FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4353073827> ?p ?o ?g. }

• W4353073827 endingPage "1706" @default.
• W4353073827 startingPage "1706" @default.
• W4353073827 abstract "A stable and reliable cloud detection algorithm is an important step of optical satellite data preprocessing. Existing threshold methods are mostly based on classifying spectral features of isolated individual pixels and do not contain or incorporate the spatial information. This often leads to misclassifications of bright surfaces, such as human-made structures or snow/ice. Multi-temporal methods can alleviate this problem, but cloud-free images of the scene are difficult to obtain. To deal with this issue, we extended four deep-learning Convolutional Neural Network (CNN) models to improve the global cloud detection accuracy for Landsat imagery. The inputs are simplified as all discrete spectral channels from visible to short wave infrared wavelengths through radiometric calibration, and the United States Geological Survey (USGS) global Landsat 8 Biome cloud-cover assessment dataset is randomly divided for model training and validation independently. Experiments demonstrate that the cloud mask of the extended U-net model (i.e., UNmask) yields the best performance among all the models in estimating the cloud amounts (cloud amount difference, CAD = −0.35%) and capturing the cloud distributions (overall accuracy = 94.9%) for Landsat 8 imagery compared with the real validation masks; in particular, it runs fast and only takes about 41 ± 5.5 s for each scene. Our model can also actually detect broken and thin clouds over both dark and bright surfaces (e.g., urban and barren). Last, the UNmask model trained for Landsat 8 imagery is successfully applied in cloud detections for the Sentinel-2 imagery (overall accuracy = 90.1%) via transfer learning. These prove the great potential of our model in future applications such as remote sensing satellite data preprocessing." @default.
• W4353073827 created "2023-03-23" @default.
• W4353073827 creator A5010089602 @default.
• W4353073827 creator A5018668652 @default.
• W4353073827 creator A5029400518 @default.
• W4353073827 creator A5042819322 @default.
• W4353073827 creator A5088354695 @default.
• W4353073827 date "2023-03-22" @default.
• W4353073827 modified "2023-09-25" @default.
• W4353073827 title "Convolutional Neural Network-Driven Improvements in Global Cloud Detection for Landsat 8 and Transfer Learning on Sentinel-2 Imagery" @default.
• W4353073827 cites W1903029394 @default.
• W4353073827 cites W1976978666 @default.
• W4353073827 cites W1977771493 @default.
• W4353073827 cites W1992085857 @default.
• W4353073827 cites W1997887332 @default.
• W4353073827 cites W2013689051 @default.
• W4353073827 cites W2018300239 @default.
• W4353073827 cites W2019812041 @default.
• W4353073827 cites W2025745000 @default.
• W4353073827 cites W2028191110 @default.
• W4353073827 cites W2028240797 @default.
• W4353073827 cites W2053811834 @default.
• W4353073827 cites W2055138256 @default.
• W4353073827 cites W2068124105 @default.
• W4353073827 cites W2071005418 @default.
• W4353073827 cites W2082684467 @default.
• W4353073827 cites W2085282193 @default.
• W4353073827 cites W2086148793 @default.
• W4353073827 cites W2101983762 @default.
• W4353073827 cites W2107118194 @default.
• W4353073827 cites W2118750827 @default.
• W4353073827 cites W2165698076 @default.
• W4353073827 cites W2166251851 @default.
• W4353073827 cites W2167968759 @default.
• W4353073827 cites W2412782625 @default.
• W4353073827 cites W2463021868 @default.
• W4353073827 cites W2512351403 @default.
• W4353073827 cites W2535388113 @default.
• W4353073827 cites W2592939477 @default.
• W4353073827 cites W2605847660 @default.
• W4353073827 cites W2618530766 @default.
• W4353073827 cites W2762941833 @default.
• W4353073827 cites W2774231404 @default.
• W4353073827 cites W2797061331 @default.
• W4353073827 cites W2799805920 @default.
• W4353073827 cites W2800388963 @default.
• W4353073827 cites W2802828972 @default.
• W4353073827 cites W2803946774 @default.
• W4353073827 cites W2806480185 @default.
• W4353073827 cites W2885850997 @default.
• W4353073827 cites W2887257732 @default.
• W4353073827 cites W2896093403 @default.
• W4353073827 cites W2910101086 @default.
• W4353073827 cites W2913323966 @default.
• W4353073827 cites W2917440533 @default.
• W4353073827 cites W2923782278 @default.
• W4353073827 cites W2945778316 @default.
• W4353073827 cites W2946072066 @default.
• W4353073827 cites W2950314938 @default.
• W4353073827 cites W2963073614 @default.
• W4353073827 cites W2963881378 @default.
• W4353073827 cites W2963999097 @default.
• W4353073827 cites W2964309882 @default.
• W4353073827 cites W2992172495 @default.
• W4353073827 cites W2995934920 @default.
• W4353073827 cites W3039156183 @default.
• W4353073827 cites W3041874188 @default.
• W4353073827 cites W3044075475 @default.
• W4353073827 cites W3096846826 @default.
• W4353073827 cites W3141753784 @default.
• W4353073827 cites W3167976421 @default.
• W4353073827 cites W3204895347 @default.
• W4353073827 cites W3208096602 @default.
• W4353073827 cites W4205510142 @default.
• W4353073827 cites W4226359564 @default.
• W4353073827 cites W4239175444 @default.
• W4353073827 cites W4291653124 @default.
• W4353073827 cites W4292702164 @default.
• W4353073827 cites W4312795296 @default.
• W4353073827 cites W4318066364 @default.
• W4353073827 doi "https://doi.org/10.3390/rs15061706" @default.
• W4353073827 hasPublicationYear "2023" @default.
• W4353073827 type Work @default.
• W4353073827 citedByCount "0" @default.
• W4353073827 crossrefType "journal-article" @default.
• W4353073827 hasAuthorship W4353073827A5010089602 @default.
• W4353073827 hasAuthorship W4353073827A5018668652 @default.
• W4353073827 hasAuthorship W4353073827A5029400518 @default.
• W4353073827 hasAuthorship W4353073827A5042819322 @default.
• W4353073827 hasAuthorship W4353073827A5088354695 @default.
• W4353073827 hasBestOaLocation W43530738271 @default.
• W4353073827 hasConcept C108583219 @default.
• W4353073827 hasConcept C111919701 @default.
• W4353073827 hasConcept C127313418 @default.
• W4353073827 hasConcept C154945302 @default.
• W4353073827 hasConcept C160633673 @default.
• W4353073827 hasConcept C2778102629 @default.
• W4353073827 hasConcept C34736171 @default.

• next