AI-Assisted Discovery of High-Temperature Record-Breaker Dielectrics for Energy Storage

Electrostatic capacitors serve as critical energy storage units in advanced electrical and electronic systems used in the energy, defense, aerospace, and transportation sectors. Energy density, the figure of merit for electrostatic capacitors, is primarily determined by the choice of dielectric material. Most industry-grade polymer dielectrics are flexible polyolefins or rigid aromatics. These polymers possess high energy density or high thermal stability, but not both. Here, we use advanced artificial intelligence (AI) techniques, established polymer chemistry, and molecular engineering to discover a handful of dielectrics in the polynorbornene and polyimide families. One exhibits a record-setting energy density of 8.3 J/cc at 200 °C, 11× that of any commercially available polymer dielectric. We find that each of the discovered dielectrics has high thermal stability but varying energy density. By incorporating oxygen into the polymer backbone, we observed the greatest impact on energy density, with an increase of over 5.5 J/cc at °C. Additionally, position and identity of the phenyl substituents modulate the energy density by nearly 1 J/cc. Our findings broaden the range of potential applications for electrostatic capacitors within the 85–200 °C range, such as wind pitch control, hybrid vehicles, and pulsed power systems. We also evaluate available pathways to further enhance the polynorbornene and polyimide families so that these capacitors may perform in even more demanding applications (e.g., aerospace) while being environmentally sustainable. More broadly, this research demonstrates the impact of AI on chemical structure generation and property prediction, highlighting the potential for materials design advancement beyond electrostatic capacitors.