Abstract
Accurate recognition of water inrush sources is important in mine water hazard control. In this study, 118 water samples of four water types in the Qinan coal mine were analysed by multiple logistic regression, and the 12 water samples that did not meet the requirements were removed. The remaining 106 were used as training samples to establish a Bayes recognition model (BRM). In addition, the BRM was used to complement multiple logistic regression analysis (MLRA) to discriminate other water samples in the mining area. The recognition accuracy of the combined model was 95.28%. The results from the model were consistent with the field water samples and showed that the combined MLRA-BRM approach fully considers the hydraulic relationships between different aquifers and a mixed water inrush source. Moreover, the MLRA-BRM combination improved water inrush source recognition accuracy and was more reliable than using MLRA or BRM alone.
Zusammenfassung
Die präzise Erkennung von Wassereinbruchsquellen ist für die Gefahrenabwehr im Zusammenhang mit Grubenwasser von zentraler Bedeutung. In der vorliegenden Studie wurden 118 Wasserproben von vier Wassertypen in der Qinan Kohlemine mittels multipler logistischer Regression analysiert. Die nach Entfernung von 12 Wasserproben, die die Voraussetzungen nicht erfüllten, verbliebenen 106 Proben wurden für den Aufbau eines Bayes Recognition Models (BRM) verwendet. Zusätzlich wurde das BRM zur Ergänzung der multiplen logistischen Regressionsanalyse (MLRA) eingesetzt, um eine Unterscheidung bei weiteren Wasserproben aus dem Bergbaugebiet vornehmen zu können. Die Erkennungsgenauigkeit des kombinierten Modells lag bei 95,28%. Die Modellergebnisse stimmten mit den Wasserproben aus dem Feld überein und zeigen, dass der kombinierte MLRA-BRM Ansatz die hydraulische Verknüpfung verschiedener Aquifere und die Vermischung von Wassereinbruchsquellen vollständig berücksichtigt. Darüber hinaus wurde die Genauigkeit der Quellenerkennung für Wassereinbrüche durch die Kombination von MLRA und BRM verbessert und die Zuverlässigkeit im Vergleich zur alleinigen Anwendung der Einzelbausteine MLRA oder BRM erhöht.
Resumen
El conocimiento exacto de las fuentes de entrada de agua es importante en el control de los riesgos del agua de las minas. En este estudio, se analizaron 118 muestras de agua de cuatro tipos de agua en la mina de carbón de Qinan mediante una regresión logística múltiple, y se retiraron las 12 muestras de agua que no cumplían los requisitos. Las 106 restantes se utilizaron como muestras de entrenamiento para establecer un modelo de reconocimiento de Bayes (BRM). Además, el BRM se utilizó para complementar el análisis de regresión logística múltiple (MLRA) para discriminar otras muestras de agua en la zona minera. La precisión de reconocimiento del modelo combinado fue del 95,28%. Los resultados del modelo fueron consistentes con las muestras de agua obtenidas en campo y mostraron que el enfoque combinado MLRA-BRM considera las relaciones hidráulicas entre diferentes acuíferos y una fuente mixta de irrupción de agua. Además, la combinación MLRA-BRM mejoró la precisión del conocimiento de la fuente de agua de irrupción y fue más fiable que el uso de MLRA o BRM por separado.
基于多重Logistic回归分析的矿井突水水源贝叶斯识别模型
准确识别矿井突水源对矿井水害防治至关重要。采用多重Logistic回归法分析了祁南煤矿4种类型的118个水样,剔除了其中12个不符合要求水样。以剩余106个水样为训练样本建立了贝叶斯识别模型(BRM),进一步基于BRM模型建立了多重Logistic回归分析法(MLRA),以识别矿区其它水样。MLRA-BRM组合模型的识别准确率95.28%。模型结果与野外水样基本一致。MLRA-BRM组合模型方法能够充分考虑不同含水层与混合突水水源之间的水力联系。MLRA-BRM组合法能提高突水源识别准确性,比单独使用MLRA或BRM更可靠。.
