Landsat-8 Sea Ice Classification Using Deep Neural Networks

• Published in: Remote Sensing
• Main Authors: Caceres, Alvaro, Schwarz, Egbert, Aldenhoff, Wiebke
• Format: Other Non-Article Part of Journal/Newspaper
• Language: English
• Published: Multidisciplinary Digital Publishing Institute (MDPI) 2022
• Subjects: Nationales Bodensegment; Sea ice; ice covered areas
• Online Access: https://elib.dlr.de/186214/; https://elib.dlr.de/186214/1/remotesensing-14-01975-v2.pdf; https://www.mdpi.com/2072-4292/14/9/1975

Abstract: Knowing the location and type of sea ice is essential for safe navigation and route op-timization in ice-covered areas. In this study, we developed a deep neural network (DNN) for pixel-based ice Stage of Development classification for the Baltic Sea using Landsat-8 optical sat-ellite imagery to provide up-to-date ice information for Near-Real-Time maritime applications. In order to train the network, we labeled the ice regions shown in the Landsat-8 imagery with classes from the German Federal Maritime and Hydrographic Agency (BSH) ice charts. These charts are routinely produced and distributed by the BSH Sea Ice Department. The compiled data set for the Baltic Sea region consists of 164 ice charts from 2014 to 2021 and contains ice types classified by the Stage of Development. Landsat-8 level 1 (L1b) images that could be overlaid with the available BSH ice charts based on the time of acquisition were downloaded from the United States Geological Survey (USGS) global archive and indexed in a data cube for better handling. The input variables of the DNN are the individual spectral bands: aerosol coastal, blue, green, red and near-infrared (NIR) out of the Operational Land Imager (OLI) sensor. The bands were selected based on the reflectance and emission properties of sea ice. The output val-ues are 4 ice classes of Stage of Development and Free Ice. The results obtained show significant improvements compared to the available BSH ice charts when moving from polygons to pixels, preserving the original classes. The classification model has an accuracy of 87.5% based on the test data set excluded from the training and validation process. Using optical imagery can there-fore add value to maritime safety and navigation in ice- infested waters by high resolution and real-time availability. Furthermore, the obtained results can be extended to other optical satel-lite imagery such as Sentinel-2. Our approach is promising for automated Near-Real-Time (NRT) services, which can be deployed and integrated at a later ...