Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
AI has tremendous potential to accelerate scientific discovery, the journey from 'deep science' to 'deep tech' and the translation of scientific & engineering research to applied products. Different categories of techniques have recently found applications in different parts of the scientific workflows. AI techniques are likely to drive fundamental changes in how HPC & numerical simulations are done, combinatorial exploration (eg: computational chemistry or biology using diffusion techniques) happens in conjunction with appropriate experimental validation, how design/modelling and operational digital twins will unfold, and how high throughput experimentation along with AI-driven experiment design and virtual lab experimentation is done. It is important to drive up adoption of AI by the scientific and engineering community, and simultaneously evolve both the tools and reimagine the workflows of science/engineering and translation.
Anusandhan National Research Foundation (ANRF) has been recently established as a statutory body with a governing board chaired by the Hon’ ble Prime Minister of India to catalyze the transformation in Research and Innovation across all stakeholders in India.
The talk will also outline the vision, principles and high level approaches ANRF will use to drive collaborations and co investments across stakeholders, and especially around a mission-mode MAHA program on AI for Science and Engineering. We invite deeper community participation from all stakeholders, and especially industry, academia, labs, foundations/philanthrophy to come together with ANRF on the journey to Viksit Bharat.

Speaker Bio
Shiv has been appointed by Hon'ble Prime Minister of India as CEO, Anusandhan National Research Foundation (ANRF). He was previously CTO, Energy Industry, Asia at Microsoft. Previously he was Executive General Manager of Growth Offerings at GE Power Conversion responsible for new Line of Business development in e-Mobility, Commercial & Industrial Solar and digital/AI innovations. Earlier he was at IBM Research - India, and the Chief Scientist of IBM Research - Australia. Before IBM, he was a tenured Full Professor at Rensselaer Polytechnic Institute in Troy, NY, USA. Shiv has degrees from Indian Institute of Technology, Madras (B.Tech, CS), Ohio State University (MS, PhD) and RPI (Executive MBA). Shiv is a Distinguished Alumnus Awardee of IIT Madras (2021, recognizing 0.3% of IITM's alumni over the years) & Ohio State University (2021), Fellow of the IEEE (2010), Fellow of Indian National Academy of Engineering (2015), ACM Distinguished Scientist (2010), Microsoft Gold Club (2024), MIT Technology Review TR100 young innovator (1999)

Abstract
Running sophisticated molecular simulations has traditionally required years of specialized training. A graduate student might spend their first year just learning how to set up a single type of calculation correctly, with subtle errors in input files leading to days of wasted computing time. This creates a bottleneck where even brilliant scientists with important questions must either become simulation experts themselves or depend entirely on the few specialists who are. Aura aims to change this by putting AI between researchers and the complexity. It is a conversational system where you describe your scientific questions such as how a new solar cell material conducts charges, how a potential drug binds to its target, or how a soap molecule organizes in water and intelligent agents translate that into the dozens of precise technical steps required. The system handles the tedious work of file format conversions, parameter selection, and error detection, while keeping researchers informed about possible underlying reasons. This doesn’t replace expertise, but it dramatically lowers the barrier to getting started and reduces the cost of mistakes.

Speaker Bio
Dr. Chandan Kumar Choudhury is a computational chemist with expertise in quantum and molecular simulations, as well as AI-based drug and materials discovery. He earned his PhD in Computational Chemistry from CSIR-National Chemical Laboratory (NCL), Pune, and subsequently completed postdoctoral research at Clemson University, USA. Since 2020, Dr. Choudhury has been an integral member of Prescience Insilico Pvt. Ltd. (Bengaluru), a deep-tech enterprise focused on expediting drug and materials innovation through artificial intelligence, machine learning, and physics-based multiscale simulations. In his current role as Manager of Material Science R&D, he leads the application of computational methodologies for the design of advanced materials, encompassing alloys, polymers, formulations, and sustainable solutions. Dr. Choudhury has authored 20 publications in peer-reviewed journals. With robust training in computational chemistry and extensive experience on both academic and industrial fronts, he is dedicated to advancing computational tools that drive meaningful progress in materials science and pharmaceuticals.

Abstract
To Be Announced Soon

Speaker Bio
Dr. Foram Thakkar is a Senior Researcher at Shell. Since 2012, he has worked across the energy spectrum—from molecular modelling of complex fluids and catalytic materials to porous media, membranes, electrochemical devices, and system‑level optimization. His current focus is on advancing multiscale modelling by integrating physics‑based approaches with AI‑driven methods, aiming to combine physical rigor with data‑centric flexibility for reliable simulations at scale. He earned an M.Tech from IIT Kharagpur and a Ph.D. in Chemical Engineering from IISc Bangalore, completed postdoctoral research at MIT, and previously worked at Samsung Research in Bangalore.

