Xiaonan Wang
Department of Chemical Engineering, Tsinghua University, Beijing, 100084, China
EXTENDED ABSTRACT: The rapid evolution of Artificial Intelligence (AI) offers enormous opportunities for the realm of chemistry and materials. Data-driven strategies are transfom血g traditional research paradigms that often reply on exhaustive trial-and-error approaches. AI emerges as a pivotal tool to navigate the complexities in materials innovation. This talk will shed light on how AI, especially machine learning(ML), can redefine traditional workflow, streamlining materials synthesis, characterization, and fabrication. By introducing an AI-integrated multi-scale chemical data platform, we demonstrate the integration of high-throughput computational and experimental methods for accelerated materials development. Such integration has proven instrumental in pioneering material technologies, highlighting innovations in eco-friendly catalysts, sustainable membrane materials, and next-generation energy solutions. Moreover, the inherent capability of AI to adeptly guide experiments, coupled with its vast data processing abilities, augments our understanding of the expansive design space. In conclusion, this talk will provide insights into the future landscape of AI-enhanced chemistry and materials research and manufacturing, underscoring the promises, potential applications, and the inevitable challenges. The synergy of AI especially future foundation models and materials development will be more and more promising with broader community efforts in building open database and platforms.
Keywords: Machine learning; AI; Data-driven; Multi-scale; Materials
References
[1] Hippalgaonkar, Kedar*, Qianxiao Li, Xiaonan Wang, John W. Fisher III, James Kirkpatrick, and Tonio Buonassisi. "Knowledge-integrated machine learning for materials: lessons from gameplaying and robotics." Nature Reviews Materials 8, no. 4 (2023): 241-260.
[2] Yang, H., Li, J.,…,Wang, X. * & Chen, P. Y. * (2022). . A Automatic strain sensor design via active learning and data augmentation for soft machines. Nature Machine Intelligence, 4(1), 84-94.
[3] Li, Jiali, Mykola Telychko,…，Lu, J*, & Wang, X. * "Machiine ne visvision i automated chiral molecule detection and classification in molecular imaging." Journal of the American Chemical Society 143, no. 27 (2021): 10177-10188.
Prof. Xiaonan Wang is currently an associate professor in the Department of Chemical Engineering at Tsinghua University. She received her BEng from Tsinghua University in 2011 and PhD from University of California, Davis in 2015. After working as a postdoctoral research associate at Imperial College London, she joined the National University of Singapore(NUS) as an assistant professor since 2017 and later became an adjunct associate professor. Her research focuses on the development of intelligent computational methods including multiscale modelling, optimization, data analytics and machine learning for applications in advanced materials, energy, environmental and manufacturing systems to support smart and sustainable development. She is leading a Smart Systems Engineering research group at Tsinghua and NUS of more than 20 team members as PI and also led the Artificial Intelligence for Accelerated Materials Development programs in China and Singapore. She has published more than 140 peer-reviewed papers with an H-index of 43, organized and chaired several international conferences, and delivered more than 60 presentations and invited talks at conferences and universities on five continents. She is an associate editor and editorial board member of 10 SCI journals e.g., Applied Energy, Advanced Intelligent Systems. She was recognized as a World's Top 2% Scientists, ACS Sustainable Chemistry & Engineering Lectureship Award Winner, AIChE-SLS Outstanding Young Principal Investigator, IChemE Global Awards Young Researcher finalist and selected for Royal Society International Exchanges Award, as well several best paper awards at IEEE and Applied Energy conferences and journals.