Toward Polar Sea-Ice Classification using Color-based Segmentation and Auto-labeling of Sentinel-2 Imagery to Train an Efficient Deep Learning Model
This work addresses the lack of labeled training data for polar sea ice monitoring, which is crucial for tracking climate change impacts, but it is incremental as it builds on existing U-Net methods with auto-labeling.
The research tackled the problem of classifying polar sea ice types using Sentinel-2 imagery by developing a system that uses color-based segmentation and auto-labeling to train a U-Net model, achieving up to 98.97% accuracy after filtering out clouds and shadows.
Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) captures high-resolution optical imagery over the polar regions. This research aims at developing a robust and effective system for classifying polar sea ice as thick or snow-covered, young or thin, or open water using S2 images. A key challenge is the lack of labeled S2 training data to serve as the ground truth. We demonstrate a method with high precision to segment and automatically label the S2 images based on suitably determined color thresholds and employ these auto-labeled data to train a U-Net machine model (a fully convolutional neural network), yielding good classification accuracy. Evaluation results over S2 data from the polar summer season in the Ross Sea region of the Antarctic show that the U-Net model trained on auto-labeled data has an accuracy of 90.18% over the original S2 images, whereas the U-Net model trained on manually labeled data has an accuracy of 91.39%. Filtering out the thin clouds and shadows from the S2 images further improves U-Net's accuracy, respectively, to 98.97% for auto-labeled and 98.40% for manually labeled training datasets.