Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385890289> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4385890289 abstract "Hydrogen diffusion in metals and alloys plays an important role in the discovery of new materials for fuel cell and energy storage technology. While analytic models use hand-selected features that have clear physical ties to hydrogen diffusion, they often lack accuracy when making quantitative predictions. Machine learning models are capable of making accurate predictions, but their inner workings are obscured, rendering it unclear which physical features are truly important. To develop interpretable machine learning models to predict the activation energies of hydrogen diffusion in metals and random binary alloys, we create a database for physical and chemical properties of the species and use it to fit six machine learning models. Our models achieve root-mean-squared-errors between 98-119 meV on the testing data and accurately predict that elemental Ru has a large activation energy, while elemental Cr and Fe have small activation energies.By analyzing the feature importances of these fitted models, we identify relevant physical properties for predicting hydrogen diffusivity. While metrics for measuring the individual feature importances for machine learning models exist, correlations between the features lead to disagreement between models and limit the conclusions that can be drawn. Instead grouped feature importances, formed by combining the features via their correlations, agree across the six models and reveal that the two groups containing the packing factor and electronic specific heat are particularly significant for predicting hydrogen diffusion in metals and random binary alloys. This framework allows us to interpret machine learning models and enables rapid screening of new materials with the desired rates of hydrogen diffusion." @default.
- W4385890289 created "2023-08-17" @default.
- W4385890289 creator A5001046383 @default.
- W4385890289 creator A5026233743 @default.
- W4385890289 creator A5043950605 @default.
- W4385890289 creator A5078686965 @default.
- W4385890289 creator A5088012345 @default.
- W4385890289 date "2023-08-15" @default.
- W4385890289 modified "2023-09-27" @default.
- W4385890289 title "Explainable Machine Learning for Hydrogen Diffusion in Metals and Random Binary Alloys" @default.
- W4385890289 doi "https://doi.org/10.48550/arxiv.2308.07823" @default.
- W4385890289 hasPublicationYear "2023" @default.
- W4385890289 type Work @default.
- W4385890289 citedByCount "0" @default.
- W4385890289 crossrefType "posted-content" @default.
- W4385890289 hasAuthorship W4385890289A5001046383 @default.
- W4385890289 hasAuthorship W4385890289A5026233743 @default.
- W4385890289 hasAuthorship W4385890289A5043950605 @default.
- W4385890289 hasAuthorship W4385890289A5078686965 @default.
- W4385890289 hasAuthorship W4385890289A5088012345 @default.
- W4385890289 hasBestOaLocation W43858902891 @default.
- W4385890289 hasConcept C119857082 @default.
- W4385890289 hasConcept C121332964 @default.
- W4385890289 hasConcept C121864883 @default.
- W4385890289 hasConcept C138885662 @default.
- W4385890289 hasConcept C154945302 @default.
- W4385890289 hasConcept C169258074 @default.
- W4385890289 hasConcept C178790620 @default.
- W4385890289 hasConcept C185592680 @default.
- W4385890289 hasConcept C2776401178 @default.
- W4385890289 hasConcept C33923547 @default.
- W4385890289 hasConcept C37668627 @default.
- W4385890289 hasConcept C41008148 @default.
- W4385890289 hasConcept C41895202 @default.
- W4385890289 hasConcept C48372109 @default.
- W4385890289 hasConcept C512968161 @default.
- W4385890289 hasConcept C69357855 @default.
- W4385890289 hasConcept C94375191 @default.
- W4385890289 hasConcept C97355855 @default.
- W4385890289 hasConceptScore W4385890289C119857082 @default.
- W4385890289 hasConceptScore W4385890289C121332964 @default.
- W4385890289 hasConceptScore W4385890289C121864883 @default.
- W4385890289 hasConceptScore W4385890289C138885662 @default.
- W4385890289 hasConceptScore W4385890289C154945302 @default.
- W4385890289 hasConceptScore W4385890289C169258074 @default.
- W4385890289 hasConceptScore W4385890289C178790620 @default.
- W4385890289 hasConceptScore W4385890289C185592680 @default.
- W4385890289 hasConceptScore W4385890289C2776401178 @default.
- W4385890289 hasConceptScore W4385890289C33923547 @default.
- W4385890289 hasConceptScore W4385890289C37668627 @default.
- W4385890289 hasConceptScore W4385890289C41008148 @default.
- W4385890289 hasConceptScore W4385890289C41895202 @default.
- W4385890289 hasConceptScore W4385890289C48372109 @default.
- W4385890289 hasConceptScore W4385890289C512968161 @default.
- W4385890289 hasConceptScore W4385890289C69357855 @default.
- W4385890289 hasConceptScore W4385890289C94375191 @default.
- W4385890289 hasConceptScore W4385890289C97355855 @default.
- W4385890289 hasLocation W43858902891 @default.
- W4385890289 hasOpenAccess W4385890289 @default.
- W4385890289 hasPrimaryLocation W43858902891 @default.
- W4385890289 hasRelatedWork W2016412471 @default.
- W4385890289 hasRelatedWork W2022898348 @default.
- W4385890289 hasRelatedWork W2334447102 @default.
- W4385890289 hasRelatedWork W2911455822 @default.
- W4385890289 hasRelatedWork W3174196512 @default.
- W4385890289 hasRelatedWork W3211546796 @default.
- W4385890289 hasRelatedWork W4293525103 @default.
- W4385890289 hasRelatedWork W4308191010 @default.
- W4385890289 hasRelatedWork W4318350883 @default.
- W4385890289 hasRelatedWork W4323021782 @default.
- W4385890289 isParatext "false" @default.
- W4385890289 isRetracted "false" @default.
- W4385890289 workType "article" @default.