1OPTICAL CLASSIFICATION OF NORTHWEST ATLANTIC WATER TYPES BASED ON SATELLITE OCEAN COLOUR DATA
Satellite ocean colour imagery provides a synoptic view of the optical properties of broad regions of the ocean, and sophisticated data analysis techniques are required for the interpretation of this data. We are developing optical water type classification approaches based on remotely-sensed water...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Text |
| Language: | English |
| Subjects: | |
| Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.557.9545 http://www.whoi.edu/science/B/sosiklab/1190.pdf |
| Summary: | Satellite ocean colour imagery provides a synoptic view of the optical properties of broad regions of the ocean, and sophisticated data analysis techniques are required for the interpretation of this data. We are developing optical water type classification approaches based on remotely-sensed water leaving radiance, with application to the study of spatial and temporal dynamics of ecologically and biogeochemically important properties of the upper ocean. For CZCS and SeaWiFS imagery of the northwest Atlantic region, pixels from several locations in the Georges Bank/Gulf of Maine area projected into distinct clusters in single-band feature space, suggesting that these waters can be easily distinguished using a few spectral bands of ocean colour data. Two different classification techniques have been developed. The Euclidean Classifier minimises the raw distance between each pixel and the centroid of the class to which it is assigned, whereas the Eigenvector Classifier is based on normalising the raw distances by the variance of each class, taking the shape of each class in feature space into account. These classifiers were applied to ocean colour images of the northwest Atlantic to elucidate the |
|---|