【講座題目】人工智能+理論驅(qū)動(dòng)框架高效設(shè)計(jì)功能材料

【時(shí) 間】2024年6月24日 周一 上午8:30

【地 點(diǎn)】保定校區(qū) 動(dòng)力工程系 教五樓102

【主講人】李昊，日本東北大學(xué) 材料科學(xué)高等研究所（WPI-AIMR）, 副教授

【主講人簡(jiǎn)介】

李昊，副教授，2022年起任職于日本東北大學(xué) (Tohoku University) 材料科學(xué)高等研究所 (WPI-AIMR)，創(chuàng)建“數(shù)字催化及電池實(shí)驗(yàn)室 (DigCat & DigBat)”，作為課題組負(fù)責(zé)人從事材料設(shè)計(jì)與計(jì)算、人工智能 (AI和數(shù)據(jù)科學(xué)) 開發(fā)研究。2014年至今已發(fā)表論文200余篇，包含Nature Catalysis、Nature Communications、Journal of the American Chemical Society、Advanced Materials、ACS Catalysis、德國(guó)應(yīng)化、Chemical Science等領(lǐng)域權(quán)威雜志。

【講座內(nèi)容簡(jiǎn)介】

The design of solid-state materials is essential for a sustainable future. However, conventional materials search sometimes relies on the trial-and-error process from experiments. Meanwhile, the intricate structure-performance relationships of materials usually hamper the development of an effective design guideline. This talk will discuss an avenue to realize a data-driven framework for materials design combining artificial intelligence, materials theory, computational methodology development, and experiments. In particular, we will discuss i) how to reduce the complexity in catalyst design by materials theory and ii) how to develop new computational methods (i.e., package, on-the-cloud platform, model, and algorithm) to accelerate materials simulation. This talk will show the predictive power of theory in electrochemical and thermal catalysis, solid-state battery electrolytes, and hydrogen storage materials. We will also discuss the successful design of an “electron-refinery” strategy by transforming high-temperature thermal catalysis into low-temperature electrocatalysis. Finally, we will discuss the practical design of materials fusing artificial intelligence, materials theory, computational screening, computational methodology development, and experiments.