Habitat quality constitutes the fundamental basis for maintaining ecosystem stability and healthy functioning. Revealing its spatiotemporal evolution patterns, key influencing mechanisms, and critical thresholds is essential for achieving regional sustainable development. Taking Sichuan Province as a case study, this research quantitatively assessed land use pattern changes (2000–2020), spatiotemporal differentiation characteristics of habitat quality, and critical influencing factors with their thresholds by integrating the InVEST model with XGBoost (eXtreme Gradient Boosting)-SHAP (Shapley Additive Explanations) coupling methodology. The results indicate: (1) From 2000 to 2020, Sichuan Province experienced an increase in construction land and forested areas, while cultivated land and grassland decreased, with minimal changes observed in unused land and water bodies. The mean habitat quality showed a slight decline, forming a spatial pattern characterized by “west-high-east-low,” with Chengdu as the core demonstrating outward radiative improvement. (2) Population density, elevation, NDVI (Normalized Difference Vegetation Index), annual mean temperature, and slope gradient were identified as primary influencing factors, where population density and elevation dominated, with population density exhibiting greater contribution than elevation. (3) Relationships between habitat quality and factors demonstrated diversified nonlinear characteristics: positive correlations (NDVI, slope) and negative correlations (annual mean temperature, distance to roads). Threshold effects manifested as single-segment (slope gradient) and multi-segment (elevation, annual mean temperature) patterns. Proposed habitat management measures based on dominant factors and thresholds can enhance governance efficiency under limited investments. The findings provide scientific references for advancing high-quality ecological development in Sichuan.