Estimating Sea Ice Concentration From SAR: Training Convolutional Neural Networks With Passive Microwave Data
| Autor: | Colin L. Cooke, K. Andrea Scott |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Synthetic aperture radar
geography geography.geographical_feature_category Computer science business.industry Deep learning 0211 other engineering and technologies 02 engineering and technology Convolutional neural network Microwave imaging Test set Sea ice General Earth and Planetary Sciences Artificial intelligence Electrical and Electronic Engineering business Sea ice concentration Microwave 021101 geological & geomatics engineering Remote sensing |
| Zdroj: | IEEE Transactions on Geoscience and Remote Sensing. 57:4735-4747 |
| ISSN: | 1558-0644 0196-2892 |
| Popis: | Historically, sea ice concentration (SIC) has been measured through the use of passive microwave sensors, as well as human interpretation of synthetic aperture radar (SAR). Although passive microwave data are processed automatically, it suffers from poor spatial resolution and the higher frequency channels are sensitive to weather conditions. Deep learning has demonstrated its ability to perform complex and accurate analysis of images; here, we apply deep learning to estimate ice concentration from SAR scenes. We developed a deep convolutional neural network (CNN) that predicts SIC from SAR, trained upon passive microwave data. The model achieves a 5.24%/7.87% error on its train and test set, respectively. To assess the real-world applicability, we performed an independent validation on 18 SAR scenes (from two distinct geographical regions), not previously seen during training or test. Comparing against human-generated ice analysis charts, we achieved an $L1$ error of 0.2059, competitive with passive microwave ( $E_{L1} = 0.1863$ ) for the Canadian Arctic Archipelago. For the Gulf of Saint Lawrence region, we achieved an $L1$ error of 0.2653, significantly better than the passive microwave result ( $E_{L1} = 0.3593$ ). By using novel techniques for model training, as well as training entirely upon passive microwave data, we present an accessible and robust method of developing similar systems for processing SAR. 1 Our results suggest that with further postprocessing, CNNs are accurate and robust enough to be used for operational tasks. 1 Code available: https://github.com/clvcooke/Estimating-SIC-from-SAR-github.com/clvcooke/Estimating-SIC-from-SAR |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|