Landslide susceptibility assessment is crucial for the disaster mitigation in mountainous regions; however, traditional models often have limited generalization on small-sample datasets, and linear approaches struggle to capture the complex interactions among influencing factors. This study introduces the TabPFN machine learning model, which, with its hyperparameter-free nature and strong generalization advantage under small-sample conditions, provides a novel approach for overcoming the modeling bottlenecks. Taking Huangshan City as the study area, based on 736 landslide points, an equal number of non-landslide samples were selected from areas beyond 1 km of these points to construct a balanced dataset with a 1:1 ratio of positive to negative samples,this research establishes a landslide susceptibility indicator system by systematically selecting 14 evaluation factors across four categories: topography, geology, hydrology, and human activity. Building upon this foundation,The study introduces the TabPFN model for landslide susceptibility evaluation, and employs SHAP to analyze the underlying driving mechanisms. The results show that, compared with baseline models, TabPFN achieves the best overall performance in terms of accuracy (0.903), precision (0.965), recall (0.841), F1-score (0.899), and AUC (0.964), demonstrating stronger generalization capability and advantages in modeling complex relationships. Furthermore, SHAP analysis reveals that distance to roads, NDVI, and lithology are the primary driving factors influencing the spatial distribution of landslides, reflecting the fundamental pattern wherein human disturbance, vegetation cover, and geological conditions collectively govern landslide development, Specifically, landslide susceptibility increases significantly in areas proximal to roads, reflecting the prominent disturbance of human engineering activities on slope stability. Higher vegetation coverage exerts a notable inhibitory effect on landslide occurrence, while landslide sensitivity varies markedly across different lithological conditions, underscoring the fundamental controlling role of the geological setting. This study integrates the TabPFN machine learning model with SHAP-based interpretability to achieve both high-accuracy prediction and interpretability analysis of landslide susceptibility, It overcomes the shortcomings of traditional "black box" models in revealing the mechanisms of disaster formation, providing a technical pathway for landslide risk assessment in mountainous cities that ensures both precision and explanatory insight.

In the field of modeling the susceptibility of county-level earthquake-induced landslides, comparative analysis research on ensemble learning models is still insufficient. This study takes Luding County as an example, where detailed information on 502 landslide events was collected based on historical records, remote sensing data, and field surveys to construct a sample database. Twelve key influencing factors were selected, including digital elevation model (DEM), slope, aspect, profile curvature, plan curvature, topographic position index, lithology, and the distances to roads, faults, rivers, and seismic sources, as well as land use. After conducting collinearity tests on these factors, the Bayesian optimization method was used to optimize ensemble learning models such as AdaBoost, GBDT, XGBoost, LightGBM, and CatBoost, thereby constructing a landslide susceptibility assessment system. The accuracy and predictive precision of each model were evaluated through ROC curves and frequency ratio comparison. The results show that after Bayesian optimization, the performance of all models was significantly improved, with the BO-GBDT model's AUC value increasing by 7.4%. Frequency ratio analysis further indicated that the BO-XGBoost model had the strongest identification capability at high susceptibility levels, with a frequency ratio of 13.73, demonstrating its superior risk area identification capability. Although the BO-GBDT model had a slight advantage in AUC value (0.974), its frequency ratio at high susceptibility levels was only 10.14. Therefore, the selected BO-XGBoost model reveals that high-susceptibility areas are mainly concentrated along the Dadu River and its nearby towns and transportation routes, while the landslide susceptibility in the eastern mountainous area is relatively low, providing important guidance for future research and disaster prevention and mitigation efforts.

Surface waves in seismic exploration data provide crucial information about the near surface overburden structure. However, the surface wave energy is distributed in each mode, it is not accurate to discriminate the surface wave mode based on dispersive energy, so the conventional multi-mode surface wave inversion has the problem of mode misidentification, which affects the accuracy of near-surface structure inversion. In this paper, the modes of dispersion curves involved in inversion are determined on the based Kuhn-Munkres pattern searches algorithm, the algorithm is also applied to process and inverse actual seismic surface waves, and the underground velocity structure is established by the inversion based on accurately determining the order of higher-mode dispersion curves. Firstly, the traditional algorithm is utilized to invert the single fundamental mode dispersion curve to obtain a preliminary model. Then, the preliminary model and a weighted bipartite graph of phase velocities with no-explicitly-specified-mode at each frequency is established. The phase velocities of different modes are optimally matched by the Kuhn-Munkres algorithm, and then the mode discrimination and joint inversion with higher-order surface wave dispersion curves are implemented. The effectiveness of this algorithm is verified by three typical theoretical stratigraphic model examples, finally, two sets of actual data are processed to obtain the near-surface one-dimensional shear-wave velocity structure and two-dimensional profile of the relevant study area. The results demonstrate that the algorithm effectively solves the problem of mode misidentification in surface wave multi-mode dispersion curve inversion.

