Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage

He Li; Hongbo Zheng; Tianle Yue; Zongliang Xie; Shao Peng Yu; Ji Zhou; Topprasad Kapri; Yunfei Wang; Zhiqiang Cao; Haoyu Zhao; Aidar Kemelbay; Jinlong He; Ge Zhang; Priscilla F. Pieters; Eric A. Dailing; John R. Cappiello; Miquel Salmeron; Xiaodan Gu; Ting Xu; Peng Wu; Ying Li; K. Barry Sharpless; Yi Liu

doi:10.1038/s41560-024-01670-z

Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage

He Li
, Hongbo Zheng
, Tianle Yue
, Zongliang Xie
, Shao Peng Yu
, Ji Zhou
, Topprasad Kapri
, Yunfei Wang
, Zhiqiang Cao
, Haoyu Zhao
, Aidar Kemelbay
, Jinlong He
, Ge Zhang
, Priscilla F. Pieters
, Eric A. Dailing
, John R. Cappiello
, Miquel Salmeron
, Xiaodan Gu
, Ting Xu
, Peng Wu

Ying Li, K. Barry Sharpless, Yi Liu

Research output: Contribution to journal › Article › peer-review

57 Scopus citations

Abstract

The development of heat-resistant dielectric polymers that withstand intense electric fields at high temperatures is critical for electrification. Balancing thermal stability and electrical insulation, however, is exceptionally challenging as these properties are often inversely correlated. A traditional intuition-driven polymer design approach results in a slow discovery loop that limits breakthroughs. Here we present a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polymers. A trustworthy feed-forward neural network is trained to predict key proxy parameters and down select polymer candidates from a library of nearly 50,000 polysulfates. The highly efficient and modular sulfur fluoride exchange click chemistry enables successful synthesis and validation of selected candidates. A polysulfate featuring a 9,9-di(naphthalene)-fluorene repeat unit exhibits excellent thermal resilience and achieves ultrahigh discharged energy density with over 90% efficiency at 200 °C. Its exceptional cycling stability underscores its promise for applications in demanding electrified environments.

Original language	English
Article number	4535
Pages (from-to)	90-100
Number of pages	11
Journal	Nature Energy
Volume	10
Issue number	1
DOIs	https://doi.org/10.1038/s41560-024-01670-z
State	Published - Jan 2025
Externally published	Yes

Funding

H.L., Z.X., P.F.P., M.S., T.X. and Y. Liu acknowledge the support from the US Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division, under contract number DE-AC02-05CH11231 within the Inorganic/Organic Nanocomposites Program (KC3104). K.B.S. acknowledges the support from the National Science Foundation (CHE-1610987). Y. Li acknowledges the support from the Air Force Office of Scientific Research (AFOSR) through the Air Force’s Young Investigator Research Program (FA9550-20-1-0183; programme manager: M.-J. Pan and D. Barbee). P.W. acknowledges the support from the National Institutes of Health (R35GM139643). X.G. acknowledges the support from the US Department of Energy, Office of Science, Office of Basic Energy Science under award number DE-SC0022050. Work at the Molecular Foundry was supported by the Office of Science, Office of Basic Energy Sciences, of the US Department of Energy under contract number DE-AC02-05CH11231. We thank T. Xu, P. Liu and Z. Peng for their advice on simulations. We thank S. W. Shelton, V. Altoé, A. M. Schwartzberg, S. Zhang, H. Zhang, A. Gashi, L. M. Klivansky and A. Pham for instrumental and technical support. We thank J. Zhang, C. Yang and M. Qi for their discussion on experimental results.

Access to Document

10.1038/s41560-024-01670-z

Cite this

Li, H., Zheng, H., Yue, T., Xie, Z., Yu, S. P., Zhou, J., Kapri, T., Wang, Y., Cao, Z., Zhao, H., Kemelbay, A., He, J., Zhang, G., Pieters, P. F., Dailing, E. A., Cappiello, J. R., Salmeron, M., Gu, X., Xu, T., ... Liu, Y. (2025). Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage. Nature Energy, 10(1), 90-100. Article 4535. https://doi.org/10.1038/s41560-024-01670-z

