This study focuses on the ecological restoration of abandoned mines to develop an evaluation model and propose policy recommendations. The research highlights that while mining contributes to economic growth, it also brings numerous abandoned mines and associated environmental issues. Western countries initiated research on abandoned mines earlier, while China continues to explore various restoration approaches. This paper, adhering to the principles of scientific validity, employs the analytic hierarchy process (AHP) and entropy method to construct an evaluation indicator system. Seven indicators were selected, and their weights were determined using both methods to derive the combined weights. The results indicate that factors such as the water source conditions significantly influence the selection of restoration methods, with different approaches yielding varied evaluation scores. Based on this foundation, sustainable development strategies are proposed for development models regarding composite tourism development, geopark development, and ecological regreening. These strategies include enhancing resource utilization efficiency, strengthening ecological protection, and promoting the transformation of ecological value, etc. The aim is to align the rehabilitation of abandoned mines with the goal of sustainable development, offering a scientific basis and policy guidance for the ecological rehabilitation of mines while fostering the sustainable development of the region.

Selecting the most effective prediction model and correctly identifying the main disaster-driving factors in a specific region are the keys to addressing the challenges of geological hazards. Fuyuan County is a typical plateau mountainous town, and slope geological hazards occur frequently. Therefore, it is highly important to study the spatial distribution characteristics of hazards in this area, explore machine learning models that can be highly matched with the geological environment of the study area, and improve the accuracy and reliability of the slope geological hazard risk zoning map (SGHRZM). This paper proposes a hazard mapping research method based on multisource remote sensing data extraction and machine learning. In this study, we visualize the risk level of geological hazards in the study area according to 10 pathogenic factors. Moreover, the accuracy of the disaster point list was verified on the spot. The results show that the coupling model can maximize the respective advantages of the models used and has highest mapping accuracy, and the area under the curve (AUC) is 0.923. The random forest (RF) model was the leader in terms of which single model performed best, with an AUC of 0.909. The grid search algorithm (GSA) is an efficient parameter optimization technique that can be used as a preferred method to improve the accuracy of a model. The list of disaster points extracted from remote sensing images is highly reliable. The high-precision coupling model and the single model have good adaptability in the study area. The research results can provide not only scientific references for local government departments to carry out disaster management work but also technical support for relevant research in surrounding mountainous towns.

Xiangyun County is a typical mountainous county. At present, few people have studied geological hazards in Xiangyun County, so it is particularly important to choose appropriate methods for disaster assessment in the study area. (1) Research background: Xiangyun County is located in western Yunnan, China, where geological disasters such as landslides and collapses occur frequently. Not only endanger the safety of people's lives and property, but also destroy the ecological environment within the territory. (2) Methods: The distribution characteristics and influencing factors of geological hazards in Xiangyun County were studied and analyzed, and 9 influencing factors such as elevation, slope, slope direction, stratigraphic lithology, NDVI and rainfall were selected to evaluate the disaster susceptibility of the study area. Through the correlation analysis of evaluation factors, the evaluation system is constructed by combining the information model and the information—logistic regression model. Using ArcGIS software, the study was divided into 5 grades: extremely high, high, medium, low and extremely low prone areas. (3) Results: ROC curve was used to test the evaluation results of the two models respectively. The accuracy of the information model was 74%, and the accuracy of the coupling model was 83%. Extremely high and high-risk areas account for 18% and 24% of the total area, respectively. (4) Conclusion: The results show that the coupled model test has a high precision and can provide a reliable basis for this evaluation.