Name
Title | ||
|---|---|---|
Automated Geophysical Classification of Sentinel-L Wave Mode Sar Images Through Deep-Learning. |
Abstract | ||
|---|---|---|
ESAu0027s two Sentinel-1 satellites collect ~120,000 synthetic aperture radar wave mode vignettes every month over the worldu0027s oceans. This provides a new and unique opportunity for routine identification and study of a wide range of oceanic and atmospheric phenomena observed in SAR imagery. To this end, the first challenge is to develop an efficient and accurate method to detect and classify key geophysical phenomena signature among the whole dataset. In this study, the deep-learning-based convolutional neural network architecture of Inception v3 model was adopted. We identified 10 geophysical categories detectable by SAR and selected 320 Sentinel-l wave mode imagettes for each category. The full pre-trained Inception v3 model was then retrained using these images. Preliminary results demonstrate that this deep-learning methodology is quite effective, with overall accuracy each of the 10 classes exceeding 0.93 and clear class differentiation in cluster analysis. This opens perspectives to rely on wave mode vignettes in order to analyze geophysical phenomena at global scale. Further work remains to address ambiguous or unknown images that often include a mix of several air-sea processes. |
Year | Venue | Field |
|---|---|---|
2018 | IGARSS | Satellite,Geophysical Phenomena,Synthetic aperture radar,Convolutional neural network,Computer science,Remote sensing,Surface wave,Feature extraction,Atmospheric model,Artificial intelligence,Deep learning,Geophysics |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen Wang | 1 | 141 | 46.56 |
| Alexis Mouche | 2 | 85 | 21.13 |
| Pierre Tandeo | 3 | 3 | 3.79 |
| Justin Stopa | 4 | 1 | 2.71 |
| Bertrand Chapron | 5 | 244 | 52.89 |
| Ralph C. Foster | 6 | 1 | 1.77 |
| Douglas C. Vandemark | 7 | 9 | 4.75 |