AI-driven literature mining speeds discovery of heat-stable lead-free dielectric materials
Artificial intelligence has analyzed data scattered across hundreds of research papers to discover new lead-free dielectric materials that maintain stable performance even at high temperatures. The study presents a new approach that could transform materials discovery from a trial-and-error process into a data-driven one.
Researchers at Seoul National University College of Engineering have developed a new method to discover heat-stable, lead-free dielectric materials using AI-driven literature mining. This approach transforms materials discovery from a trial-and-error process into a data-driven one. Professor Ho Won Jang and his team combined multimodal literature mining with physics-informed machine learning to create an inverse-design approach.
By analyzing data from 448 scientific papers, they identified 1,202 dielectric-property records and narrowed down a virtual compositional space to 37 candidate materials. Two compositions, with 1 mol% and 2 mol% tin (Sn) substitution, were synthesized and experimentally confirmed to have high dielectric constants and excellent high-temperature stability.
These materials maintain high dielectric constants more consistently over a broader temperature range, surpassing existing barium titanate-based capacitors. The findings were published in Nature Communications, highlighting the growing importance of dielectric materials for high-temperature applications, such as in electric vehicles and aerospace equipment.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
