Predicting the Molecular Models, Types, and Maturity of Kerogen in Shale Using Machine Learning and Multi-NMR Spectra

doi:10.1021/acs.energyfuels.2c00738

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	Predicting the Molecular Models, Types, and Maturity of Kerogen in Shale Using Machine Learning and Multi-NMR Spectra
	Kang, Dongliang 1,2; Zhao, Ya-Pu 1,2
刊名	ENERGY & FUELS
	2022-05-16
页码	13
ISSN号	0887-0624
DOI	10.1021/acs.energyfuels.2c00738
通讯作者	Zhao, Ya-Pu(yzhao@imech.ac.cn)
英文摘要	Kerogen is the primary hydrocarbon source of shale oil/gas. The kerogen types and maturity are the two most crucial indicators that can reflect the hydrocarbon generation potential of shale o il/gas reservoirs. These indicators and the other mechanochemical properties can be effectively studied in a bottom-up strategy using kerogen molecular models. Thus, the rapid construction of kerogen molecular models is the cornerstone of shale oil/gas exploitation research. Because of the combinatorial explosion problem, there are two inherent disadvantages of traditional methods: being time- and material-consuming and labor-intensive. We propose a new method that combines machine learning with multiple nuclear magnetic resonance spectra to intelligently and with a high throughput predict the kerogen structures, types, and maturity. Neither the manual analysis of experimental spectra nor the enormous trial-and-error process is required in our method. The 650,000 groups of samples are annotated as the sample datasets. Various spectral types can be analyzed comprehensively using the multi-spectral form, and the predictive capability beyond that of the single input form is obtained. The results demonstrate that the average similarity of prediction molecules and the targets is 91.78%. The prediction accuracy of kerogen components, types, and maturity indexes is better than 92.4%, and the coefficients of determination R-2 are all over 0.934. The results exhibit the excellent comprehensive performance and effectiveness of our method. Thus, we anticipate that this work will shorten the research cycle and tremendously reduce costs in constructing kerogen models and predicting kerogen properties.
资助项目	National Natural Science Foundation of China (NSFC)[12032019] ; National Natural Science Foundation of China (NSFC)[11872363] ; National Natural Science Foundation of China (NSFC)[51861145314] ; Chinese Academy of Sciences (CAS) Key Research Program of Frontier Sciences[QYZDJ-SSW-JSC019] ; CAS Strategic Priority Research Program[XDB22040401]
WOS关键词	ORGANIC TYPE ; ADSORPTION ; OIL ; METHANE ; SIMULATION ; VITRINITE ; MIXTURES ; MOISTURE
WOS研究方向	Energy & Fuels ; Engineering
语种	英语
WOS记录号	WOS:000819242600001
资助机构	National Natural Science Foundation of China (NSFC) ; Chinese Academy of Sciences (CAS) Key Research Program of Frontier Sciences ; CAS Strategic Priority Research Program
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/89727]
专题	力学研究所_非线性力学国家重点实验室
通讯作者	Zhao, Ya-Pu
作者单位	1.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Kang, Dongliang,Zhao, Ya-Pu. Predicting the Molecular Models, Types, and Maturity of Kerogen in Shale Using Machine Learning and Multi-NMR Spectra[J]. ENERGY & FUELS,2022:13.
APA	Kang, Dongliang,&Zhao, Ya-Pu.(2022).Predicting the Molecular Models, Types, and Maturity of Kerogen in Shale Using Machine Learning and Multi-NMR Spectra.ENERGY & FUELS,13.
MLA	Kang, Dongliang,et al."Predicting the Molecular Models, Types, and Maturity of Kerogen in Shale Using Machine Learning and Multi-NMR Spectra".ENERGY & FUELS (2022):13.