In the field of geophysical oil and gas exploration, the velocity of seismic wave is regarded as one of the key parameters to distinguish underground media. Full Waveform Inversion (FWI) is a popular geophysical imaging technique in which a high-resolution subsurface velocity model is learned by first giving an initial velocity model and then minimizing the deviation between the simulated seismic record generated by the velocity model and the actual observed seismic record through an iterative process. The initialization of accurate velocity model is a prerequisite for the realization of full waveform inversion imaging, which is strongly dependent on the initial velocity model. When there is a big difference between the initial velocity model and the real model, the matching between the theoretical wave field and the observed wave field is easy to produce the phenomenon of period hopping. This paper proposes a full-waveform inversion model (FWI with initial velocity learnable by neural network, FWI_IVLNN)based on generative adversarial networks that can learn initial velocity parameters. It learns initial velocity parameters through neural networks and integrates stochastic velocity to generate velocity models. Based on generative adversarial idea, the velocity model is inversion, the simulated seismic record is generated by physics generator, the simulated record and the observation record are discriminated by discriminator, and the initial velocity model and network parameters are learned by unsupervised mode. The gradient returned by the network is transmitted to both the neural network and the physical generator, and the data-driven and model-driven velocity model inversion is realized with the help of the gradient. Quantitative and qualitative experiments show that FWI_IVLNN is less dependent on the initial velocity model, and the accuracy of velocity model inversion is higher.

To achieve refined inversion outcomes of TEM and enhance the precision of geological problem interpretation, conducting research on inversions under different initial models holds substantial significance. This study selected two distinct initial models: the homogeneous half-space model and the model derived from the inversion result of the least-squares method with a smoothing factor. Initially, the forward-response data of a three-layer geoelectric model (H-type and K-type) were utilized to conduct inversion computations via the least-squares method with a smoothing factor and the regularization-damped least squares method under different initial models. The inversion performances under various initial models were then compared and analyzed. Subsequently, field - measured data were employed to perform inversion calculations identical to those of the forward - fitting data. The normalized potential of the secondary field at a single point with different decay times, resistivity, the result model, and their corresponding errors were selected for comparative analysis. Additionally, the inversion effect of a complete apparent-resistivity profile was analyzed in conjunction with geological data. Finally, the research findings were validated through engineering cases. The results show that: The inversion of the least - squares method with a smoothing factor is poorly fitted with transient electromagnetic data. Under equivalent conditions, although the regularization-damped least squares method can more realistically reflect the stratal characteristics, its depiction of deep - stratum information is less accurate compared to when the initial model is the inversion - result model of the least - squares method with a smoothing factor. The inversion result of the regularization-damped least-squares method, with the inversion result of the least-squares method with a smoothing factor serving as the initial model, provides a more precise reflection of the underground geological conditions. The choice of different initial models exerts a remarkable influence on the inversion effect of TEM data. Through comparative analysis, it is further verified that the inversion of the regularization-damped least-squares method, with the inversion result of the least-squares method with a smoothing factor as the initial model, enjoys significant advantages in terms of accuracy and reliability. This conclusion offers crucial references and practical guidance for the application of the TEM in detecting complex geoelectric structure.

Located in the Augaro-Adobha metallogenic belt in the Nubian terrane, the Kerkebet exploration area shows superior metallogenic conditions in Eritrea. Recent years, major breakthroughs have been made in this exploration area, and the Mier medium-sized gold deposit has been found and evaluated. It is also found by field investigation that many target areas (e.g., Shukula, Locotat, Yasiney, Koken et al.) in this area show great gold polymetallic prospecting potential, and the mineralization is obviously controlled by geological-tectonic evolution. However, due to the limitation of previous basic geological survey and comprehensive researches, this region has not yet carried out systematic studies on geological-tectonic evolution, which seriously restricts the prospecting exploration and theoretical guidance. Based on this, after systematically sorting out the existing data of this region, this paper adopts the "multi-island-arc-basin system" tectonic theory to re-divide the previous Nakfa terrane into three new tectonic units (Barka magmatic arc, Kerkebet subduction accretionary complex, and Nakfa magmatic arc), among which the Kerkebet subduction accretionary complex was further divided into three second tectonic units, and reveals the relationship between tectonic evolution stages and different gold deposit types of the Kerkebet subduction accretion complex belt, combined with field investigations and researches. We also construct the tectonic-stratigraphic framework of this region, based on the fact that different tectonic units correspond to similar or different rock groups/segments. According to the fact that specific deposits have the characteristics of reflecting the temporal-spatial specificity of the tectonic environment, we also constructed the tectonic-mineralization model based on regional deposit types and distribution. These researches will not only provide the basis for deepening the theory of regional tectonics-metallogenesis, but also point out the directions for the next prospecting and exploration practice at Kerkebet.

