Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385492055> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4385492055 abstract "<strong class=journal-contentHeaderColor>Abstract.</strong> We investigate how different Convolutional Neural Network (CNN) U-Net models specialised in addressing partial labelling tasks related to mapping Sea Ice Concentration (SIC) can improve performance. We use Sentinel-1 SAR images and human-labelled ice charts as the reference to train models that benefit from advantages gained from different model optimisation objectives by utilising a multistage inference scheme. We find our multistage model inference approach that apply a classification (CrossEntropy or Earth Mover's Distance squared) optimised model to separate open water, intermediate SIC and fully covered ice in conjunction with a regression (Mean Square Error or Binary CrossEntropy) optimised model, that assigns specific intermediate classes, to perform the best. To evaluate the models we introduce several specific metrics illustrating the performance in key areas, such as the separation of macro classes, intermediate class, and an accuracy metric better encapsulating uncertainties in the reference data. We achieve <em>R</em><sup>2</sup>-score of ~93 %, similar to state-of-the-art in the literature (Kucik and Stokholm, 2023). However, our models exhibit significantly better open water and 100 % SIC detections. The multistage synergises high open water and fully covered sea ice accuracies achieved with classification optimised objectives with good intermediate class performance obtained by regressional loss functions. In addition, our findings indicate that the number of classes that the intermediate concentrations are compressed into does not influence the result significantly it is the loss function used to optimise the model that assigns the specific intermediate class to have the largest impact." @default.
- W4385492055 created "2023-08-03" @default.
- W4385492055 creator A5008212117 @default.
- W4385492055 date "2023-08-02" @default.
- W4385492055 modified "2023-10-12" @default.
- W4385492055 title "Comment on egusphere-2023-976" @default.
- W4385492055 doi "https://doi.org/10.5194/egusphere-2023-976-rc1" @default.
- W4385492055 hasPublicationYear "2023" @default.
- W4385492055 type Work @default.
- W4385492055 citedByCount "0" @default.
- W4385492055 crossrefType "peer-review" @default.
- W4385492055 hasAuthorship W4385492055A5008212117 @default.
- W4385492055 hasBestOaLocation W43854920551 @default.
- W4385492055 hasConcept C105795698 @default.
- W4385492055 hasConcept C124101348 @default.
- W4385492055 hasConcept C139945424 @default.
- W4385492055 hasConcept C14036430 @default.
- W4385492055 hasConcept C153180895 @default.
- W4385492055 hasConcept C154945302 @default.
- W4385492055 hasConcept C162324750 @default.
- W4385492055 hasConcept C176217482 @default.
- W4385492055 hasConcept C21547014 @default.
- W4385492055 hasConcept C2776214188 @default.
- W4385492055 hasConcept C2777212361 @default.
- W4385492055 hasConcept C33923547 @default.
- W4385492055 hasConcept C41008148 @default.
- W4385492055 hasConcept C48372109 @default.
- W4385492055 hasConcept C78458016 @default.
- W4385492055 hasConcept C81363708 @default.
- W4385492055 hasConcept C86803240 @default.
- W4385492055 hasConcept C94375191 @default.
- W4385492055 hasConceptScore W4385492055C105795698 @default.
- W4385492055 hasConceptScore W4385492055C124101348 @default.
- W4385492055 hasConceptScore W4385492055C139945424 @default.
- W4385492055 hasConceptScore W4385492055C14036430 @default.
- W4385492055 hasConceptScore W4385492055C153180895 @default.
- W4385492055 hasConceptScore W4385492055C154945302 @default.
- W4385492055 hasConceptScore W4385492055C162324750 @default.
- W4385492055 hasConceptScore W4385492055C176217482 @default.
- W4385492055 hasConceptScore W4385492055C21547014 @default.
- W4385492055 hasConceptScore W4385492055C2776214188 @default.
- W4385492055 hasConceptScore W4385492055C2777212361 @default.
- W4385492055 hasConceptScore W4385492055C33923547 @default.
- W4385492055 hasConceptScore W4385492055C41008148 @default.
- W4385492055 hasConceptScore W4385492055C48372109 @default.
- W4385492055 hasConceptScore W4385492055C78458016 @default.
- W4385492055 hasConceptScore W4385492055C81363708 @default.
- W4385492055 hasConceptScore W4385492055C86803240 @default.
- W4385492055 hasConceptScore W4385492055C94375191 @default.
- W4385492055 hasLocation W43854920551 @default.
- W4385492055 hasOpenAccess W4385492055 @default.
- W4385492055 hasPrimaryLocation W43854920551 @default.
- W4385492055 hasRelatedWork W2055243143 @default.
- W4385492055 hasRelatedWork W2102148524 @default.
- W4385492055 hasRelatedWork W2314720829 @default.
- W4385492055 hasRelatedWork W2811106690 @default.
- W4385492055 hasRelatedWork W2936819511 @default.
- W4385492055 hasRelatedWork W4239306820 @default.
- W4385492055 hasRelatedWork W4293226380 @default.
- W4385492055 hasRelatedWork W4313906399 @default.
- W4385492055 hasRelatedWork W4321444604 @default.
- W4385492055 hasRelatedWork W4321487865 @default.
- W4385492055 isParatext "false" @default.
- W4385492055 isRetracted "false" @default.
- W4385492055 workType "peer-review" @default.