Title :
Upwelling Detection in AVHRR Sea Surface Temperature (SST) Images using Neural-Network Framework
Author :
Chaudhari, Swapnil ; Balasubramanian, Ramprasad ; Gangopadhyay, Avijit
Author_Institution :
Dept of Comput. & Inf. Sci., Univ. of Massachusetts at Dartmouth, Dartmouth, MA
Abstract :
In this paper we present a novel method for the detection and segmentation of upwelling regions in AVHRR SST data. We demonstrate the effectiveness of the algorithm on data from the Monterey Bay region, with prominent upwelling regions. A byproduct of the upwelling detection algorithm is the detection of frontal boundaries. The process is started with the training of a feed-forward back-propagation neural network for the purpose of finding regions of "uniform" temperatures, resulting in labeled clusters. Then statistical information is gathered from the various clusters. A quantitative criterion is developed that is used to test the existence of prominent upwelling region followed by detection and segmentation. The algorithm is applied on data from July 2003 to September 2003 and their results presented.
Keywords :
geophysics computing; neural nets; ocean temperature; oceanographic regions; oceanographic techniques; remote sensing; AD 2003 07 to 09; AVHRR; Advanced Very High Resolution Radiometer; California Current System; Central California coast; Monterey Bay region; SST; automatic detection; coastal upwelling feature; frontal boundary; neural-network; ocean color image; ocean upwelling detection algorithm; oceanographic feature; remote sensing; sea surface temperature; Artificial neural networks; Backpropagation algorithms; Clustering algorithms; Image segmentation; Neural networks; Ocean temperature; Satellite broadcasting; Sea measurements; Sea surface; Temperature sensors; Neural Network; Sea-WiFS; Upwelling detection;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-2807-6
Electronic_ISBN :
978-1-4244-2808-3
DOI :
10.1109/IGARSS.2008.4779875
