Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ...

• Main Authors: de Lima, Rafael Pires, Vahedi, Behzad, Hughes, Nick, Barrett, Andrew P., Meier, Walter, Karimzadeh, Morteza
• Format: Other Non-Article Part of Journal/Newspaper
• Language: unknown
• Published: Taylor & Francis 2023
• Subjects: Space Science; Medicine; Environmental Sciences not elsewhere classified; Chemical Sciences not elsewhere classified; Sociology; FOS Sociology; Biological Sciences not elsewhere classified; Sea ice
• Online Access: https://dx.doi.org/10.6084/m9.figshare.24089798; https://tandf.figshare.com/articles/journal_contribution/Enhancing_sea_ice_segmentation_in_Sentinel-1_images_with_atrous_convolutions/24089798

Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, ...