|
2023, 42(3) 488-500 DOI:
ISSN: 1004-5589 CN: 22-1111/P |
|
|
|
|
Current Issue |
Archive |
Search
[Print]
[Close]
|
|
|
|
Logging identification of complex pyroclastic reservoir fluid properties based on machine learning: taking Tongbomiao Formation of Wuerxun depression in Hailar Basin as an example |
|
|
ZHAO Xiaoqing 1,2 , ZHANG Zheqing 1 , YU Jichong 3 , LI Minghui 3 , JIANG Yanjiao 1 |
|
|
1. School of Geosciences, Northeast Petroleum University, Daqing 163318, Heilongjiang, China;
2. Key Laboratory of Continental Shale Oil and Gas Accumulation and Efficient Development of Ministry of Education, Northeast Petroleum University, Daqing 163318, Heilongjiang, China;
3. Daqing Branch, China Petroleum Logging Company Limited, Daqing 163318, Heilongjiang, China |
|
|
Abstract:
In order to more accurately identify the fluid properties of Tongbomiao Formation reservoir of Wuerxun depression in Hailar Basin, the authors consider that the saturated pure water resistivity (R0 ) is influ? enced by lithology, physical properties and pore structure through experimental analysis of parent rock composition, pore structure and core experiments. In this paper, the value of R0 is predicted by neural network to eliminate the influence of lithology and pore structure on resistivity value, and comparison of receiver operating characteristic curves (ROC) and self?validation accuracy to optimize the combination of logging curves with high relevance for reservoir fluid properties identification: interval transit time (DT24), natural gamma (GR), density ( ZDEN), neutron (CNC), deep investigate double lateral resistivity (RLLD), and R0 . The results of three machine learning methods, namely, decision tree, support vector machine and neural network, were combined with the test well sec? tions to derive a machine learning architecture method for fluid properties identification in Tongbomiao Formation reservoir of Wuerxun depression in Hailar Basin, the BP neural network with three hidden layers and activation function of Relu has an accuracy of 92. 5% for identifying fluid properties. |
|
Keywords:
pyroclastic rock
fluid properties identification
machine learning
neural network
Hailar Basin
|
|
|
Received Revised Online: |
|
|
DOI: |
|
|
Fund: |
|
Corresponding Authors: |
|
Email: |
|
|
About author: |
|
|
References: |
|
Similar articles |
1.WU Haibo,HOU Yanping,WANG Pujun,CHEN Hongping,SHEN Wenjing,PENG Wei,CHEN Chongyang . Hydrocarbon source in Jurassic and its exploration significance in Hongqi Sag, Hailar Basin [J]. , 2024,42(4): 676-690 |
2.LUO Xiujie,LIU Ziwei,XU Mengxia,WANG Mingchang . Extraction method of urban core feature elements based on multi?feature information: a case study of Shenzhen City [J]. , 2024,42(4): 731-739 |
3.GU Chunsheng,XU Shugang,YANG Peng,TANG Xin,ZHANG Qiqi,LI Haomin . Prediction of shear strength of cohesive soil in Gehu Formation based on LASSO??BP neural network model
[J]. , 2023,42(3): 577-587 |
4.LIU Lijuan. Physical property boundaries and grouping evaluation of sandstone reservoirs in Nantun Formation from Wuerxun??Beier sag, Hailar Basin[J]. , 2023,42(2): 297-308 |
5.CHENGZeyu,BIANWeihua,CHENChongyang,YANGZhuo1ong,GAOHang,WANGPujun.Chronology, geochemistry and geological significance of Jurassic volcanic rocks in Cuogang uplift, Hailar Basin[J]. , 2022,41(3): 451-464 |
6.LIDeqi,WEIZhengda,CHENHong,MABoxuan,YANGChangbao.CorreIation between water depth and sea surface temperature in Lingshui--Sanya Bay based on Landsat--8 image[J]. , 2022,41(3): 654-663 |
7.SUNShangbiao1,ZHANGHaiming,XIONGLinghua,ZHANGYuhan,ZHONGLinshan,WANGMinshui,WANGMingchang.Building extraction of remote sensing images based on U-net mode[J]. , 2022,41(2): 342-348 |
8.HONG Yi-ming,WANG Pu-jun,LI Rui-lei,BIAN Wei-hua,HUANG Bu-zhou,ZHENG Jian.Neural network recognition of volcanic rock lithology based
on conventional logging data: a case study of Changling fault depression,southern Songliao Basin[J]. , 2021,40(2): 408-418 |
9.LEI Ting,JIA Jun-yuan,TIAN Fu-jin,MA Qing-shan,KANG Jian-guo,YU Zi-wang. Prediction of rock thermal conductivity based on BP neural network[J]. , 2021,40(1): 131-139 |
10.SU Gang,QIN Sheng-wu,QIAO Shuang-shuang,HU Xiu-yu,CHEN Yang,CHE Wen-chao. Debris flow susceptibility evaluation based on Stacking ensemble learning:
a case study in Yajiang,Sichuan Province [J]. , 2021,40(1): 175-184 |
11.LIU Zi-wei, ZHANG Xu-qing, WANG Ming-chang, YANG Guo-dong, WANG Si-qi.Application of improved convolutional neural network model in remote sensing image scene classification[J]. , 2020,39(4): 953-959 |
12.HOU Yan-ping, REN Yan-guang, SUN Li, ZHANG Hai-jun, WU Hai-bo, PENG Wei, LI Jing-sheng.Analysis of Cretaceous sedimentary characteristics and environment from Well MD2 in Dongming depression, Hailar Basin[J]. , 2020,39(2): 332-343 |
13.LI Jin-feng, LIU Yun-he.Performance analysis of different structure deep neural networks in time-domain airborne EM data imaging[J]. , 2020,39(1): 159-166 |
14.DENG Hao, ZHANG Yan-jun, SHAN Kun, NI Jin, YUE Gao-fan.Study on dynamic compaction of gravelly soil foundation in northeast coast of Dalian based on neural network[J]. , 2020,39(1): 121-126 |
15.YU Hai-yang, CHEN Sheng-bo, YANG Bei-ping, AN Qin.Method of remote sensing estimation of corn yield based on genetic algorithm optimized BP neural network[J]. , 2020,39(1): 208-214 |
|
Copyright by |