Reliable long-term runoff prediction for Wudongde and Three Gorges reservoirs, two major reservoirs in the upper Yangtze River basin, is crucial for optimal operation of cascade reservoirs and hydropower generation planning. This study develops a data-driven model that integrates large-scale climate factors with a Gated Recurrent Unit (GRU) neural network to enhance runoff forecasting at lead times of 7–18 months. Key climate predictors were systematically selected using correlation analysis and stepwise regression before being fed into the GRU model. Evaluation results demonstrate that the proposed model can skillfully predict the variability and magnitude of reservoir inflow. For Wudongde Reservoir, the model achieved a mean correlation coefficient (CC) of 0.71 and Kling–Gupta Efficiency (KGE) of 0.57 during the training period, and values of 0.69 and 0.53 respectively during the testing period. For Three Gorges Reservoir, the CC was 0.67 (training) and 0.66 (testing), and the KGE was 0.52 and 0.49 respectively. The model exhibited robust forecasting capabilities across a range of lead times but showed distinct seasonal variations, with superior performance in summer and winter compared to transitional months (April and October). This framework provides a valuable tool for long-term runoff forecasting by effectively linking large-scale climate signals to local hydrological responses.

Global warming and rapid urbanization have increased population exposure to heatwaves, with compound day- and night-time heatwaves (CDNH) posing greater health risks than individual heatwave events. Although air conditioning (AC) adaptation effectively mitigates heat-related impacts, its role in reducing CDNH exposure under climate change remains unknown. Using meteorological and socioeconomic data, this study quantified population exposure to CDNHs and the impacts that could be avoided through AC adaptation across China and its regional variations. Results show that CDNH exposure risks were particularly high in the middle–lower Yangtze–Huaihe Basin and south China, with an increasing trend observed over the period of 2001–2022. AC adaptation has reduced the exposure risk and its upward trend by 5.85% and 37.87%, respectively, with higher mitigating effects in urban areas. By breaking down the total exposure changes into climatic, demographic, and AC-driven changes, this study reveals that increased AC contributes 10.16% to exposure reduction, less than the effect of climate warming (59.80%) on the exposure increases. These findings demonstrate that expanding AC adaptation alone is insufficient to offset climate-driven increases in exposure, highlighting the urgent need for more effective adaptation measures to address climate change and thereby alleviate its adverse impacts on human beings.