Discriminant analysis of mine water inrush sources with multi-aquifer based on multivariate statistical analysis

Bi, Yaoshan; Wu, Jiwen; Zhai, Xiaorong; Wang, Guangtao; Shen, Shuhao; Qing, Xianbin

doi:10.1007/s12665-021-09450-8

Cited by 24 publications

(13 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the basis of the investigation of the geological background and hydrogeological conditions of the study area, groundwater sampling of coal mines in the study area was carried out to lay a scientific and reliable foundation for further research on the chemical characteristics of groundwater and the establishment of a water source identification model [ 26 ]. The groundwater samples in the study area were sent to the key laboratory of mine water resource utilization within 10 min after collection, filtered using 0.45 μ cellulose filter, and stored in a refrigerator at 4 °C.…”

Section: Methodsmentioning

confidence: 99%

Groundwater chemical characteristic analysis and water source identification model study in Gubei coal mine, Northern Anhui Province, China

Jiang,

Liu,

Liu

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Groundwater chemical characteristic analysis and water source identification model study in Gubei coal mine, Northern Anhui Province, China

Jiang,

Liu,

Liu

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…A dynamic balance is reached between groundwater and rocks through a series of physical and chemical reactions, such as dissolution and precipitation, redox, and alternate ion adsorption reactions. Therefore, the same aquifer exhibits consistent water chemistry characteristics, whereas different aquifers exhibit distinct water chemistry characteristics (Liu et al 2017;Zhang et al 2020a, b;Hou et al 2020;Bi et al 2021). This provides a basis for the discrimination of mine water sources based on hydrochemical characteristics.…”

Section: Introductionmentioning

confidence: 98%

Deep learning model based on big data for water source discrimination in an underground multiaquifer coal mine

Jiang

Zhu

et al. 2021

Bull Eng Geol Environ

View full text Add to dashboard Cite

In view of the difficulty and low efficiency of models established with big data, a deep feedforward network-based mine water inrush discriminant model is established. The stochastic gradient descent (SGD) algorithm is employed to optimize model parameter training. The cross-entropy loss and accuracy of the training and test samples are considered to characterize the model training effect. To prevent overfitting during model training, the dropout optimization method is incorporated into the hidden layers of the model. The four main water-filled aquifers in the Huainan Panxie mining area are chosen as discrimination objects, 1952 sets of water samples are applied as modeling data, and a total of nine indicators, including K + + Na + , Ca 2+ , Mg 2+ , Cl − , SO 4 2− , HCO 3 − , CO 3 2− , pH, and total dissolved solids (TDS), are selected as discriminating factors. Through model training, the dropout rate, epoch number, batch size, and learning rate are set as 0.1, 90, 25, and 10 −2 , respectively, and the discriminant accuracy rates for the training and test samples are 93.34% and 96.68%, respectively. The trained model is applied to discriminate 30 groups of water samples, and the discrimination results for 28 groups of water samples are consistent with observations. The results indicate that the deep learning discriminant model based on big data achieves high accuracy, good applicability, and a suitable discrimination ability, and provides a certain guiding significance in the prevention and control of water inrush hazards and related field work. KeywordsMine water inrush • Water sources • Big data • Deep learning • Underground coal mine * Chunlu Jiang

show abstract

“…Multivariate statistical analyses 56 , 57 , including correlation analysis (CA) 58 , principal component analysis (PCA) 59 , 60 , and Fisher discriminant analysis (FDA) 61 – 63 , have been widely used as tools to identify sources and determine the main influential factors from compositional data. For example, Jin et al 56 applied PCA and CA to identify potential sources in soil and dust at children's playgrounds in Beijing; Ranjbar et al 60 utilized CA to establish the relationship between variables and PCA to reduce the dataset to several determining factors; He et al 62 used PCA and FDA to model, assess, and classify ecological and environmental quality and the impacts of coal mining; Bi et al 61 utilized the FDA model for mine water inrush sources. Hence, these methods can be used to reveal core carcinogenic elements in combination with toxicology.…”

Section: Introductionmentioning

confidence: 99%

Identification of core carcinogenic elements based on the age-standardized mortality rate of lung cancer in Xuanwei Formation coal in China

Chen,

Cheng,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In this study, the core carcinogenic elements in Xuanwei Formation coal were identified. Thirty-one samples were collected based on the age-standardized mortality rate (ASMR) of lung cancer; Si, V, Cr, Co, Ni, As, Mo, Cd, Sb, Pb, and rare earth elements and yttrium (REYs) were analyzed and compared; multivariate statistical analyses (CA, PCA, and FDA) were performed; and comprehensive identification was carried out by combining multivariate statistical analyses with toxicology and mineralogy. The final results indicated that (1) the high-concentration Si, Ni, V, Cr, Co, and Cd in coal may have some potential carcinogenic risk. (2) The concentrations of Cr, Ni, As, Mo, Cd, and Pb meet the zoning characteristics of the ASMR, while the Si concentration is not completely consistent. (3) The REY distribution pattern in Longtan Formation coal is lower than that in Xuanwei Formation coal, indicating that the materials of these elements in coal are different. (5) The heatmap divides the sampling sites into two clusters and subtypes in accordance with carcinogenic zoning based on the ASMR. (6) PC1, PC2, and PC3 explain 62.629% of the total variance, identifying Co, Ni, As, Cd, Mo, Cr, and V. (7) Fisher discriminant analysis identifies Ni, Si, Cd, As, and Co based on the discriminant function. (8) Comprehensive identification reveals that Ni is the primary carcinogenic element, followed by Co, Cd, and Si in combination with toxicology. (9) The paragenesis of Si (nanoquartz), Ni, Co, and Cd is an interesting finding. In other words, carcinogenic elements Ni, Co, Cd, and Si and their paragenetic properties should receive more attention.

show abstract

Discriminant analysis of mine water inrush sources with multi-aquifer based on multivariate statistical analysis

Cited by 24 publications

References 45 publications

Groundwater chemical characteristic analysis and water source identification model study in Gubei coal mine, Northern Anhui Province, China

Groundwater chemical characteristic analysis and water source identification model study in Gubei coal mine, Northern Anhui Province, China

Deep learning model based on big data for water source discrimination in an underground multiaquifer coal mine

Identification of core carcinogenic elements based on the age-standardized mortality rate of lung cancer in Xuanwei Formation coal in China

Contact Info

Product

Resources

About