Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Dong, Farrell, Sinead L, Duncan, Kyle, Eun, Jaemin
Natura: Dataset Open Access
Lingua:en
Pubblicazione: PANGAEA 2024
Soggetti:
Accesso online:https://doi.org/10.1594/PANGAEA.972753
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1867171045323046912
author Chen, Dong
Farrell, Sinead L
Duncan, Kyle
Eun, Jaemin
author_facet Chen, Dong
Farrell, Sinead L
Duncan, Kyle
Eun, Jaemin
collection Datos científicos de ciencias marinas y ambientales
contents This data collection encompasses 1,387 classified LVIS georeferenced images, which include four classes: Ice, Melt Pond, Open Water, and Shadow. The original LVIS images were acquired in July 2022 using a PhaseOne medium-format camera during the ICESat-2 2022 Arctic Summer calibration campaign, with spatial resolution ranging between 0.39 m and 0.5 m. An image screening was conducted prior to the image classification to remove cloudy images from the collection. The image classification was based on the Random Forest algorithm. An accuracy assessment using 20 randomly selected classified images indicated that the classified imagery has an overall accuracy of more than 85%. The classified images can be used for tracking sea ice dynamics over time and for providing reference for the interpretation of altimetry data.
format Dataset Open Access
id pangaea_https___doi_org_10_1594_PANGAEA_972753
institution PANGAEA
language en
publishDate 2024
publisher PANGAEA
record_format pangaea
spellingShingle University of Maryland classified LVIS georeferenced imagery of Arctic summer sea ice, version 1
Chen, Dong
Farrell, Sinead L
Duncan, Kyle
Eun, Jaemin
Arctic; DATE/TIME; ice; image classication; machine learning; NASA_ICESat-2_Summer_Sea_Ice_Calibraiton_Campaign; Raster graphic, GeoTIFF format; Raster graphic, GeoTIFF format (File Size); remote sensing; Satellite imagery; SATI; Sea ice
This data collection encompasses 1,387 classified LVIS georeferenced images, which include four classes: Ice, Melt Pond, Open Water, and Shadow. The original LVIS images were acquired in July 2022 using a PhaseOne medium-format camera during the ICESat-2 2022 Arctic Summer calibration campaign, with spatial resolution ranging between 0.39 m and 0.5 m. An image screening was conducted prior to the image classification to remove cloudy images from the collection. The image classification was based on the Random Forest algorithm. An accuracy assessment using 20 randomly selected classified images indicated that the classified imagery has an overall accuracy of more than 85%. The classified images can be used for tracking sea ice dynamics over time and for providing reference for the interpretation of altimetry data.
title University of Maryland classified LVIS georeferenced imagery of Arctic summer sea ice, version 1
topic Arctic; DATE/TIME; ice; image classication; machine learning; NASA_ICESat-2_Summer_Sea_Ice_Calibraiton_Campaign; Raster graphic, GeoTIFF format; Raster graphic, GeoTIFF format (File Size); remote sensing; Satellite imagery; SATI; Sea ice
url https://doi.org/10.1594/PANGAEA.972753