References
Aiken L, West ST (1991) Multiple regression: testing and interpreting interactions. Sage, Newbury Park
Chen HJ, Li XB, Liu AH (2009) Studies of water source determination method of mine water inrush based on Bayes multi-group stepwise discriminant analysis theory. Rock Soil Mech 30(12):3655–3659. https://doi.org/10.16285/j.rsm.2009.12.011(in Chinese)
Chen LW, Yin XX, Liu X, Gui HR (2013) Multivariate statistical analysis on hydrochemical evolution of groundwater in the concealed coal mines in north China. Coal Geol Explor 41(6):43–51. https://doi.org/10.3969/j.issn.1001-1986.2013.06.011(in Chinese)
Chen LW, Xu DQ, Yin XX, Xie WP, Zeng W (2017) Analysis on hydrochemistry and its control factors in the concealed coal mining area in north China: a case study of dominant inrush aquifers in Suxian mining area. J China Coal Soc 42(4):996–1004. https://doi.org/10.13225/j.cnki.jccs.2016.0685(in Chinese)
Dou HP, Ma ZY, Cao HD, Liu F, Hu WW, Li T (2011) Application of isotopic and hydro-geochemical methods in identifying sources of mine inrushing water. Int J Min Sci Technol 21(3):319–323. https://doi.org/10.1016/j.mstc.2011.05.021
Efron B (2010) Large-Scale inference: empirical Bayes methods for estimation, testing, and prediction. Cambridge University Press, Cambridge
Efron B (2019) Bayes, oracle Bayes and empirical Bayes. Stat Sci 34(2):177–201. https://doi.org/10.1214/18-sts674
Farnham IM, Stetzenbach KJ, Singh AK, Johannesson KH (2000) Deciphering groundwater flow systems in Oasis Valley, Nevada, using trace element chemistry, multivariate statistics, and geographical information system. Math Geosci 32(8):943–968. https://doi.org/10.1023/A:1007522519268
Ganyaglo SY, Banoeng Yakubo B, Osae S, Dampare SB, Fianko JR (2011) Water quality assessment of groundwater in some rock types in parts of the eastern region of Ghana. Environ Earth Sci 62(5):1055–1069. https://doi.org/10.1007/s12665-010-0594-3
Gong F, Lu J (2014) Recognition method of mine water inrush sources based on the principal element analysis and distance discrimination analysis. J Min Saf Eng 31(2):236–242. https://doi.org/10.13545/j.issn1673-3363.2014.02.012(in Chinese)
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New York
Hu WY, Dong SN, Yan L (2011) Water Hazard control technology for safe extraction of coal resources influenced by faulted zone. Procedia Earth Plan Sci 3:1–10. https://doi.org/10.1016/j.proeps.2011.09.058
Huang PH, Han SM (2016) assessment by multivariate analysis of groundwater-surface water interactions in the coal-mining exploring district, China. Earth Sci Res J 20(1):1–8. https://doi.org/10.15446/esrj.v20n1.37601
Huang PH, Wang XY (2018) Piper-PCA-Fisher recognition model of water inrush source: a case study of the Jiaozuo mining area. Geofluids 2018:1–10. https://doi.org/10.1155/2018/9205025
Huang PH, Yang ZY, Wang XY, Ding FF (2019) Research on Piper-PCA-Bayes-LOOCV discrimination model of water inrush source in mines. Arab J Geosci 12:334. https://doi.org/10.1007/s12517-019-4500-3
Katz MH (2006) Assumptions of multiple linear regression, multiple logistic regression, and proportional hazards analysis. Multivariable analysis: a practical guide for clinicians, 2nd edn. Cambridge University Press, Cambridge, pp 38–67
Kawakubo S, Omori T, Suzuki Y, Ueta I (2018) Droplet-counting microtitration system for precise on-site analysis. Anal Sci 34(2):243–247. https://doi.org/10.2116/analsci.34.243
Keskin TE, Düğenci M, Kaçaroğlu F (2015) Prediction of water pollution sources using artificial neural networks in the study areas of Sivas, Karabük and Bartın (Turkey). Environ Earth Sci 73(9):5333–5347. https://doi.org/10.1007/s12665-014-3784-6
Kim JH, Kim RH, Lee J, Cheong TJ, Yum BW, Chang HW (2005) Multivariate statistical analysis to identify the major factors governing groundwater quality in the coastal area of Kimje, South Korea. Hydrol Process 19(6):1261–1276. https://doi.org/10.1002/hyp.5565
Lafazani P, Lagarias A (2016) Applying multiple and logistic regression models to investigate periurban processes in Thessaloniki, Greece. Geocarto Int 31(8):927–942. https://doi.org/10.1080/10106049.2015.1094523
Li GQ, Meng ZP, Wang XQ, Yang J (2017) Hydrochemical prediction of mine water inrush at the Xinli Mine, China. Mine Water Environ 36(1):78–86. https://doi.org/10.1007/s10230-016-0405-5
Ma FS, Zhao HJ, Guo J (2015) Investigating the characteristics of mine water in a subsea mine using groundwater geochemistry and stable isotopes. Environ Earth Sci 74(9):6703–6715. https://doi.org/10.1007/s12665-015-4680-4
Mou L (2016) Application of dynamic curve prediction method in discriminating water-bursting source. Coal Geol Explor 44(3):70–74. https://doi.org/10.3969/j.issn.1001-1986.2016.03.013(in Chinese)
