Identifying regions of importance in wall-bounded turbulence through explainable deep learning

Cremades, AndrésKTH,Teknisk mekanik,Linné Flow Center, FLOW,CMT-Motores Térmicos, Universitat Politècnica de València, Camino de Vera s/n, 46022, Valencia, Spain, Camino de Vera s/n (författare)

QC 20240527
Despite its great scientific and technological importance, wall-bounded turbulence is an unresolved problem in classical physics that requires new perspectives to be tackled. One of the key strategies has been to study interactions among the energy-containing coherent structures in the flow. Such interactions are explored in this study using an explainable deep-learning method. The instantaneous velocity field obtained from a turbulent channel flow simulation is used to predict the velocity field in time through a U-net architecture. Based on the predicted flow, we assess the importance of each structure for this prediction using the game-theoretic algorithm of SHapley Additive exPlanations (SHAP). This work provides results in agreement with previous observations in the literature and extends them by revealing that the most important structures in the flow are not necessarily the ones with the highest contribution to the Reynolds shear stress. We also apply the method to an experimental database, where we can identify structures based on their importance score. This framework has the potential to shed light on numerous fundamental phenomena of wall-bounded turbulence, including novel strategies for flow control.

Hoyas, SergioInstituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València, 46022, Valencia, Spain (författare)
Deshpande, RahulDepartment of Mechanical Engineering, University of Melbourne, 3010, Parkville, VIC, Australia (författare)
Quintero, PedroCMT-Motores Térmicos, Universitat Politècnica de València, Camino de Vera s/n, 46022, Valencia, Spain, Camino de Vera s/n (författare)
Lellep, MartinSUPA, School of Physics and Astronomy, The University of Edinburgh, James Clerk Maxwell Building, Peter Guthrie Tait Road, EH9 3FD, Edinburgh, UK, James Clerk Maxwell Building, Peter Guthrie Tait Road (författare)
Lee, Will JunghoonDepartment of Mechanical Engineering, University of Melbourne, 3010, Parkville, VIC, Australia (författare)
Monty, Jason P.Department of Mechanical Engineering, University of Melbourne, 3010, Parkville, VIC, Australia (författare)
Hutchins, NicholasDepartment of Mechanical Engineering, University of Melbourne, 3010, Parkville, VIC, Australia (författare)
Linkmann, MoritzSchool of Mathematics and Maxwell Institute for Mathematical Sciences, University of Edinburgh, EH9 3FD, Edinburgh, UK (författare)
Marusic, IvanDepartment of Mechanical Engineering, University of Melbourne, 3010, Parkville, VIC, Australia (författare)
Vinuesa, RicardoKTH,Teknisk mekanik,Linné Flow Center, FLOW(Swepub:kth)u12xffui (författare)
KTHTeknisk mekanik (creator_code:org_t)

Av författaren/redakt...: Cremades, Andrés; Hoyas, Sergio; Deshpande, Rahul; Quintero, Pedro; Lellep, Martin; Lee, Will Jungho ...; visa fler...; Monty, Jason P.; Hutchins, Nichol ...; Linkmann, Moritz; Marusic, Ivan; Vinuesa, Ricardo; visa färre...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Maskinteknik; och Strömningsmekani ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.