Revealing Dengue Dynamics: A Novel Bin-Wise Gaussian Process Model for Probabilistic Forecasting

Background : Aedes aegypti 's adaptability to urban environments and interaction with socio-economic and climatic factors drive dengue transmission, posing persistent public health challenges in tropical and subtropical regions. This study develops a generalizable Gaussian Process (GP) model to predict dengue incidence, addressing limitations in traditional models by integrating socio-economic and weather determinants, improving forecasting accuracy and intervention strategies across diverse urban settings. Method : This study analyzed dengue transmission dynamics in Barranquilla, Colombia, using a dataset from 2018–2023 across 20 metropolitan areas. Monthly dengue cases were modeled against socio-environmental factors, including socio-economic strata, temperature, and rainfall. The dataset was normalized to adjust for population variations, allowing location-independent analysis. Rainfall was modeled using an exponential distribution, introducing a novel approach. Variables were discretized into 32 bins based on socio-economic infrastructure, temperature, and rainfall thresholds. A parameter-dependent function framework predicted month-to-month dengue progression, emphasizing environmental and socio-economic influences on disease transmission patterns. Results : This study leveraged GP regression to predict month-to-month dengue case variations using socio-economic, temperature, and rainfall data. The models classified transmission dynamics into six categories: extinction, monotonic growth, oscillations, transient pulses, low-level persistence, and high uncertainty. High-risk scenarios were linked to elevated temperatures, rainfall, and lower socio-economic strata, while conditions limiting mosquito development predicted rapid transmission declines. Bin-specific analysis revealed ecological feedback driving oscillatory patterns and transient outbreaks. These robust predictions informed targeted mitigation strategies, despite uncertainties in certain parameter combinations, providing nuanced insights into dengue dynamics. Conclusion : This study breaks new ground by integrating socio-economic, environmental, and epidemiological factors in a probabilistic, adaptable model. The findings challenge location-dependent approaches and offer a scalable framework that could revolutionize vector-borne disease forecasting and public health decision-making.