The Jussiape Complex developed in Gaviao Block of Sao Francisco Craton is composed by Jussiape Ⅰ granite and Jussiape Ⅱ syenogranite with intrusion ages of 2 121 Ma and 2 052 Ma respectively. In order to determination the intrusive age and petrological characteristics of the Jussiape Complex, and discuss the significance to regional magmatic activity, tectonic setting, and mineralization,petrology,zircon U−Pb isotope chronology, and Lu−Hf isotope studies of the jussiape granite are carried out. Finally, a group of mesoarchean monzogranite intrusions with zircon U−Pb isotopic age of (3108±22) Ma were identified in the jussiape Ⅰ granite. Petrogeochemical date show that, the samples SiO₂ content is 72.23%–72.50%, Al₂O₃ content is 14.68%–15.09%, TiO₂ content is 0.24%, Na₂O content ranges from 5.29%–5.26%,K₂O content is less than 2% with K₂O/Na₂O value is 0.29, the average value of TFeO+MgO is 2.42%. The samples exhibit depletion in Nb, Ta, P, Ti, Sr, and compatible elements such as Ni and Cr, the Hf−Rb−Ta diagram shows a collision tectonic granite feature; The rare earth element distribution curve shows a relatively gentle right tilt type and the La/Yb ratio is greater than 15, with enrichment of LREE and negative Ce andEu anomalies. Lu−Hf isotope analysis show that the ε_Hf (t) value range from −18.31 to −0.53 and the value of T_DM2 is 3 523–4 063 Ma,indicating that the Jussiape monzogranite originated from the recycling of ancient crustal materials and controlled by the Barra do Mendes−Joao Correa lineament which is responding to the magmatic arc activity in the west of the southern part of the Gaviao Block.It is consistent with the subduction and collisional orogeny tectonic background that briefly existed in the southern part of the Gaviao Block during the Mesoarchean. The Barra do Mendes−Joao Correa lineament reactivated during the period of 2.1–1.9 Ga, forming a series of granite bodies such as Jussiape Ⅰ granite,Jussiape Ⅱ syenogranite and Ibitiara granodiorite that spread in a NNW direction.It is the most important structral−magmatic−metallogenetic belt in the region and has potential for IOCG-type deposits.

Bolivia is located at the junction of the Antarctic Plate and the American Plate, situated at the intersection of two major tectonic units, the Andes and the Amazonia craton. It has experienced a long and complex geological evolution process and has been significantly influenced by the Andean orogeny. The stratigraphy of Bolivia is well-developed from the Archean to the Cenozoic, with Cenozoic magmatic activity being closely related to the formation of metal mineral deposits in Bolivia. Bolivia is rich in mineral resources, with iron, lead, zinc, tungsten, tin, bismuth, antimony, silver, lithium, and other minerals being the dominant ones. It holds an important position globally and is a world-renowned mineral-rich country and traditional exporter of mineral products. Historically, it was known as the "Republic of Mining." Due to natural conditions, political situations, and mining policies, the overall geological work level in Bolivia is relatively low, with significant differences in work levels among different regions. The degree of mineral resource development is far behind that of neighboring countries such as Brazil, Peru, and Chile. Therefore, Bolivia is considered one of the most prospective countries for exploration in the world today. In recent years, the Bolivian government has issued new decrees, implemented tax reforms, and abolished the value-added tax on the import of capital goods, industrial plants, machinery, and equipment to attract foreign mining companies to invest and cooperate in Bolivia, thereby increasing the added value of Bolivian mineral exports. This paper introduces the geological and mineral resources overview of Bolivia, with a focus on interpreting the mining regulations and other documents issued since 2014. Four mining investment suggestions are proposed: First, it is necessary to study the geological background and mineralization laws of Bolivia to prepare for entering the Bolivian mining market. Second, systematic exploration preparations should be made to conduct regional or small-scale mineral rights resource exploration work together with Bolivia and to refine and correct existing data. Third, respect for the indigenous people and environmental organizations of Bolivia is essential. While exploiting resources, efforts should be made to promote the development of surrounding communities and gain public recognition. Fourth, professional legal teams should be hired to conduct due diligence and establish flexible exit mechanisms.

