Based on a comprehensive evaluation index system for regional economic resilience and port logistics development, this study employs multiple methodologies including coupling coordination degree model, kernel density estimation, gravity center model, spatial autocorrelation model, and geographic detector model to explore the spatial–temporal evolution patterns and driving factors of coupling coordination between regional economic resilience and port logistics in the Guangxi Beibu Gulf Economic Zone from 2012 to 2022. The results indicate that: (1) The coupling coordination degree between the two systems showed an upward trend during the study period, although with stage-specific bipolar differentiation that weakened in the later stages. (2) The spatial distribution pattern of coupling coordination evolved from a “single-core” driven by Nanning to a “dual-core” led by Nanning and Yulin, forming a distinct concentric layer structure; the gravity center of coupling coordination exhibited a “southeast–northwest” dynamic migration pattern. (3) Spatial autocorrelation analysis revealed significant positive spatial dependence of coupling coordination within the study area, with spatial agglomeration values showing a “core–transition–depression” differentiation pattern. (4) Information technology level emerged as the dominant driving factor, forming a “technology–finance–infrastructure” ternary collaborative driving model with financial development level and logistics infrastructure level, which became the main force promoting the coordinated development of the coupled systems.

Against the background of the global green transition, digitalization has become an important driver of energy-efficiency improvement and carbon mitigation, making its overall environmental effects worthy of further investigation. This study constructs a pollution and carbon mitigation pressure (PCMP) index covering emission load, governance support, and ecological carrying capacity to examine the effect of the digital economy on PCMP, its transmission mechanism, boundary conditions, and regional heterogeneity. Using panel data for 30 Chinese provinces from 2013 to 2024, we apply a two-way fixed-effects model, mechanism analysis, a moderation model, instrumental-variable estimation, and a spatial Durbin model. The results show that digital-economy development significantly reduces PCMP, and this conclusion remains stable across multiple robustness checks. The digital economy alleviates PCMP by promoting industrial structure upgrading, while urbanization significantly strengthens this effect. The effect is more pronounced in Northern China, with a statistically significant north–south difference. Spatial analysis further shows that higher digital-economy development in neighboring regions is significantly associated with lower local PCMP. These findings extend research on the environmental effects of the digital economy by showing how industrial upgrading, urban conditions, and cross-regional linkages shape its contribution to pollution control, low-carbon transition, and regional sustainable development, with implications for the broader goals of the 2030 Agenda. Given the limitations of provincial data and the identification strategy, future research could use city-level data to further examine the underlying mechanisms and causal effects.

High-resolution spatiotemporal sea ice concentration (SIC) estimates are essential for Arctic navigation and ice analysis, but existing observational products are often too coarse, and physics-based models are computationally expensive. This study proposes a data-driven framework that couples Light Gradient Boosting Machine (LightGBM) temporal prediction with Kriging-based spatial interpolation to reconstruct SIC fields over the Northern Sea Route sector. LightGBM is trained on a grid-based SIC time series with engineered features representing persistence, seasonality, and short-term variability, enabling multi-horizon forecasting across large spatial grids. The predicted SIC fields are then refined using Ordinary Kriging (OK) and Co-Kriging (CK) with Gaussian and spherical semi-variogram models. Prediction performance is evaluated using root mean square error, and interpolation accuracy is assessed through cross-validation. Results show that, for high-latitude regions and resolutions finer than 0.25° × 0.25°, OK with a spherical semi-variogram achieves lower interpolation errors than CK and Gaussian-based alternatives. By sequentially coupling temporal learning and spatial refinement, the proposed framework improves temporal continuity, spatial structure, and error quantification, providing high-resolution SIC information suitable for large-scale Arctic ice analysis and navigation support.