Bayesian model based on Markov chain Monte Carlo for identifying mine water sources in Submarine Gold Mining

Yan, Bingqian; Ren, Fenhua; Cai, Meifeng; Qiao, Chen

doi:10.1016/j.jclepro.2020.120008

Cited by 23 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interval estimates in RFQR provide quantiles that help gain a more complete picture of the potential outcomes in the target. Markov chain Monte Carlo-based methods also exist when it comes to making probabilistic estimates about the dependent variable (Amaya et al 2022;Kumar et al 2020;Yan et al 2020). However, scaling them to large datasets poses an issue; therefore, we opt for the Random Forest Quantile Regression algorithm.…”

Section: Random Forest Quantile Regression (Rfqr)mentioning

confidence: 99%

Mapping a novel metric for Flash Flood Recovery using Interpretable Machine Learning

Kumar,

Saharia,

Kirstetter

2024

Preprint

View full text Add to dashboard Cite

Flash floods are one of the most devastating natural disasters, yet many aspects of their severity and impact are poorly understood. The recession limb is related to post-flood recovery and its impact on communities, yet it remains less documented than the rising limb of the hydrograph to predict the peak discharge and timing of floods. . This work introduces a new metric called the flash flood recovery or recoveriness, which is the potential for recovery of a watershed to pre-flood conditions. Using a comprehensive database of 78 years and supervised machine learning algorithms, flash flood recovery is mapped in the conterminous United States. A suite of geomorphological and climatological variables is used as predictors to provide probabilistic estimates of recoveriness. Slope index, river basin area and river length are found to be the most significant predictors to predict recoveriness. Several new localized hotspots were identified, such as the western slopes of the Appalachians consisting of Kentucky, Tennessee, and West Virginia and the interlinked areas of western Montana and northern Idaho. This new metric can be useful for prioritizing relief and rehabilitation efforts as well as precautionary measures for disaster risk reduction.

show abstract

Section: Random Forest Quantile Regression (Rfqr)mentioning

confidence: 99%

Mapping a novel metric for Flash Flood Recovery using Interpretable Machine Learning

Kumar,

Saharia,

Kirstetter

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…where Q is water inflow (m 3 •day −1 ); K is hydraulic conductivity (m•day −1 ); a and b are working face length and width, respectively (m); η is the calculation factor (see Table 1); r 0 is the reference radius (m); R is the influence radius (m); R 0 is the large well reference radius (m); M is the thickness of the aquifer (m); and, S is the drawdown of the water table (m). The assumptions according to Eq.…”

Section: Prediction Equation For Interval Water Inflowmentioning

confidence: 99%

“…Water damage is a key problem during mining 1 – 3 . The large-well method is commonly used for predicting mine water inflow 4 – 6 , however, the accuracy of the results are subject to the constraints of hydrogeological conditions 7 – 9 .…”

Section: Introductionmentioning

confidence: 99%

Interval uncertainty analysis of a confined aquifer

Wang

2021

Sci Rep

View full text Add to dashboard Cite

Water inflow forecast is influenced by many factors and yields uncertain results. To more accurately predict the magnitude of water inflow and quantitatively define the corresponding response in the parameter change interval, this study combined a non-probabilistic set theory and uncertainty analysis to derive an equation for the confined water inflow. Using mining area data and comparing the calculation of upper and lower boundary limits obtained by a Monte Carlo method, results of the confined water inflow equation were calculated with relative errors of 5% and 10%. When corresponding to the rate of change of the variable parameter, the results showed that under the same error conditions, the allowable rate of change when calculating the minimum value using Eq. A was greater than when using Eq. B, and the maximum value using Eq. B yielded a greater allowable rate of change than the maximum value calculated by Eq. A. Thus, the obtained rate of change for Eq. A is indicative of the lower limit, and Eq. B is conducive to the calculation of the upper limit of mine water inflow.

show abstract

“…At present, some scholars have made some achievements in applying machine learning algorithms to build water source, identification models. such as Yan et al 13 who established a Bayesian water source discrimination model, which guides the study of water inrush in undersea mines. Jiang et al 14 took the Panxie mining area as an example to establish a water source identification model based on big data depth learning, which proved that the depth learning model has good applicability in the identification of water source of mine water inrush.…”

Section: Introductionmentioning

confidence: 99%

Discrimination of water inrush source in coal mine based on PCA-GA-ET

Lv¹,

Yang²,

Yan³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, mine water inrush has hindered coal mining, and accurate identification of the source of water inrush is essential for the prevention and control of mine water disasters. To study the source of water inrush in Pingdingshan coalfield, water source samples of 124 groups of main water inrush aquifers were collected. The main water-filled aquifers in Pingdingshan coalfield include surface water (I), Quaternary pore water (II), Carboniferous limestone karst water (III), Permian sandstone water (IV) and Cambrian limestone karst water (IV).In this paper, the conventional hydrochemical discriminant ions Na++K+, Ca2+, Mg2+, Cl-, SO42-, and HCO3- of observed water samples are extracted to build a water source discriminant model. According to the Pearson correlation coefficient, Na++K+has a strong correlation with HCO3-. To avoid the impact of information overlap on the accuracy of the model, principal component analysis (PCA) is used to extract the main indicators. Based on the adaptive differential evolution genetic algorithm (GA) to optimize the super parameters of the extreme tree (ET), the PCA-GA-ET water source identification model is constructed. To further verify the reliability of the model, PCA-GA-ET is compared with grid search-random forest (GS-RF), artificial neural network (MLP), and particle swarm optimization-support vector machine (PSO-SVM). Finally, using the trained model to discriminate 25 groups of validation samples, it can be concluded that the discrimination results of 24 groups of samples are consistent with the observation results, and the accuracy of PCA-GA-ET is 96%. Research shows that the use of principal component analysis can reduce the information overlap of data, and the extreme tree (ET) model optimized by genetic algorithm (GA) greatly improves the efficiency and accuracy of water inrush source identification.

show abstract

Bayesian model based on Markov chain Monte Carlo for identifying mine water sources in Submarine Gold Mining

Cited by 23 publications

References 7 publications

Mapping a novel metric for Flash Flood Recovery using Interpretable Machine Learning

Mapping a novel metric for Flash Flood Recovery using Interpretable Machine Learning

Interval uncertainty analysis of a confined aquifer

Discrimination of water inrush source in coal mine based on PCA-GA-ET

Contact Info

Product

Resources

About