Deep learning-based temporal inference of hydraulic fracture length and branching using acoustic emission

Simple item page
dc.contributor.authorLiu, Jian
dc.contributor.authorAlDajani, Omar
dc.contributor.authorLi, Bing Qiuyi
dc.contributor.authorLi, Zili
dc.contributor.funderChina Scholarship Council
dc.contributor.funderTaighde Éireann - Research Ireland
dc.date.accessioned2026-07-16T09:50:02Z
dc.date.available2026-07-16T09:50:02Z
dc.date.issued2026-03-20
dc.description.abstractAcoustic emissions (AE) have been widely employed to infer fracture growth and cracking evolution in rocks and engineered structures. This study investigates the correlation between fracture growth – characterized by fracture length and the number of branches – and AE parameters, including counts, locations, and seismic moments, using deep learning (DL) approaches. A novel strategy is proposed that leverages spatiotemporal AE inputs from a historical period (L seconds) and a future timestep (Δt) to predict the incremental fracture length (IFL) and incremental number of fracture branches (INB) within each timestep. A customized DL model, termed AENet, is specifically designed to process the spatiotemporal AE inputs and predict IFL/INB, from which cumulative fracture growth metrics, including cumulative fracture length (CFL) and cumulative number of branches (CNB), are derived. Three hydraulic fracture experimental datasets from the MIT Rock Mechanics Laboratory are used to implement this DL-based correlation analysis. The results demonstrate that fracture growth exhibits a strong correlation with AE evolution, and the trained AENet model is capable of accurately predicting fracture growth from spatiotemporal AE data. Specifically, the AENet model (Δt = 1.0 s) achieves an average coefficient of determination (R2) of 0.7512 and a mean relative error (MRE) of 0.3372 for CFL and CNB inference.en
dc.description.sponsorshipResearch Ireland|21/FFP-P/10090
dc.description.versionPublished Version
dc.format.extent16
dc.format.mimetypeapplication/pdfen
dc.identifier.authororcidLiu, Jian
dc.identifier.authororcidAlDajani, Omar
dc.identifier.authororcidLi, Bing Qiuyi
dc.identifier.authororcidLi, Zili
dc.identifier.citationLiu, J, AlDajani, O, Li, B Q & Li, Z 2026, 'Deep learning-based temporal inference of hydraulic fracture length and branching using acoustic emission', Journal of Rock Mechanics and Geotechnical Engineering, pp. 1-16. https://doi.org/10.1016/j.jrmge.2025.12.046
dc.identifier.doi10.1016/j.jrmge.2025.12.046
dc.identifier.endpage16
dc.identifier.issn1674-7755
dc.identifier.journaltitleJournal of Rock Mechanics and Geotechnical Engineering
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/10468/19076
dc.language.isoen
dc.publisherChinese Academy of Sciences
dc.relation.urihttps://www.scopus.com/pages/publications/105043749399
dc.rights© 2026, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by- nc-nd/4.0/).
dc.rights.accessrightsopen access
dc.rights.licensenameAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.statusPeer reviewed
dc.subjectAcoustic emission
dc.subjectDeep learning
dc.subjectFracture growth
dc.subjectHydraulic fracture
dc.subject[EngineeringArchitecture]
dc.titleDeep learning-based temporal inference of hydraulic fracture length and branching using acoustic emissionen
dc.typeArticle (peer-reviewed)
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
1-s2.0-S1674775526001526-mmc1.docx
Size:
632.2 KB
Format:
Microsoft Word XML
Download
Thumbnail Image
Name:
1-s2.0-S1674775526001526-main.pdf
Size:
11.05 MB
Format:
Adobe Portable Document Format
Download
Collections
School of Engineering and Architecture