In the context of global climate change, the increasing frequency of extreme heat events has exacerbated urban thermal issues, affecting the quality of life and posing a serious challenge to the sustainable development of cities. Urban lakes are regarded as effective nature-based solutions for alleviating outdoor thermal environments. In this study, the cooling intensity and extent of 82 urban lakes with their surrounding cooling landscapes across China were quantified based on land surface temperature (LST). eXtreme Gradient Boosting (XGBoost) models were constructed to analyze the indicators of cooling intensity and extent. Furthermore, SHapley Additive exPlanations (SHAP) and partial dependency plots (PDP) were used to interpret the models. The results, measured based on LST, showed that the cooling intensity ranged from 2.87 to 14.10 °C, and the cooling extent spanned from 150 to 1085 m. In terms of overall contribution of all the indicators, lake indices had the most significant impact on cooling intensity, accounting for 33.78 % of the total contribution. Landscape indicators had the most significant impact on the cooling extent, accounting for 67.78 % of the total contribution. Regarding the influence of specific factors, Lake_area played a key role in enhancing cooling intensity, increasing it by up to 0.8 °C when the lake area exceeded 5 km