Nasiri EF, Kebria DY, Qaderi F (2018) An experimental study on the simultaneous phenol and chromium removal from water using titanium dioxide photocatalyst. Civ Eng J 4(3):585. https://doi.org/10.28991/cej-0309117
Ostir GV, Uchida T (2000) Logistic regression: a nontechnical review. Am J Phys Med 79(6):565–572. https://doi.org/10.1097/00002060-200011000-00017
Pan GY, Wang SN, Sun XY (2009) Application of isotopic technique in identification of mine water inrush source. Min Saf Environ Prot 4:7–9. https://doi.org/10.3969/j.issn.1008-4495.2009.01.011(in Chinese)
Panagopoulos GP, Angelopoulou D, Tzirtzilakis EE et al (2016) The contribution of cluster and discriminant analysis to the classification of complex aquifer systems. Environ Monit Assess 188(10):591. https://doi.org/10.1007/s10661-016-5590-y
Qian JZ, Wang L, Ma L, Lu YH, Zhao WD, Zhang Y (2016) Multivariate statistical analysis of water chemistry in evaluating groundwater geochemical evolution and aquifer connectivity near a large coal mine, Anhui, China. Environ Earth Sci 75(9):747. https://doi.org/10.1007/s12665-016-5541-5
Qiu M, Shi LQ, Teng C, Zhou Y (2017) Assessment of water inrush risk using the fuzzy Delphi analytic hierarchy process and grey relational analysis in the Liangzhuang coal mine, China. Mine Water Environ 36:39–50. https://doi.org/10.1007/s10230-016-0391-7
Robison AL, Scanlon TM, Cosby BJ, Webb JR, Galloway JN (2013) Roles of sulfate adsorption and base cation supply in controlling the chemical response of streams of western Virginia to reduced acid deposition. Biogeochemistry 116:119–130. https://doi.org/10.1007/s10533-013-9921-6
Sikdar PK, Sarkar SS, Palchoudhury S (2001) Geochemical evolution of groundwater in the Quaternary aquifer of Calcutta and Howrah, India. J Asian Earth Sci 19:579–594. https://doi.org/10.1016/s1367-9120(00)00056-0
(in Chinese)
Sun LH, Gui HR (2013) Statistical analysis of deep groundwater geochemistry from Taoyuan coal mine, northern Anhui Province. J China Coal Soc 38(Supp.2):442–447. https://doi.org/10.13225/j.cnki.jccs.2013.s2.006(in Chinese)
U.S. EPA NERL (National Exposure Research Laboratory) [formerly EMSL] (1971) Methods for the chemical analysis of water and wastes (MCAWW) (EPA/600/4-79/020): calcium by flame AA (Method 215.1), magnesium by flame AA (Method 242.1), potassium by flame AA (Method 258.1), sodium by flame AA (Method 273.1); U.S. EPA; EPA/600/4-79/020
U.S. EPA Office of Ground Water and Drinking Water/Technical Support Center (1997) Methods for the determination of organic and inorganic compounds in drinking water, Volume 1 (EPA/815-R-00-014): EPA Method 300.1: determination of inorganic anions in drinking water by ion chromatography; U.S. EPA; EPA/815-R-00-014
Villegas P, Paredes V, Betancur T, Ribeiro L (2013) Assessing the hydrochemistry of the Urabá Aquifer, Colombia by principal component analysis. J Geochem Explor 134:120–129. https://doi.org/10.1016/j.gexplo.2013.08.011
Wen TX, Zhang B, Shao LB (2014) Research on prediction of mine water inrush source identification—Xinzhuangzi coalfield as an example. China Saf Sci J 24(2):100–106. https://doi.org/10.16265/j.cnki.issn1003-3033.2014.02.007(in Chinese)
Wu Q, Guo XM, Shen JJ, Xu S, Liu SQ, Zeng YF (2016) Risk assessment of water inrush from aquifers underlying the Gushuyuan coal mine, China. Mine Water Environ 36(1):96–103. https://doi.org/10.1007/s10230-016-0410-8
Yao M, Liu PG, Shang MT, Tao YZ, Lei C, Cao LG (2016) Determining sources of mine water based on hydraulic characteristics analysis of a fault system. Environ Earth Sci 75(10):858. https://doi.org/10.1007/s12665-016-5660-z
Zhang H, Yao D, Lu H, Xue L, Zhu NN (2017) Study on water source discrimination based on multinomial logistic regression model using principal component analysis. Geol J China Univ 23(2):366–372. https://doi.org/10.16108/j.issn1006-7493.2016198(in Chinese)
Zhang H, Xing HF, Yao DX, Liu LL, Xue DR, Guo F (2019) The multiple logistic regression recognition model for mine water inrush source based on cluster analysis. Environ Earth Sci 78(20):612. https://doi.org/10.1007/s12665-019-8624-2
Acknowledgements
The project was supported by the National Natural Science Foundation of China (51474008) and the Anhui Natural Science Foundation of China (1508085QE89). The research was also substantially supported by the Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education (Tongji University).
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Zhang, H., Yao, D. The Bayes Recognition Model for Mine Water Inrush Source Based on Multiple Logistic Regression Analysis. Mine Water Environ 39, 888–901 (2020). https://doi.org/10.1007/s10230-020-00699-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10230-020-00699-2