Identifying the driving factors of soil environmental quality is critical in raising countermeasures for managing the soil environment efficiently and precisely. In 2018, China issued risk control standards to divide soil environmental quality into three classes to meet the demands of environment management. However, there is a lack of knowledge of this new standard. An intensive field-sampling research (2598 top-soil samples were analyzed) was conducted in the agricultural land of Hubei province, central China, to find the driving factors of pollutants based on this new standard. According to the standard, the proportion of classes 1, 2, and 3 in the overall quality grade was 57.3%, 41.7%, and 1%, respectively. The standardized index showed that the pollution levels of cadmium, arsenic, lead, and chromium were higher than that of mercury. The first component of the principal component analysis explained 56.4% of the total variance, and the loading of cadmium, arsenic and lead were −53.5%, −52.1%, and −51.2%, respectively. The general linear modeling found that cadmium and arsenic showed positive and significant effects (p < 0.001) on the grading results of soil environmental quality. Based on the random forest algorithm, cadmium showed the greatest importance on soil environmental quality (increase in mean squared error = 32.5%). Overall, this study revealed that cadmium, arsenic, and lead were driving pollutants affecting soil environment quality grade. The large data size increased the reliability and robustness of the study’s conclusions, and it provided reference methods for future studies investigating China’s new standard for assessing soil environmental quality.

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.