Scientific Achievement
- Researchers in the Inorganic/Organic Nanocomposites program determined that machine learning accelerated the discovery of novel polymers as outstanding dielectric materials for high temperature energy-storing capacitors
Significance and Impact
- Developing heat-resistant dielectric polymers is crucial for energy storage applications, yet achieving both thermal stability and electrical insulation is challenging. This work highlights a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polysulfates, underscores its promise for applications in demanding electrified environments
Research Details
- Feed-forward neuron network machine learning predicted key parameters for down selecting polysulfates as high performing heat-resistant dielectric polymers
- Polysulfate candidates are synthesized through click chemistry.
- The film capacitors showcased superior high temperature energy storage properties
Publication Details
H. Li, H. Zheng, T. Yue, Z. Xie, SP. Yu, J. Zhou, T. Kapri, Y. Wang, Z. Cao, H. Zhao, A. Kemelbay, J. He, G. Zhang, P.F. Pieters, E.A. Dailing, J,R. Cappiello, M. Salmeron, X. Gu, T. Xu, P. Wu, Y. Li, K.B. Sharpless, Y. Liu, Nature Energy (2025).
DOI: 10.1038/s41560-024-01670-z
Work was performed at Molecular Foundry.
