<![CDATA[Dengue fever remains a critical public-health threat in Indonesia’s densely populated urban centers, where climatic fluctuations and human mobility accelerate transmission dynamics. This study aims to develop a predictive model for dengue outbreaks using machine-learning techniques that integrate multi-source climate indicators (temperature, rainfall, humidity) and population-mobility data. A quantitative research design employing supervised learning algorithms including Random Forest, Gradient Boosting, and Long Short-Term Memory (LSTM) networks—was applied to historical datasets from 2015–2023 across six major Indonesian cities. Model performance was evaluated using accuracy, precision, recall, and AUC metrics. Results indicate that the LSTM model achieved the highest predictive accuracy (92.3%) and superior temporal sensitivity to climatic shifts and mobility surges compared with traditional regression models. These findings demonstrate that machine-learning-based early-warning systems can identify outbreak hotspots up to four weeks in advance, providing actionable insights for urban health authorities. The study concludes that integrating climate and mobility analytics enhances the effectiveness of public-health surveillance and supports proactive dengue-control interventions in rapidly urbanizing environments.]]>
Copyrights © 2026
