Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313010265> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4313010265 abstract "Abstract This paper proposes an approach to diagnosing the skill of a machine-learning prediction model based on finding combinations of variables that minimize the normalized mean square error of the predictions. This technique is attractive because it compresses the positive skill of a forecast model into the smallest number of components. The resulting components can then be analyzed much like principal components, including the construction of regression maps for investigating sources of skill. The technique is illustrated with a machine-learning model of week 3–4 predictions of western US wintertime surface temperatures. The technique reveals at least two patterns of large-scale temperature variations that are skillfully predicted. The predictability of these patterns is generally consistent between climate model simulations and observations. The predictability is determined largely by sea surface temperature variations in the Pacific, particularly the region associated with the El Nino-Southern Oscillation. This result is not surprising, but the fact that it emerges naturally from the technique demonstrates that the technique can be helpful in “explaining” the source of predictability in machine-learning models." @default.
- W4313010265 created "2023-01-05" @default.
- W4313010265 creator A5019988239 @default.
- W4313010265 creator A5045680211 @default.
- W4313010265 date "2022-01-01" @default.
- W4313010265 modified "2023-10-05" @default.
- W4313010265 title "Advancing interpretability of machine-learning prediction models" @default.
- W4313010265 cites W1970422298 @default.
- W4313010265 cites W2023372691 @default.
- W4313010265 cites W2125896587 @default.
- W4313010265 cites W2150511633 @default.
- W4313010265 cites W2172718203 @default.
- W4313010265 cites W2172996726 @default.
- W4313010265 cites W2193503481 @default.
- W4313010265 cites W2548285523 @default.
- W4313010265 cites W2583306805 @default.
- W4313010265 cites W2947707259 @default.
- W4313010265 cites W2960668489 @default.
- W4313010265 cites W2964178568 @default.
- W4313010265 cites W2969309273 @default.
- W4313010265 cites W2993514765 @default.
- W4313010265 cites W3175417087 @default.
- W4313010265 cites W4210258364 @default.
- W4313010265 cites W4243517362 @default.
- W4313010265 doi "https://doi.org/10.1017/eds.2022.13" @default.
- W4313010265 hasPublicationYear "2022" @default.
- W4313010265 type Work @default.
- W4313010265 citedByCount "1" @default.
- W4313010265 countsByYear W43130102652023 @default.
- W4313010265 crossrefType "journal-article" @default.
- W4313010265 hasAuthorship W4313010265A5019988239 @default.
- W4313010265 hasAuthorship W4313010265A5045680211 @default.
- W4313010265 hasBestOaLocation W43130102651 @default.
- W4313010265 hasConcept C105795698 @default.
- W4313010265 hasConcept C119857082 @default.
- W4313010265 hasConcept C127313418 @default.
- W4313010265 hasConcept C134097258 @default.
- W4313010265 hasConcept C154945302 @default.
- W4313010265 hasConcept C170061395 @default.
- W4313010265 hasConcept C197640229 @default.
- W4313010265 hasConcept C205649164 @default.
- W4313010265 hasConcept C27438332 @default.
- W4313010265 hasConcept C2778439541 @default.
- W4313010265 hasConcept C2778755073 @default.
- W4313010265 hasConcept C2781067378 @default.
- W4313010265 hasConcept C33923547 @default.
- W4313010265 hasConcept C41008148 @default.
- W4313010265 hasConcept C49204034 @default.
- W4313010265 hasConcept C54355233 @default.
- W4313010265 hasConcept C58640448 @default.
- W4313010265 hasConcept C83546350 @default.
- W4313010265 hasConcept C86803240 @default.
- W4313010265 hasConceptScore W4313010265C105795698 @default.
- W4313010265 hasConceptScore W4313010265C119857082 @default.
- W4313010265 hasConceptScore W4313010265C127313418 @default.
- W4313010265 hasConceptScore W4313010265C134097258 @default.
- W4313010265 hasConceptScore W4313010265C154945302 @default.
- W4313010265 hasConceptScore W4313010265C170061395 @default.
- W4313010265 hasConceptScore W4313010265C197640229 @default.
- W4313010265 hasConceptScore W4313010265C205649164 @default.
- W4313010265 hasConceptScore W4313010265C27438332 @default.
- W4313010265 hasConceptScore W4313010265C2778439541 @default.
- W4313010265 hasConceptScore W4313010265C2778755073 @default.
- W4313010265 hasConceptScore W4313010265C2781067378 @default.
- W4313010265 hasConceptScore W4313010265C33923547 @default.
- W4313010265 hasConceptScore W4313010265C41008148 @default.
- W4313010265 hasConceptScore W4313010265C49204034 @default.
- W4313010265 hasConceptScore W4313010265C54355233 @default.
- W4313010265 hasConceptScore W4313010265C58640448 @default.
- W4313010265 hasConceptScore W4313010265C83546350 @default.
- W4313010265 hasConceptScore W4313010265C86803240 @default.
- W4313010265 hasFunder F4320306076 @default.
- W4313010265 hasLocation W43130102651 @default.
- W4313010265 hasOpenAccess W4313010265 @default.
- W4313010265 hasPrimaryLocation W43130102651 @default.
- W4313010265 hasRelatedWork W2052332013 @default.
- W4313010265 hasRelatedWork W2052651488 @default.
- W4313010265 hasRelatedWork W2084389539 @default.
- W4313010265 hasRelatedWork W2113956159 @default.
- W4313010265 hasRelatedWork W2133601928 @default.
- W4313010265 hasRelatedWork W2145311378 @default.
- W4313010265 hasRelatedWork W2172462666 @default.
- W4313010265 hasRelatedWork W2602638098 @default.
- W4313010265 hasRelatedWork W2731203953 @default.
- W4313010265 hasRelatedWork W4255248504 @default.
- W4313010265 hasVolume "1" @default.
- W4313010265 isParatext "false" @default.
- W4313010265 isRetracted "false" @default.
- W4313010265 workType "article" @default.