English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Solid polymer electrolytes hold significant promise as materials fornext-generation batteries due to their superior safety performance, enhancedspecific energy, and extended lifespans compared to liquid electrolytes.However, the material's low ionic conductivity impedes its commercialization,and the vast polymer space poses significant challenges for the screening anddesign. In this study, we assess the capabilities of generative artificialintelligence (AI) for the de novo design of polymer electrolytes. To optimizethe generation, we compare different deep learning architectures, includingboth GPT-based and diffusion-based models, and benchmark the results withhyperparameter tuning. We further employ various evaluation metrics andfull-atom molecular dynamics simulations to assess the performance of differentgenerative model architectures and to validate the top candidates produced byeach model. Out of only 45 candidates being tested, we discovered 17 polymersthat achieve superior ionic conductivity better than any other polymers in ourdatabase, with some of them doubling the conductivity value. In addition, byadopting a pretraining and fine-tuning methodology, we significantly improvethe efficacy of our generative models, achieving quicker convergence, enhancedperformance with limited data, and greater diversity. Using the proposedmethod, we can easily generate a large number of novel, diverse, and validpolymers with a chance of synthesizability, enabling us to identify promisingcandidates with markedly improved efficiency.

De novo Design of Polymer Electrolytes with High Conductivity using GPT-based and Diffusion-based Generative Models