Proof of Concept for Sea Ice Stage of Development Classification Using Deep Learning
Autor: | Dustin Isleifson, M. Christopher Fuller, Ian Jeffrey, Alexander Komarov, Ryan Kruk |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
010504 meteorology & atmospheric sciences
Science 0211 other engineering and technologies sea ice Arctic Canadian sea ice chart deep learning SAR RADARSAT-2 classification U-Net DenseNet 02 engineering and technology 01 natural sciences Canadian Ice Service Sea ice 021101 geological & geomatics engineering 0105 earth and related environmental sciences Remote sensing geography geography.geographical_feature_category Artificial neural network business.industry Deep learning Proof of concept General Earth and Planetary Sciences Ice type Artificial intelligence Stage (hydrology) business Geology |
Zdroj: | Remote Sensing, Vol 12, Iss 2486, p 2486 (2020) Remote Sensing; Volume 12; Issue 15; Pages: 2486 |
ISSN: | 2072-4292 |
Popis: | Accurate maps of ice concentration and ice type are needed to address increased interest in commercial marine transportation through the Arctic. RADARSAT-2 SAR imagery is the primary source of data used by expert ice analysts at the Canadian Ice Service (CIS) to produce sea ice maps over the Canadian territory. This study serves as a proof of concept that neural networks can be used to accurately predict ice type from SAR data. Datasets of SAR images served as inputs, and CIS ice charts served as labelled outputs to train a neural network to classify sea ice type. Our results show that DenseNet achieves the highest overall classification accuracy of 94.0% including water and the highest ice classification accuracy of 91.8% on a three class dataset using a fusion of HH and HV SAR polarizations for the input samples. The 91.8% ice classification accuracy validates the premise that a neural network can be used to effectively categorize different ice types based on SAR data. |
Databáze: | OpenAIRE |
Externí odkaz: |