Identifying the key factors influencing agricultural carbon emissions and accurately predicting future trends are essential for achieving carbon peak and carbon neutrality goals. This study aims to assess carbon emissions in agriculture from 1997 to 2022, construct an accurate model to identify the key influencing factors, and predict carbon emissions in agriculture from 2023 to 2030 with an intelligent prediction system to discuss risk management. Additionally, the Dagum method was employed to explore regional differences in agricultural carbon emissions across China. The results reveal that China’s agricultural carbon emissions exhibited a fluctuating trend from 1997 to 2022, peaking in 2015, followed by a period of decline and a moderate rebound in recent years. Elastic Net Regression identified eleven key variables, including Agricultural Machinery Level (MA), Numbers of Agricultural Tools (AT), and Agricultural Industrial Structure Upgrading (AICE), as major determinants of agricultural carbon emissions. Furthermore, the RF-PSO method demonstrated the highest predictive accuracy, forecasting a minor peak in agricultural carbon emissions in 2027, followed by stabilization. Regionally, imbalances in emissions were observed, with the intensity of transvariation accounting for 37.078% of the disparity. Therefore, the Chinese government is advised to implement region-specific strategies for controlling agricultural carbon emissions, cultivate new high-quality agricultural productivity, and promote advanced technologies.

Reducing agricultural carbon emissions is key to promoting the sustainable development of agriculture. Carbon sources play a significant role in the carbon emissions of China’s planting industry. Researching the principles of evolutionary trends of carbon sources regarding carbon emissions in China’s planting industry helps formulate scientific policies to control such emissions in the industry. This paper adopted an emission factor approach from the IPCC to estimate the CO₂ emissions of all kinds of carbon sources in China’s planting industry from 1997 to 2017. On the basis of the data, the principles of dynamic evolution in China’s planting industry and six carbon sources were analyzed by the kernel density estimation approach. Notably, the study discovered that carbon emissions peaked in 2015. In terms of the contributions of various carbon sources to the carbon emissions of the planting industry, sorted by chemical fertilizers, agricultural diesel oil, agricultural films, pesticides, agricultural irrigation, and seeding, their contribution rates were 60.82%, 13.95%, 12.88%, 9.83%, 1.88%, and 0.64%. At the same time, the kernel density results show that there was an increasing trend in carbon emissions across the whole of China’s planting industry and six kinds of carbon sources nationwide, with apparent “multipolarization”. From the perspective of various regions, the carbon emissions of chemical fertilizers, diesel oil, films, and pesticides in China’s planting industry had an evolutionary trend of multipolarization in central regions, while there was an evolutionary trend of monopolarization in eastern and western regions. The carbon emissions of seeding and irrigation had a similarly evolutionary trend in eastern, central, and western regions. Basically, they all had a double increase pattern in carbon emissions and regional differences. Therefore, China’s government needs a target to set up long-term mechanisms to ensure a stable and orderly reduction in carbon emissions in the planting industry, leading its development from the traditional planting industry to a climate-smart planting industry.

At present, the digital transformation in the global economy is accelerating. In order to understand the development of e‐commerce in China correctly, the study establishes eight secondary indicators to estimate the level of e‐commerce in China from 2013 to 2021 with the entropy weight–CRITIC method. Using the Dagum Gini coefficient, we investigated the overall, intraregional, and interregional differences in the level of e‐commerce in China. Through Kernel density estimation and Markov chain analysis, the study explored the dynamic evolution characteristics of their distribution. From 2013 to 2021, the level of e‐commerce in China exhibited a fluctuating upward trend, with an overall growth rate of 71.82%, but the overall level of e‐commerce was still low, showing a strong presence in the east and a weak presence in the west. It is evident that the differences in the level of e‐commerce mainly came from regional variations, with an average contribution rate of 72.98%. From the perspective of the dynamic evolution of distribution, the level of Chinese e‐commerce exhibited strong stability and characteristics of club convergence. Considering the spatial factors, the convergence of Chinese e‐commerce levels is evident. Based on the results, the study will propose a series of countermeasures and suggestions for adopting a regional coordinated development strategy to reduce the gap in e‐commerce levels between different regions.

Agriculture is a major source of carbon emissions, and the widespread use of plastic film in China has raised growing environmental concerns. To address this issue, this study develops the SDETI framework (Spatiotemporal characteristics-Dynamic evolution-Explanation-Threshold-Interaction) to investigate the spatiotemporal evolution and driving mechanisms of agricultural plastic film carbon emissions. Based on the panel data from China's 31 provinces from 1997 to 2022, this study evaluates the agricultural plastic film carbon emissions and analyses across multiple dimensions. The study indicates that China's agricultural plastic film carbon emissions fluctuated between 1997 and 2022, peaking in 2015 at 13.49 million tCO ₂ e (with a provincial average of 0.44 million tCO ₂ e), and then gradually declining in recent years, with total emissions stabilizing below 12.30 million tCO ₂ e and the average around 0.40 million tCO ₂ e after 2020. Specially, emissions were generally higher in the western and northern regions and lower in the eastern and southern regions. Furthermore, China's agricultural plastic film carbon emissions followed a multi-peak distribution with an initial rise and subsequent decline, showed a strong club convergence effect, and displayed a diffusion pattern shifting from the southeast to the northwest with increasing spatial dispersion. Meanwhile, agricultural machinery power (MACH) and plastic film usage (PFU) are identified as dominant factors, exerting heterogeneous and increasing agricultural plastic film carbon emissions in many regions. Furthermore, high input intensity, mechanization, and large-scale operations are found to amplify emissions, reflecting both regional disparities and synergistic input-driven effects. The integration of dynamic analytical methods with the LightGBM-SHAP framework enhances understanding of the spatiotemporal heterogeneity of agricultural plastic film emissions in China and provides evidence to support ecosystem management and the transition toward low-carbon agriculture.