Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386631004> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386631004 abstract "Sea surface slicks naturally occur on the ocean. They have important physical, biogeochemical and ecological functionalities. The automatic detection of slicks on images is useful in many scenarios, e.g., to evaluate long time series of images. However, to the best of our knowledge, no methods for the automatic recognition of sea surface slicks on images exist. In this work, a binary classifier is developed that recognises if a slick is present on an image with the help of Automated Machine Learning (AutoML). AutoML automatically finds a machine learning pipeline for a given problem. Two AutoML approaches are compared: auto-sklearn and AutoKeras. Images from seven sites were available from the North and Baltic Seas. Initially, one site was used for training and testing. It was found that the AutoKeras method demonstrated superior performance compared to the auto-sklearn approach in both f1-score and balanced accuracy. After further optimising the model found by AutoKeras and training it on data from the additional sites, the final model reaches an f1-score of 0.924 and a balanced accuracy of 0.954 on the test dataset. Furthermore, the model achieved an f1-score of 0.710 and a balanced accuracy of 0.925 on a holdout dataset only containing images from a site which was excluded from the training. This shows that the model is not only able to reliably recognise sea surface slicks but it also generalises fairly well to unseen data." @default.
- W4386631004 created "2023-09-13" @default.
- W4386631004 creator A5007185169 @default.
- W4386631004 creator A5056343285 @default.
- W4386631004 creator A5066936780 @default.
- W4386631004 creator A5090702474 @default.
- W4386631004 creator A5092851559 @default.
- W4386631004 date "2023-06-05" @default.
- W4386631004 modified "2023-10-18" @default.
- W4386631004 title "Detecting Sea Surface Slicks using Automated Machine Learning" @default.
- W4386631004 cites W2013609771 @default.
- W4386631004 cites W2014985692 @default.
- W4386631004 cites W2015159529 @default.
- W4386631004 cites W2051913974 @default.
- W4386631004 cites W2108598243 @default.
- W4386631004 cites W2148143831 @default.
- W4386631004 cites W2164777277 @default.
- W4386631004 cites W2964024268 @default.
- W4386631004 cites W2966284335 @default.
- W4386631004 cites W3006256397 @default.
- W4386631004 cites W3009320958 @default.
- W4386631004 cites W3018957966 @default.
- W4386631004 cites W3095983934 @default.
- W4386631004 cites W3128929752 @default.
- W4386631004 cites W3136501774 @default.
- W4386631004 cites W3210758216 @default.
- W4386631004 cites W4213308398 @default.
- W4386631004 cites W4232533539 @default.
- W4386631004 cites W4320718524 @default.
- W4386631004 doi "https://doi.org/10.1109/oceanslimerick52467.2023.10244633" @default.
- W4386631004 hasPublicationYear "2023" @default.
- W4386631004 type Work @default.
- W4386631004 citedByCount "0" @default.
- W4386631004 crossrefType "proceedings-article" @default.
- W4386631004 hasAuthorship W4386631004A5007185169 @default.
- W4386631004 hasAuthorship W4386631004A5056343285 @default.
- W4386631004 hasAuthorship W4386631004A5066936780 @default.
- W4386631004 hasAuthorship W4386631004A5090702474 @default.
- W4386631004 hasAuthorship W4386631004A5092851559 @default.
- W4386631004 hasConcept C119857082 @default.
- W4386631004 hasConcept C12267149 @default.
- W4386631004 hasConcept C154945302 @default.
- W4386631004 hasConcept C199360897 @default.
- W4386631004 hasConcept C41008148 @default.
- W4386631004 hasConcept C43521106 @default.
- W4386631004 hasConcept C50251070 @default.
- W4386631004 hasConcept C51632099 @default.
- W4386631004 hasConcept C66905080 @default.
- W4386631004 hasConcept C87360688 @default.
- W4386631004 hasConcept C95623464 @default.
- W4386631004 hasConceptScore W4386631004C119857082 @default.
- W4386631004 hasConceptScore W4386631004C12267149 @default.
- W4386631004 hasConceptScore W4386631004C154945302 @default.
- W4386631004 hasConceptScore W4386631004C199360897 @default.
- W4386631004 hasConceptScore W4386631004C41008148 @default.
- W4386631004 hasConceptScore W4386631004C43521106 @default.
- W4386631004 hasConceptScore W4386631004C50251070 @default.
- W4386631004 hasConceptScore W4386631004C51632099 @default.
- W4386631004 hasConceptScore W4386631004C66905080 @default.
- W4386631004 hasConceptScore W4386631004C87360688 @default.
- W4386631004 hasConceptScore W4386631004C95623464 @default.
- W4386631004 hasLocation W43866310041 @default.
- W4386631004 hasOpenAccess W4386631004 @default.
- W4386631004 hasPrimaryLocation W43866310041 @default.
- W4386631004 hasRelatedWork W2163707935 @default.
- W4386631004 hasRelatedWork W2556319748 @default.
- W4386631004 hasRelatedWork W3133593829 @default.
- W4386631004 hasRelatedWork W3196324843 @default.
- W4386631004 hasRelatedWork W3200179079 @default.
- W4386631004 hasRelatedWork W3215867059 @default.
- W4386631004 hasRelatedWork W4205288553 @default.
- W4386631004 hasRelatedWork W4322008322 @default.
- W4386631004 hasRelatedWork W4328092580 @default.
- W4386631004 hasRelatedWork W4328134586 @default.
- W4386631004 isParatext "false" @default.
- W4386631004 isRetracted "false" @default.
- W4386631004 workType "article" @default.