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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Data-driven materials design often encounters challenges where systemsrequire or possess qualitative (categorical) information. Metal-organicframeworks (MOFs) are an example of such material systems. The representationof MOFs through different building blocks makes it a challenge for designers toincorporate qualitative information into design optimization. Furthermore, thelarge number of potential building blocks leads to a combinatorial challenge,with millions of possible MOFs that could be explored through time consumingphysics-based approaches. In this work, we integrated Latent Variable GaussianProcess (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) toidentify top-performing MOFs adaptively, autonomously, and efficiently withoutany human intervention. Our approach provides three main advantages: (i) nospecific physical descriptors are required and only building blocks thatconstruct the MOFs are used in global optimization through qualitativerepresentations, (ii) the method is application and property independent, and(iii) the latent variable approach provides an interpretable model ofqualitative building blocks with physical justification. To demonstrate theeffectiveness of our method, we considered a design space with more than 47,000MOF candidates. By searching only ~1% of the design space, LVGP-MOBBO was ableto identify all MOFs on the Pareto front and more than 97% of the 50top-performing designs for the CO$_2$ working capacity and CO$_2$/N$_2$selectivity properties. Finally, we compared our approach with the RandomForest algorithm and demonstrated its efficiency, interpretability, androbustness.

Rapid Design of Top-Performing Metal-Organic Frameworks with Qualitative Representations of Building Blocks