Peru is extremely rich in copper resources, with both its reserves and production ranking second globally. It is one of the world’s most significant regions for copper exploration and development and serves as a major source of copper imports for China. The porphyry copper deposits are the dominant deposit type in Peru and the primary target of exploration and development activities. Peru has discovered 12 large copper mines, and its copper reserves and resource increments are among the highest in the world. Copper exploration and development in Peru are predominantly led by European, American, and local Peruvian mining companies. Peru's copper production has steadily increased, and its production costs are globally competitive. China is the largest importer of Peruvian copper, with Chinese companies actively participating in the exploration and development of peru’s copper resources. This paper systematically sorts out the copper resource endowment, exploration and development status, and potential in Peru. It also analyzes the opportunities and risks associated with copper-related cooperation. There are significant risks and challenges, such as strikes and community issues, that are commonly encountered in the process of copper investment cooperation in Peru especially for Chinese companies. This paper concludes by offering policy and strategic recommendations for Chinese companies seeking to participate in copper resource exploration and development activities in Peru.

The magmatic-hydrothermal evolution during the differentiation of granitic magma is a key stage to the formation of magmatic pegmatites and related rare-metal mineralization. However, the controlling factors during this process are still unclear. Numerous Paleozoic felsic plutons and rare-metal-mineralized granitic pegmatites occur in the East Qinling tectonic belt, and their genetic relationship has attracted much attention. In order to examine the magmatic-hydrothermal evolution at the late stage of the felsic plutons and shed light on the formation of rare-metal mineralization in East Qinling, we carried out comprehensive analyses on in situ major and trace elements for tourmaline from the Piaochi pluton, the largest S-type granite in East Qinling. Tourmaline from the Piaochi pluton can be divided into four types, i.e., disseminated tourmaline (Tur-D), quartz-tourmaline nodules (Tur-N), tourmaline-quartz veins (Tur-V), and tourmaline along schistosity (Tur-d). The substitution of major elements of Tur-N and Tur-V tourmalines is mainly controlled by (Na, Mg) (X_vac, Al)_-1 and (Mg, OH) (Al,O)_-1, instead of Fe³⁺Al_–1 substitution. This indicates that the hydrothermal fluids of the Piaochi pluton are in a reducing environment with medium-high salinity content. Based on the occurrence and composition of Tur-D tourmaline, it can be further divided into Tur-D1 and Tur-D2. Tur-D1 is schorlite with a considerable amount of Al in the Y-site, indicating that they crystallize at an early stage of magma cooling. In contrast, Tur-D2 is dravite and replaces Tur-D1 in local places with Tur-D1 tourmaline inclusions, possibly due to the interaction with external fluids at a late stage. Tur-N tourmaline can be further divided into Tur-N1 and Tur-N2. Tur-N1 is schorlite with high Fe, Sn, Nb, Ta, and Zn and low Mg, V, and Sr, and crystallizes from immiscible aqueous boron-rich fluids at the late stage of magma differentiation. Tur-N2 and Tur-V tourmaline have similar compositions, varying from schorlite to dravite, with higher Mg, V, Sr, and Pd compared to Tur-N1. This suggests the influence of the external fluids from country rocks on the composition of magmatic-hydrothermal evolution of the Piaochi pluton. Tur-d tourmaline (dravite) is closely related to biotite, with magnetite occurring along its rims and fractures, indicating that the metasomatism of biotite by boron-rich fluids. Additionally, the high Nb and Ta concentrations of Tur-N1 tourmaline suggest a transient Nb-Ta enrichment on cooling of the Piaochi pluton. Nevertheless, the reduced condition and intensive interaction with country rocks may impede the Nb-Ta mineralization at a late stage of cooling. Therefore, rare metals would be enriched by the felsic melt differentiation and the exsolution of immiscible fluid during the magmatic-hydrothermal stage. However, the potential of rare-metal mineralization is mainly controlled by the redox condition of the fluids and the interaction with wall-rocks.