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

We address the degree to which machine learning can be used to accurately andtransferably predict post-Hartree-Fock correlation energies. Refined strategiesfor feature design and selection are presented, and the molecular-orbital-basedmachine learning (MOB-ML) method is applied to several test systems.Strikingly, for the MP2, CCSD, and CCSD(T) levels of theory, it is shown thatthe thermally accessible (350 K) potential energy surface for a single watermolecule can be described to within 1 millihartree using a model that istrained from only a single reference calculation at a randomized geometry. Toexplore the breadth of chemical diversity that can be described, MOB-ML is alsoapplied to a new dataset of thermalized (350 K) geometries of 7211 organicmodels with up to seven heavy atoms. In comparison with the previously reported$\Delta$-ML method, MOB-ML is shown to reach chemical accuracy with three-foldfewer training geometries. Finally, a transferability test in which modelstrained for seven-heavy-atom systems are used to predict energies forthirteen-heavy-atom systems reveals that MOB-ML reaches chemical accuracy with36-fold fewer training calculations than $\Delta$-ML (140 versus 5000 trainingcalculations).

A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules