RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0

• Main Authors: Jon Schwenk, Joel Rowland
• Format: Dataset
• Language: unknown
• Published: ESS-DIVE: Deep Insight for Earth Science Data 2022
• Subjects: rivers; training data; landsat; sediment; floodplain; water; water occurrence; Arctic; New Zealand; Kolyma; Indigirka; Yana River; kolyma river; Alaska
• Online Access: https://search.dataone.org/view/ess-dive-bb53164aeb28c5c-20220425T154912574

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.