气候变化领域集成服务门户(CCPortal): A hybrid physics-informed data-driven neural network for CO2 storage in depleted shale reservoirs

CCPortal

DOI	10.1016/j.petsci.2023.08.032
	A hybrid physics-informed data-driven neural network for CO2 storage in depleted shale reservoirs
	Wang, Yan-Wei; Dai, Zhen-Xue; Wang, Gui-Sheng; Chen, Li; Xia, Yu-Zhou; Zhou, Yu-Hao
发表日期	2024
ISSN	1672-5107
EISSN	1995-8226
起始页码	21
结束页码	1
卷号	21 期号:1
英文摘要	To reduce CO2 emissions in response to global climate change, shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport processes. However, most current CO2 sequestration models do not adequately consider multiple transport mechanisms. Moreover, the evaluation of CO2 storage processes usually involves laborious and time-consuming numerical simulations unsuitable for practical prediction and decision-making. In this paper, an integrated model involving gas diffusion, adsorption, dissolution, slip flow, and Darcy flow is proposed to accurately characterize CO2 storage in depleted shale reservoirs, supporting the establishment of a training database. On this basis, a hybrid physics-informed data-driven neural network (HPDNN) is developed as a deep learning surrogate for prediction and inversion. By incorporating multiple sources of scientific knowledge, the HPDNN can be configured with limited simulation resources, significantly accelerating the forward and inversion processes. Furthermore, the HPDNN can more intelligently predict injection performance, precisely perform reservoir parameter inversion, and reasonably evaluate the CO2 storage capacity under complicated scenarios. The validation and test results demonstrate that the HPDNN can ensure high accuracy and strong robustness across an extensive applicability range when dealing with field data with multiple noise sources. This study has tremendous potential to replace traditional modeling tools for predicting and making decisions about CO2 storage projects in depleted shale reservoirs. (c) 2023 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).
英文关键词	Deep learning; Physics-informed data-driven neural; network; Depleted shale reservoirs; CO2 storage; Transport mechanisms
语种	英语
WOS研究方向	Energy & Fuels ; Engineering
WOS类目	Energy & Fuels ; Engineering, Petroleum
WOS记录号	WOS:001189047400001
来源期刊	PETROLEUM SCIENCE
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/300781
作者单位	Jilin University; Jilin University; China University of Geosciences; Sinopec; Xi'an Jiaotong University; China University of Petroleum; University of Fribourg
推荐引用方式 GB/T 7714	Wang, Yan-Wei,Dai, Zhen-Xue,Wang, Gui-Sheng,et al. A hybrid physics-informed data-driven neural network for CO2 storage in depleted shale reservoirs[J],2024,21(1).
APA	Wang, Yan-Wei,Dai, Zhen-Xue,Wang, Gui-Sheng,Chen, Li,Xia, Yu-Zhou,&Zhou, Yu-Hao.(2024).A hybrid physics-informed data-driven neural network for CO2 storage in depleted shale reservoirs.PETROLEUM SCIENCE,21(1).
MLA	Wang, Yan-Wei,et al."A hybrid physics-informed data-driven neural network for CO2 storage in depleted shale reservoirs".PETROLEUM SCIENCE 21.1(2024).