BEGIN:VCALENDAR

VERSION:2.0

PRODID:-//wp-events-plugin.com//6.6.4.4//EN

TZID:Asia/Jerusalem

X-WR-TIMEZONE:Asia/Jerusalem
BEGIN:VEVENT

UID:0-1522@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20260112T133000

DTEND;TZID=Asia/Jerusalem:20260112T143000

DTSTAMP:20251222T133330Z

URL:https://aerospace.technion.ac.il/events/seminar-slot-2026-01-12/

SUMMARY:Efficient high-fidelity turbulence modeling using convolutional neu
 ral networks
DESCRIPTION:Lecturer:Amir Israel\n Faculty:Aerodynamics\n Institute:Technio
 n – Israel Institute of Technology\n Location:Classroom 165\, ground flo
 or\, Library\, Aerospace Eng.\n Zoom: https://technion.zoom.us/j/935496917
 66\n Abstract: \n\n\nIn the past few years\, the field of Machine Learning
  (ML) in general\, and Deep Learning (DL) in particular\, has been getting
  a lot of attention\, both due to the continued growth of computational po
 wer\, and the generation of large datasets. The field of fluid mechanics i
 s rich in large amount of datasets from experiments and simulations.  Mor
 eover\, the fact that fluid flow often contains reoccurring patterns that 
 can be studied and predicted makes fluid mechanics an excellent candidate 
 for the use of ML.\nThis talk discusses the ability of convolutional neura
 l networks (CNN) to replace classic turbulence models for a specific set o
 f problems efficiently. Although some attempts have been made to use neura
 l networks to create a data-informed turbulence model\, none have managed 
 to do so efficiently for an unsteady case with walls. The unique approach 
 of this work\, necessitating fast predictions\, required using a specific 
 CNN architecture and the use of image processing algorithms. The model can
  be effectively used for problems that require a lot of high-fidelity simu
 lations of flow fields that share similarities. Nevertheless\, the chosen 
 CNN would not necessarily improve cases substantially different from the o
 nes used for the model dataset.\nThe focus is on predicting the Reynolds s
 tresses using CNNs. Specifically\, U-Net . The chosen test case is a flow 
 over a cylinder since it presents different patterns in a relatively low-R
 eynolds number range and has a lot of documentation for comparison. While 
 most papers attempt to create a general model\, this paper explores the po
 ssibility of a case-specific DL model\, enabling the use of different meth
 ods from the ones used so far. Nevertheless\, some generalization is still
  required from the model and will be tested. Specifically\, its ability to
  generalize over various Reynolds numbers.&nbsp\;\n\n&nbsp\;\n\n\n\n Detai
 ls: \n 
CATEGORIES:Seminars,סמינרים
LOCATION:Classroom 165\, ground floor\, Library\, Aerospace Eng.

END:VEVENT

BEGIN:VTIMEZONE

TZID:Asia/Jerusalem

X-LIC-LOCATION:Asia/Jerusalem

BEGIN:STANDARD

DTSTART:20251026T010000

TZOFFSETFROM:+0300

TZOFFSETTO:+0200

TZNAME:IST

END:STANDARD

END:VTIMEZONE
END:VCALENDAR