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

Mitigating the climate crisis requires a rapid transition towardslower-carbon energy. Catalyst materials play a crucial role in theelectrochemical reactions involved in numerous industrial processes key to thistransition, such as renewable energy storage and electrofuel synthesis. Toreduce the energy spent on such activities, we must quickly discover moreefficient catalysts to drive electrochemical reactions. Machine learning (ML)holds the potential to efficiently model materials properties from largeamounts of data, accelerating electrocatalyst design. The Open Catalyst ProjectOC20 dataset was constructed to that end. However, ML models trained on OC20are still neither scalable nor accurate enough for practical applications. Inthis paper, we propose task-specific innovations applicable to mostarchitectures, enhancing both computational efficiency and accuracy. Thisincludes improvements in (1) the graph creation step, (2) atom representations,(3) the energy prediction head, and (4) the force prediction head. We describethese contributions and evaluate them thoroughly on multiple architectures.Overall, our proposed PhAST improvements increase energy MAE by 4 to 42$\%$while dividing compute time by 3 to 8$\times$ depending on the targetedtask/model. PhAST also enables CPU training, leading to 40$\times$ speedups inhighly parallelized settings. Python package:\url{https://phast.readthedocs.io}.

PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design