The low-grade bauxite in southern Shanxi Province, China is enriched in multiple critical metal elements, including Li, Ga, V, Se, and rare earth elements (REEs), which have reached the standard of comprehensive utilization as independent deposits or associated resources. Even more importantly, identifying the modes of occurrence of these critical elements is essential for designing technologies to extract critical metals from bauxite ores. This study used a combination of direct (X-ray diffraction, scanning electron microscopy–energy dispersive X-ray spectroscopy, and micro-X-ray fluorescence spectrometer), and indirect (size sieving method, float-sink experiment, and correlation analysis) methods to effectively reveal the distribution of critical elements in the different identified mineral phases. The results regarding the low-grade bauxite are as follows: Li was mainly hosted in cookeite as an independent mineral; Ga was mainly associated with diaspore; anatase is the main carrier mineral for V; REEs were present in the low-grade bauxite in multiples modes of occurrence, the most common of which were goyazite, and to a lesser extent, florencite; Se primarily occurs in sulfides. This study contributes to the development and utilization of these essential metal resources in bauxite by providing a useful reference.

Through the stability evaluation of a slope, a landslide geological disaster can be identified, and the safety and risk control of a project can be ensured. This work proposes an improved sparrow search algorithm to optimize the slope safety factor prediction model (ISSA–BP) of a BP neural network, through an improvement in two aspects: introducing dynamic weight factors and reverse learning strategies to realize adaptive searches. The optimal value improves a defect in the traditional model, preventing it from easily falling into the local minimum. First, combined with 352 sets of actual slope data, three machine learning models were used to predict the safety factor of the slope. Then, the accuracy index was used for evaluation. Compared with other models, the MAPE, RMSE, and R² of the ISSA-BP model were 1.64%, 0.0296, and 0.99, respectively, and the error was reduced by 78% compared with the BP neural network, showing better accuracy. Finally, the three models were applied to the slope stability analysis of Tianbao Port in Wenshan Prefecture. The research shows that the predicted value of the ISSA–BP model was the closest to the actual safety factor, which verified the experimental results. The improved ISSA–BP model can effectively predict the safety factor of slopes under different conditions, and it provides a new technology for slope disaster warning and control.