BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.3.5//EN TZID:Asia/Kolkata X-WR-TIMEZONE:Asia/Kolkata BEGIN:VEVENT UID:207@cds.iisc.ac.in DTSTART;TZID=Asia/Kolkata:20260629T113000 DTEND;TZID=Asia/Kolkata:20260629T123000 DTSTAMP:20260623T112123Z URL:https://cds.iisc.ac.in/events/seminar-cds-102-june-29th-1130-physics-g uided-deep-learning-for-large-eddy-simulation-of-turbulent-combustion/ SUMMARY:{Seminar} @ CDS: #102\, June 29th: 11:30: " Physics-Guided Deep Lea rning for Large-Eddy Simulation of Turbulent Combustion." DESCRIPTION:Department of Computational and Data Sciences\nDepartment Semin ar\n\n\n\nSpeaker : Dr. Shubhangi Bansude\, Assistant Professor\, Mechanic al Engineering Department\, IIT Gandhinagar\nTitle : Physics-Guided Deep L earning for Large-Eddy Simulation of Turbulent Combustion.\nDate &\; Ti me : June 29th\, 2026 (Monday)\, 11:30 AM\nVenue : # 102\, CDS Seminar Hal l\n\n\n\nABSTRACT:\n\nThe transition toward carbon-free propulsion and pow er systems demands advancedcomputational models capable of accurately pred icting and optimizing both existing and emerging combustion technologies. Large-eddy simulation (LES) offers a promising approach\, resolving large- scale spatiotemporal features and capturing transient phenomena such as fl ame dynamics and instabilities. However\, LES still faces major challenges : modeling the effects of unresolved subgrid scale (SGS) turbulence\, mana ging the high computational cost of finite-rate chemical kinetics\, and ac curately representing turbulence-chemistry interactions.\n\nThis talk pres ents a physics guided\, data-driven approach that leverages deep learning to address these challenges. It will first discuss a neural ordinary diffe rential equation (NODE) framework developed to accelerate the integration of stiff chemical kinetics within the transported filtered density functio n (FDF) method\, where physical constraints are embedded as a soft penalty to improve adherence to physical laws and generalizability. Results will be presented for this framework across multiple fuels - hydrogen\, methane \, and ammonia - in a pairwise mixing stirred reactor (PMSR) spanning a ra nge of mixing timescales\, demonstrating that the NODE substantially reduc es numerical stiffness and achieves an order-of-magnitude speedup over dir ect integration of detailed kinetics. The talk will then turn to a complem entary\, lower-fidelity alternative: a moments-based method that condenses the chemistry description to a small set of characteristic variables and incorporates SGS statistics through a presumed FDF. Within this framework\ , a deep neural network (DNN) trained to predict the FDF of the mixture fr action will be presented\, along with results showing how this DNN-FDF mod el\, evaluated in LES of variable-density 3D mixing layers\, improves accu racy over the conventional beta-FDF model in reproducing direct numerical simulation (DNS) results. The talk will conclude with a discussion of emer ging opportunities and open challenges in embedding physics-informed machi ne learning within multi-scale simulations of turbulent reacting flows.\n\ nBIOGRAPHY:\n\nDr. Shubhangi Bansude is an Assistant Professor in the Mech anical Engineering Department at IIT Gandhinagar\, where she is PI of the Computational Combustion and Machine Learning (CCML) Lab. She is a researc her in turbulent combustion modeling with specialization in scientific mac hine learning and combustion chemical kinetics. In particular\, her work i nvolves developing physics-guided\, data-driven approaches for turbulent c ombustion modeling and applying them to the simulation of full-scale energ y systems\, with an emphasis on large-eddy simulation (LES). Previously\, she was a Postdoctoral Researcher at Argonne National Laboratory. She comp leted her PhD at the University of Connecticut (UConn) in 2023\, during wh ich she served as a Graduate Teaching Fellow and was awarded the prestigio us General Electric Graduate Fellowship for Innovation. Prior to her docto ral studies\, she worked as an Application Engineer at Siemens PLM Softwar e contributing to advanced computational fluid dynamics (CFD) solutions fo r the automotive and OEM industries. She obtained her BTech in Mechanical Engineering from IIT Gandhinagar in 2014.\n\nHost Faculty: Dr. Konduri Adi tya\n\n\n\nALL ARE WELCOME CATEGORIES:Events,Talks END:VEVENT BEGIN:VTIMEZONE TZID:Asia/Kolkata X-LIC-LOCATION:Asia/Kolkata BEGIN:STANDARD DTSTART:20250629T113000 TZOFFSETFROM:+0530 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE END:VCALENDAR