Mining-induced geo-hazard mapping (MGM) is a critical step for reducing and avoiding tremendous losses of human life, mine production, and property that are caused by ore mining. Due to the restriction of the survey techniques and data sources, high-resolution MGM remains a big challenge. To overcome this problem, in this research, such an MGM was conducted using detailed geological exploration and topographic survey data as well as Gaofen-1 satellite imagery as multi-source geoscience datasets and machine learning technique taking Liaojiaping Orefield, Central China as an example. First, using Gaofen-1 panchromatic and multispectral (PMS) sensor data and Random Forest (RF) non-parametric ensemble classifier, a seven-class land cover map was generated for the study area with an overall accuracy (OA) and Kappa coefficient (KC) of 99.69% and 98.37%, respectively. Next, several environmental drivers including land cover, topography (aspect and slope), lithology, distance from fault, elevation difference between surface and underground excavation, and the difference of spectral information from PMS multispectral data of different years were integrated as predictors to construct an RF-based MGM model. The constructed model showed an excellent prediction performance, with an OA of 98.53%, KC of 97.06%, and AUC of 0.998, and the 85.60% of the observed geo-disaster that have occurred in the predicted high susceptibility class (encompassing 2.82% of the study area). The results suggested that the changes in environmental factors in the high susceptibility areas can be used as indicators for monitoring and early-warning of the geo-disaster occurrence.

It is important to analyze the trend in land use changes and assess the suitability of resource development for protecting natural resources, developing ecological industries, and land use planning issues. Ruijin City is located in South Jiangxi and has abundant resources for red tourism development. By analyzing the landscape changes in land use and the spatial distribution characteristics of local red culture resources, a supervised machine learning-based prediction model was constructed to quantitatively assess the suitability of red tourism development in a geographic information system (GIS) and the R language environment using geographical, economical, and human-related datasets. The results revealed that: (i) the increasing of human activities and economic vitality provide a beneficial social environment for the development of tourism resources; (ii) highly concentrated red resources, or those with special significance, are conducive to developing red tourism resources; (iii) preferentially, central–eastern Ruijin was followed by the extension areas to peripheral towns, which are potentially suitable areas for the development of red scenic spots. Generally, the findings of this study were consistent with the conventional cognitions and lessons on tourism development, and the constructed evaluation system is expected to be promoted to similar research.

Creeping landslides constitute the predominant form of long-term, slow-moving geohazards in high mountain gorge regions. Under the combined influence of gravity and external triggering factors, these landslides undergo persistent deformation, posing continuous threats to major transportation corridors, hydropower infrastructures, and nearby settlements. Li County is located within the active tectonic belt along the eastern margin of the Tibetan Plateau, characterized by highly variable topography, intensely fractured rock masses, and dense development of creeping landslides. The slip surfaces are typically deeply buried and concealed. Consequently, conventional drilling and profile-based investigations, limited by high costs, sparse sampling points, and poor spatial continuity, are insufficient for identifying the deep-seated structures of such landslides. To address this challenge, this study applies Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) to obtain ascending and descending deformation rate fields for 2022–2024, revealing pronounced spatial heterogeneity and persistent activity across three types of landslides. Based on the principle of mass conservation, the sliding-surface depths of eight typical landslides were inverted, revealing pronounced heterogeneity. The maximum sliding-surface depths range from 32 to 98 m and show strong agreement with borehole and profile data (R² > 0.92; RMSE ±4.96–±16.56 m), confirming the reliability of the inversion method. The GeoDetector model was used to quantitatively evaluate the dominant factors controlling landslide depth. Elevation was identified as the primary control factor, while slope aspect exhibited significant influence in several landslides. All factor combinations showed either “bi-factor enhancement” or “nonlinear enhancement”, indicating that slip-surface depth is governed by synergistic interactions among multiple factors. Boxplot-based statistical analyses further revealed three typical patterns of slip-surface variation with elevation and slope, based on which the landslides were classified into rotational, push-type translational, and traction-type translational categories. By integrating statistical patterns with mechanical models, the study achieves a transition from “form” to “state”, enabling inference of the internal mechanical conditions and evolutionary stages from the observed surface morphology. The results of this study provide an effective technical approach for deep structural detection, identification of controlling factors, and stability evaluation of creeping landslides in high mountain gorge environments.

Soil heavy metal contamination in mining areas poses a serious environmental challenge, requiring monitoring approaches with both wide coverage and high accuracy. Hyperspectral remote sensing provides an effective solution, yet its performance in complex mining environments is often limited by mixed-pixel effects and nonlinear spectral responses. To address these issues, this study proposes a Physically-Constrained Collaborative Endmember Extraction (PCCEE) framework that integrates spectral unmixing with machine learning for multi-element inversion. Using Gaofen-5 hyperspectral imagery, a collaborative workflow combining Pixel Purity Index (PPI), Vertex Component Analysis (VCA), and prior-spectral-constrained Spectral Angle Mapper (SAM) was developed to improve endmember purity and physical interpretability. Among three unmixing models (LMM, NMF, and SVR), the Linear Mixing Model achieved the best balance between accuracy and efficiency. Random Forest regression using retrieved abundances enabled high-accuracy inversion of eight heavy metals (mean R² = 0.85). Spatial analysis revealed significant co-enrichment of Pb, Cd, and Zn related to sulfide weathering, while PCA distinguished compound and independent pollution sources. The proposed PCCEE framework effectively mitigates mixed-pixel interference and provides a transferable approach for heavy metal monitoring and risk assessment in complex mining environments.

The remote sensing classification of urban functional zones provides scientific support for urban planning, land resource optimization, and ecological environment protection. However, urban functional zone classification encounters significant challenges in accuracy and efficiency due to complicated image structures, ambiguous critical features, and high computational complexity. To tackle these challenges, this work proposes a novel XT-SECA algorithm employing a strengthened efficient channel attention mechanism (SECA) to integrate the feature-extraction XGBoost branch and the feature-enhancement Transformer feedforward branch. The SECA optimizes the feature-fusion process through dynamic pooling and adaptive convolution kernel strategies, reducing feature confusion between various functional zones. XT-SECA is characterized by sufficient learning of complex image structures, effective representation of significant features, and efficient computational performance. The Futian, Luohu, and Nanshan districts in Shenzhen City are selected to conduct urban functional zone classification by XT-SECA, and they feature administrative management, technological innovation, and commercial finance functions, respectively. XT-SECA can effectively distinguish diverse functional zones such as residential zones and public management and service zones, which are easily confused by current mainstream algorithms. Compared with the commonly adopted algorithms for urban functional zone classification, including Random Forest (RF), Long Short-Term Memory (LSTM) network, and Multi-Layer Perceptron (MLP), XT-SECA demonstrates significant advantages in terms of overall accuracy, precision, recall, F1-score, and Kappa coefficient, with an accuracy enhancement of 3.78%, 42.86%, and 44.17%, respectively. The Kappa coefficient is increased by 4.53%, 51.28%, and 52.73%, respectively.