Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205087189> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4205087189 endingPage "1513" @default.
- W4205087189 startingPage "1502" @default.
- W4205087189 abstract "Convolutional neural networks (CNNs) are being increasingly investigated as a means to extract sea ice concentration from synthetic aperture radar (SAR) in an automated manner. This is often done using ice charts as training data. However, in these charts, an ice concentration label is given to a large region, which may not have a spatially uniform sea ice concentration distribution at the prediction scale of the CNN. This leads to representativity errors, which can be more pronounced at intermediate sea ice concentrations. In this study, we first investigate ways to perturb the ice chart labels to obtain improved predictions to account for the label uncertainty for intermediate ice concentrations. We then propose a method to augment the ice chart data by rescaling the information in the SAR imagery. The method is found to lead to improved accuracy in comparison to using the ice chart labels alone, with accuracy improving from 0.919 to 0.966. The sea ice concentration maps with the augmented labels also have much finer detail than the other approaches evaluated. These details are visually in agreement with expected sea ice concentration from the SAR data." @default.
- W4205087189 created "2022-01-25" @default.
- W4205087189 creator A5043205759 @default.
- W4205087189 creator A5056017119 @default.
- W4205087189 creator A5083200788 @default.
- W4205087189 date "2022-01-01" @default.
- W4205087189 modified "2023-09-26" @default.
- W4205087189 title "Accounting for Label Errors When Training a Convolutional Neural Network to Estimate Sea Ice Concentration Using Operational Ice Charts" @default.
- W4205087189 cites W1922460326 @default.
- W4205087189 cites W1979124440 @default.
- W4205087189 cites W2004817876 @default.
- W4205087189 cites W2017975941 @default.
- W4205087189 cites W2068258889 @default.
- W4205087189 cites W2072996485 @default.
- W4205087189 cites W2074145556 @default.
- W4205087189 cites W2096413136 @default.
- W4205087189 cites W2149635781 @default.
- W4205087189 cites W2412782625 @default.
- W4205087189 cites W2498631646 @default.
- W4205087189 cites W2608569001 @default.
- W4205087189 cites W2772239202 @default.
- W4205087189 cites W2912226897 @default.
- W4205087189 cites W2915023258 @default.
- W4205087189 cites W3036494218 @default.
- W4205087189 cites W3038391328 @default.
- W4205087189 cites W3040593397 @default.
- W4205087189 cites W3047096992 @default.
- W4205087189 cites W3158152196 @default.
- W4205087189 doi "https://doi.org/10.1109/jstars.2022.3141063" @default.
- W4205087189 hasPublicationYear "2022" @default.
- W4205087189 type Work @default.
- W4205087189 citedByCount "1" @default.
- W4205087189 countsByYear W42050871892023 @default.
- W4205087189 crossrefType "journal-article" @default.
- W4205087189 hasAuthorship W4205087189A5043205759 @default.
- W4205087189 hasAuthorship W4205087189A5056017119 @default.
- W4205087189 hasAuthorship W4205087189A5083200788 @default.
- W4205087189 hasBestOaLocation W42050871891 @default.
- W4205087189 hasConcept C105795698 @default.
- W4205087189 hasConcept C127313418 @default.
- W4205087189 hasConcept C136894858 @default.
- W4205087189 hasConcept C149767477 @default.
- W4205087189 hasConcept C154945302 @default.
- W4205087189 hasConcept C161798024 @default.
- W4205087189 hasConcept C190812933 @default.
- W4205087189 hasConcept C194520297 @default.
- W4205087189 hasConcept C33923547 @default.
- W4205087189 hasConcept C41008148 @default.
- W4205087189 hasConcept C49204034 @default.
- W4205087189 hasConcept C62649853 @default.
- W4205087189 hasConcept C81363708 @default.
- W4205087189 hasConcept C87360688 @default.
- W4205087189 hasConceptScore W4205087189C105795698 @default.
- W4205087189 hasConceptScore W4205087189C127313418 @default.
- W4205087189 hasConceptScore W4205087189C136894858 @default.
- W4205087189 hasConceptScore W4205087189C149767477 @default.
- W4205087189 hasConceptScore W4205087189C154945302 @default.
- W4205087189 hasConceptScore W4205087189C161798024 @default.
- W4205087189 hasConceptScore W4205087189C190812933 @default.
- W4205087189 hasConceptScore W4205087189C194520297 @default.
- W4205087189 hasConceptScore W4205087189C33923547 @default.
- W4205087189 hasConceptScore W4205087189C41008148 @default.
- W4205087189 hasConceptScore W4205087189C49204034 @default.
- W4205087189 hasConceptScore W4205087189C62649853 @default.
- W4205087189 hasConceptScore W4205087189C81363708 @default.
- W4205087189 hasConceptScore W4205087189C87360688 @default.
- W4205087189 hasFunder F4320322676 @default.
- W4205087189 hasFunder F4320325263 @default.
- W4205087189 hasLocation W42050871891 @default.
- W4205087189 hasLocation W42050871892 @default.
- W4205087189 hasLocation W42050871893 @default.
- W4205087189 hasOpenAccess W4205087189 @default.
- W4205087189 hasPrimaryLocation W42050871891 @default.
- W4205087189 hasRelatedWork W2040832422 @default.
- W4205087189 hasRelatedWork W2097781128 @default.
- W4205087189 hasRelatedWork W2100235001 @default.
- W4205087189 hasRelatedWork W2142672783 @default.
- W4205087189 hasRelatedWork W2164810141 @default.
- W4205087189 hasRelatedWork W3207011232 @default.
- W4205087189 hasRelatedWork W4234822209 @default.
- W4205087189 hasRelatedWork W609223539 @default.
- W4205087189 hasRelatedWork W2472193750 @default.
- W4205087189 hasRelatedWork W3021435055 @default.
- W4205087189 hasVolume "15" @default.
- W4205087189 isParatext "false" @default.
- W4205087189 isRetracted "false" @default.
- W4205087189 workType "article" @default.