Abstract: The county level serves as a fundamental regional unit for an in-depth analysis of the relationship between agricultural carbon emissions and urbanization. Understanding the spatiotemporal evolution and driving mechanisms of agricultural carbon emissions at the county level is crucial for guiding green and low-carbon development in rural areas and advancing rural revitalization efforts. The aim of this study was to elucidate the spatiotemporal evolution patterns and driving factors of county-level agricultural carbon emissions in Guangdong Province from 2000 to 2022. This study systematically calculated agricultural carbon emissions for 124 counties (cities, districts) in Guangdong Province using the latest emissions inventory system. We collaboratively identified the key driving factors and spatiotemporal evolution patterns of agricultural carbon emissions at the county level by integrating GIS and machine learning techniques, including local spatial autocorrelation analysis and the random forest (RF) algorithm. The results were as follows: 1) Overall, agricultural carbon emissions at county level in Guangdong Province exhibited a downward trend from 2000 to 2020, with total emission being 4533.27×10⁴, 3895.21×10⁴, 4034.23×10⁴ and 3553.97×10⁴ t in 2000, 2010, 2016 and 2022, respectively, while carbon emissions within the province were uneven and had strong spatial heterogeneity. 2) Geographic Information System (GIS)-based local spatial autocorrelation analysis revealed distinct spatial clustering characteristics of agricultural carbon emissions. High-high values were predominantly located in Western Guangdong, whereas low-low values were concentrated in the core area of the Pearl River Delta. Notably, the degree of internal clustering within each region showed a continuous upward trend over time. 3) A notable distinction between agricultural carbon emissions per capita and total emissions was observed, with high-high values of emissions per capita appearing mainly in Northern Guangdong and Western Guangdong, while low-low values were concentrated in the Pearl River Delta and Eastern Guangdong, indicating a “spatial spillover” effect where emissions in densely populated urban areas impact surrounding regions. 4) The RF model, constructed using agricultural indicators selected through Pearson correlation analysis, identified the primary factors influencing agricultural carbon emissions. These included plowing area, fertilizer and pesticide usage, and total power of agricultural machinery. Among these indicators, the increase of fertilizer and pesticide usage was adverse to the reduction of agricultural carbon emissions, whereas the advancement of agricultural mechanization emerged as a positive driving factor for reducing agricultural carbon emissions. The results of this study highlight the complexity and regional variability of agricultural carbon emissions in Guangdong Province. The integration of local spatial autocorrelation and RF algorithms provides a robust analytical framework for understanding these dynamics. In addition, this study offers valuable policy insights and quantitative tools for regional agricultural carbon emission reduction and promotes green and low-carbon development strategies. Overall, our findings underscore the importance of targeted region-specific policies to address the unique challenges and opportunities within different areas of Guangdong Province. By leveraging advanced analytical techniques and comprehensive datasets, policymakers can better understand and mitigate the factors driving agricultural carbon emissions, paving the way for sustainable and environmentally friendly agricultural practices.