Research on aquifer water abundance evaluation by borehole transient electromagnetic method based on FCNN

Authors

CHENG Jiulong, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow
WANG Huijie, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
XU Zhongzhong, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
HUANG Qisong, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China; School of Civil Engineering and Architecture, Anhui University of Technology, Maanshan 243002, China
JIANG Guoqing, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China

Abstract

Predicting the location and water abundance of aquifers by drilling or geophysical methods before tunneling is very important to prevent water disasters in advance for the safety of coal mine production. The use of borehole transient electromagnetic method (BTEM) for advanced detection has obvious advantages. At present, the interpretation method is based on the calculated resistivity to qualitatively analyze rock water abundance, and it is impossible to predict the aquifer water abundance grade. So, the fully convolutional neural network (FCNN) method is proposed to predict the aquifer water abundance grade for BTEM. Firstly, according to the Archie formula, Kozeny-Carman formula, conductivity formula, and unit water inflow formula, the corresponding relationship between the resistivity per unit thickness of the sandstone and the four grades of aquifer water abundance grades according to the amount of water inflow per borehole is established. Then, the geological-geophysical model of different rock water abundance under the whole space condition is simulated by the three-dimensional finite difference time domain (FDTD) method, and the characteristic parameters used to predict the water abundance grades are extracted. To be close to the actual situation, 5%-15% random noise is added to the forward modeling results, and FCNN is used to train and simulate the prediction of aquifer water abundance. The average accuracy of aquifer water abundance grade predicted by the test set is 91.8%. Finally, the proposed method is used to predict the water abundance grade of coal seam after hydraulic fracturing in a mine. The results show that FCNN method is feasible and effective to predict the aquifer water abundance grade in the radial direction of the borehole and improve the detection accuracy of BTEM. This method will play an important role in the advanced detection of aquifer water abundance.

Keywords

borehole transient electromagnetic method, FCNN, feature extraction, aquifer water abundance, prediction

DOI

10.12363/issn.1001-1986.22.12.0937

Recommended Citation

CHENG Jiulong, WANG Huijie, XU Zhongzhong, et al. (2023) "Research on aquifer water abundance evaluation by borehole transient electromagnetic method based on FCNN," Coal Geology & Exploration: Vol. 51: Iss. 1, Article 26.
DOI: 10.12363/issn.1001-1986.22.12.0937
Available at: https://cge.researchcommons.org/journal/vol51/iss1/26

Reference

[1] 武强,徐华,赵颖旺,等. 基于云平台的矿井水害智慧应急救援系统与应用[J]. 煤炭学报,2018,43(10):2661−2667.

WU Qiang,XU Hua,ZHAO Yingwang,et al. Cloud–based smart emergency rescue system and its application in mine water disaster[J]. Journal of China Coal Society,2018,43(10):2661−2667.

[2] 张幼振,范涛,阚志涛,等. 煤矿巷道掘进超前钻探技术应用与发展[J]. 煤田地质与勘探,2021,49(5):286−293.

ZHANG Youzhen,FAN Tao,KAN Zhitao,et al. Application and development of advanced drilling technology for coal mine roadway heading[J]. Coal Geology & Exploration,2021,49(5):286−293.

[3] 程久龙,李飞,彭苏萍,等. 矿井巷道地球物理方法超前探测研究进展与展望[J]. 煤炭学报,2014,39(8):1742−1750.

CHENG Jiulong,LI Fei,PENG Suping,et al. Research progress and development direction on advanced detection in mine roadway working face using geophysical methods[J]. Journal of China Coal Society,2014,39(8):1742−1750.

[4] 洪德成,杨善德. 大介电常数地层中多分量感应测井响应研究[J]. 物理学报,2011,60(10):109101.

HONG Decheng,YANG Shande. Multi–component induction logging response in large dielectric formation[J]. Acta Physica Sinica,2011,60(10):109101.

[5] WANG Lei,WU Zhenguan,FAN Yiren,et al. Fast anisotropic resistivities inversion of logging–while–drilling resistivity measurements in high–angle and horizontal wells[J]. Applied Geophysics,2021,17(3):390−400.

[6] 袁习勇,邓少贵,胡旭飞,等. 瞬变电磁波测井边界远探测方法研究[J]. 地球物理学报,2020,63(7):2751−2761.

