Predicting the water-yield properties of K₂ limestones based on multivariate LSTM neural network: A case study of the Poli mining area in Yangquan

Authors

SHI Suzhen, State Key Laboratory for Coal Resources and Safe Mining, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow
SHI Guifei, School of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
LIU Zuiliang, Huayang New Material Technology Group Co., Ltd., Yangquan 045000, China
LI Li, School of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
YAO Xuejun, School of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
PEI Jinbo, School of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
HE Yazhou, School of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China

Abstract

The Taiyuan Formation K₂ limestones are the main aquifer in the upper part of the No.15 coal seam in the Poli mining area, Yangquan City. Therefore, determining the water yield properties of K₂ limestones is critical to the safe mining of coal seams in the upper and lower formations. To determine the exact distribution of areas with high water-yield properties of the K₂ limestones, this study determined the accurate spatial distribution of K₂ limestones using the conventional wave impedance inversion firstly. Then, nine optimal seismic attributes were selected using the Pearson correlation coefficient method and the cross-validation method in stepwise regression in order to form the training data. By introducing the long short-term memory (LSTM) neural network, which is applicable for processing time-series data and is capable of capturing the correlation with log curves, this study established a multivariate LSTM neural network-based intelligent model for apparent resistivity prediction (also referred to as the multivariate LSTM-based prediction model). The purpose is to accurately predict the apparent resistivity of the study area and further obtain the water yield properties of K₂ limestones. Moreover, this study established the mapping relationship between resistivity log curves of the well locations and the seismic attributes of near-well seismic traces using the conventional multivariate regression algorithm and the multivariate LSTM-based prediction model, respectively. Finally, the multivariate LSTM-based prediction model trained using the data on the well locations were extended to the areas without wells to obtain the apparent resistivity volume of the whole study area. Subsequently, the areas with high water yield properties in the limestones were delineated according to the apparent resistivity values, as well as the development of the geological structures and collapse columns in the mining area. As shown by the test results of actual data, compared to the conventional multivariate regression algorithm, the multivariate LSTM-based prediction model yielded smaller prediction errors and higher correlation coefficients with logs. Therefore, the multivariate LSTM-based prediction model can accurately predict the apparent resistivity of a survey area and is of high application value in predicting the water-yield properties of coal-bearing strata.

Keywords

water-yield properties, apparent resistivity, selection of optimal attributes, coal-bearing strata, long short-term memory neural network

DOI

10.12363/issn.1001-1986.22.06.0471

Recommended Citation

SHI Suzhen, SHI Guifei, LIU Zuiliang, et al. (2023) "Predicting the water-yield properties of K₂ limestones based on multivariate LSTM neural network: A case study of the Poli mining area in Yangquan," Coal Geology & Exploration: Vol. 51: Iss. 5, Article 16.
DOI: 10.12363/issn.1001-1986.22.06.0471
Available at: https://cge.researchcommons.org/journal/vol51/iss5/16

Reference

[1] 崔若飞,孙学凯,崔大尉. 基于地震反演方法的奥陶系顶部含隔水层探测[J]. 岩石力学与工程学报,2009,28(2):319−323.

CUI Ruofei,SUN Xuekai,CUI Dawei. Detection of water–resisting layer in upper Ordovician system based on seismic inversion method[J]. Chinese Journal of Rock Mechanics and Engineering,2009,28(2):319−323.

[2] MAITI S，ERRAM V C，GUPTA G，et al. ANN based inversion of DC resistivity data for groundwater exploration in hard rock terrain of western Maharashtra (India)[J]. Journal of Hydrology，2012，464/465：294–308.

[3] ADAGUNODO T A,SUNMONU L A,OJOAWO A,et al. The hydro geophysical investigation of Oyo State industrial estate Ogbomosho,southwestern Nigeria using vertical electrical soundings[J]. Research Journal of Applied Sciences,Engineering and Technology,2013,5(5):1816−1829.

[4] ADELUSI A O,AYUK M A,KAYODE J S. VLF–EM and VES:An application to groundwater exploration in a Precambrian basement terrain SW Nigeria[J]. Annals of Geophysics,2014,57(1):S0184.

[5] JOEL E S,OLASEHINDE P I,DE D K,et al. Estimation of aquifer transmissivity from geo–physical data:A case study of Covenant University and environs,southwestern Nigeria[J]. Science International,2016,28(4):3379−3385.

[6] ZOHDY A A R,JACKSON D B. Application of deep electrical soundings for groundwater exploration in Hawaii[J]. Geophysics,1969,34(4):584−600.

[7] MOHAMADEN M I I,HAMOUDA A Z,MANSOUR S. Application of electrical resistivity method for groundwater exploration at the Moghra area,western Desert,Egypt[J]. Egyptian Journal of Aquatic Research,2016,42(3):261−268.

[8] ANOMOHANRAN O,OFOMOLA M O,OKOCHA F O. Investigation of groundwater in parts of Ndokwa district in Nigeria using geophysical logging and electrical resistivity methods:Implications for groundwater exploration[J]. Journal of African Earth Sciences,2017,129:108−116.

[9] MOHAMADEN M I I,EHAB D. Application of electrical resistivity for groundwater exploration in Wadi Rahaba,Shalateen,Egypt[J]. NRIAG Journal of Astronomy and Geophysics,2017,6(1):201−209.

[10] RIWAYAT A I，NAZRI M A A，ABIDIN M H Z. Application of electrical resistivity method (ERM) in groundwater exploration[C]//Journal of Physics：Conference Series. IOP Publishing，2018，995(1)：012094.

[11] 施龙青,翟培合,魏久传,等. 三维高密度电法技术在岩层富水性探测中的应用[J]. 山东科技大学学报(自然科学版),2008,27(6):1−4.

SHI Longqing,ZHAI Peihe,WEI Jiuchuan,et al. Application of 3D high density electrical technique in detecting the water enrichment of strata[J]. Journal of Shandong University of Science and Technology (Natural Science),2008,27(6):1−4.

[12] 钱进,崔若飞,崔大尉,等. 波阻抗反演预测奥陶系灰岩顶部含隔水性[J]. 地球物理学进展,2009,24(6):2169−2174.

QIAN Jin,CUI Ruofei,CUI Dawei,et al. Aquosity and watertight prediction of the top Ordovician limestone using impedance inversion[J]. Progress in Geophysics,2009,24(6):2169−2174.

[13] 刘德民,连会青,韩永,等. 基于概率神经网络的煤层顶板砂岩含水层富水性预测[J]. 煤炭技术,2014,33(9):336−338.

LIU Demin,LIAN Huiqing,HAN Yong,et al. Study on water enrichment prediction of coal roof sandstone aquifer based on PNN[J]. Coal Technology,2014,33(9):336−338.

[14] 张明川,杨文强,崔若飞. 基于地震反演方法的太原组灰岩含水性预测[J]. 地球物理学进展,2016,31(3):1289−1294.

ZHANG Mingchuan,YANG Wenqiang,CUI Ruofei. Prediction of Taiyuan group limestone’s water–bearing property based on the seismic inversion method[J]. Progress in Geophysics,2016,31(3):1289−1294.

[15] 马丽,薛海军,汶小岗,等. 测井与地震资料联合反演预测K₂灰岩及其含水性[J]. 煤田地质与勘探,2016,44(4):142−146.

MA Li,XUE Haijun,WEN Xiaogang,et al. Prediction of K₂ limestone and its aquosity by joint inversion of logging and seismic data[J]. Coal Geology & Exploration,2016,44(4):142−146.

[16] 李梁宁,魏久传,李立尧,等. 基于测井资料的含水层富水性预测模型:以鄂尔多斯地区营盘壕井田为例[J]. 中国矿业,2019,28(9):143−147.

LI Liangning,WEI Jiuchuan,LI Liyao,et al. Water yield property prediction model of aquifer based on logging data:A case study from Yingpanhao mine field in Ordos area[J]. China Mining Magazine,2019,28(9):143−147.

[17] 安鹏,曹丹平,赵宝银,等. 基于LSTM循环神经网络的储层物性参数预测方法研究[J]. 地球物理学进展,2019,34(5):1849−1858.

AN Peng,CAO Danping,ZHAO Baoyin,et al. Reservoir physical parameters prediction based on LSTM recurrent neural network[J]. Progress in Geophysics,2019,34(5):1849−1858.

[18] 周恒,武中原,张欣,等. 基于LSTM循环神经网络的横波预测方法[J]. 断块油气田,2021,28(6):829−834.

ZHOU Heng,WU Zhongyuan,ZHANG Xin,et al. Shear wave prediction method based on LSTM recurrent neural network[J]. Fault–Block Oil & Gas Field,2021,28(6):829−834.

[19] HOCHREITER S,SCHMIDHUBER J. Long short−term memory[J]. Neural Computation,1997,9(8):1735−1780.

[20] GRAVES A. Supervised sequence labelling with recurrent neural networks[M]. Berlin：Springer，2012.

[21] HAMPSON D,TODOROV T,RUSSELL B. Using multi–attribute transforms to predict log properties from seismic data[J]. Exploration Geophysics,2000,31:481−487.