Exploring spatio-temporal heterogeneity of rural settlement patterns on carbon emission across more than 2800 Chinese counties using multiple supervised machine learning models.

China, the world's largest carbon emitter, plays a pivotal role in achieving carbon neutrality. This study systematically analyzes the impact of landscape indices on carbon emissions from rural settlements across more than 2800 counties using eight supervised machine learning models. To assess variable influences under diverse conditions, we also employed the SHapley Additive exPlanations (SHAP) and Accumulated Local Effects (ALE) methods.

Human-earth system dynamics in China's land use pattern transformation amidst climate fluctuations and human activities.

Amid rapid environmental changes, the interplay between climate change and human activity is reshaping land use, emphasizing the significance of human-earth system dynamics. This study, rooted in human-earth system theory, explores the complex relationships between land use patterns, climate change, and human activities across China from 1996 to 2022. Using a comprehensive analytical framework that combines Geographical Detector (GeoDetector), Random Forest (RF) model, Data Envelopment Analysis (DEA), Spearman's rank correlation, and k-means clustering, we analyzed data from national land surveys, climate records, and nighttime light observations.