Physics-Informed Machine Learning Society
FDP: 25 September 2026
Annual Meeting: 08-09 July 2027
Andhra Pradesh, India
pimlsociety@gmail.com
Learn how engineering physics, governing equations and data-driven AI can work together - from fundamentals to an introductory hands-on PIML workflow.
Engineering research is entering a phase in which purely equation-based modelling and purely data-driven machine learning may each be insufficient for complex problems. Physics-Informed Machine Learning (PIML) bridges these approaches by incorporating scientific and engineering knowledge into learning systems.
The FDP introduces the fundamentals of PIML, shows how governing equations, conservation laws, constitutive relations, physical constraints, and initial or boundary conditions can be incorporated into machine-learning models, and explores engineering applications and emerging research opportunities.
Participants will gain introductory hands-on exposure to a PIML research workflow: defining a research problem, identifying governing physics, preparing data, building a preliminary model, interpreting results and developing an AI-assisted research narrative.
Interested participants from Chemical Engineering, Aerospace Engineering, Computer Science, Electronics and allied branches are welcome.
Registration is free and seats are limited.
From core concepts to research problem identification and a simple hands-on workflow.
Introduction to machine learning, the need for physics-informed methods and the fundamentals of PIML.
Physics-Informed Neural Networks (PINNs), how they work and how they connect data with physical knowledge.
Governing equations, boundary conditions, conservation laws, constraints and physics-based loss functions.
An introductory practical session applying a simple PIML workflow to an engineering problem.
PIML for engineering modelling, simulation and prediction across multiple application domains.
Research opportunities, current challenges and methods for identifying engineering research problems using PIML.
Fundamentals of Physics-Informed Machine Learning with a Case Study
Adjunct Professor, Economics Department, Massry School of Business, University at Albany, New York, USA; Founder & CEO, ML PowersAI, Inc., USA.
Hands-on Session on PIML
Assistant Professor, Department of Industrial Engineering and Management, Ramaiah Institute of Technology, Bengaluru, India.
Organized by MSRIT AICTE IDEA Lab in association with the Department of Chemical Engineering, Department of CSE (AI & ML), and Department of CSE (Cyber Security), Ramaiah Institute of Technology.
Principal, RIT, Bengaluru; Chief Mentor, MSRIT AICTE IDEA Lab
Vice Principal, RIT; Professor and Head, Department of Chemical Engineering; Coordinator, MSRIT AICTE IDEA Lab
Professor and Head, Department of CSE (AI & ML) and CSE (Cyber Security)
Co-Coordinator, MSRIT AICTE IDEA Lab; Assistant Professor, Department of Chemical Engineering, RIT
Faculty In-Charge, MSRIT AICTE IDEA Lab; Assistant Professor, Mechanical Engineering
Dr. Sravanthi V.; Dr. Sangeeta V.; Dr. Inamul Hasan; and Dr. Naveen N. C.
Chief Patron: Dr. M. R. Seetharam, Chairman, Gokula Education Foundation
Patrons: Sri M. R. Sampangiramaiah; Sri M. R. Kodandaram; Dr. Parswanath H. V.; and Dr. Karisiddappa.
Dr. Alex Koshy; Dr. Vishwachetan D.; Dr. Rakesh Kalshetty; Dr. Senthamilselvi Alagappasamy; and Mr. Chandrashekar N.
Register online using the button or scan the QR code. For registration enquiries, contact the organizing secretary.
MSRIT AICTE IDEA Lab, Ramaiah Institute of Technology, MSR Nagar, Bengaluru, Karnataka 560054
Scan to register