Publish smarter with AI + Engineering Knowledge
Physics-Informed Machine Learning (PIML) is a modern Artificial Intelligence approach where a computer learns not only from data but also from the engineering and scientific knowledge that humans already know.
Normally, an Artificial Neural Network (ANN) learns by analyzing large amounts of data and discovering patterns on its own.
With Physics-Informed Machine Learning, we give the AI an additional teacher—engineering equations (Newton’s Law, Hooke’s Law, Faraday’s Law or any law governing engineering principles) that describe how real-world systems work. The word "Physics" does not mean studying Physics as an academic subject.
This is where Computer Science, Circuit Branches, and Non-Circuit Branches must work together. ICARM is initiating PIMLS to build that bridge.
It is not about studying Physics as a subject. It means training AI models with the engineering laws, mathematical equations and scientific constraints that already govern real-world systems.
A normal Artificial Neural Network learns mainly from raw data. It may give useful predictions, but it behaves like a black box and may ignore basic engineering reality.
In Physics-Informed Machine Learning, the neural network is trained using both data and governing equations. This makes the model more meaningful, reliable and suitable for engineering research.
Experimental, simulation, industrial or field data from a real system.
Include governing laws, constraints or domain equations during training.
The model learns from data while respecting engineering reality.
Here, “physics” means the governing laws of a system. Every engineering and science branch has such laws, equations and constraints.
This is why Computer Science alone is not enough, and domain engineering alone is also not enough. PIML needs both.
A Computer Science expert can train an ANN, but may not know the engineering law behind a real system. A domain engineer knows the system, but may not know how to build AI models. PIMLS connects both sides for interdisciplinary research and publications.
Computer Science, AI, IT, ECE, EEE and related fields contribute programming, algorithms, ANN training and model development.
Mechanical, Civil, Chemical, Biotech, Agriculture and other branches contribute equations, systems, data and domain problems.
Members receive structured support to develop one publication-ready manuscript through mentoring, review and submission guidance.
Designed for faculty, researchers, scholars and students who want continuous research support instead of one-time workshops.
Topic selection, literature review, manuscript preparation, formatting, submission guidance and publication mentoring.
Constructive technical review for one manuscript before submission to improve quality, clarity and readiness.
Find AI collaborators, domain experts and research partners from other branches for meaningful publication-oriented work.
Learn literature review, research planning, scientific writing, publication ethics and reviewer-response preparation.
Learn how normal engineering equations can be included in ANN/ML training for real-world engineering applications.
30% discount for the February 2027 International Conference and priority preference for participation.
As a Founding Member, you will be invited to participate in the First Annual General Body Meeting of the Physics-Informed Machine Learning Society (PIMLS).
The meeting will discuss and finalize the Society's future roadmap, governing structure, and the appointment or election (as applicable) of the inaugural office bearers, including the Honorary President, Honorary Vice President, Honorary Secretary, Honorary Treasurer, and Directors.
Be part of the team that helps shape the future of PIMLS.
Valid for one year. Includes society activities, mentoring, peer review support, workshops, project networking and one publication guidance track. Membership resources are allocated toward publication-related academic support for one manuscript.
Register & Pay NowEvery Second/Fourth Sunday/Saturday at 7:00 PM IST on Google Meet. Ask doubts about research ideas, publication planning, collaborator matching, manuscript preparation and AI applications.
Understand the vision and ask your questions directly.
Register as a Founding Member for 2026–2027.
Get guidance and connect with suitable collaborators.
Develop your manuscript with peer-review support.
Submit your idea or logo and help create the official identity of the Society.
12–13 February 2027
Venue: M. S. Ramaiah Institute of Technology, Bengaluru.
Members receive 30% discount, priority registration, and are invited to the Annual General Body Meeting.
The Society and the Computing Technology Research Journal (CTRJ) will be officially announced during the Annual General Body Meeting. Members receive updates on publication opportunities.
Join India’s emerging interdisciplinary AI research community and receive structured support for research, collaboration and one publication guidance track per year.