Wildfires release large amounts of greenhouse gases into the atmosphere, exacerbating climate change and causing severe impacts on air quality and human health. In this study, based on a bottom-up approach and using satellite data, combined with emission factor and aboveground biomass data for different vegetation cover types (forest, shrub, grassland, and cropland), the dynamic changes in CO₂ emissions from wildfires in China from 2001 to 2022 were analyzed. The results showed that between 2001 and 2022, the total CO₂ emissions from wildfires in China were 937.7 Tg (522.6–1516.0 Tg, 1 Tg = 10¹² g), with an annual average of 42.6 Tg (23.8–68.9 Tg). The CO₂ emissions from cropland and forest fires were relatively high, accounting for 45 % and 46 % of the total, respectively. The yearly variation in CO₂ emissions from forest and shrub fires showed a significant downward trend, while emissions from grassland fires remained relatively stable. In contrast, the CO₂ emissions from cropland fires showed an upward trend, primarily in Northeast China. Hot spot analysis and geographically and temporally weighted regression (GTWR) models revealed significant spatial heterogeneity in emissions across vegetation types. Persistent hot spots of shrub and forest fires were located in Southwest and South China, while Northeast China experienced sporadic but extreme fire events. The GTWR model for shrub fire CO₂ emissions exhibited the highest predictive performance (R²= 0.87), and climatic factors (particularly temperature and humidity) were the main influencing factors. Notably, the recent rise in cropland fire CO₂ emissions in Northeast China is closely linked to region-specific straw-burning policies. The research results provide valuable references for atmospheric transport models, regional fire management, and national carbon accounting frameworks in the context of climate change.