Abstract
The development of next-generation smart materials has been increasingly relying on hybrid approaches combining state-of-the-art computational and data driven approaches. Density Functional Theory (DFT) has played a central role in materials science by providing reliable, physics-based predictions at the atomic scale. However, the high computational cost of DFT restricts its use for large-scale exploration and rapid design. The advent of advanced data driven AI-ML approaches has introduced a disruptive transformation in materials innovation during the past decade. In this talk, we shall discuss how a combination of high throughput data, machine learning and selective DFT checks can lead to efficient design of smart materials, spanning aerospace to renewable energy applications. We shall take up an example from a recent work on a unique deep learning (DNN) tool coupled with DFT, that can accurately predict next-generation energy-efficient Na-ion batteries.

Speaker Bio
Prof. G.P. Das is a Condensed Matter Physicist cum Materials Scientist, specializing in the field of first principles investigation of clusters, solids and heterostructures, with specific applications in materials science and nano-devices. His field of research includes alloys and intermetallics, 2D materials, Semiconductor Spintronics, Quantum Structures, topological materials and energy materials. He served in senior positions at BARC Mumbai, IACS Kolkata and IIT Kharagpur, and is currently an Emeritus Professor in the Research Institute for Sustainable Energy (RISE), TCG-CREST, Kolkata. Prof. Das served as visiting scientist in Max Planck Institute for Solid State Research, Stuttgart (Germany), Virginia Commonwealth University, Richmond (USA), Institute of Materials Research, Sendai (Japan) and University of New South Wales (Australia). He has authored and coauthored about 200 peer reviewed publications, review articles and book chapters, and also spearheaded a number of research programmes nationally and internationally. He has recently been honoured with “Life Time Achievement” award by the Asian Consortium for Computational Materials Science (ACCMS).

Abstract
The development of artificial intelligence (AI) systems for scientific discovery presents unique challenges that differ significantly from traditional AI applications. In this talk, we will discuss an end-to-end AI framework that addresses these challenges, using materials discovery as a compelling use case. We will explore how AI approaches can transform a traditionally sequential and time-intensive process into an efficient computational workflow. The discussion will center on a three-tier AI system architecture: (i) specialized large language models (LLMs) and other information extraction models incorporating domain-specific knowledge representations for intelligent search space reduction, (ii) graph neural networks that combine physics-based inductive biases for materials simulation, and (iii) LLM agents for automated experiments. Through practical demonstrations, we will examine how these AI components handle complex scientific problems, particularly focusing on information extraction from tables, generative modeling of crystal structures, and atomistic modeling of materials. We will analyze the integration of physical constraints and domain knowledge into neural architectures, demonstrating how this enhances model interpretability and generalization. The talk concludes by examining open problems in scientific AI, including causal discovery, out-of-distribution generalization, and the seamless integration of symbolic and neural reasoning for scientific applications.

Speaker Bio
Prof. 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. Anoop completed his Ph.D. in Civil Engineering from Indian Institute of Science Bangalore in 2015, after which, he worked as a postdoctoral researcher in University of California Los Angeles from 2015 to 2017. Prior to this, he completed his B.Tech. in Civil Engineering from National Institute of Technology Calicut in 2009. He works at the intersection of materials, mechanics, simulations, and AI and ML with the goal of accelerating materials modeling and discovery. He has published more than 120 international peer-reviewed journal publications and has 2 granted patents. He has won several awards including Sir A. Pilkington Award by Society of Glass Technology, UK (2024), Alexander von Humboldt Fellowship (2023) for experienced researchers, Google Research Scholar Award (2023), W. A. Weyl International
Glass Science Award by International Commission on Glass (2022), Indian National Academy of Engineering Young Engineer Award (INAE YAE 2020), BRNS-DAE Young Scientist Award (2021), Indian Academy of Sciences Associateship (2022), and National Academy of Science India Young Scientist Award (NASI YSA 2021).

Abstract
One of our recent interests has been to design permanent magnets without rare earth elements. This is both a fundamental and a strategic challenge, the latter due to supply side constraints on RE elements. We developed two generative models, one a variational
autoencoder, and the other a score-based diffusion model, for design of RE-free magnets. I will present why the problem is challenging from both fundamental and technical angles, and how our models perform relative to other baseline models.

Speaker Bio
Prof. Prasenjit Sen is a professor of Physics at HRI, Prayagraj (Allahabad). He completed his PhD from IIT Kanpur in theoretical Condensed Matter Physics in 1997. He did postdoctoral research at TIFR, Mumbai (and Univ. of Illinois at Urbana-Champaign jointly), University of Illinois at Chicago and the North Carolina State Univ. He has been at HRI since 2004. He has worked on a wide variety of problems related to materials science including atomic clusters, 2D materials, materials for battery electrodes, materials for hydrogen generation via water electrolysis, design of rare earth free magnets etc. using first
principles electronic structure calculations. Recently, he has been applying machine learning and AI to address some of the materials problems. Prof. Sen has been on the Editorial Board of Physica Scripta, and a Regular Associate of the Adbus Salam ICTP Italy from 2012-2017. He is a member of the Materials Research Society of India. Prof. Sen also
spent a year at IISER Tirupati where he was the Dean Faculty.

