Yefeng Jiang

The expansion of intensive agriculture has made soil acidification a key constraint on global agricultural productivity. Thus, comparing acidification rates under alternative management scenarios in current soil conditions and formulating regional governance plans accordingly are critical for ensuring food security. In this study, we systematically investigated red soil dry land in the Jitai Basin, quantified acidification rates via nutrient balance, and compared soil acidification rates under multiple nutrient-management scenarios evaluated in present soil conditions. The results show the following: Crop removal and nitrogen fertilizer input are the main driving factors that lead to the acidification of red soil dry land. The overuse of nitrogen fertilizer accelerates soil acidification. Regular scattering of lime is the most effective scenario for alleviating acidification. The total nitrogen, soil organic matter, cation exchange capacity, soil pH and soil type dominate the spatial distribution of the soil acidification rate. The total soil acidification rate and the actual acidification rate show a concentric-ring pattern, with high rates in the center and at the periphery and lower rates in the intermediate ring, while the potential soil acidification rate shows a gradient difference of “high in the west and low in the east”. By integrating multiple scenarios, the study area is divided into four levels of acidification control zones. It is suggested that, in future treatment of acidification in red soil dry land, fertilization management should be optimized and the rate at which the residual part of the crop harvest is returned to the field should be appropriately increased. The strategy of sprinkling lime can be adopted for areas with severe acidification.

Dynamic monitoring of soil moisture (βg) is crucial for optimizing agricultural water use.Non-invasive electromagnetic induction (EMI) presents a promising alternative, adopting measurements of apparent electrical conductivity (ECa) to establish inversion models for predicting βg across different soil layers. However, the accuracy of these static models is limited. This study aimed to develop and validate a dynamic monitoring framework by integrating EMI with an Extended Kalman Filter (EKF) algorithm. The research was conducted in cotton fields using drip irrigation under plastic films in the Alaer Reclamation Area. First, ECa data were acquired using an EM38-MK2 ground conductivity meter in both vertical and horizontal dipole orientations during different growth periods. The optimal modeling factor was determined by combining βg values at various periods and soil depths. Subsequently, the EKF algorithm was implemented to assimilate the time-series ECa data, thereby refining the accuracy of the βg estimations. Finally, natural neighbor interpolation (NNI) was used to generate and analyze three-dimensional (3D) spatiotemporal distributions of soil moisture. The results show that the EKF improved the model accuracy. For the soil depth of 60-80 cm in October, the coefficient of determination (R2) is increased from 0.36 to 0.83; at a soil depth of 60-80 cm in March, the Root Mean Square Error (RMSE) is decreased from 12.37 to 1.65. This research validates a novel methodology for monitoring high-accuracy, real-time soil moisture in arid regions. The proposed framework provides critical guidance for precision irrigation management in cotton cultivation, contributing to more sustainable agricultural water use.

Elucidating the multi-scale driving mechanisms of the spatiotemporal distribution of soil pH is critical for regional soil ecological regulation and the preservation of cultivated land fertility. However, systematic elucidation of the multi-scale driving mechanisms of the spatiotemporal distribution of soil pH remains limited. Here, we integrated random forest, XGBoost, and geographically interpretable SHAP (GeoShapley) to systematically investigate the spatiotemporal changes in soil pH and their driving mechanisms across three analytical scales (global, raster, and point-level) before and after high-standard farmland construction, based on 149 paired soil sampling points collected in 2008 and 2023 in Taihe County, Jiangxi Province. The mean soil pH in the study area increased from 5.12 in 2008 to 5.53 in 2023, suggesting mitigation of soil acidification. XGBoost outperformed random forest in both periods, with R² values of 0.71 and 0.67 for the two periods, respectively, and the spatial predictions indicated that soil pH in the western and southeastern regions increased following high-standard farmland construction. At the global scale, feature importance based on XGBoost indicated that climate contributed most to soil pH variation in both periods, followed by anthropogenic activities. At the raster scale, GeoShapley revealed a shift from a combination of anthropogenic activities and climate in 2008 to an interplay among climate, vegetation, and topography in 2023, suggesting a decreasing influence of anthropogenic disturbance. At the point level, the factors primarily influencing soil pH shifted from topographic and anthropogenic ones in 2008 to topographic and climatic ones in 2023, regardless of whether the sampling points exhibited low or high pH values, further corroborating the diminishing role of anthropogenic influence. Interaction analyses indicated that topography and vegetation consistently modulated the effects of anthropogenic and climatic factors throughout the study period, suggesting that these two factors were consistently associated with soil pH dynamics across the study area. In summary, this study provides a scientific basis for the targeted improvement of cultivated land fertility and the formulation of differentiated soil management strategies for high-standard farmland in the hilly regions of southern China.

