RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0
RiverPIXELS contains GeoTIFFs of hand-labeled water and sediment pixels from Landsat images containing rivers. Each of the 104 labeled patches contains 256 x 256 Landsat pixels (30 meter resolution). Our aim in releasing RiverPIXELS is to provide an "off-the-shelf" training and testing dat...
Main Authors: | , |
---|---|
Language: | unknown |
Published: |
2023
|
Subjects: | |
Online Access: | http://www.osti.gov/servlets/purl/1865732 https://www.osti.gov/biblio/1865732 https://doi.org/10.15485/1865732 |
id |
ftosti:oai:osti.gov:1865732 |
---|---|
record_format |
openpolar |
spelling |
ftosti:oai:osti.gov:1865732 2023-07-30T04:01:50+02:00 RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 Schwenk, Jon Rowland, Joel 2023-04-10 application/pdf http://www.osti.gov/servlets/purl/1865732 https://www.osti.gov/biblio/1865732 https://doi.org/10.15485/1865732 unknown http://www.osti.gov/servlets/purl/1865732 https://www.osti.gov/biblio/1865732 https://doi.org/10.15485/1865732 doi:10.15485/1865732 54 ENVIRONMENTAL SCIENCES 2023 ftosti https://doi.org/10.15485/1865732 2023-07-11T10:12:07Z RiverPIXELS contains GeoTIFFs of hand-labeled water and sediment pixels from Landsat images containing rivers. Each of the 104 labeled patches contains 256 x 256 Landsat pixels (30 meter resolution). Our aim in releasing RiverPIXELS is to provide an "off-the-shelf" training and testing dataset for building machine-learned models to automatically identify rivers from multispectral imagery. While a number of trained models and/or surface water products already exist, RiverPIXELS aims for pixel-level accuracy in order to precisely identify river boundaries in particular. Our selection of rivers is heavily Arctic, but we include tropical and temperate rivers as well. Patches are provided for the Colville (7), Indigirka (6), Kolyma (4), Ucayali (54), Waitaki (21), and Yana (12) Rivers. For each patch, all surface water pixels are labeled (1) and all in-channel sediment pixels are labeled (2). Sediments not in-channel are considered part of the land (0) class. RiverPIXELS also includes paired surface water data from the Global Surface Water dataset that may be useful as additional features in machine learning models. Each patch therefore contains four aligned GeoTIFFs: labeled, landsat, gswmo, and gswocc. Other/Unknown Material Arctic SciTec Connect (Office of Scientific and Technical Information - OSTI, U.S. Department of Energy) Arctic Indigirka ENVELOPE(149.609,149.609,70.929,70.929) Kolyma ENVELOPE(161.000,161.000,69.500,69.500) |
institution |
Open Polar |
collection |
SciTec Connect (Office of Scientific and Technical Information - OSTI, U.S. Department of Energy) |
op_collection_id |
ftosti |
language |
unknown |
topic |
54 ENVIRONMENTAL SCIENCES |
spellingShingle |
54 ENVIRONMENTAL SCIENCES Schwenk, Jon Rowland, Joel RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
topic_facet |
54 ENVIRONMENTAL SCIENCES |
description |
RiverPIXELS contains GeoTIFFs of hand-labeled water and sediment pixels from Landsat images containing rivers. Each of the 104 labeled patches contains 256 x 256 Landsat pixels (30 meter resolution). Our aim in releasing RiverPIXELS is to provide an "off-the-shelf" training and testing dataset for building machine-learned models to automatically identify rivers from multispectral imagery. While a number of trained models and/or surface water products already exist, RiverPIXELS aims for pixel-level accuracy in order to precisely identify river boundaries in particular. Our selection of rivers is heavily Arctic, but we include tropical and temperate rivers as well. Patches are provided for the Colville (7), Indigirka (6), Kolyma (4), Ucayali (54), Waitaki (21), and Yana (12) Rivers. For each patch, all surface water pixels are labeled (1) and all in-channel sediment pixels are labeled (2). Sediments not in-channel are considered part of the land (0) class. RiverPIXELS also includes paired surface water data from the Global Surface Water dataset that may be useful as additional features in machine learning models. Each patch therefore contains four aligned GeoTIFFs: labeled, landsat, gswmo, and gswocc. |
author |
Schwenk, Jon Rowland, Joel |
author_facet |
Schwenk, Jon Rowland, Joel |
author_sort |
Schwenk, Jon |
title |
RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
title_short |
RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
title_full |
RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
title_fullStr |
RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
title_full_unstemmed |
RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
title_sort |
riverpixels: paired landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0 |
publishDate |
2023 |
url |
http://www.osti.gov/servlets/purl/1865732 https://www.osti.gov/biblio/1865732 https://doi.org/10.15485/1865732 |
long_lat |
ENVELOPE(149.609,149.609,70.929,70.929) ENVELOPE(161.000,161.000,69.500,69.500) |
geographic |
Arctic Indigirka Kolyma |
geographic_facet |
Arctic Indigirka Kolyma |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
http://www.osti.gov/servlets/purl/1865732 https://www.osti.gov/biblio/1865732 https://doi.org/10.15485/1865732 doi:10.15485/1865732 |
op_doi |
https://doi.org/10.15485/1865732 |
_version_ |
1772812578074918912 |