With the rapid acceleration of global urbanization, the impact of land use/cover change (LUCC) on the environment and ecosystems has become increasingly prominent, particularly in terms of air quality, which has emerged as a significant issue demanding attention. Focusing on the coastal city of Lianyungang, the spatiotemporal dynamics of land use/cover changes were explored by utilizing land use dynamic degree and land use transfer matrix methods. By integrating a comprehensive historical dataset, multiple linear regression analysis was used to analyze the driving mechanism of land use conversion and to explore the effect of LUCC on the variations in PM₁₀ levels. The results showed an overall decreasing trend in PM₁₀ levels over the 24-year period from 2000 to 2023, with distinct seasonal fluctuations, showing higher concentrations in winter and lower concentrations in summer. The impact of land use on PM₁₀ variations can be categorized into three stages: initial (2000–2006), transitional (2007–2013), and deepening development (2014–2022). Notably, during the third stage, with the involvement of policy interventions and industrial upgrading, a strong negative correlation of −0.97 was identified between urban land expansion and the decrease in PM₁₀ levels. The correlation between LUCC and PM₁₀ levels was insignificant over shorter periods, but the analysis of data from 2000 to 2022 revealed a significant positive correlation of 0.77, emphasizing the importance of adopting a long-term perspective to accurately assess the impact of LUCC on air quality. This research provides valuable insights into the implications of LUCC on air quality during urbanization and establishes a scientific foundation for developing air pollution management strategies in Lianyungang and similar regions.

Storm surge current-time estimations are strongly influenced by recent water-level conditions, while the temporal dependence among samples from the same typhoon event can complicate the assessment of model generalization to unseen events. This study evaluated storm surge estimation at the Lianyungang tide gauge using 2168 samples from 28 typhoon events during 2002–2024. A 41-feature extreme gradient boosting (XGBoost) model integrating historical surge and physics-motivated information was evaluated using fully nested event-grouped cross-validation, with complete outer-test typhoon events excluded from hyperparameter optimization, early stopping, and model fitting. The 41-feature XGBoost model achieved a mean absolute error (MAE) of 0.083 m, a root mean square error (RMSE) of 0.128 m, and a coefficient of determination (R²) of 0.794. On the common valid sample subset, its RMSE was 9.15% lower than that of Persistence, and it achieved a lower event-level RMSE in 18 of the 28 independently held-out typhoon events. Controlled information-source experiments showed that historical surge information accounted for most of the aggregate predictive skill, whereas adding core storm-state variables and the complete set of physics-motivated descriptors produced only limited changes in overall performance. The relative improvement over Persistence was larger for samples in which the shortest available historical surge lag was 3–6 h than for those with a 1 h lag, but this advantage did not extend consistently to the highest-surge conditions, where systematic underestimation remained evident. These results demonstrate the importance of event-independent validation for assessing machine-learning storm surge estimation and show that the model skill depends strongly on both information availability and the surge magnitude. The framework should be interpreted as a retrospective, single-station current-time estimation approach rather than an operational forecasting or extreme-surge warning system.