As the underlying model of ChatGPT-4V and scientific computing models (e.g., AlphaFold 3), the application of Transformer in the field of soil property mapping is worth exploring. In this study, we aim to explore the application value of Transformer models in soil potassium mapping. To achieve this objective, random forest (RF), feedforward neural network (FNN), one-dimensional convolutional neural network (1D-CNN), and geospatial Transformer (GT) models were used to map the spatial distribution of total potassium and available potassium in regional soil. In addition, the explanatory SHAP model was used to elucidate the contribution of each environmental variable to the model. The GT model exhibited the best effect and accuracy in modeling total and available potassium. The model improved the total potassium prediction accuracy to 0.77, representing increases of 208%, 156.67%, and 41.54% over the RF model, FNN model, and 1D-CNN model, respectively. It also improved the available potassium prediction accuracy to 0.42, representing improvements of 16.02%, 88.34%, and 19.66% over the RF model, FNN model, and 1D-CNN model, respectively. The geographical-feature explanatory model revealed that the red edge index exhibited a synergistic response to the spatial distribution of total potassium and available potassium. In the modeling of available potassium, it was found that the accuracy of GT model driven by ‘ physical laws ‘ rather than pure data was not only higher than that of ordinary deep learning model, but also higher than that of machine learning model, which broke the traditional rule that the accuracy of machine learning model was higher than that of deep learning model using small samples and a few feature variables, and confirmed the huge mapping potential of GT model for soil attribute data.

In recent years, China’s hilly and mountainous areas have faced widespread farmland abandonment. However, research on farmland abandonment and its driving mechanisms in hilly and mountainous regions is limited. This study proposes a transferable methodological framework that integrates Landsat data, Google Earth Engine, a time sliding-window algorithm, and the interpretable XGBoost–Shapley Additive explanation (SHAP) model. The time sliding-window algorithm is used to robustly detect long-term land cover changes across the entire study period. The SHAP quantifies the contributions of key drivers to farmland abandonment, providing transparent insights into the driving mechanisms. Applying this framework, we systematically analyzed the spatiotemporal evolution patterns and driving factors of farmland abandonment in Ji’an City, a typical city located in the hilly and mountainous areas of southern China and ultimately developed a farmland abandonment probability distribution map. The findings demonstrate the following. (1) Methodological validation showed that the random forest classifier achieved a mean overall accuracy (OA) of 91.05% (Kappa = 0.88) and the abandonment maps achieved OA of 91.58% (Kappa = 0.83). (2) Spatiotemporal analysis revealed that farmland area increased by 13.26% over 1990–2023, evolving through three stages: fluctuation (1990–2005), growth (2006–2015), and stability (2016–2023). The abandonment rate showed a long-term decreasing trend, peaking in 1998, whereas the abandoned area reached its minimum in 2007. From a spatial perspective, abandonment was more pronounced in mountainous and hilly regions of the study areas. (3) The XGBoost–SHAP model (R² > 0.85) identified key driving factors, including the potential crop yield, soil properties, mean annual precipitation, population density, and terrain features. By offering an interpretable and transferable monitoring framework, this study not only advances farmland abandonment research in complex terrains but also provides concrete policy implications. The results can guide targeted protection of high-risk abandonment zones, promote sustainable land-use planning, and support adaptive agricultural policies in hilly and mountainous regions.

Cropland abandonment, a global challenge, necessitates comprehensive monitoring to achieve the zero hunger goal. Prior monitoring approaches to cropland abandonment often face constraints in resolution, time series, drivers, prediction, or a combination of these. Here, we proposed an artificial intelligence framework to comprehensively monitor cropland abandonment and tested the framework in Hengyang City, China. Specifically, we first mapped land cover at 30 m resolution from 1985 to 2023 using Landsat, stable sample points, and a machine learning model. Subsequently, we constructed the extent, time, and frequency of cropland abandonment from 1986 to 2022 by analyzing pixel-level land-use trajectories. Finally, we quantified the drivers of cropland abandonment using machine learning models and predicted the spatial distribution of cropland abandonment risk from 2032 to 2062. Our results indicated that the abandonment maps achieved overall accuracies of 0.88 and 0.78 for identifying abandonment locations and timing, respectively. From 1986 to 2022, the proportion of cropland abandonment ranged between 0.15% and 4.06%, with an annual average abandonment rate of 1.32%. Additionally, the duration of abandonment varied from 2 to 38 years, averaging approximately 14 years, indicating widespread cropland abandonment in the study area. Furthermore, 62.99% of the abandoned cropland experienced abandonment once, 27.17% experienced it twice, and only 0.23% experienced it five times or more. Over 50% of cropland abandonment remained unreclaimed or reused. During the study period, tree cover, soil pH, soil total phosphorus, potential crop yield, and the multiresolution index of valley bottom flatness emerged as the five most important environmental covariates, with relative importances of 0.087, 0.074, 0.068, 0.050, and 0.043, respectively. Temporally, cropland abandonment in 1992 was influenced by transportation inaccessibility and low agricultural productivity, soil quality degradation became an additional factor by 2010, and synergistic effects of all three drivers were observed from 2012 to 2022. Notably, most cropland had a low abandonment risk (mean: 0.36), with only 0.37% exceeding 0.7, primarily distributed in transitional zones between cropland and non-cropland. Future risk predictions suggested a gradual decline in both risk values and the spatial extent of cropland abandonment from 2032 to 2062. In summary, we developed a comprehensive framework for monitoring cropland abandonment using artificial intelligence technology, which can be used in national or regional land-use policies, warning systems, and food security planning.

Soil texture, defined by the proportions of sand, silt, and clay particles in the soil, is one of the most essential physical properties of soil. High-resolution soil texture data can provide critical parameter support for soil hydrological modeling, agricultural production management, and ecosystem assessment. In digital soil mapping, previous studies often predicted the sand, silt, and clay contents in soil and then indirectly calculated soil texture. Currently, approaches that directly map soil texture by classification modeling are gaining increasing attention due to the decreased error from data conversion, but few studies have systematically compared these two methods yet. In this study, we comprehensively assessed the performance of direct and indirect predicting soil texture using four machine learning algorithms (e.g., extreme gradient boosting, random forest, gradient boosting decision tree, and extremely randomized tree) with 190 covariates from the Digital Elevation Model, Sentinel-1/2 satellite images, and classification maps and generated a 10 m resolution soil texture map based on 405 topsoil (0–20 cm) sample data collected in Suichuan County, China. The results showed that compared with indirect predictions, direct predictions improved overall accuracy (OA) by 20.57–44.19% and the Kappa coefficient (Kappa) by 0.220–0.402. Among the models used, the XGB model achieved the highest accuracy (OA: 0.948; Kappa: 0.931) and the lowest uncertainty (confusion index: 0.052). The direct prediction map (nine classes recorded) exhibited more detailed and diverse spatial distribution patterns than the indirect prediction map (six classes recorded), aligning better with the actual environment. Based on accuracy validation and spatial distribution, the performance of the XGB model was best during direct prediction. The Shapley additive explanation from the XGB model revealed that the normalized height and stream power indices were the most significant factors driving the soil texture in the study area. Our results provide a reference for future studies on soil texture mapping using machine learning models.

The concept of ecosystem health (EH), proposed in the 1980s

Soil total phosphorus plays an important role in soil fertility, plant growth, and bioge-ochemical cycles. This study aims to determine the spatial distribution characteristics of soil total phosphorus and identify its main influencing factors in the study area, thereby providing a basis for the scientific management of soil total phosphorus. Here, we conducted a comprehensive analysis by combining classical statistical analysis, ge-ostatistics methods, Pearson correlation analysis, one-way analysis of variance (ANOVA), and structural equation modeling (SEM) to explore the spatial distribution patterns of soil total phosphorus and its influencing factors. The results showed that soil total phosphorus in the study area ranged from 161.00 to 991.00 mg/kg, with an average of 495.71 mg/kg. Spatially, soil total phosphorus exhibited a patchy distribu-tion pattern, with high values primarily concentrated in cultivated areas along rivers and low values mainly located in forested areas in the southeastern and central re-gions. Additionally, the nugget effect of soil total phosphorus was 71.5%, indicating a moderate level of spatial variability. The Pearson correlation analysis revealed that soil total phosphorus content was significantly correlated with multiple factors, including land use types, soil parent material, distance from settlements, slope, and soil pH. Based on these findings, we employed ANOVA to analyze the impacts of various fac-tors. The results indicated that soil total phosphorus content showed significant differences under the influence of different factors. Subsequently, we further explored in depth the action paths through which these factors affect soil total phosphorus us-ing SEM. The SEM results showed that the absolute values of the total effects of the influencing factors on soil total phosphorus, ranked from highest to lowest, were as follows: land use types (0.499) > soil parent material (0.240) > distance from settle-ments (0.178) > slope (0.161) > elevation (0.127) > soil pH (0.114) > normalized differ-ence vegetation index (0.103). These findings provide a scientific foundation for the effective management of soil total phosphorus in similar study areas.