Source identification of mine water inrush based on principal component analysis and grey situation decision

Ju, Qiding; Hu, Youbiao

doi:10.1007/s12665-021-09459-z

Cited by 27 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Principal component analysis (PCA) was widely used as a multivariate statistical and exploratory analysis methodology to interpret many-variable data matrix. PCA is widely used to explain the processes which influence groundwater quality by examining chemical associations defined by one or more variable loadings on factors (Chen and Jiao 2007;Souid et al 2018;Bi et al 2021;Zakhem et al 2017;Shirnezhad et al 2020;Ju and Hu 2021). The PCA is based on the reduction of large variables in the initial matrix and the construction of new ones named components.…”

Section: Statistical Methodologiesmentioning

confidence: 99%

Geochemical processes of groundwater salinization in an arid area, southeastern Tunisia

et al. 2021

View full text Add to dashboard Cite

Salinization is an environmental issue that affects different regions worldwide. Geochemical approaches and statistical tools are combined to investigate the origin and process of groundwater salinization in Menzel Habib shallow aquifer. The inland aquifer from Menzel Habib area is in the northwest of Gabès, southeastern Tunisia. A total of twenty-five water samples were selected and collected in the study area. Physicochemical parameters (electrical conductivity, pH, total dissolved solids) were measured in situ, and major ions (Na, Mg, Ca, K, Cl, SO 4 , HCO 3 , F, and Br) were determined. The obtained results show a Na-Cl groundwater dominant facies (60%), Na-SO 4 (36%), and mixed water type (4%). Thus, a correlation between total dissolved solids and major ions shows the contribution of SO 4 , Cl, Na, Ca, and Mg in groundwater salinization. The salinization of groundwater is due to the dissolution of Triassic evaporites, which are related to the tectonic context of the region, and to the cationic exchange. Furthermore, statistical approaches, especially principal component analysis, reveal that the high groundwater mineralization is due to the evaporite dissolution. Multiple linear regression leads to establish a model linking total dissolved solids to the different chemical elements involved in groundwater salinization.Keyword Salinization . Groundwater . Geochemical approaches . Principal component analysis . Multiple linear regression .

show abstract

Section: Statistical Methodologiesmentioning

confidence: 99%

Geochemical processes of groundwater salinization in an arid area, southeastern Tunisia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Gas drainage borehole leakage data are multidimensional and multivariate 35 , 36 , with complex correlations. MDF theory was used to preprocess the data 37 .…”

Section: Model Applicationmentioning

confidence: 99%

Application of an improved naive Bayesian analysis for the identification of air leaks in boreholes in coal mines

Pan

Zhang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Borehole extraction is the basic method used for control of gases in coal mines. The quality of borehole sealing determines the effectiveness of gas extraction, and many influential factors result in different types of borehole leaks. To accurately identify the types of leaks from boreholes, characteristic parameters, such as gas concentration, flow rate and negative pressure, were selected, and new indexes were established to identify leaks. A model based on an improved naive Bayes framework was constructed for the first time in this study, and it was applied to analyse and identify boreholes in the 229 working face of the Xiashijie Coal Mine. Eight features related to single hole sealing sections were taken as parameters, and 144 training samples from 18 groups of real-time monitoring time series data and 96 test samples from 12 groups were selected to verify the accuracy and speed of the model. The results showed that the model eliminated strong correlations between the original characteristic parameters, and it successfully identified the leakage conditions and categories of 12 boreholes. The identification rate of the new model was 98.9%, and its response time was 0.0020 s. Compared with the single naive Bayes algorithm model, the identification rate was 31.8% better, and performance was 55% faster. The model developed in this study fills a gap in the use of algorithms to identify types of leaks in boreholes, provides a theoretical basis and accurate guidance for the evaluation of the quality of the sealing of boreholes and borehole repairs, and supports the improved use of boreholes to extract gases from coal mines.

show abstract

“…As seen from Table 12, thirty-two water samples of the aquifers were generally ranked from high to low according to the scores. It means that the principal sources of mine water inrushes caused by exploiting the No.2 1 coal seams of the Shanxi group in the Jiaozuo mining area are the roof sandstone aquifers [60][61][62][63][64][65][66][67][68][69][70], followed by the floor limestone aquifers and the hydrated layer of the quaternary system [71][72][73][74][75][76][77][78][79]. In order to further illustrate the situation of mine water inrushes with the working face advanced during the process of exploitation in the Jiaozuo mining area, we adopted the analytic procedure of hierarchical clustering to carry on the discrimination and classification of the mine water gushing sources for the four detected water exits.…”

Section: Modeling For the Recognition Of Mine Water Gushing Sources B...mentioning

confidence: 99%

Recognition Method of Mine Water Sources Based on Factor Analysis

Shi

2020

Glob. J. Earth Sci. Eng.

View full text Add to dashboard Cite

Taking Jiaozuo mining area as the research background, according to the survey of water samples among the main water-filled aquifers of the mine and water gushing sources due to the exploitation of the No.21 coal seams in Shanxi group, six kinds of water chemical composition were selected as the sample indexes, including Cl-, SO42-, HCO3-, Na++K+, Ca2+, Mg2+, based on the data of groundwater chemical composition, and a principal component analysis was applied to establish the mathematical model by the method of factor analysis. A piper diagram was used to intuitively conduct the synthetical analyses for the general chemical characteristics and water quality types of the water samples. At the same time, via the comparative analysis between the water properties of water exits and that of the main aquifers in the Jiaozuo mining area, discrimination of the hybridization of the multiple water gushing sources due to coal mining was done. Moreover, by dint of the SPSS factor analysis, the water chemical proxies were carried on dimensionality reduction from the six kinds of water chemical composition to the three major factors, which replaced the original variables to participate in the data modeling. The results of the study showed that the combination of the piper diagram and the factor analysis modeling could effectively identify the water gushing sources owing to exploiting the No.21 coal seams of the Shanxi group in the Jiaozuo mining area and rank on the basis of the contributions of each aquifer to the amounts of water bursting in the mine, solving the problems of information superposition and correlations consisted in the identification of water gushing sources, which provides a theoretical basis for the prevention and cure of the mine water disasters.

show abstract

Source identification of mine water inrush based on principal component analysis and grey situation decision

Cited by 27 publications

References 34 publications

Geochemical processes of groundwater salinization in an arid area, southeastern Tunisia

Geochemical processes of groundwater salinization in an arid area, southeastern Tunisia

Application of an improved naive Bayesian analysis for the identification of air leaks in boreholes in coal mines

Recognition Method of Mine Water Sources Based on Factor Analysis

Contact Info

Product

Resources

About