Urban green spaces (UGS) are critical regulators of carbon sequestration in industrial cities; however, the configuration mechanisms underlying their carbon dynamics remain insufficiently understood. This study investigates how landscape configuration influences carbon sequestration capacity in Lanzhou and Baotou using multi-temporal datasets from 2000, 2011, and 2022. Net primary productivity (NPP) derived from the CASA model was employed to represent carbon sequestration capacity. An integrated XGBoost-SHAP framework was applied to identify dominant configuration metrics, nonlinear responses, and structural thresholds. The XGBoost model showed stable predictive performance across the three periods, with test-set R² values ranging from 0.470 to 0.510 in Lanzhou and from 0.325 to 0.379 in Baotou. The results reveal systematic and persistent differences in configuration-driven controls between the two cities. In Lanzhou, aggregation-related metrics, particularly COHESION, consistently exert the strongest influence across all three periods, indicating that spatial cohesion and connectivity function as primary stabilizing mechanisms in a mountainous, valley-constrained urban system. Carbon sequestration performance increases once sufficient structural integration is achieved, with aggregation thresholds remaining relatively stable, for example AI values of approximately 0.31–0.34 across 2000–2022, reflecting the importance of maintaining ecological continuity under semi-arid climatic stress. In contrast, Baotou is more strongly regulated by fragmentation-related metrics, especially edge density (ED) and division index (DIVISION), suggesting that its relatively open terrain and industrial spatial structure render carbon sequestration more sensitive to patch separation and edge proliferation. Here, fragmentation acts as a dominant structural constraint, limiting vegetation productivity once spatial disintegration intensifies; for example, ED thresholds shifted from approximately −0.23 in 2000 to −0.56 in 2022. Landscape–carbon relationships exhibit pronounced nonlinear and threshold-dependent behavior in both cities. Rather than responding gradually to structural modification, NPP shifts across identifiable transition points that remain broadly stable over time; for instance, Lanzhou’s AI threshold remains within 0.31–0.34, whereas Baotou’s ED threshold changes from −0.23 to −0.56 across 2000–2022, indicating that these thresholds represent intrinsic structural characteristics of the respective urban ecological systems. However, the magnitude and configuration logic of these thresholds differ between Lanzhou and Baotou, confirming the existence of city-specific nonlinear regimes. These findings demonstrate that urban carbon sequestration operates through context-dependent configuration pathways shaped by terrain, climatic constraints, and long-term spatial organization. The study advances understanding of how structural heterogeneity governs carbon dynamics in arid and semi-arid industrial cities and provides a quantitative basis for configuration-sensitive land planning.

Megacities in developing countries are still undergoing rapid urbanization, with different cities exhibiting ecosystem services (ESs) heterogeneity. Evaluating ESs among various cities and analyzing the influencing factors from a resilience perspective can effectively enhance the ability of cities to deal with and react quickly to the risks of uncertainty. This approach is also crucial for optimizing ecological security patterns. This study focuses on Xi’an and Jinan, two important megacities along the Yellow River in China. First, we quantified four ecosystem services for both cities: carbon storage (CS), habitat quality (HQ), food production (FP), and soil conservation (SC). Second, we analyzed the synergies and trade-offs between these ESs using bivariate local spatial autocorrelation and Spearman’s rank correlation coefficient. Finally, we conducted a driver analysis using the Geographic Detector. Results: (1) The spatial and temporal distribution of the four ESs in Xi’an and Jinan is quite different, but both cities show lower ES levels in the urban core area. (2) ESs in Xi’an showed a strong synergistic effect. Among them, CS-HQ had the strongest synergy of 0.93. In terms of space, the north is dominated by low–low clustering, while the south is dominated by high–high clustering. The FP-SC in Jinan showed a trade-off effect of −0.35 in 2000, which gradually weakened over time and was mainly distributed in the northern area of the city where cropland and construction were concentrated. (3) Edge density, patch density, and NDVI have the greatest influence on CS in Xi’an and Jinan. DEM, slope, and patch density have the greatest influence on Xi’an HQ. Temperature, edge density, and patch density have the greatest impact on Jinan HQ. NDVI and temperature have the greatest influence on FP in the two cities. DEM, slope, and edge density have the greatest influence on SC. Landscape fragmentation has a great impact on CS, HQ, and SC in Xi’an and Jinan. Due to insufficient research data, this study focused on only four ESs in Xi’an and Jinan, the megacities in the middle and lower reaches of the Yellow River. However, the research results can provide a new perspective for solving the problem of regional sustainable development and new directions and ideas for follow-up research in this field.