Weimeng Zhang

Fine-scale evidence remains scarce regarding where ecological quality has improved or deteriorated in the Yangtze River Delta (YRD) and which landscape conditions are associated with these trajectories. We developed a 1 km² hexagon-based diagnostic framework integrating the Remote Sensing Ecological Index (RSEI), Sen–Mann–Kendall trend analysis, Local Moran’s I clustering, recurrence-based ecological stress typology, and XGBoost–SHAP interpretation for 2000–2025. Annual RSEI was standardized by year to capture relative trajectories of ecological quality rather than absolute change under a fixed loading system. The regional mean RSEI fluctuated markedly and declined only slightly, from 0.639 in 2000 to 0.632 in 2025, suggesting that long-term ecological change was nonlinear. At the hexagon scale, 64.77% of valid units showed positive RSEI trends, with significant improvement covering 15.08% of units and significant degradation covering 5.47%. Local Moran’s I identified distinct High–High and Low–Low clusters; persistent low-quality clusters and stable high-quality areas accounted for 10.0% and 7.8% of valid hexagons, respectively. XGBoost–SHAP results indicated statistical associations between RSEI trends and soil moisture, elevation, impervious surface change, and nighttime light change, rather than direct causal effects. This framework provides a spatially explicit basis for identifying priority monitoring areas, ecological stress zones, and differentiated land management units across rapidly urbanizing megaregions.

Cultivated land fragmentation (CLF) has evolved from a physical landscape phenomenon into a systemic constraint on agricultural sustainability, especially in rapidly urbanizing regions such as the Yangtze River Delta (YRD). Existing studies are limited by static “snapshot” comparisons that obscure continuous trajectories and by linear models that fail to capture nonlinear interactions and threshold effects. This study integrates the Space–Time Cube (STC) model with an interpretable machine learning framework (Extreme Gradient Boosting–Shapley Additive Explanations, XGBoost–SHAP) to explore the spatiotemporal dynamics and driving mechanisms of CLF in the YRD (1990–2020) at a 1 km² resolution. The STC identifies a distinct north–south gradient, with persistent hotspots in low-lying plains and intensifying fragmentation at peri-urban interfaces. SHAP interpretation suggests a “Base–Stabilizer–Amplifier” structure in the modeled relationships: hydrological accessibility and soil fertility form the dominant background linked to higher CLF, whereas topography correlates with lower CLF, and socioeconomic variables exhibit nonlinear, threshold-like increases in fragmentation beyond higher development levels. Overall, CLF reflects coupled natural–anthropogenic interactions with pronounced nonlinear responses. This mechanism-oriented framework provides actionable guidance for adaptive farmland governance. It also offers a transferable methodology for analyzing land system changes in other deltaic agricultural regions worldwide.