In the era of the digital economy, where digitization permeates all sectors of society, digital transformation in agriculture stands as a crucial solution for addressing the growing challenges in agricultural production. Amid the competition to enhance the resilience of sustainable food systems, China sets an exemplary model with its achievements in digital agricultural transformation, providing a blueprint for developing countries in Asia and the Pacific. Primarily based on statistical data and typical case studies, this paper presents analytical findings on how digital transformation of agriculture enhances the adoption of green agricultural practices and promotes inclusive development in China. In light of the intricate challenges faced by China’s food system, the adoption of digitization emerges to facilitate the transformation from conventional agriculture to smart and sustainable practices. The pathways by which digital transformation of agriculture have the potential to address the over-application of chemical fertilizer and irrigation water, mitigation of carbon emissions, and the challenge of climate change and contribute to environmental sustainability of agriculture have been discussed. The implementation of digital transformation in sustainable agriculture—which enhances green practices and social inclusiveness by promoting digital literacy, reducing workload, creating job opportunities for low-skilled labor, and developing rural inclusive finance—has been completely explored. The challenges in digital transformation of agriculture are explained in this paper, which also provides evidence-based policy recommendations for its sustainable development applicable to developing countries.

The rising number of disturbances caused by natural hazards, epidemics, and international conflicts seriously threatens global agriculture and food systems. In order to combat the increasing uncertainty, the Chinese government proposed a “dual circulation” strategy, which puts forward a new requirement of promoting self-sufficiency. Among various food categories, grain serves as a cornerstone for sustaining human life during public crises. Guangdong Province is one of the most economically developed and highly densely populated regions in China; therefore, it faces significant pressure to enhance food security. This study investigates the spatial and temporal patterns of the rate of grain self-sufficiency (RSSG) at the county levels in Guangdong Province from 2014 to 2023. The findings reveal the following: (1) rice remains the predominant grain crop, with its sown area and production consistently accounting for over 75%; (2) the RSSG is 28.14% on average, which is lower than the governmental goal of 30%; (3) the RSSG has significant regional disparities and distinct agglomeration patterns; and (4) scenario simulations indicate that grain yield improvement and grain loss reduction have the potential to promote the RSSG to 34.14%. Based on the research findings, this paper proposes the following policy recommendations: (1) prioritize farmland preservation and implement the “storing grain in the land” strategy to ensure food supply; (2) adopt advanced agricultural technologies under the “storing grain in the technology” strategy to improve grain yield; (3) reduce grain loss by strengthening disaster prevention, improving storage management, and enhancing storage efficiency; and (4) strengthen interdepartmental coordination. The integrated application of these strategies will help Guangdong Province enhance its grain self-sufficiency, ensure food security, and contribute to the achievement of national food security goals.

Northeast China, a traditional heavy industrial base, faces significant carbon emissions challenges. This study analyzes the drivers of carbon emissions in 35 cities from 2000–2022, utilizing a machine-learning approach based on a stacking model. A stacking model, integrating random forest and eXtreme Gradient Boosting (XGBoost) as base learners and a support vector machine (SVM) as the meta-model, outperformed individual algorithms, achieving a coefficient of determination (R²) of 0.82. Compared to traditional methods, the stacking model significantly improves prediction accuracy and stability by combining the strengths of multiple algorithms. The Shapley additive explanations (SHAP) analysis identified key drivers: total energy consumption, urbanization rate, electricity consumption, and population positively influenced emissions, while sulfur dioxide (SO₂) emissions, smoke dust emissions, average temperature, and average humidity showed negative correlations. Notably, green coverage exhibited a complex, slightly positive relationship with emissions. Monte Carlo simulations of three scenarios (Baseline Scenario (BS), Aggressive De-coal Scenario (ADS), and Climate Resilience Scenario (CRS)) the projected carbon peak by 2030 under the ADS, with the lowest emissions fluctuation (standard deviation of 5) and the largest carbon emissions reduction (17.5–24.6%). The Baseline and Climate Resilience scenarios indicated a peak around 2039–2040. These findings suggest the important role of de-coalization. Targeted policy recommendations emphasize accelerating energy transition, promoting low-carbon industrial transformation, fostering green urbanization, and enhancing carbon sequestration to support Northeast China’s sustainable development and the achievement of dual-carbon goals.

