Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361005429> ?p ?o ?g. }
Showing items 1 to 48 of
48
with 100 items per page.
- W4361005429 abstract "Coarse-grained molecular dynamics (CGMD) simulations address lengthscales and timescales that are critical to many chemical and material applications. Nevertheless, contemporary CGMD modeling is relatively bespoke and there are no black-box CGMD methodologies available that could play a comparable role in discovery applications that density functional theory plays for electronic structure. This gap might be filled by machine learning (ML) based CGMD potentials that simplify model development, but these methods are still in their early stages and have yet to demonstrate a significant advantage over existing physics-based CGMD methods. Here we explore the potential of $Delta$-learning models to leverage the advantages of these two approaches. This is implemented by using ML-based potentials to learn the difference between the target CGMD variable and the predictions of physics-based potentials. The $Delta$-models are benchmarked against the baseline models in reproducing on-target and off-target atomistic properties as a function of CG resolution, mapping operator, and system topology. The $Delta$-models outperform the reference ML-only CGMD models in nearly all scenarios. In several cases, the ML-only models also manage to minimize training error while still producing qualitatively incorrect dynamics, which is corrected by the $Delta$-models. Given their negligible added cost, $Delta$-models provide essentially free gains over their ML-only counterparts. Nevertheless, an unexpected finding is that neither the $Delta$-learning models nor ML-only models significantly outperform the elementary pair-wise models in reproducing atomistic properties. This fundamental failure is attributed to the relatively large irreducible force errors associated with coarse-graining that produces little benefit from using more complex potentials." @default.
- W4361005429 created "2023-03-30" @default.
- W4361005429 creator A5013076223 @default.
- W4361005429 creator A5040584481 @default.
- W4361005429 date "2023-03-27" @default.
- W4361005429 modified "2023-09-30" @default.
- W4361005429 title "∆-Learning for Coarse-Grained Potentials" @default.
- W4361005429 doi "https://doi.org/10.26434/chemrxiv-2023-wq9t3" @default.
- W4361005429 hasPublicationYear "2023" @default.
- W4361005429 type Work @default.
- W4361005429 citedByCount "0" @default.
- W4361005429 crossrefType "posted-content" @default.
- W4361005429 hasAuthorship W4361005429A5013076223 @default.
- W4361005429 hasAuthorship W4361005429A5040584481 @default.
- W4361005429 hasBestOaLocation W43610054291 @default.
- W4361005429 hasConcept C121332964 @default.
- W4361005429 hasConcept C121864883 @default.
- W4361005429 hasConcept C147597530 @default.
- W4361005429 hasConcept C153083717 @default.
- W4361005429 hasConcept C154945302 @default.
- W4361005429 hasConcept C185592680 @default.
- W4361005429 hasConcept C41008148 @default.
- W4361005429 hasConcept C59593255 @default.
- W4361005429 hasConceptScore W4361005429C121332964 @default.
- W4361005429 hasConceptScore W4361005429C121864883 @default.
- W4361005429 hasConceptScore W4361005429C147597530 @default.
- W4361005429 hasConceptScore W4361005429C153083717 @default.
- W4361005429 hasConceptScore W4361005429C154945302 @default.
- W4361005429 hasConceptScore W4361005429C185592680 @default.
- W4361005429 hasConceptScore W4361005429C41008148 @default.
- W4361005429 hasConceptScore W4361005429C59593255 @default.
- W4361005429 hasFunder F4320306076 @default.
- W4361005429 hasLocation W43610054291 @default.
- W4361005429 hasOpenAccess W4361005429 @default.
- W4361005429 hasPrimaryLocation W43610054291 @default.
- W4361005429 hasRelatedWork W1505529854 @default.
- W4361005429 hasRelatedWork W1979636120 @default.
- W4361005429 hasRelatedWork W2000045761 @default.
- W4361005429 hasRelatedWork W2007535360 @default.
- W4361005429 hasRelatedWork W2052104336 @default.
- W4361005429 hasRelatedWork W2078162783 @default.
- W4361005429 hasRelatedWork W2089020875 @default.
- W4361005429 hasRelatedWork W2255250153 @default.
- W4361005429 hasRelatedWork W2923284750 @default.
- W4361005429 hasRelatedWork W3101568290 @default.
- W4361005429 isParatext "false" @default.
- W4361005429 isRetracted "false" @default.
- W4361005429 workType "article" @default.