Construction of an ecological security pattern is crucial to achieve ecological security and socioeconomic sustainability. Climate change and human activities jointly impact ecological security, but the construction of existing ecological security frameworks primarily considers human activities while rarely accounting for the effects of climate change. The Dawen River basin ecological security pattern was developed with the objectives of improving ecological function, safeguarding ecological security, and promoting sustainable development. Habitat quality was selected as an ecosystem service function in this study, and the InVEST model was employed for assessment. Based on the framework of “ecological sources identification-ecological resistance surface establishment-ecological security pattern”, a new framework was developed by considering the effect of climate change on the establishment of ecological resistance. The results showed that: (1) a total of 34 ecological source areas were primarily distributed in Mount Tai, Mount Culai, Mount Xinfu and Dongping Lake regions; (2) a total of 42 ecological pinch points, 73 ecological barriers, and 76 ecological corridors were primarily distributed in the eastern part of the basin; and (3) an ecological security pattern characterized by “Two Belts and Four Zones” was constructed for the Dawen River basin, and corresponding protection strategies were proposed. The findings elucidate the impacts of climate change on ecological security pattern, offering valuable scientific insights for ESP development at basin scale.

To further improve prediction accuracy, a VMD-VPPSO-LSTM model is proposed in this study, which combines Variational Mode Decomposition (VMD) for signal decomposition, Velocity-Pause Particle Swarm Optimization (VPPSO) for parameter optimization, and Long Short-Term Memory (LSTM) for runoff prediction. The model was evaluated at Huangtaiqiao station in the Xiaoqing River Basin, Dawenkou station in the Dawen River Basin, and Tangnaihai station in the source region of the Yellow River Basin. The proposed model achieved the best overall performance among all comparison models, with Nash–Sutcliffe Efficiency (NSE) values of 0.970, 0.962, and 0.994 and Root Mean Square Error (RMSE) values of 1.357, 0.989, and 46.804 at the three stations, respectively. Compared with VMD-LSTM, VPPSO further reduced the RMSE at all stations and maintained training-test NSE gaps below 0.006, indicating strong generalization performance. The model also achieved the lowest Peak Percent Standard Deviation (PPSD) values for high-flow events, reaching 9.03%, 14.42%, and 3.88% at the three stations, respectively. These results demonstrate that VMD-VPPSO-LSTM is a reliable and effective model for daily runoff prediction.