The dataset contains 912 Sentinel-1 (S1) Synthetic Aperture Radar (SAR) scenes matched with sea ice charts produced by the Danish Meteorological Institute from 2014-2017. Ice charts containing sea ice concentrations provided in manual drawn polygon over the scene has been projected into the S1 geometry for use as labels in machine learning algorithm training processes. The dataset also includes co-located AMSR2 microwave radiometer sensor measurements to compliment the learning of the of sea ice concentrations although in a much lower resolution than the S1 data. Details are described in the manual that is published together with the dataset.
Note that in order to unpack the ASIP dataset you will need to download all the 16 zip-archives first.
David Malmgren-Hansen, Leif Toudal Pedersen, Allan Aasbjerg Nielsen, Matilde Brandt Kreiner, Roberto Saldo, Henning Skriver, John Lavelle, Jørgen Buus-Hinkler, Klaus Harnvig. A Convolutional Neural Network Architecture for Sentinel-1 and AMSR2 Data Fusion. Submitted to the IEEE Transactions on Geoscience and Remote Sensing (TGRS) in December 2019.