IIT Madras develops AI platform to accelerate sustainable materials discovery
Chennai, Aug 24 (TNT): Researchers at the Indian Institute of Technology Madras (IIT Madras) have developed an Artificial Intelligence-based platform to accelerate the discovery of sustainable, high-performance materials for applications in electric vehicles, aerospace, renewable energy and marine infrastructure.
The researchers have created a large publicly available database of advanced metallic alloys using Large Language Models (LLMs) to extract and organise scientific information from more than 10,000 research papers, the Institute said in a release here on Monday.
The AI-driven framework can extract information on alloy compositions, manufacturing processes and testing conditions and analyse more than 350 material properties, enabling researchers and manufacturers to identify materials with improved performance and sustainability characteristics.
The databases and supporting software have been made freely available through the Alloy Tattvasar platform and GitHub, enabling researchers, startups and industries to use the resources for materials innovation.
The platform addresses a key challenge in materials research, where experimental data is scattered across thousands of scientific publications in text, tables and figures. Manual extraction of such information is time-consuming and prone to errors, the researchers said.
The AI system uses Retrieval-Augmented Generation (RAG) to retrieve relevant examples during information extraction and has been designed to process information from both scientific text and tables.
The platform generated two databases containing more than 185,000 structured records, which the researchers said are among the largest publicly available multicomponent alloy databases. The databases also incorporate environmental, economic and social sustainability indicators.
The researchers demonstrated the application of the database by identifying promising high-entropy alloy compositions for lightweight structural materials for automotive and aerospace applications, soft magnetic materials for electric motors, transformers and electric vehicles, and corrosion-resistant alloys for marine infrastructure, offshore engineering, chemical processing and energy systems.
The research was carried out by Aravindan Kamatchi Sundaram, Dual Degree student; Mohit Chakraborty and Sai Mani Kumar Devathi, BS (Data Science) students and research interns; and B. Pabitramohan Prusty, doctoral scholar, under the guidance of Dr Rohit Batra, Assistant Professor, Department of Metallurgical and Materials Engineering, IIT Madras.
The work received funding from the Anusandhan National Research Foundation (ANRF), the Defence Research and Development Organisation’s Directorate of Industry and Academia (DRDO-DIA), and the Wadhwani School of Data Science and AI at IIT Madras. Computational resources were provided by the Robert Bosch Centre for Data Science and AI (RBCDSAI) at IIT Madras.
The findings have been published in Advanced Science, a peer-reviewed open-access journal published by Wiley.
Dr Rohit Batra said the framework would help reduce the time spent manually collecting data from scientific publications and enable faster identification of materials that combine high performance with sustainability.
The research team plans to expand the AI system to extract information from figures and microstructural images, incorporate life-cycle assessment methodologies and extend the framework to polymers, ceramics and composite materials.
TNT KS
