N M Anoop Krishnan
IIT-Delhi, Delhi
N M Anoop Krishnan is an Associate Professor in the Department of Civil Engineering, IIT-Delhi with a joint appointment in the Yardi School of Artificial Intelligence. He completed his Ph.D. in Civil Engineering from the Indian Institute of Science Bengaluru in 2015, after which, he worked as a postdoctoral researcher at the University of California, Los Angeles from 2015 to 2017. He completed his B.Tech. in Civil Engineering from the National Institute of Technology, Calicut, in 2009. He works at the intersection of materials, mechanics, simulations, and AI and ML to accelerate materials modelling and discovery. He has published more than 100 international peer-reviewed journal publications and has 2 granted patents. He has founded a start-up: Substantial AI Pvt. Ltd, incubated at IIT Delhi, for AI-driven materials discovery and process optimization. He has won several awards including the Humboldt Fellowship (2023) for experienced researchers, Google Research Scholar Award (2023), W A Weyl International Glass Science Award by ICG and Penn State University (2022), Indian National Academy of Engineering Young Engineer Award (INAE YAE 2020), BRNS-DAE Young Scientist Award (2021), and National Academy of Science India Young Scientist Award (NASI YSA 2021). He was selected Associate of IASc in 2022.
Session 1D: Lectures by Fellows/Associates
Chairperson: S Sivaram, IISER, Pune
Artificial Intelligence for End-to-End Materials Modeling and Discovery
Materials form the backbone of society. Traditional materials discovery relies on trial-and-error approaches, thereby leading to a design-to-deployment period of 20–30 years. To address this challenge, we will discuss the application of artificial intelligence (AI) and machine learning (ML) in accelerating materials modeling and discovery. Specifically, we propose how an end-to-end AI-driven framework can enable filtering the design space, identify potential candidates with target properties, and then finally test them. To this end, a three-step framework is proposed, including (i) materials-aware large language models for information extraction and candidate selection, (ii) in-silico modeling and design of materials, and (iii) automated experiments driven by large language models (LLMs). Through several examples, we will discuss how AI and ML have made tractable some of the challenging problems in materials and mechanics in particular and the scientific domain in general. We will also discuss how physics-based inductive biases can be leveraged along with data-driven models. Finally, we will discuss some of the outstanding problems in the domain to accelerate real-world materials discovery.