Deep multi-scale learning for automatic tracking of internal layers of ice in radar data

• Published in: Journal of Glaciology
• Main Authors: Maryam Rahnemoonfar, Masoud Yari, John Paden, Lora Koenig, Oluwanisola Ibikunle
• Format: Article in Journal/Newspaper
• Language: English
• Published: Cambridge University Press 2021
• Subjects: Ice and climate; radio-echo sounding; remote sensing; Environmental sciences; GE1-350; Meteorology. Climatology; QC851-999; Journal of Glaciology
• Online Access: https://doi.org/10.1017/jog.2020.80; https://doaj.org/article/be4c6b32316a49288f9c587e06270b4d

In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.