spatial data (GeoAI), this model effectively captures non-linear patterns and spatio temporal dynamics, serving as a sustainable early warning system.
References
[1] X. Chen and P. Moraga, “Forecasting dengue across Brazil with LSTM neural networks and SHAP-driven lagged climate and spatial effects,” BMC Public Health, vol. 25, no. 1, p. 973, 2025.
[2] C. Xu, J. Xu, and L. Wang, “Long-term effects of climate factors on dengue fever over a 40-year period,” BMC Public Health, vol. 24, no. 1, p. 1451, 2024.
[3] S. Bailly et al., “Spatiotemporal modeling of Aedes aegypti risk: enhancing dengue virus control through meteorological and remote sensing data in French Guiana,” Pathogens, vol. 13, no. 9, p. 738, 2024.
[4] V.-H. Nguyen et al., “Deep learning models for forecasting dengue fever based on climate data in Vietnam,” PLoS Negl. Trop. Dis., vol. 16, no. 6, p. e0010509, 2022.
[5] X. Chen and P. Moraga, “Assessing dengue forecasting methods: a comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil,” Trop. Med. Health, vol. 53, no. 1, p. 52, 2025.
[6] I. G. N. M. Jaya, Y. Andriyana, B. Tantular, S. S. Pangastuti, and F. Kristiani, “Spatiotemporal Dengue Forecasting for Sustainable Public Health in Bandung, Indonesia: A Comparative Study of Classical, Machine Learning, and Bayesian Models,” Sustainability, vol. 17, no. 15, p. 6777, 2025.
[7] Z. Li, “Forecasting weekly dengue cases by integrating google earth engine-based risk predictor generation and google colab-based deep learning modeling in fortaleza and the federal district, Brazil,” Int. J. Environ. Res. Public Health, vol. 19, no. 20, p. 13555, 2022.
[8] J. Xu et al., “Forecast of dengue cases in 20 Chinese cities based on the deep learning method,” Int. J. Environ. Res. Public Health, vol. 17, no. 2, p. 453, 2020.
[9] 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, 2023.
[10] E. Mussumeci and F. C. Coelho, “Large-scale multivariate forecasting models for Dengue-LSTM versus random forest regression,” Spat. Spatiotemporal. Epidemiol., vol. 35, p. 100372, 2020.
[11] Z. Li and J. Dong, “Big geospatial data and data-driven methods for urban dengue risk forecasting: a review,” Remote Sens., vol. 14, no. 19, p. 5052, 2022.
[12] Z. Li, H. Gurgel, L. Xu, L. Yang, and J. Dong, “Improving dengue forecasts by using geospatial big data analysis in google earth engine and the historical dengue information-aided long short term memory modeling,” Biology (Basel)., vol. 11, no. 2, p. 169, 2022.
[13] L. R. C. Farias, T. P. Silva, and P. H. M. Araújo, “Multitask LSTM for Arboviral Outbreak Prediction Using Public Health Data,” arXiv Prepr. arXiv2505.04566, 2025.
[14] O. Sakulkeo, C. Wattanapiromsakul, T. Pitakbut, and S. Dej-Adisai, “Alpha-Glucosidase Inhibition and Molecular Docking of Isolated Compounds from Traditional Thai Medicinal Plant, Neuropeltis racemosa Wall.,” Molecules, vol. 27, no. 3, p. 639, 2022.
[15] S. Buján, J. Guerra-Hernández, E. González-Ferreiro, and D. Miranda, “Forest road detection using LiDAR data and hybrid classification,” Remote Sens., vol. 13, no. 3, p. 393, 2021.
[16] A. Dimitrova, S. McElroy, M. Levy, A. Gershunov, and T. Benmarhnia, “Precipitation variability and risk of infectious disease in children under 5 years for 32 countries: a global analysis using Demographic and Health Survey data,” Lancet Planet. Heal., vol. 6, no. 2, pp. e147--e155, 2022.
[17] L. D. Alves, R. M. Lana, and F. C. Coelho, “A framework for weather-driven dengue virus transmission dynamics in different Brazilian regions,” Int. J. Environ. Res. Public Health, vol. 18, no. 18, p. 9493, 2021.
[18] S. Patil and S. Pandya, “Forecasting dengue hotspots associated with variation in meteorological parameters using regression and time series models,” Front. public Heal., vol. 9, p. 798034, 2021.
[19] S. Bhatia, D. Bansal, S. Patil, S. Pandya, Q. M. Ilyas, and S. Imran, “A retrospective study of climate change affecting dengue: evidences, challenges and future directions,” Front. public Heal., vol. 10, p. 884645, 2022.
[20] Y. T. Damtew et al., “Effects of high temperatures and heatwaves on dengue fever: a systematic review and meta-analysis,” EBioMedicine, vol. 91, 2023.
[21] M. J. F. Putra and K. S. Lestari, “Climatic Factors Related to the Incidence Rate of Dengue Haemorrhagic Fever in Malang District Year 2011-2020,” Media Gizi Kesmas, vol. 12, no. 1, pp. 219–227, 2023.
