Annotated time-series of lake ice C-band synthetic aperture radar backscatter created using Sentinel-1, ERS-1/2, and RADARSAT-1 imagery of Old Crow Flats, Yukon, Canada ...

• Main Authors: Shaposhnikova, Maria, Duguay, Claude R, Roy-Léveillée, Pascale
• Format: Dataset
• Language: English
• Published: PANGAEA 2022
• Subjects: deep learning; floating ice; ice regime; lake ice; Old Crow Flats; synthetic aperture radar; temporal convolutional neural network; File content; Binary Object; Binary Object Media Type; Binary Object File Size; Canada; Yukon; Old Crow
• Online Access: https://dx.doi.org/10.1594/pangaea.947789; https://doi.pangaea.de/10.1594/PANGAEA.947789

The lake ice backscatter time-series dataset was created for the purpose of developing an automated temporal deep learning method of lake ice regime classification and study of lake ice dynamics in the Old Crow Flats (OCF), Yukon, Canada. The dataset consists of approximately 129,000 labeled backscatter time-series collected using imagery from four C-band synthetic aperture radar (SAR) spaceborne platforms: Sentinel-1 A (VV polarization), ERS-1 and 2 (VV polarization), and RADARSAT-1 (HH polarization), which cover the time period between 1992 to 2021. Labeling was done in Sentinel Application Platform (SNAP) by manually placing pins at locations identified as either floating ice, bedfast ice, or land through visual assessment of the ice regime/land on the last day of the time-series for a given season. Due to variable temporal coverage, the dates of labeling ranged from March 4 to March 22. The labeling date was selected as close as possible to mid-March, and care was taken to ensure that the air temperature ... : dataset.7z contains a csv file with backscatter time-series. The first column is called "Class" and it contains a label for each row of backscatter time-series, where "0" stands for "bedfast ice", "1" stands for "floating ice", and "2" stands for "land". The time-series have a daily frequency and extend from October 4 to March 13. The label corresponds to the state of the pixel from which a specific time series was extracted on the last day of the time-series (March 13). The units of the backscatter values are decibels (dB) traditionally used for C-band synthetic aperture radar (SAR) analysis. The dataset consists of approximately 129,000 labeled backscatter time-series (rows in the csv file) collected using imagery from four C-band synthetic aperture radar (SAR) spaceborne platforms: Sentinel-1 A (VV polarization), ERS-1 and 2 (VV polarization), and RADARSAT-1 (HH polarization), which cover the time period between 1992 to 2021. The first row contains dates (October 4 to March 13). Although the year included ...