Abstract
This presentation briefly surveys how modern AI/ML can be coupled to first-principles physics to accelerate discovery and optimization of energy materials, materials that enable clean energy conversion, storage, and efficient catalysis. The talk will begin with a brief introduction of the energy materials, their importance and challenges in this field. Next, I briefly introduce the core methodologies used across the presented studies: density functional theory (DFT), cluster expansion (CE), deep neural networks (DNNs), and symbolic regression (SR). DFT and CE provide physically grounded energetics and scalable alloy thermodynamics; DNN enables rapid prediction and uncertainty-aware screening; and SR yields compact, interpretable relations linking descriptors to target performance metrics. Three case studies illustrate the approaches: (i) exploration of Ti2AC MAX-phase alloys using DFT+CE to map stability and composition-property trends; (ii) DFT-informed DNN models, augmented with LLM-guided candidate generation, for predicting hydrogen-storage capacities; and (iii) rational design of single-atom catalysts on MXenes for Oxygen Evolution Reaction and multifunctional activity.

Speaker Bio
Dr. Satadeep Bhattacharjee is Head of Research and Development at the Indo-Korea Science and Technology Center in Bangalore, India. He received his Ph.D. from the University of Madras while working as a research fellow at the Indira Gandhi Center for Atomic Research (IGCAR), India. He worked as a postdoctoral researcher at the University of Bonn in Germany and the University of Liège in Belgium. He then worked as a researcher at Uppsala University, Sweden and University Arkansas, USA. His research interests encompass a broad aspect of materials theory that includes magnetic materials, spintronics, the role of magnetism in heterogeneous catalysis, electron transport in compound semiconductors, and the development of machine learning models for functional materials. He is also interested in code development and contributes to open-source codes.

Abstract
Elastomeric polymers exhibit high reversible deformation due to their long, flexible, and coiled chains, connected by a small number of cross-links. Due to their unique structure and properties, they find applications in various areas – from simple rubber bands to aerospace sealants. Therefore, accurate computation of their elastic response is paramount for current applications as well as designing next generation elastomers. For this, a machine learning (ML) approach was adopted to train the algorithm using experimentally generated parameters obtained from poly(dimethyl siloxane) (PDMS) and carboxylated nitrile butadiene rubber (XNBR). Further, the trained model was used to predict the stressstrain responses of not only PDMS and XNBR but also that of styrene-butadiene rubber (SBR), which was unknown to the model. It was found that the model could efficiently predict the stress-strain behavior of the SBR with R2 =0.86. The factors obtained from SHAP (shapely additive explanations) analysis are stress, base polymer (weight fraction), chain molecular weight of the base polymer, curing temperature, and cross-link density. The second part of my talk will highlight our recent work on carbon foam. Carbon foam, a lightweight, porous material predominantly constituted of carbon, is made by carbonization of polymeric precursors. The foam is of great interest for structural, thermal management, electromagnetic interference (EMI) shielding, and energy storage electrodes due to its high porosity and electrical conductivity. Accurately predicting the properties of carbon foam using a generalized model is highly desirable since it is difficult to control the pore size, foam density, and pore morphology experimentally. This work introduces an artificial intelligence framework that incorporates physics to predict compressive strength, thermal conductivity, electrical conductivity, and EMI shielding effectiveness. The compressive strength and thermal conductivity are predicted using hybrid physics and machine learning models. In these models, machine learning learns correction factors that are consistent with physical principles based on material, microstructure, and processing conditions. For electrical conductivity, a physics-guided percolation approach combined with machine learning on logarithmic conductivity was used to capture trends related to graphitization. To improve prediction accuracy and model generalization, physics-guided sensitivity augmentation was used. This method systematically enriches the training dataset within meaningful ranges of parameters. EMI shielding effectiveness is treated as a derived response, estimating it mathematically from the predicted electrical conductivity. The validated models serve as an interactive prediction calculator. This tool allows us to estimate properties of previously uncharacterized carbon foams by entering their own input parameters.

Speaker Bio
Dr. T. Umasankar Patro obtained his MSc Chemistry from Berhampur University, Odisha, MTech in Materials Technology from erstwhile IT-BHU (IIT-BHU), and PhD in Chemical Engineering from IIT Bombay. Subsequently, he was a Feinberg postdoctoral fellow at the Weizmann Institute of Science in Israel from 2008-2010. Currently, he is working as an associate professor in the Department of Metallurgical & Materials Engineering in the Defence Institute of Advanced Technology (DIAT), Pune. He has published around 70 international journal papers, including 3 book chapters, filed 4 Indian patents, out of which two are granted. His research interests include the development of polymer nanocomposites for EMI shielding, environmental remediation and biological scaffolds, structure-property relationships in polymer composites, polyurethane synthesis, AI-ML for material property prediction, and polymeric and carbon foams for acoustic insulation and energy storage.

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon

Abstract
To Be Announced Soon

Speaker Bio
To Be Announced Soon