@article{986755d29a854c1698d00019289d5312,

title = "Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage",

abstract = "The development of heat-resistant dielectric polymers that withstand intense electric fields at high temperatures is critical for electrification. Balancing thermal stability and electrical insulation, however, is exceptionally challenging as these properties are often inversely correlated. A traditional intuition-driven polymer design approach results in a slow discovery loop that limits breakthroughs. Here we present a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polymers. A trustworthy feed-forward neural network is trained to predict key proxy parameters and down select polymer candidates from a library of nearly 50,000 polysulfates. The highly efficient and modular sulfur fluoride exchange click chemistry enables successful synthesis and validation of selected candidates. A polysulfate featuring a 9,9-di(naphthalene)-fluorene repeat unit exhibits excellent thermal resilience and achieves ultrahigh discharged energy density with over 90\% efficiency at 200 °C. Its exceptional cycling stability underscores its promise for applications in demanding electrified environments.",

author = "He Li and Hongbo Zheng and Tianle Yue and Zongliang Xie and Yu, \{Shao Peng\} and Ji Zhou and Topprasad Kapri and Yunfei Wang and Zhiqiang Cao and Haoyu Zhao and Aidar Kemelbay and Jinlong He and Ge Zhang and Pieters, \{Priscilla F.\} and Dailing, \{Eric A.\} and Cappiello, \{John R.\} and Miquel Salmeron and Xiaodan Gu and Ting Xu and Peng Wu and Ying Li and Sharpless, \{K. Barry\} and Yi Liu",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive licence to Springer Nature Limited 2024.",

year = "2025",

month = jan,

doi = "10.1038/s41560-024-01670-z",

language = "English",

volume = "10",

pages = "90--100",

journal = "Nature Energy",

issn = "2058-7546",

publisher = "Nature Research",

number = "1",

}

Li, H, Zheng, H, Yue, T, Xie, Z, Yu, SP, Zhou, J, Kapri, T, Wang, Y, Cao, Z, Zhao, H, Kemelbay, A, He, J, Zhang, G, Pieters, PF, Dailing, EA, Cappiello, JR, Salmeron, M, Gu, X, Xu, T, Wu, P, Li, Y, Sharpless, KB & Liu, Y 2025, 'Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage', Nature Energy, vol. 10, no. 1, 4535, pp. 90-100. https://doi.org/10.1038/s41560-024-01670-z

TY - JOUR

T1 - Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage

AU - Li, He

AU - Zheng, Hongbo

AU - Yue, Tianle

AU - Xie, Zongliang

AU - Yu, Shao Peng

AU - Zhou, Ji

AU - Kapri, Topprasad

AU - Wang, Yunfei

AU - Cao, Zhiqiang

AU - Zhao, Haoyu

AU - Kemelbay, Aidar

AU - He, Jinlong

AU - Zhang, Ge

AU - Pieters, Priscilla F.

AU - Dailing, Eric A.

AU - Cappiello, John R.

AU - Salmeron, Miquel

AU - Gu, Xiaodan

AU - Xu, Ting

AU - Wu, Peng

AU - Li, Ying

AU - Sharpless, K. Barry

AU - Liu, Yi

PY - 2025/1

Y1 - 2025/1

N2 - The development of heat-resistant dielectric polymers that withstand intense electric fields at high temperatures is critical for electrification. Balancing thermal stability and electrical insulation, however, is exceptionally challenging as these properties are often inversely correlated. A traditional intuition-driven polymer design approach results in a slow discovery loop that limits breakthroughs. Here we present a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polymers. A trustworthy feed-forward neural network is trained to predict key proxy parameters and down select polymer candidates from a library of nearly 50,000 polysulfates. The highly efficient and modular sulfur fluoride exchange click chemistry enables successful synthesis and validation of selected candidates. A polysulfate featuring a 9,9-di(naphthalene)-fluorene repeat unit exhibits excellent thermal resilience and achieves ultrahigh discharged energy density with over 90% efficiency at 200 °C. Its exceptional cycling stability underscores its promise for applications in demanding electrified environments.

AB - The development of heat-resistant dielectric polymers that withstand intense electric fields at high temperatures is critical for electrification. Balancing thermal stability and electrical insulation, however, is exceptionally challenging as these properties are often inversely correlated. A traditional intuition-driven polymer design approach results in a slow discovery loop that limits breakthroughs. Here we present a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polymers. A trustworthy feed-forward neural network is trained to predict key proxy parameters and down select polymer candidates from a library of nearly 50,000 polysulfates. The highly efficient and modular sulfur fluoride exchange click chemistry enables successful synthesis and validation of selected candidates. A polysulfate featuring a 9,9-di(naphthalene)-fluorene repeat unit exhibits excellent thermal resilience and achieves ultrahigh discharged energy density with over 90% efficiency at 200 °C. Its exceptional cycling stability underscores its promise for applications in demanding electrified environments.

UR - https://www.scopus.com/pages/publications/85211086136

U2 - 10.1038/s41560-024-01670-z

DO - 10.1038/s41560-024-01670-z

M3 - Article

AN - SCOPUS:85211086136

SN - 2058-7546

VL - 10

SP - 90

EP - 100

JO - Nature Energy

JF - Nature Energy

IS - 1

M1 - 4535

ER -

Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this