YUAN Xiyong,DENG Shaogui,HU Xufei,et al. Detection of the remote boundary using the transient electromagnetic logging method[J]. Chinese Journal of Geophysics,2020,63(7):2751−2761.

[7] 范涛. 基于钻孔瞬变电磁的煤层气压裂效果检测方法[J]. 煤炭学报,2020,45(9):3195−3207.

FAN Tao. Coalbed methane fracturing effectiveness test using bore–hole transient electromagnetic method[J]. Journal of China Coal Society,2020,45(9):3195−3207.

[8] 范涛,张幼振,赵睿,等. 基于钻孔TEM智能立体成像的快速掘进超前探测方法[J]. 煤炭学报,2021,46(2):578−590.

FAN Tao,ZHANG Youzhen,ZHAO Rui,et al. Advance detection method of rapid excavation based on borehole TEM intelligent stereo imaging[J]. Journal of China Coal Society,2021,46(2):578−590.

[9] 刘国辉,侯征,王天意,等. 一种新型的地下含水层涌水量预测模型[J]. 地球物理学进展,2012,27(3):1268−1273.

LIU Guohui,HOU Zheng,WANG Tianyi,et al. A new model to predict the water inflow of aquifer[J]. Progress in Geophysics,2012,27(3):1268−1273.

[10] 郎玉泉,陈同俊,马丽,等. 煤层顶板砂岩富水性AVO预测技术[J]. 煤田地质与勘探,2018,46(3):127−132.

LANG Yuquan,CHEN Tongjun,MA Li,et al. Water content prediction of roof sandstone using AVO technology[J]. Coal Geology & Exploration,2018,46(3):127−132.

[11] 程久龙,赵家宏,董毅,等. 基于LBA–BP的矿井瞬变电磁法岩层富水性的定量预测研究[J]. 煤炭学报,2020,45(1):330−337.

CHENG Jiulong,ZHAO Jiahong,DONG Yi,et al. Quantitative prediction of water abundance in rock mass by transient electro–magnetic method with LBA–BP neural network[J]. Journal of China Coal Society,2020,45(1):330−337.

[12] OLSEN C,HONGDUL T,FABRICIUS I L. Prediction of Archie’s cementation factor from porosity and permeability through specific surface[J]. Geophysics,2008,73(2):E81−E87.

[13] SAFARI M,GHOLAMI R,JAMI M,et al. Developing a porosity–permeability relationship for ellipsoidal grains:A correction shape factor for Kozeny–Carman’s equation[J]. Journal of Petroleum Science and Engineering,2021,205:108896.

[14] HASAN M,SHANG Yanjun,AKHTER G,et al. Evaluation of groundwater potential in Kabirwala Area,Pakistan:A case study by using geophysical,geochemical and pump data[J]. Geophysical Prospecting,2018,66(9):1737−1750.

[15] TIZRO A T,VOUDOURIS K S,SALEHZADE M,et al. Hydrogeological framework and estimation of aquifer hydraulic parameters using geoelectrical data:A case study from West Iran[J]. Hydrogeology Journal,2010,18(4):917−929.

[16] 马莲净,赵宝峰. 顶板含水层放水试验的钻孔单位涌水量计算方法[J]. 中国安全生产科学技术,2019,15(3):49−54.

MA Lianjing,ZHAO Baofeng. Calculation method of borehole specific capacity based on dewatering tests of roof aquifer[J]. Journal of Safety Science and Technology,2019,15(3):49−54.

[17] 国家煤矿安全监察局. 煤矿防治水细则[M]. 北京：煤炭工业出版社，2018.

[18] 李飞,温来福,郑贵强. 基于全空间初始场源的半空间TEM三维FDTD正演[J]. 地球物理学进展,2022,37(5):2147−2155.

LI Fei,WEN Laifu,ZHENG Guiqiang. Half–space TEM 3D FDTD forward modeling based on whole–space initial field[J]. Progress in Geophysics,2022,37(5):2147−2155.

[19] 姜国庆,程久龙,孙晓云,等. 全空间瞬变电磁全区视电阻率优化二分搜索算法[J]. 煤炭学报,2014,39(12):2482−2488.

JIANG Guoqing,CHENG Jiulong,SUN Xiaoyun,et al. Optimized binary search algorithm of full space transient electromagnetic method all–time apparent resistivity[J]. Journal of China Coal Society,2014,39(12):2482−2488.

[20] LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(4):640−651.