The prediction of soil organic matter is important for measuring the soil’s environmental quality and the degree of degradation. In this study, we combined China’s GF-6 remote sensing data with the organic matter content data obtained from soil sampling points in the study area to predict soil organic matter content. To these data, we applied the random forest (RF), light gradient boosting machine (LightGBM), gradient boosting tree (GBDT), and extreme boosting machine (XGBoost) learning models. We used the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE) to evaluate the prediction model. The results showed that XGBoost (R² = 0.634), LightGBM (R² = 0.627), and GBDT (R² = 0.591) had better accuracy and faster computing time than that of RF (R² = 0.551) during training. The regression model established by the XGBoost algorithm on the feature-optimized anthrosols dataset had the best accuracy, with an R² of 0.771. The inversion of soil organic matter content based on GF-6 data combined with the XGBoost model has good application potential.

Cultivated land quality is an essential agricultural resource and production element. To increase cultivated land quality in a targeted way, it is crucial to understand the features of regional elements that constrain its quality. In order to diagnose the restriction factors affecting the improvement of cultivated land quality grades and conduct a quantitative analysis of the regional cultivated land quality improvement restriction factors, the restriction index model was used in this study to analyze the distribution characteristics of cultivated land quality grades in East Anhui, China. The results show that there are six main restriction factors of cultivated land quality in the study area, which are effective soil layer thickness, soil organic matter, soil acidity and alkalinity, plough layer texture, irrigation capacity, drainage capacity, and obstacle factors, among which the main restriction factors of the first to third grades are soil organic matter, soil acidity and alkalinity, and the main restriction factors of the fourth to seventh grades are soil organic matter, and soil acidity and alkalinity. The main restriction factors of the soil organic matter, effective soil layer thickness, and obstacle factors are the key restriction factors in the ninth to tenth classes.

Selection of rice varieties and application of amendments are effective measures to ensure food safety. Here we report that in the non-Cd area, the grain quality of all rice varieties met the Chinese National Grain Safety Standards (CNGSS). In the high-Cd area, rice varieties showed significant different bioaccumulation of Cd with lower rice yields than those in non-Cd area with the average decrease of 31.1%. There was a negative correlation between grain Cd content and yields. A total of 19 rice varieties were selected as low Cd accumulating rice varieties and their Cd content met CNGSS in the low-Cd area. Six of them met CNGSS in the high-Cd area. The application of amendments significantly reduced Cd content in rice grains by 1.0–84.7% with an average of 52.6% and 13 of varieties met CNGSS. The amendments reduced available Cd content in soils by 1.1–75.8% but had no significant effects on rice yields. Therefore, the current study implied that proper agronomic management with selection of rice varieties and soil amendments was essential in controlling Cd accumulation in rice grains.

Timely and accurate prediction of winter wheat yields, which is crucial for optimizing production management, maintaining supply–demand balance, and ensuring food security, depends on interactions among numerous factors, such as climate, surface characteristics, and soil quality. Despite the extensive application of deep learning models in this field, few studies have analyzed the effect of the large-scale geospatial characteristics of neighboring regions on crop yields. Therefore, we present an attention-based spatio-temporal Graph Neural Network (ASTGNN) model coupled with geospatial characteristics and multi-source data for improved accuracy of winter wheat yield estimation. The datasets used in this study included multiple types of remote sensing, meteorological, soil, crop yield, and planting area data for Anhui, China, from 2005 to 2020. The results showed that multi-source data led to higher prediction performance than single-source data, and enabled accurate prediction of winter wheat yields three months prior to harvest. Furthermore, the ASTGNN model provided better prediction performance than two traditional crop yield prediction models (R² = 0.70, RMSE = 0.21 t/ha, MAE = 0.17 t/ha). Therefore, ASTGNN enhances the accuracy of crop yield prediction by incorporating geospatial characteristics. This research has implications for improving agricultural production management, promoting the development of digital agriculture, and addressing climate change in agriculture.

Metal(loid) pollution in vegetable field soils has become increasingly severe and affects the safety of vegetable crops. Research in China has mainly focused on greenhouse vegetables (GV), while open field vegetables (OV) and the spatial distribution patterns of metal(loid)s in the surrounding soils have rarely been assessed. In the present study, spatial analysis methods combining Geographic Information Systems (GIS) and Moran’s I were applied to analyze the effects of vegetable fields on metal(loid) accumulation in soils. Overall, vegetable fields affected the spatial distribution of metal(loid)s in soils. In long-term vegetable production, the use of large amounts of organic fertilizer led to the bioconcentration of cadmium (Cd) and mercury (Hg), and long-term fertilization resulted in a significant pH decrease and consequent transformation and migration of chromium (Cr), lead (Pb), and arsenic (As). Thus, OV fields with a long history of planting had lower average pH and Cd, and higher average As, Cr, Hg, and Pb than GV fields, reached 0.93%, 10.1%, 5.8%, 3.0%, 80.8%, and 0.43% respectively. Due to the migration and transformation of metal(loid)s in OV soils, these should be further investigated regarding their abilities to reduce the accumulation of metal(loid)s in soils and protect the quality of the cultivated land.