Debris flows in alpine canyon regions pose serious threats to infrastructure and human settlements due to their abrupt onset and high mobility, yet the interactions among topographic complexity, sediment supply, and mitigation performance remain insufficiently understood. This study integrates field investigations, hydro-meteorological analysis, and dynamic numerical simulations to investigate the “8·03” event in Ridi Gully, eastern Qinghai–Tibet Plateau. The results indicate that the initiation and subsequent evolution of the debris flow were jointly controlled by intense localized rainfall, abundant unconsolidated sediment, and steep channel gradients, with local blockage-breaching processes further amplifying flow velocity and impact energy. Mitigation simulations further show that the single slit-dam configuration reduced the debris flow deposition volume and area by 14.29% and 16.23%, respectively, whereas the combined slit-dam/rigid-check-dam configuration achieved reductions of 65.54% and 44.97% relative to the no-protection scenario. These results highlight the potential contribution of temporary blockage-breaching to downstream hazard amplification and demonstrate the different regulating effects of the tested mitigation configurations on flow intensity and sediment deposition. The findings provide case-specific insights into debris flow hazard evolution and staged structural mitigation in alpine mountainous environments.

Accurate and timely short-term forecasting of gridded PM_2.5 concentrations is essential for air-quality management and public health protection, especially for the growing elderly population who are particularly vulnerable to air pollution. Advances in multi-source environmental data and deep learning have substantially improved the spatiotemporal prediction of PM_2.5 concentrations. However, existing studies have mainly focused on developing increasingly sophisticated model architectures and optimization strategies while insufficiently considering the temporal nonstationarity of PM_2.5 pollution and the recurrent characteristics associated with similar seasonal environmental regimes. Changes in natural environmental conditions and anthropogenic emissions can continuously alter the relationships governing PM_2.5 concentrations, challenging the stability of continuous short-term forecasting; meanwhile, historically recurring seasonal pollution characteristics provide potentially valuable prior information for model adaptation. To address this problem, we propose a Seasonal Prior-guided Elastic Weight Consolidation (Seasonal EWC) framework for dynamic forecasting of nonstationary gridded PM_2.5 concentrations in China. The framework derives season-specific parameter anchors and Fisher-based parameter importance from historical seasonal conditions and uses this prior knowledge to guide parameter updates during continuous short-term forecasting. Experiments with four representative spatiotemporal forecasting models showed that Seasonal EWC produced architecture-dependent changes in forecasting performance, reducing the annual mean MAE and RMSE by 30.3% and 31.7% for U-Net and by 10.9% and 7.6% for Earthformer, with only small improvements for IAM4VP and mixed changes for ConvLSTM. Parameter analysis revealed that Seasonal EWC reduced parameter-update magnitudes by approximately 27–32% and substantially limited long-term parameter deviation, indicating more stable adaptation during continuous forecasting. These findings demonstrate that seasonal prior knowledge can effectively guide dynamic model adaptation under evolving PM_2.5 conditions, providing a promising approach for continuous short-term air-quality forecasting.