To promote high-quality agricultural development and implement the “storing grain in the land” strategy, the construction of Well-Facilitated Farmland (WFF) plays a critical role in enhancing grain production capacity and optimizing the spatial distribution of food supply, thereby contributing to national food security. However, accurately assessing the potential impact of WFF construction on China’s grain production and regional self-sufficiency by 2030 remains a significant challenge. Existing studies predominantly focus on the provincial level, while fine-grained analyses at the city level are still lacking. This study quantifies the potential increase in grain production in China under the 2030 WFF construction target by employing effect size analysis, multi-weight prediction, and Monte Carlo simulation across multiple spatial scales (national, provincial, and city levels), thereby addressing the research gap at finer spatial resolutions. By integrating 2030 population projections and applying a grain self-sufficiency calculation formula, it further evaluates the contribution of WFF to regional grain self-sufficiency: (1) WFF could generate an additional 31–48 million tons of grain, representing a 5.26–8.25% increase; (2) grain supply in major crop-producing regions would expand, while the supply–demand gap in balanced regions would narrow; and (3) the number of cities with grain self-sufficiency ratios below 50% would decrease by 11.1%, while those exceeding 200% would increase by 25.5%. These findings indicate that WFF construction not only enhances overall grain production potential but also facilitates a transition from “overall supply-demand balance” to “structural security” within China’s food system. This study provides critical data support and policy insights for building a more resilient and regionally adaptive agricultural system.

With the continuous advancement of sustainable agriculture, drone technology has become a focus of attention. Current research primarily relies on classical models for questionnaire surveys and analyses within specific regions, rather than implementing macro-level investigations that incorporate innovative algorithms. This study designed a survey questionnaire to investigate Chinese farmers’ preferences for agricultural drones and their technology adoption mechanisms under sustainable agriculture context. The Ant Colony Optimization-Decision Tree (ACO-DT) model and SHAP (Shapley Additive exPlanations) value analysis are applied to analyze the contribution of different indicators to technology adoption. The ACO-DT model outperformed traditional machine learning models with approximate accuracy 0.85, recall 0.98, and F1 Score 0.90, effectively identifying potential drone users compared to other traditional machine learning models. The SHAP analysis showed “Time Required for Promotion” (average SHAP value exceeds 1.25) and “Understanding of UAV Agriculture” (average SHAP value is about 1.0) were core influencing factors. Specifically, high-cognition farmers preferred shorter promotion cycles, while low-cognition group favored longer cycles to reduce decision-making uncertainty. Practically, the study enriches agricultural technology adoption research methodologically and offers references for advancing smart agriculture and optimizing rural production factors.

Against the backdrop of global climate change and the “dual carbon” goals, the issue of agricultural greenhouse gas emissions has garnered increasing attention. As a major grain and oilseed crop in China, carbon emissions from soybean production have a significant impact on the green and low-carbon development of agriculture. Although research on agricultural carbon footprints has grown in recent years, existing studies have largely focused on single regions or specific stages of crop production, and analyses of the carbon footprint of production systems in China’s major soybean-producing regions remain relatively limited. This study employs the Life Cycle Assessment (LCA) methodology to calculate and analyze the carbon footprint of soybean production systems across China’s 10 major soybean-producing provinces, utilizing agricultural input data from 2014 to 2023. The study establishes a carbon footprint accounting system based on two key aspects: carbon emissions from agricultural inputs and soil N₂O emissions. It further analyzes the temporal trends, regional variations, and contribution characteristics of each component within the carbon footprint. The results indicate that the average carbon footprint of soybean production in China is approximately 528 kg CO₂eq/ha (ranging from 273 to 855) and 0.25 CO₂eq/kg of soybean (ranging from 0.13 to 0.46). Specifically, the carbon footprint per unit of area and yield declined simultaneously, indicating a continuous improvement in the low-carbon efficiency of soybean production. Spatially, there are significant regional differences in the carbon footprint of soybean production. Henan, Anhui, and Inner Mongolia have relatively low carbon footprints, while Shaanxi and Shanxi have relatively high levels. In terms of composition, chemical fertilizer inputs and soil N₂O emissions are the primary sources of the carbon footprint in soybean production, with chemical fertilizer inputs being the largest source, accounting for approximately 40–60%, and soil N₂O emissions being the second major source. Overall, differences among regions in natural conditions, agricultural input structures, and production methods result in distinct regional characteristics in the carbon footprint composition. The findings of this study provide a scientific basis for the low-carbon transition of China’s soybean production system and serve as a reference for the formulation of policies related to green agricultural development.