Application of Partial Least Squares-Discriminate Analysis Model Based on Water Chemical Compositions in Identifying Water Inrush Sources from Multiple Aquifers in Mines

Mine water inrush seriously threatens the safety of coal mine production. Quick and accurate identification of mine water inrush sources is of great significance to preventing mine water hazards. This paper combined partial least squares-discriminate analysis (PLS-DA) with inrush water chemical composition to identify the source of water inrush from multiple aquifers in mines. The Renlou Coal Mine in the Linhuan mining area was selected for this study, and seven conventional water chemical compositions from 54 water samples in three aquifers were collected and tested, of which 45 water samples were used to establish the PLS-DA discriminant model, and nine were used to test the prediction effect. To improve model accuracy and predictive ability, hierarchical clustering analysis method was used to eliminate seven unqualified water samples to reduce the errors caused by improper data. PCA and PLS-DA methods were used to analyze and process the remaining water sample data, and on the basis of PCA analysis, the remaining 38 water samples were used to establish the PLS-DA discriminant model. The model was validated using permutation and external prediction tests. The research shows the following results: (1) Both PCA and PLS-DA methods can distinguish water samples from three different water sources, but the classification effect of PLS-DA was better than PCA because it can strengthen the difference of water chemical composition between different water sources. (2) The correct discrimination rate of the PLS-DA discriminant model was as high as 100%, and permutation tests showed that the model was not overfit. External validation found that the model had good stability and discrimination. (3) HCO3- and total dissolved solids (TDS) were the most important differential marker compositions that affected the discrimination results based on Variable Importance for the Projection (VIP) scores. The discriminant model established in this study combined the advantages of principal component analysis and multiple regression analysis, providing a new method for accurately identifying the sources of water inrush in mines.

A Simultaneous Model for Simulating the Propagation of Hydraulic Head in Aquifers with Leakage Pathways

A three-dimensional simultaneous solution model was developed for analysis of variable transient flows, specifically leakage associated with arbitrary groundwater aquifers. The model simultaneously calculates leakage rates using the hydraulic gradients between coupled leakage points at two leaky aquifers and evaluates the propagation of hydraulic heads in multiple aquifers resulting from that leakage. Important considerations for leakage simulation are variant leakage rates with time and leakage starting time. Two types of leakage pathways are specified in terms of the generated time, including (1) pre-existing leakage pathways and (2) abruptly-induced leakage pathways at specific times. The governing equation with a leakage term is composed of three finite difference equations, and its form depends on whether leakage pathways pre-exist or are induced at specified times according to known or assumed aquifer histories. The developed numerical code was validated by comparison with the results of the TOUGH2/EOS1 program for a three-dimensional conceptual domain.