BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:212@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260713T160000
DTEND;TZID=Asia/Kolkata:20260713T170000
DTSTAMP:20260707T061226Z
URL:https://cds.iisc.ac.in/events/cds-kiac-seminar-cds-102-13th-july-adapt
 ive-physics-informed-neural-network-modeling-framework-for-dual-porosity-f
 low/
SUMMARY:CDS-KIAC {Seminar} @ CDS: #102: 13th\, July "Adaptive Physics-Infor
 med Neural Network Modeling Framework for Dual-Porosity Flow"
DESCRIPTION:We welcome you to CDS-KIAC talk on 13th July 2026 (Monday). The
  details are as below:\n\n\n\nSpeaker : Prof. Kalyana B. Nakshatrala\, Uni
 versity of Houston\nTitle : Adaptive Physics-Informed Neural Network Model
 ing Framework\nfor Dual-Porosity Flow\nDate and Time : July 13\, 2026: 04:
 00 PM\nVenue : # 102\, CDS Seminar Hall\n\n\n\nABSTRACT:\nPorous materials
  are central to many scientific and technological systems\, from fractured
  geological formations and tight shales to engineered foams\, biological s
 caffolds\, and plant vascular networks. Across these systems\, flow is oft
 en governed by two hydraulically coupled pore networks: a highly permeable
  macro-network that provides preferential pathways\, and a finer micro-net
 work that controls storage and inter-network exchange. Accurately modeling
  such dual- network systems is essential for predictive simulations in sub
 surface energy\, critical-mineral recovery\, geological carbon and hydroge
 n storage\, geothermal systems\, and engineered porous materials. This tal
 k presents an adaptive physics-informed machine learning framework for flu
 id flow in double-porosity/permeability media. The approach embeds the mix
 ed-form governing equations for coupled pressure and velocity fields direc
 tly into a physics-informed neural network\, enabling both forward predict
 ion and inverse parameter identification. To resolve the multiscale featur
 es and sharp solution gradients typical of dual-network porous media\, the
  framework combines a shared-trunk neural architecture with adaptive loss 
 weighting and error-guided collocation-point refinement. Together\, these 
 elements balance competing physical constraints\, focus learning in high-r
 esidual regions\, and preserve coupling between macro- and micro-pore netw
 orks. Representative numerical studies show that this mesh-free formulatio
 n captures discontinuities across layered media\, remains stable under lar
 ge permeability contrasts\, and avoids spurious oscillations often encount
 ered in classical mixed finite element schemes. Beyond forward simulation\
 , the framework provides a natural platform for assimilating sparse experi
 mental\, field\, or sensor data to infer difficult-to-measure quantities s
 uch as permeability fields and inter-porosity transfer coefficients. By in
 crementally updating the model as new data become available\, the approach
  enables continuously refined forecasting of porous media systems. These c
 apabilities support critical-mineral extraction\, tight-shale production\,
  CO₂ and hydrogen storage-integrity assessment\, and geothermal heat-exc
 hange optimization. The talk concludes by discussing how adaptive scientif
 ic machine learning can complement—and\, in some settings\, transform—
  traditional computational mechanics workflows for porous media modeling.\
 n\nBIOGRAPHY:\nProfessor Kalyana Nakshatrala is the Carl F. Gauss Professo
 r and Department Associate Chair of Civil and Environmental Engineering at
  the University of Houston\, with a courtesy appointment in Mechanical Eng
 ineering. His research and teaching have been recognized with several hono
 rs\, including the Andrea Prosperetti Research Computing Faculty Award\, t
 he Kittinger Teaching Excellence Award\, and the University of Houston Tea
 ching Excellence Award. He previously served as a faculty associate at Cal
 tech and completed postdoctoral work at UIUC in collaboration with Los Ala
 mos and Pacific Northwest National Laboratories. He holds a Ph.D. in Civil
  Engineering\, M.S. degrees in Civil Engineering and Applied Mathematics\,
  and a certificate in Computational Science and Engineering from UIUC\, as
  well as a bachelor’s degree from IIT Madras. He is an associate editor 
 of ASCE’s Journal of Engineering Mechanics and serves on the EMSL User E
 xecutive Committee.\n\nHost Faculty: Prof. Soumyendu Raha\, CDS\n\n\n\nALL
  ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250713T160000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR