Application of unlabelled big data and deep semi-supervised learning to significantly improve the logging interpretation accuracy for deep-sea gas hydrate-bearing sediment reservoirs

doi:10.1016/j.egyr.2022.01.139

CORC > 深海科学与工程研究所 > 中国科学院深海科学与工程研究所 > 深海科学研究部 > 深海地球物理与资源研究室

	Application of unlabelled big data and deep semi-supervised learning to significantly improve the logging interpretation accuracy for deep-sea gas hydrate-bearing sediment reservoirs
	Zhu, Linqi 6,7,8; Wei, Jiangong 1,3,4; Wu, Shiguo 6,7,8; Zhou, Xueqing 6,8; Sun, Jin 2,5,6
刊名	ENERGY REPORTS
	2022-11-01
卷号	8 页码:2947-2963
关键词	Gas hydrate-bearing sediments Deep learning Big data application India national gas hydrate program
ISSN号	2352-4847
DOI	10.1016/j.egyr.2022.01.139
通讯作者	Wei, Jiangong
英文摘要	Due to the extremely complex reservoirs and strong heterogeneity, deep-sea gas hydrate logging porosity calculations still have problems, which further leads to insufficient resource calculation accuracy. Logging reservoir evaluation methods based on intelligence may be able to provide more reliable prediction results, especially the logging evaluation model based on deep learning with great potential. This paper proposes a new method to form unlabelled logging big data, and based on this, establishes a semi-supervised deep learning method suitable for deep-sea gas hydrate-bearing sediments porosity calculation, forming a porosity evaluation model. The method of forming logging big data expands 380 original data samples into 2280 labelled samples and 60050 unlabelled samples, which reduces the sampling requirements for deep-sea sediment formations with high sampling costs. The evaluation results show that the model not only obtains better results than other methods in the inspection wells corresponding to the areas where the training wells are located, but also obtains very good results in other wells that are not involved in the modelling. Compared with traditional prediction methods, the average relative error of porosity prediction is less than 4%. As far as we know, this is the first time that deep learning has been successfully applied to deep-sea hydrate sediment reservoir logging evaluation. It provides a new idea for intelligent logging evaluation of deep-sea hydrate sediment reservoirs.(c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license
资助项目	Laboratory for Marine Geology, Qingdao National Laboratory for Marine Science and Technol-ogy, China[MGQNLM-KF202004] ; National Natural Science Foundation of China[42106213] ; Innovation Group Project of Southern Marine Science and Engineering Guangdong Labo-ratory (Zhuhai) , China[311021003] ; China Postdoctoral Sci-ence Foundation[2021M690161] ; China Postdoctoral Sci-ence Foundation[2021T140691] ; Hainan Provincial Natural Science Foundation of China[421QN281] ; Post-doctorate Funded Project in Hainan Province, China ; Chinese Academy of Sciences-Special Research Assistant Project, China
WOS关键词	KRISHNA-GODAVARI BASIN ; ARTIFICIAL NEURAL-NETWORKS ; NGHP-02 EXPEDITION ; LOG DATA ; WELL ; OFFSHORE ; POROSITY ; PERMEABILITY ; PREDICTION ; SHALE
WOS研究方向	Energy & Fuels
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000783884000008
资助机构	Laboratory for Marine Geology, Qingdao National Laboratory for Marine Science and Technol-ogy, China ; National Natural Science Foundation of China ; Innovation Group Project of Southern Marine Science and Engineering Guangdong Labo-ratory (Zhuhai) , China ; China Postdoctoral Sci-ence Foundation ; Hainan Provincial Natural Science Foundation of China ; Post-doctorate Funded Project in Hainan Province, China ; Chinese Academy of Sciences-Special Research Assistant Project, China
内容类型	期刊论文
源URL	[http://ir.idsse.ac.cn/handle/183446/9273]
专题	深海科学研究部_深海地球物理与资源研究室
通讯作者	Wei, Jiangong
作者单位	1.China Geol Survey, Acad South China Sea Geol Sci, Sanya 572025, Peoples R China 2.CNOOC Res Inst, State Key Lab Nat Gas Hydrate, Beijing 100028, Peoples R China 3.Southern Marine Sci & Engn Guangdong Lab Guangzho, Guangzhou 511458, Peoples R China 4.Guangzhou Marine Geol Survey, MLR Key Lab Marine Mineral Resources, Guangzhou 510075, Peoples R China 5.Key Lab Marine Georesources & Prospecting, Sanya 572000, Hainan, Peoples R China 6.Chinese Acad Sci, Inst Deep sea Sci & Engn, Sanya 572000, Peoples R China 7.Lab Marine Geol, Qingdao Natl Lab Marine Sci & Technol, Qingdao 266237, Peoples R China 8.Southern Marine Sci & Engn Guangdong Lab Zhuhai, Zhuhai 519000, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Linqi,Wei, Jiangong,Wu, Shiguo,et al. Application of unlabelled big data and deep semi-supervised learning to significantly improve the logging interpretation accuracy for deep-sea gas hydrate-bearing sediment reservoirs[J]. ENERGY REPORTS,2022,8:2947-2963.
APA	Zhu, Linqi,Wei, Jiangong,Wu, Shiguo,Zhou, Xueqing,&Sun, Jin.(2022).Application of unlabelled big data and deep semi-supervised learning to significantly improve the logging interpretation accuracy for deep-sea gas hydrate-bearing sediment reservoirs.ENERGY REPORTS,8,2947-2963.
MLA	Zhu, Linqi,et al."Application of unlabelled big data and deep semi-supervised learning to significantly improve the logging interpretation accuracy for deep-sea gas hydrate-bearing sediment reservoirs".ENERGY REPORTS 8(2022):2947-2963.