The Xiahe-Hezuo area in Gansu Province, China, located in the West Qinling Metallogenic Belt, is characterized by complex regional geological structures and abundant mineral resources. A number of gold-polymetallic deposits have been identified in this region, demonstrating significant potential for gold-polymetallic mineral prospecting within the metallogenic belt. This study focuses on regional Mineral Prospectivity Mapping (MPM) in the Xiahe-Hezuo area. To address the common challenge of small-sample data limitations in geological prediction, we introduce a Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to generate high-fidelity geological feature samples, effectively expanding the training dataset. A Convolutional Neural Network (CNN) was used to train and predict on both pre- and post-augmentation data. The experimental results show that, before augmentation, the CNN model’s Receiver Operating Characteristic (ROC) value was 0.9648. After data augmentation with the WGAN-GP, the CNN model’s ROC value improved to 0.9792. Additionally, the CNN model’s classification performance was significantly enhanced, with the training set accuracy increasing by 5% and the test set accuracy improving by 2%, successfully overcoming the issue of insufficient model generalization caused by small sample sizes. The mineralization prediction results based on data augmentation delineate five prospective mineralization targets, whose spatial distribution exhibits strong correlations with known deposits and fault structural belts, confirming the reliability of the predictions. This study validates the effectiveness of data augmentation techniques in MPM and provides a transferable technical framework for MPM in data-scarce regions.

As a critical ecological security barrier in the Indo-China Peninsula, the Lao People’s Democratic Republic (Lao PDR) is increasingly threatened by forest degradation, frequent geological hazards, and intensified anthropogenic disturbances. To address the urgent need for a scientific evaluation of eco-geological environmental quality, this study develops a comprehensive assessment framework integrating multi-source remote sensing imagery, geological maps, and socio-economic datasets. A total of ten indicators were selected across four dimensions—geology, topography, ecology, and human activity. A stacking ensemble learning model was constructed by combining seven heterogeneous base classifiers—AdaBoost, KNN, Gradient Boosting, Random Forest, SVC, MLP, and XGBoost—with a logistic regression meta-learner. Model interpretability was enhanced using SHAP values to quantify the contribution of each input variable. The stacking model outperformed all individual models, achieving an accuracy of 91.14%, an F1 score of 93.62%, and an AUC of 95.05%. NDVI, GDP, and slope were identified as the most influential factors: vegetation coverage showed a strong positive relationship with environmental quality, while economic development intensity and steep terrain were associated with degradation. Spatial zoning results indicate that high-quality eco-geological zones are concentrated in the low-disturbance plains of the northeast and southeast, whereas vulnerable areas are primarily distributed around the Vientiane metropolitan region and tectonically active mountainous zones. This study offers a robust and interpretable methodological approach to support ecological diagnosis, zonal management, and sustainable development in tropical mountainous regions.

Exploration geochemical data are typically collected and analyzed according to standard map sheets. Different map sheets may be tested by different companies, at different times, or using different instruments. As a result, “systematic errors” inevitably arise, which are directly reflected in the “shift” effect between different map sheets. This study compares various leveling methods, including contrast return (CR), boundary leveling (BL), and multi-scale correction (MSC), based on compositional data transformation of six map sheets from the Baiyinchagan–Maodeng area. The results show the following features: the raw data from multiple map sheets contain certain errors, and these raw data cannot be directly used to create geochemical maps; the CR method is unsuitable for leveling in areas with small scales or significant geological background differences; the BL method yields more reasonable results when there is a similar geochemical background (geological background) between map sheets, and it is better suited for leveling between map sheets in areas with small scales or significant regional differences in geochemical backgrounds; finally, the MSC method yields results similar to the BL method, but it does not require boundary consistency, thus having fewer limitations, although it requires multi-scale geochemical data. In practical terms, this study provides valuable guidance for selecting appropriate geochemical data leveling methods in exploration projects, thereby improving the accuracy and reliability of geochemical mapping and enhancing the effectiveness of mineral exploration.

The efficacy of data-driven automatic target recognition (ATR) algorithms relies on the prior knowledge acquired from the target sample set. However, the lack of knowledge of high-value unknown target samples hinders the practical application of existing ATR models, as the acquisition of this SAR imagery is often challenging. In this paper, we propose an out-of-distribution knowledge inference-based approach for the implementation of open-set-recognition tasks in SAR imagery. The proposed method integrates two modules: out-of-distribution feature inference and a knowledge-sharing retrain mechanism. First, the proposed out-of-distribution feature inference module aims to provide the requisite prior knowledge for the ATR model to effectively recognize unknown target samples. Furthermore, the aforementioned module also employs a compact feature extraction scheme to mitigate the potential overlap between the constructed out-of-distribution feature distribution and the known sample feature distribution. Finally, the proposed method employs the novel knowledge-sharing retraining mechanism to learn prior knowledge of unknown SAR target samples. Several experimental results show the superiority of the proposed approach based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set. Some ablation experiments also demonstrate the role of each module of the proposed approach. Even when one category of target sample information is completely absent from the training set, the recognition accuracy of the proposed approach still achieves $90.31\%$.

Regarding the “step effect” issue in the geochemical data of the Baiyinchagan Dongshan-Maodeng area, this study aims to compare the leveling effects of the contrast return method and the boundary leveling method, and to evaluate the applicability of these methods in eliminating deviations between maps and improving data quality. The geochemical data of six sheets in the study area were preprocessed using compositional data transformation. The preprocessed data were then leveling processed using both the mean-based and median-based contrast return methods, as well as the boundary leveling method. The effectivenesses of these methods in eliminating step effect and improving data continuity were then compared. The results show that the step effect cannot be effectively eliminated by using both the mean-based and median-based contrast return methods, especially for data of areas with relatively significant geological background differences. In contrast, the step effects of geochemical data can be effectively eliminated using the boundary leveling method for processing, particularly for data of areas with consistent geological backgrounds, with the best performance of large-scale maps. The study confirms that the boundary leveling method is more effective than the contrast return method for addressing the step effect of geochemical data. This research provides an effective leveling approach for processing geochemical data of complex regions.