Xiaonan Wang*

Department of Chemical Engineering, Tsinghua University, Beijing, China

EXTENDED ABSTRACT: In light of the pressing environmental and climate change challenges, smart approaches are indispensable for sustainable development towards the target of net-zero emissions in future. Advances in artificial intelligence (AI), especially machine learning (ML), provide an enormous variety of smart tools for processing complex data and information generated from experimental and computational research, as well as industrial applications. AI and ML have substantially impacted the research and development norm of new materials and processes for energy and environment. Different data-driven strategies can be utilized at each stage of material characterization, property prediction, synthesis, and theory paradigm discovery to accelerate the whole development process. This talk will first provide an overview and perspectives on ML applications to materials/chemicals discovery and synthesis. Furthermore, active learning strategies to incorporate ML in the high-throughput computational and/or experimental loop are introduced, as an effective approach to accelerate the discovery of new materials with desired functionality. Ultimately, these smart technologies could enable autonomous materials discovery, process optimization, and all aspects of the next-generation intelligent laboratory and industry, thereby facilitating improvement in energy efficiency, emission reduction, and eventually the realization of carbon neutrality target. The challenges to be addressed and prospects of AI applications in material and process discovery are also highlighted.

Keywords: Machine learning; AI; Data-driven; Carbon neutrality; Materials

REFERENCES 

[1] 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.

[2] Guan, J., Huang, T.,…,Wang, X. * & Zhang, S. * (2022). Design and prediction of metal organic framework-based mixed matrix membranes for CO2 capture via machine learning. Cell Reports Physical Science, 3(5), 100864.
[3] Xu, S., Li, J.,..., Liu, B*, & Wang, X.* (2021). Self-improving photosensitizer discovery system via Bayesian search with first-principle simulations. Journal of the American Chemical Society, 143(47), 19769-19777.
[4] Li, Jiali, Mykola Telychko, ..., Lu, J*, & Wang, X. * "Machiine visvision i automated chiral molecule detection and classification in molecular imaging." Journal of the American Chemical Society 143, no. 27 (2021): 10177-10188.