FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313200744> ?p ?o ?g. }

• W4313200744 endingPage "103152" @default.
• W4313200744 startingPage "103152" @default.
• W4313200744 abstract "Accurate and timely land cover products are critical inputs for landscape planning, and provide key information for biodiversity conservation and food security. However, poor mapping quality and low resolution are considerable issues in existing land cover maps over the African savanna, where land use is complex and changing rapidly, and necessary ground-truth data are sparse and hard to obtain. To overcome this problem, to make optimal use of existing maps, and to minimize manual training data collection, we developed a three-stage ensemble method to make land cover maps. In the first stage, we extracted the consensus of multiple existing land cover products to generate fragmented pixel-wise training labels. In the second stage, we translated pixel-wise training labels to image-wise labels using Random Forest (RF) as a “gap-filling model”, with temporal features extracted from Sentinel-1 time series, raw bands, and vegetation indices derived from PlanetScope basemaps. These image-wise labels were scored and edited by humans and the quality information was used in the next stage. For stage three, we trained a U-Net network based upon these image-wise labels, using Sentinel-1 time series and raw bands of PlanetScope basemaps as image features. Using the information on label quality, a quality-weighted loss function was used in the network to reduce the impact of noise in the training labels. Using Northern Tanzania as a case study, the results demonstrate that ensembles of existing land cover maps provide a useful source of data for developing improved land cover maps over hard-to-classify, data-sparse landscapes. The Random Forest “gap-filling model” had an overall accuracy of 80.26% on our independent test dataset with 7 classes. The final U-Net model had an overall accuracy of 83.57%. This approach can be readily applied to other regions and extents (e.g., regional, global) and other data sources (e.g., Sentinel-2)." @default.
• W4313200744 created "2023-01-06" @default.
• W4313200744 creator A5029034236 @default.
• W4313200744 creator A5065503808 @default.
• W4313200744 creator A5089787049 @default.
• W4313200744 date "2023-02-01" @default.
• W4313200744 modified "2023-09-26" @default.
• W4313200744 title "A super-ensemble approach to map land cover types with high resolution over data-sparse African savanna landscapes" @default.
• W4313200744 cites W1964217023 @default.
• W4313200744 cites W1984670836 @default.
• W4313200744 cites W2011500029 @default.
• W4313200744 cites W2063623478 @default.
• W4313200744 cites W2082201041 @default.
• W4313200744 cites W2094677081 @default.
• W4313200744 cites W2101807845 @default.
• W4313200744 cites W2114385036 @default.
• W4313200744 cites W2129305329 @default.
• W4313200744 cites W2145862305 @default.
• W4313200744 cites W2171979590 @default.
• W4313200744 cites W2307094448 @default.
• W4313200744 cites W2322750819 @default.
• W4313200744 cites W2588316148 @default.
• W4313200744 cites W2731888247 @default.
• W4313200744 cites W2743194349 @default.
• W4313200744 cites W2756660268 @default.
• W4313200744 cites W2766338595 @default.
• W4313200744 cites W2793603191 @default.
• W4313200744 cites W2802420741 @default.
• W4313200744 cites W2885696803 @default.
• W4313200744 cites W2892654670 @default.
• W4313200744 cites W2911964244 @default.
• W4313200744 cites W2920254659 @default.
• W4313200744 cites W2922502341 @default.
• W4313200744 cites W2943472941 @default.
• W4313200744 cites W2954996726 @default.
• W4313200744 cites W2973660294 @default.
• W4313200744 cites W2980338915 @default.
• W4313200744 cites W2991488782 @default.
• W4313200744 cites W2999884118 @default.
• W4313200744 cites W3000627240 @default.
• W4313200744 cites W3002867668 @default.
• W4313200744 cites W3012668426 @default.
• W4313200744 cites W3013341479 @default.
• W4313200744 cites W3014372673 @default.
• W4313200744 cites W3034315405 @default.
• W4313200744 cites W3044364573 @default.
• W4313200744 cites W3088162569 @default.
• W4313200744 cites W3090679658 @default.
• W4313200744 cites W3093130013 @default.
• W4313200744 cites W3105127913 @default.
• W4313200744 cites W3110829070 @default.
• W4313200744 cites W3128870861 @default.
• W4313200744 cites W3137259566 @default.
• W4313200744 cites W3161145518 @default.
• W4313200744 cites W3178168147 @default.
• W4313200744 cites W3198940810 @default.
• W4313200744 cites W3206021776 @default.
• W4313200744 cites W4211220484 @default.
• W4313200744 cites W4225473286 @default.
• W4313200744 cites W4255421341 @default.
• W4313200744 cites W4281643045 @default.
• W4313200744 cites W4283331952 @default.
• W4313200744 cites W4285736602 @default.
• W4313200744 cites W4292970449 @default.
• W4313200744 cites W4294898295 @default.
• W4313200744 doi "https://doi.org/10.1016/j.jag.2022.103152" @default.
• W4313200744 hasPublicationYear "2023" @default.
• W4313200744 type Work @default.
• W4313200744 citedByCount "0" @default.
• W4313200744 crossrefType "journal-article" @default.
• W4313200744 hasAuthorship W4313200744A5029034236 @default.
• W4313200744 hasAuthorship W4313200744A5065503808 @default.
• W4313200744 hasAuthorship W4313200744A5089787049 @default.
• W4313200744 hasBestOaLocation W43132007441 @default.
• W4313200744 hasConcept C127413603 @default.
• W4313200744 hasConcept C146849305 @default.
• W4313200744 hasConcept C154945302 @default.
• W4313200744 hasConcept C160633673 @default.
• W4313200744 hasConcept C169258074 @default.
• W4313200744 hasConcept C18903297 @default.
• W4313200744 hasConcept C205649164 @default.
• W4313200744 hasConcept C2780428219 @default.
• W4313200744 hasConcept C2780648208 @default.
• W4313200744 hasConcept C41008148 @default.
• W4313200744 hasConcept C4792198 @default.
• W4313200744 hasConcept C58640448 @default.
• W4313200744 hasConcept C62649853 @default.
• W4313200744 hasConcept C78519656 @default.
• W4313200744 hasConcept C86803240 @default.
• W4313200744 hasConceptScore W4313200744C127413603 @default.
• W4313200744 hasConceptScore W4313200744C146849305 @default.
• W4313200744 hasConceptScore W4313200744C154945302 @default.
• W4313200744 hasConceptScore W4313200744C160633673 @default.
• W4313200744 hasConceptScore W4313200744C169258074 @default.
• W4313200744 hasConceptScore W4313200744C18903297 @default.
• W4313200744 hasConceptScore W4313200744C205649164 @default.
• W4313200744 hasConceptScore W4313200744C2780428219 @default.
• W4313200744 hasConceptScore W4313200744C2780648208 @default.

• next