BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:174@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260115T100000
DTEND;TZID=Asia/Kolkata:20260115T110000
DTSTAMP:20260106T155850Z
URL:https://cds.iisc.ac.in/events/m-tech-research-thesis-colloquium-cds-a-
 physics-informed-framework-for-super-resolution-of-fluid-flows/
SUMMARY:M.Tech Research Thesis {Colloquium}: CDS: "A physics-informed frame
 work for super-resolution of fluid flows"
DESCRIPTION:DEPARTMENT OF COMPUTATIONAL AND DATA SCIENCES\nM.Tech Research 
 Thesis Colloquium\n\n\n\nSpeaker : Ms. Diya Nag Chaudhury\nS.R. Number : 0
 6-18-01-10-22-23-1-23885\nTitle : "A physics-informed framework for super-
 resolution of fluid flows"\nResearch Supervisor : Prof. Sashikumaar Ganesa
 n\nDate &amp\; Time : January 15\, 2026\, 10.00 AM\nVenue : # 102 CDS Semi
 nar Hall\n\n\n\nABSTRACT\n\nThe reconstruction of high-resolution flow fie
 lds from low-resolution data remains a persistent challenge within fluid d
 ynamics. Super-resolution using deep learning is a valuable tool for enhan
 cing visualizations of flow fields to recover detailed features from low-r
 esolution data. This work introduces the Bicubic Fourier Neural Operator (
 Bicubic FNO)\, which combines the benefits of both bicubic interpolation a
 nd FNO.\n\nWe compare our architecture against standard FNO and two convol
 utional neural network (CNN) models reported in the literature for super-r
 esolution: Super-resolution Convolutional Neural Network (SRCNN)\, widely 
 used for natural images\, and the DSC/MS model\, designed for reconstructi
 ng high-resolution turbulent flow fields. We tested our model on two-dimen
 sional decaying homogeneous isotropic turbulence and achieved a 10.47% imp
 rovement over the standard FNO and a 19.59% improvement over the DSC/MS mo
 del in terms of Peak Signal-to-Noise Ratio (PSNR). Moreover\, for a simila
 r performance\, the Bicubic FNO led to a significant reduction of 74% in p
 arameter count over standard FNO. We extend our research to integrate phys
 ics constraints into the framework\, ensuring that the model is able to re
 construct physically consistent flow fields even with extremely sparse dat
 a.\n\nThis research highlights the contributions of Bicubic FNO\, its exte
 nsion with physical constraints and demonstrates that we can extract meani
 ngful turbulent features while significantly reducing the dependency on ma
 ssive datasets.\n\n\n\nALL ARE WELCOME
CATEGORIES:MTech Research Thesis Colloquium
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250115T100000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR