Machine learning-based upscaling of rock permeability from pore scale to core scale:Effect of training dataset size and sub-core volumesOA
Permeability characterizes the capacity of porous formations to conduct fluids,thereby governing the performance of carbon capture,utilization,and storage(CCUS),hydrocarbon extraction,and subsurface energy storage.A reliable assessment of rock permeability is therefore essential for these applications.Direct estimation of permeability from low-resolution CT images of large rock samples offers a rapid approach to obtain permeability data.However,the limited resolution fails to capture detailed pore-scale structural features,resulting in low prediction accuracy.To address this limitation,we propose a convolutional neural network(CNN)-based upscaling method that integrates high-precision pore-scale permeability information into core-scale,low-resolution CT images.In our workflow,the large core sample is partitioned into sub-core volumes,whose permeabilities are predicted using CNNs.The upscaled permeability at the core scale is then determined through a Darcy flow solver based on the predicted sub-core permeability map.Additionally,we examine the optimal sub-core volume size that balances computational efficiency and prediction accuracy.This framework effectively incorporates small-scale heterogeneity,enabling accurate permeability upscaling from micrometer-scale pores to centimeter-scale cores.
Yaotian Guo;Fei Jiang;Takeshi Tsuji;Yoshitake Kato;Mai Shimokawara;Lionel Esteban;Mojtaba Seyyedi;Marina Pervukhina;Maxim Lebedev;Ryuta Kitamura
Department of Mechanical Engineering,Yamaguchi University,2-16-1 Tokiwadai,Ube,Yamaguchi 755-8611,JapanDepartment of Mechanical Engineering,Yamaguchi University,2-16-1 Tokiwadai,Ube,Yamaguchi 755-8611,JapanSchool of Engineering,The University of Tokyo,7-3-1 Hongo,Bunkyo-ku,Tokyo 113-8656,JapanJapan Organization for Metals and Energy Security(JOGMEC),1-2-2 Hamada,Mihama-ku,Chiba 261-0025,JapanJapan Organization for Metals and Energy Security(JOGMEC),1-2-2 Hamada,Mihama-ku,Chiba 261-0025,JapanCSIRO Energy Business Unit,26 Dick Perry Avenue,Kensington,Perth,WA 6151,AustraliaCSIRO Energy Business Unit,26 Dick Perry Avenue,Kensington,Perth,WA 6151,AustraliaCSIRO Energy Business Unit,26 Dick Perry Avenue,Kensington,Perth,WA 6151,AustraliaEdith Cowan University,270 Joondalup Drive,Joondalup,WA 6027,AustraliaJapan Organization for Metals and Energy Security(JOGMEC),1-2-2 Hamada,Mihama-ku,Chiba 261-0025,Japan
信息技术与安全科学
Permeability upscalingMachine learningDigital rock physics
《Earth Energy Science》 2026 (1)
P.30-42,13
supported by JSPS KAKENHI Grant Numbers JP22K03927,JP24H00440 and JP21H05202,and JST SPRING Grant Number JPMJSP2111.
评论