FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289793550> ?p ?o ?g. }

• W4289793550 abstract "Abstract Progress in the application of machine learning (ML) methods to materials design is hindered by the lack of understanding of the reliability of ML predictions, in particular for the application of ML to small data sets often found in materials science. Using ML prediction of lattice parameter, formation energy and band gap of ABO 3 perovskites as an example, we demonstrate that 1) similar to the composition-structure-property relationships, inclusion in the ML training data set of materials from classes with different chemical properties will not be beneficial and will decrease the accuracy of ML prediction; 2) Reliable results likely will be obtained by ML model for narrow classes of similar materials even in the case where the ML model will show large errors on the dataset consisting of several classes of materials, and 3) materials that satisfy all well-known chemical and physical principles that make a material physically reasonable are likely to be similar and show strong relationships between the properties of interest and the standard features used in ML. We also show that analysis of ML results by construction of a convex hull in features space that encloses accurately predicted systems can be used to identify high-reliability chemically similar regions and extract physical understanding. Our results indicate that the accuracy of ML prediction may be higher than previously appreciated for the regions in which the ML model interpolates the available data, and that inclusion of physically unreasonable systems is likely to decrease ML accuracy. Our work suggests that analysis of the error distributions of ML methods will be beneficial for the further development of the application of ML methods in material science." @default.
• W4289793550 created "2022-08-04" @default.
• W4289793550 creator A5013587381 @default.
• W4289793550 creator A5022094533 @default.
• W4289793550 creator A5023247876 @default.
• W4289793550 date "2022-08-04" @default.
• W4289793550 modified "2023-09-29" @default.
• W4289793550 title "Identification of high-reliability regions of machine learning predictions in materials science using perovskite oxides as an example" @default.
• W4289793550 cites W1865566486 @default.
• W4289793550 cites W1865667476 @default.
• W4289793550 cites W1982598895 @default.
• W4289793550 cites W1984389479 @default.
• W4289793550 cites W2011314414 @default.
• W4289793550 cites W2016587795 @default.
• W4289793550 cites W2039224564 @default.
• W4289793550 cites W2059885388 @default.
• W4289793550 cites W2076498834 @default.
• W4289793550 cites W2084225101 @default.
• W4289793550 cites W2158327254 @default.
• W4289793550 cites W2464725281 @default.
• W4289793550 cites W2749612575 @default.
• W4289793550 cites W2788500979 @default.
• W4289793550 cites W2884430236 @default.
• W4289793550 cites W2903483166 @default.
• W4289793550 cites W2972465042 @default.
• W4289793550 cites W3023659252 @default.
• W4289793550 cites W3085265214 @default.
• W4289793550 cites W3090572406 @default.
• W4289793550 cites W3102994515 @default.
• W4289793550 cites W3167641868 @default.
• W4289793550 cites W3183767639 @default.
• W4289793550 cites W3198188640 @default.
• W4289793550 cites W4221034234 @default.
• W4289793550 cites W4213455561 @default.
• W4289793550 doi "https://doi.org/10.21203/rs.3.rs-1843605/v1" @default.
• W4289793550 hasPublicationYear "2022" @default.
• W4289793550 type Work @default.
• W4289793550 citedByCount "0" @default.
• W4289793550 crossrefType "posted-content" @default.
• W4289793550 hasAuthorship W4289793550A5013587381 @default.
• W4289793550 hasAuthorship W4289793550A5022094533 @default.
• W4289793550 hasAuthorship W4289793550A5023247876 @default.
• W4289793550 hasBestOaLocation W42897935501 @default.
• W4289793550 hasConcept C112680207 @default.
• W4289793550 hasConcept C11413529 @default.
• W4289793550 hasConcept C116834253 @default.
• W4289793550 hasConcept C119857082 @default.
• W4289793550 hasConcept C121332964 @default.
• W4289793550 hasConcept C154945302 @default.
• W4289793550 hasConcept C163258240 @default.
• W4289793550 hasConcept C192562407 @default.
• W4289793550 hasConcept C206194317 @default.
• W4289793550 hasConcept C24890656 @default.
• W4289793550 hasConcept C2524010 @default.
• W4289793550 hasConcept C2781204021 @default.
• W4289793550 hasConcept C33923547 @default.
• W4289793550 hasConcept C41008148 @default.
• W4289793550 hasConcept C43214815 @default.
• W4289793550 hasConcept C59822182 @default.
• W4289793550 hasConcept C86803240 @default.
• W4289793550 hasConcept C97355855 @default.
• W4289793550 hasConceptScore W4289793550C112680207 @default.
• W4289793550 hasConceptScore W4289793550C11413529 @default.
• W4289793550 hasConceptScore W4289793550C116834253 @default.
• W4289793550 hasConceptScore W4289793550C119857082 @default.
• W4289793550 hasConceptScore W4289793550C121332964 @default.
• W4289793550 hasConceptScore W4289793550C154945302 @default.
• W4289793550 hasConceptScore W4289793550C163258240 @default.
• W4289793550 hasConceptScore W4289793550C192562407 @default.
• W4289793550 hasConceptScore W4289793550C206194317 @default.
• W4289793550 hasConceptScore W4289793550C24890656 @default.
• W4289793550 hasConceptScore W4289793550C2524010 @default.
• W4289793550 hasConceptScore W4289793550C2781204021 @default.
• W4289793550 hasConceptScore W4289793550C33923547 @default.
• W4289793550 hasConceptScore W4289793550C41008148 @default.
• W4289793550 hasConceptScore W4289793550C43214815 @default.
• W4289793550 hasConceptScore W4289793550C59822182 @default.
• W4289793550 hasConceptScore W4289793550C86803240 @default.
• W4289793550 hasConceptScore W4289793550C97355855 @default.
• W4289793550 hasLocation W42897935501 @default.
• W4289793550 hasOpenAccess W4289793550 @default.
• W4289793550 hasPrimaryLocation W42897935501 @default.
• W4289793550 hasRelatedWork W2002509893 @default.
• W4289793550 hasRelatedWork W2160116025 @default.
• W4289793550 hasRelatedWork W2373150346 @default.
• W4289793550 hasRelatedWork W2963262460 @default.
• W4289793550 hasRelatedWork W2963392414 @default.
• W4289793550 hasRelatedWork W3092244581 @default.
• W4289793550 hasRelatedWork W3120847218 @default.
• W4289793550 hasRelatedWork W4225307033 @default.
• W4289793550 hasRelatedWork W4289761297 @default.
• W4289793550 hasRelatedWork W4302176079 @default.
• W4289793550 isParatext "false" @default.
• W4289793550 isRetracted "false" @default.
• W4289793550 workType "article" @default.