Context Ongoing climate change has intensified compound climate extremes, increasing the long-term exposure of ecosystems to compound climatic stress and posing growing risks to ecosystem services (ESs) through complex and spatially heterogeneous associations. Understanding these associations, and whether CES-level relationships exhibit nonlinear features, is essential for formulating effective landscape management and adaptation strategies under increasing climatic pressure. Objectives This study aims to (1) characterize the spatiotemporal dynamics of four types of compound climate extreme exposure, six key ESs, and comprehensive ecosystem services (CESs) from 2000 to 2020, and (2) compare the nonlinear associations and spatial explanatory effects of different compound climate extremes on CESs. Methods Daily data were used to identify compound extreme days, while five-year aggregated indicators were used to characterize recent cumulative exposure corresponding to CESs observation years. We integrated long-term high-resolution datasets with random forest (RF) and the optimal parameter geographic detector (OPGD). RF was used to assess the relative national-scale contribution of compound climate extremes to CESs prediction and to identify CES-level nonlinear association patterns, whereas OPGD was used to quantify spatial explanatory power and interaction effects associated with CESs heterogeneity. Results The spatial patterns of the six ESs and CESs remained relatively stable during 2000–2020, whereas the total amount of CESs showed an initial increase followed by a decline. In contrast, compound climate extremes showed clear regional divergence. RF-based analyses suggested apparent nonlinear association patterns at the equal-weighted CES level. Among the four extreme events, WD showed the most pronounced nonlinear pattern in the PDPs, with a curve-based transition from a weak positive association at lower exposure levels to a stronger negative association at higher exposure levels, most apparent around 10 days of recent cumulative WD exposure under the aggregation framework used in this study. Across both the national-scale contribution and spatial analyses, dry-related compound climate extremes showed stronger associations with CESs than CW and WW. Conclusions These findings indicate that recent cumulative exposure to compound climate extremes is associated with CES-level nonlinear and spatially heterogeneous patterns across contrasting regional climate–landscape contexts in China. This study provides an empirical basis for ecosystem management and region-specific adaptation under escalating climate risk.

Land surface temperature (LST) is increasing with rapid urbanization and climate warming. However, the relative roles of green quantity, vegetation condition, and inequality in local green resource availability in shaping the urban thermal environment remain insufficiently understood across regions. This study examined built-up areas in five major Chinese urban agglomerations. A Random Forest model combined with SHAP analysis was used to quantify the relative importance of green-related, natural background, built-environment, and socio-economic variables and to identify their nonlinear associations with LST. Green-related variables contributed consistently across the five urban agglomerations, although their contribution structures differed markedly among regions. NDVI generally showed stronger explanatory power than green cover. The weighted Gini coefficient of local green resource availability exhibited a strongly nonlinear and region-dependent association with LST. Cross-regional comparisons indicated greater sensitivity to changes in the weighted Gini coefficient in the Yangtze River Delta and weaker responses in the Chengdu–Chongqing region. SHAP results further indicated that built-environment morphology was also relevant alongside green-related variables. Built-up density consistently showed positive SHAP values. These findings provide interpretable cross-regional evidence for heat-mitigation planning. Effective strategies should prioritize vegetation quality, the spatial continuity of green resources, and a more balanced distribution of green space rather than focusing solely on the total quantity of green space.

With the growing use of human perception data streams in audits of the built environment, their value for enhancing objectivity and human-centeredness has become increasingly evident. This review synthesizes 63 publications through July 2024, providing a comprehensive analysis of perception data types, collection modalities and spatial strategies. This review introduces an Artificial Intelligence (AI)-enabled framework and utilizes Artificial Intelligence-Generated Content (AIGC) to assist literature retrieval and analysis, improving efficiency and transparency. The results indicate that heart rate and mood are currently the most frequently used perception data types in built-environment audits. Existing audit practices primarily focus on roads, green spaces, and residential areas at community and block-scale settings, with data choices varying by spatial typology. This review advances a systematic understanding of the application of perception data streams in built-environment audits and offers evidence-based recommendations for data collection, thereby providing stronger data support for future research.