Respiratory infectious diseases like influenza pose a significant global public health challenge, causing substantial morbidity, mortality, and economic costs. Environmental factors—such as temperature, humidity, and air quality—critically influence influenza transmission by affecting viral survival, host susceptibility, and human behavior. However, most existing influenza models rely solely on disease incidence data for forecasts and early warning signals. This project integrates environmental conditions into a hybrid forecasting and early warning system for influenza outbreaks, enhancing public health preparedness and response to emerging and re-emerging infectious diseases in a changing environment. The interdisciplinary nature of this work—bridging mathematics, statistics, epidemiology, environmental science, and artificial intelligence (AI)—fosters collaboration across fields, accelerating scientific progress and knowledge exchange. Additionally, the project inspires the next generation of mathematical scientists, supports workforce development in quantitative public health, and expands access to high-quality STEM education. This project develops a cutting-edge hybrid framework that combines differential equations, machine learning, and statistical techniques to forecast influenza outbreaks and detect early warning signals driven by environmental conditions. The principal investigator and her team refine inverse methods to estimate time-varying transmission rates, eva