Predicting the Effects of Climate Change on Culex Tritaeniorhynchus Density: A Random Forest Modeling Analysis

Culex tritaeniorhynchus is a primary vector of Japanese encephalitis and other diseases, with population dynamics highly sensitive to climatic conditions. Predicting its distribution relies on understanding the correlation between mosquito density and meteorological factors. In this study, the Random Forest model, an innovative machine learning approach for classification and regression, was used to simulate monthly variations in mosquito density around key future time points (2030 and 2090). Simulations integrated four CMIP6 scenarios (SSP126, SSP245, SSP370, and SSP585). Results indicated an overall increase in peak mosquito density over time, accompanied by a delayed seasonal peak. Significant density variations were observed across scenarios, with the highest radiative forcing scenario (SSP585) exhibiting the most pronounced increase: by August 2090, mean density reached 0.51 0.01 mosquitoes/(lamphour), and the maximum monthly density rose to 1.09 mosquitoes/(lamphour). Under the SSP370 scenario, the mean density in August 2090 was also elevated, at 0.52 0.01 mosquitoes/(lamphour). These findings suggest that climate change will substantially increase the density of Culex tritaeniorhynchus and shift its seasonal peak, potentially exacerbating public health and ecological risks. This study represents a methodological advance from traditional vector distribution forecasting to quantitative density prediction, providing a critical foundation for precise early warning and control of mosquito-borne diseases in high-risk regions. It offers practical implications for safeguarding public health.