Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011106738> ?p ?o ?g. }
- W3011106738 endingPage "3191" @default.
- W3011106738 startingPage "3185" @default.
- W3011106738 abstract "The binding site and energy is an invaluable descriptor in high-throughput screening of catalysts, as it is accessible and correlates with the activity and selectivity. Recently, comprehensive binding energy prediction machine-learning models have been demonstrated and promise to accelerate the catalyst screening. Here, we present a simple and versatile representation, applicable to any deep-learning models, to further accelerate such process. Our approach involves labeling the binding site atoms of the unrelaxed bare surface geometry; hence, for the model application, density functional theory calculations can be completely removed if the optimized bulk structure is available as is the case when using the Materials Project database. In addition, we present ensemble learning, where a set of predictions is used together to form a predictive distribution that reduces the model bias. We apply the labeled site approach and ensemble to crystal graph convolutional neural network and the ∼40 000 data set of alloy catalysts for CO2 reduction. The proposed model applied to the data set of unrelaxed structures shows 0.116 and 0.085 eV mean absolute error, respectively, for CO and H binding energy, better than the best method (0.13 and 0.13 eV) in the literature that requires costly geometry relaxations. The analysis of the model parameters demonstrates that the model can effectively learn the chemical information related to the binding site." @default.
- W3011106738 created "2020-03-23" @default.
- W3011106738 creator A5006743557 @default.
- W3011106738 creator A5024574386 @default.
- W3011106738 creator A5056868768 @default.
- W3011106738 creator A5058710447 @default.
- W3011106738 creator A5078798665 @default.
- W3011106738 creator A5090795969 @default.
- W3011106738 date "2020-03-19" @default.
- W3011106738 modified "2023-09-29" @default.
- W3011106738 title "Practical Deep-Learning Representation for Fast Heterogeneous Catalyst Screening" @default.
- W3011106738 cites W1531674615 @default.
- W3011106738 cites W1974324776 @default.
- W3011106738 cites W1975997599 @default.
- W3011106738 cites W1978607450 @default.
- W3011106738 cites W1982153238 @default.
- W3011106738 cites W1992985800 @default.
- W3011106738 cites W2001955532 @default.
- W3011106738 cites W2022714449 @default.
- W3011106738 cites W2060745946 @default.
- W3011106738 cites W2061623168 @default.
- W3011106738 cites W2080386283 @default.
- W3011106738 cites W2104489082 @default.
- W3011106738 cites W2120318938 @default.
- W3011106738 cites W2126954122 @default.
- W3011106738 cites W2133406747 @default.
- W3011106738 cites W2151631165 @default.
- W3011106738 cites W2167035995 @default.
- W3011106738 cites W2254794768 @default.
- W3011106738 cites W2314642759 @default.
- W3011106738 cites W2319865050 @default.
- W3011106738 cites W2352719088 @default.
- W3011106738 cites W2408537094 @default.
- W3011106738 cites W2462003543 @default.
- W3011106738 cites W2527189750 @default.
- W3011106738 cites W2531472991 @default.
- W3011106738 cites W2554421598 @default.
- W3011106738 cites W2611493662 @default.
- W3011106738 cites W2619468913 @default.
- W3011106738 cites W2620687153 @default.
- W3011106738 cites W2766856748 @default.
- W3011106738 cites W2772753449 @default.
- W3011106738 cites W2778051509 @default.
- W3011106738 cites W2784179142 @default.
- W3011106738 cites W2785768358 @default.
- W3011106738 cites W2789575256 @default.
- W3011106738 cites W2793372905 @default.
- W3011106738 cites W2798718650 @default.
- W3011106738 cites W2802420383 @default.
- W3011106738 cites W2890961624 @default.
- W3011106738 cites W2896511002 @default.
- W3011106738 cites W2906943923 @default.
- W3011106738 cites W2909236073 @default.
- W3011106738 cites W2936053551 @default.
- W3011106738 cites W2946232728 @default.
- W3011106738 cites W2989657674 @default.
- W3011106738 cites W3101744125 @default.
- W3011106738 cites W3131685164 @default.
- W3011106738 cites W566353445 @default.
- W3011106738 cites W2961429249 @default.
- W3011106738 doi "https://doi.org/10.1021/acs.jpclett.0c00634" @default.
- W3011106738 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32191473" @default.
- W3011106738 hasPublicationYear "2020" @default.
- W3011106738 type Work @default.
- W3011106738 sameAs 3011106738 @default.
- W3011106738 citedByCount "55" @default.
- W3011106738 countsByYear W30111067382020 @default.
- W3011106738 countsByYear W30111067382021 @default.
- W3011106738 countsByYear W30111067382022 @default.
- W3011106738 countsByYear W30111067382023 @default.
- W3011106738 crossrefType "journal-article" @default.
- W3011106738 hasAuthorship W3011106738A5006743557 @default.
- W3011106738 hasAuthorship W3011106738A5024574386 @default.
- W3011106738 hasAuthorship W3011106738A5056868768 @default.
- W3011106738 hasAuthorship W3011106738A5058710447 @default.
- W3011106738 hasAuthorship W3011106738A5078798665 @default.
- W3011106738 hasAuthorship W3011106738A5090795969 @default.
- W3011106738 hasConcept C119857082 @default.
- W3011106738 hasConcept C121332964 @default.
- W3011106738 hasConcept C147597530 @default.
- W3011106738 hasConcept C152365726 @default.
- W3011106738 hasConcept C154945302 @default.
- W3011106738 hasConcept C177264268 @default.
- W3011106738 hasConcept C17744445 @default.
- W3011106738 hasConcept C185544564 @default.
- W3011106738 hasConcept C185592680 @default.
- W3011106738 hasConcept C199360897 @default.
- W3011106738 hasConcept C199539241 @default.
- W3011106738 hasConcept C2776359362 @default.
- W3011106738 hasConcept C41008148 @default.
- W3011106738 hasConcept C45942800 @default.
- W3011106738 hasConcept C50644808 @default.
- W3011106738 hasConcept C81363708 @default.
- W3011106738 hasConcept C93282013 @default.
- W3011106738 hasConcept C94625758 @default.
- W3011106738 hasConceptScore W3011106738C119857082 @default.
- W3011106738 hasConceptScore W3011106738C121332964 @default.
- W3011106738 hasConceptScore W3011106738C147597530 @default.