Gully erosion is one of the significant environmental issues facing the black soil regions in Northeast China, and its formation is closely related to various environmental factors. This study employs multiple machine learning models to assess gully erosion susceptibility in this region. The primary objective is to evaluate and optimize the top-performing model under high-resolution UAV data conditions, utilize the optimized best model to identify key factors influencing the occurrence of gully erosion from 11 variables, and generate a local gully erosion susceptibility map. Using 0.2 m resolution DEM and DOM data obtained from high-resolution UAVs, 2,554,138 pixels from 64 gully and 64 non-gully plots were analyzed and compiled into the research dataset. Twelve models, including Logistic Regression, K-Nearest Neighbors, Classification and Regression Trees, Random Forest, Boosted Regression Trees, Adaptive Boosting, Extreme Gradient Boosting, an Artificial Neural Network, a Convolutional Neural Network, as well as optimized XGBOOST, a CNN with a Multi-Head Attention mechanism, and an ANN with a Multi-Head Attention Mechanism, were utilized to evaluate gully erosion susceptibility in the Dahewan area. The performance of each model was evaluated using ROC curves, and the model fitting performance and robustness were validated through Accuracy and Cohen’s Kappa statistics, as well as RMSE and MAE indicators. The optimized XGBOOST model achieved the highest performance with an AUC-ROC of 0.9909, and through SHAP analysis, we identified roughness as the most significant factor affecting local gully erosion, with a relative importance of 0.277195. Additionally, the Gully Erosion Susceptibility Map generated by the optimized XGBOOST model illustrated the distribution of local gully erosion risks.

Black soil is a precious soil resource, yet it is severely affected by gully erosion, which is one of the most serious manifestations of land degradation. The determination of the location and shape of gullies is crucial for the work of gully erosion control. Traditional field measurement methods consume a large amount of human resources, so it is of great significance to use artificial intelligence techniques to automatically extract gullies from satellite remote sensing images. This study obtained the gully distribution map of the southwestern region of the Dahe Bay Farm in Inner Mongolia through field investigation and measurement and created a gully remote sensing dataset. We designed a multi-scale content structure feature extraction network to analyze remote sensing images and achieve automatic gully extraction. The multi-layer information obtained through the resnet34 network is input into the multi-scale structure extraction module and the multi-scale content extraction module designed by us, respectively, obtained richer intrinsic information about the image. We designed a structure content fusion network to further fuse structural features and content features and improve the depth of the model’s understanding of the image. Finally, we designed a muti-scale feature fusion module to further fuse low-level and high-level information, enhance the comprehensive understanding of the model, and improve the ability to extract gullies. The experimental results show that the multi-scale content structure feature extraction network can effectively avoid the interference of complex backgrounds in satellite remote sensing images. Compared with the classic semantic segmentation models, DeepLabV3+, PSPNet, and UNet, our model achieved the best results in several evaluation metrics, the F1 score, recall rate, and intersection over union (IoU), with an F1 score of 0.745, a recall of 0.777, and an IoU of 0.586. These results proved that our method is a highly automated and reliable method for extracting gullies from satellite remote sensing images, which simplifies the process of gully extraction and provides us with an accurate guide to locate the location of gullies, analyze the shape of gullies, and then provide accurate guidance for gully management.

The advancement of precision agriculture and smart tillage relies on high-precision, real-time perception of unmanned ground vehicle (UGV) positions. In large-scale farmland operations, conventional Global Navigation Satellite System (GNSS)-based positioning may suffer from short-term signal loss, degrading accuracy. Multi-unmanned aerial vehicle (UAV)-assisted vehicle localization based on direction-of-arrival (DOA) estimation can provide critical positioning compensation for UGV, where compressed sensing (CS)-based DOA-assisted localization algorithms are commonly employed. However, existing schemes neither account for the bias induced by the local positional oscillation of UAVs, nor address the limited accuracy and real-time performance of CS-based DOA estimation, restricting their agricultural deployment. To this end, this paper first develops an assisted-localization architecture that explicitly incorporates the local positional offsets of multiple UAVs, together with a corresponding array signal reception model. To overcome the accuracy–efficiency trade-off of conventional CS-DOA methods, an adaptive local overcomplete dictionary (LOD) is then constructed to robustly refine the angular resolution around the region of interest. With the number of sources K assumed to be known and fixed, a particle swarm optimization (PSO)-based local refinement algorithm is further introduced to adaptively optimize the DOA estimates within the constructed local dictionary, thereby improving estimation robustness under low-SNR and coherent-source conditions. Consequently, the proposed method improves robustness while maintaining favorable localization accuracy and computational efficiency in the simulated scenarios. Simulation results show that it substantially reduces localization error compared with state-of-the-art algorithms, suggesting its potential as a localization-assistance approach for UGV navigation in sustainable tillage.

Feng Dai was removed from the list of authors in the original publication