Cupressaceae pollen is a significant allergen responsible for the onset of allergic diseases. Predicting changes in its concentration under global warming can provide essential insights for the scientific prevention and treatment of hay fever. This study focuses on daily Cupressaceae pollen concentration data from northern Beijing over four years (2018–2021) and synthesizes multi-source predictors comprising thermal indices (GDD), extreme temperature events, and vegetation phenology indicators, to develop a Random Forest model for predicting pollen concentration trends under different warming scenarios. The key findings are as follows: (1) The Random Forest model effectively predicts Cupressaceae pollen concentration, achieving an R2 of 0.79 and a root mean square error (RMSE) of 0.73, indicating a strong fit between observed and predicted values. (2) The pollen concentration of Cupressaceae plants is strongly influenced by long-term temperature effects, particularly growing degree days (GDD), and extreme temperature events. Among the various environmental factors, the most influential variables for predicting daily pollen concentration are thermal accumulation metrics (GDD>10°C.d) across 40-80 day windows (GDD_40_10, GDD_60_10, GDD_80_10), as well as the daily maximum temperature (Tmax). (3) Temperature rise scenarios of 0.5°C, 1.0°C, 1.5°C, and 2.6°C reveal a nonlinear response in Cupressaceae pollen concentration. Specifically, Cupressaceae concentration initially increases, then decreases, and increases again as the temperature rises. This nonlinear trend is likely influenced by the interplay between plant physiological mechanisms, adaptive responses to environmental changes, and temperature-induced shifts in flowering phenology. This study explores the impact of various environmental variables on Cupressaceae pollen concentration in northern Beijing using a Random Forest model to predict changes under different warming scenarios. It highlights the significant role of growing degree days (GDD) and identifies a nonlinear trend in pollen concentrations with future warming. These findings provide valuable insights for the prevention, diagnosis, and treatment of pollen-related allergies and offer crucial guidance for optimizing urban green space planning.