Exploration of the Spatio-Temporal Evolution and Influencing Factors of Fragmentation of Cultivated Land in China

From the perspective of food security, cultivated land fragmentation is a major constraint to agricultural modernization. Based on 1-km resolution land use data from 1995 to 2020 in China, this study builds a comprehensive evaluation system and applies a Geographically Weighted Random Forest (GW-RF) model with SHAP interpretation to explore spatial-temporal patterns and the nonlinear, multi-factor drivers of fragmentation. Key findings include: (1) Fragmentation first intensified then eased, with clear regional differences—engineering efforts reduced fragmentation in the southwest by up to 18.7%, while urbanization and lagging land transfer increased it in the Huang-Huai-Hai region; the Qinghai-Tibet Plateau showed a unique “expansion–fluctuation” pattern under ecological policies. (2) Slope and population density are dominant nonlinear drivers, with threshold effects observed for precipitation, temperature, and elevation. For example, fragmentation rises sharply with slopes of 0–3° or population densities over 125 persons/km². (3) Spatial heterogeneity reveals that natural drivers vary by region and can be reshaped by policy—e.g., rainfall effects reversed in the southwest due to terracing, elevation constraints offset by farmland projects in Huang-Huai-Hai, and ecological policies reduced the impact of population density by 35% on the Plateau. The model highlights key thresholds (e.g., 800 mm rainfall, 3° slope) that support the need for region-specific governance.