To study the evolution of geological hazard sources of waste dump slopes under rainfall conditions, a physical model of a rainfall-affected slope was designed. The apparent resistivity of the slope rock and soil mass at different rainfall times was measured via the high-density resistivity method, and the formation process of internal disaster sources of the rainfall-affected slope was obtained. The variation characteristics of the resistivity of the rain-affected slope were analyzed when it had a weak surface and crack development. Based on the three-water model and Maxwell conductivity formula, the evolution process of geological hazard sources of the rainfall-affected slope was summarized. A resistivity response mechanism equation for rainfall-induced slope hazard sources was derived and compared to the Archie formula, verifying the model rationality. The test results showed that the behavior of the rainfall-affected slope conforms to the saturated–unsaturated dynamic cycle process. The apparent resistivity was positively correlated with the development of slope pores and cracks and negatively correlated with the water content in the slope. The apparent resistivity increased during fracture development and decreased during water seepage. In the slope failure and disaster process, the apparent resistivity varies under the coupling effect of crack development and water seepage. During the formation of geological hazard sources, the apparent resistivity abruptly changes and fluctuates. Therefore, according to the abrupt changes and abnormal fluctuations in the apparent resistivity detected, the development of geological hazard sources of slopes can be determined.

In view of the complexity of mine water inflow data analysis and the uncertainty of prediction and prediction and other key issues, according to the data characteristics of metal mine water inflow, a method of mine water inflow analysis and prediction based on EEMD PSO-ELM-LSTM is proposed by applying the phase space reconstruction idea and the fusion modeling concept. Taking the monthly average water inflow of JIAOJIA Gold Mine in China from January 2014 to October 2021 as an example. Firstly, the Ensemble Empirical Mode Decomposition (EEMD) is used to decompose the measured data series of mine water inflow into trend components, seasonal components, and remainder components, and the remainder components are treated as noise and removed; Subsequently, based on the data characteristics of the decomposed component data, the PSO-ELM algorithm is selected to analyze and predict the seasonal components of water inflow, and the LSTM model is applied to analyze and predict the trend components of water inflow; Finally, the analysis and prediction results of the two are superimposed and reconstructed to obtain the final analysis and prediction results. In addition, comparative predictions were made using EEMD PSO-ELM-LSTM, LSTM, and EEMD LSTM. Compared with the independent prediction models LSTM and EEMD LSTM, the Root Mean Square Error (RMSE) of the EEMD PSO-ELM-LSTM algorithm proposed in this paper has been reduced by 248.04 and 76.27, respectively; Mean Square Error (MSE) decreased by 0.047 and 0.011, respectively; At the same time, the Nash-Sutcliffe efficiency coefficient (NSE) of the model proposed in this article is closer to 1. In summary, the EEMD PSO-ELM-LSTM mine water inflow analysis and prediction method has certain reliability and superiority, which helps to promote accurate prediction of average mine water inflow and reduce the occurrence of water inrush accidents in metal mines.

Water inrush accidents in metal mines are prone to occur during the construction and production process of mines, which can cause serious casualties and property losses. The prevention of accidents in metal mines is closely related to geophysics. In order to solve the problem of accurately monitoring water permeability, the resistivity method was proposed to effectively monitor water rich fault zones in metal mines. The typical metal mine and water rich fracture zone model are simulated by ANSYS. The calculated resistance data are processed by inversion image processing and compared with the original model; The inversion image clearly shows the abnormal area of the water fracture zone and the location is relatively accurate, which verifies the reliability of the numerical simulation method and the resistivity theory. At the same time, the response characteristics of water rich fracture zone of metal ore under different water content and different development distance are studied by using numerical simulation method. The results show that the resistivity measured by electrical method decreases with the increase of water content in the water rich fracture zone, and the resolution of low resistivity anomaly is strong. When the measuring node of high-density electrical method is inside the water rich fracture zone, the resistivity change curve tends to be a straight line; When the measuring node of high-density electrical method is not near the water rich fracture zone, the resistivity change line tends to curve. In addition, with the expansion and development of the water rich fracture zone, the electrical resistance at the measuring node decreases; When the water rich fracture zone is about to develop and reach the measuring node, the measured resistance value has an abnormal mutation. This paper reveals the characteristics of resistivity and pervious precursor response through numerical tests, and clarifies that resistivity decline and abnormal mutation are important pervious precursor information, which has important reference significance for the monitoring and prediction of pervious disasters in practical projects.