Onboard SVM analysis of Hyperion data to detect sulfur deposits in Arctic regions

Onboard classification of remote sensing data can permit autonomous, intelligent scheduling decisions without ground interaction. In this study, we observe the sulfur-rich Borup-Fiord glacial springs in Canada with the Hyperion instrument aboard the EO-1 spacecraft. This system offers an analog to far more exotic locales such as Europa where remote sensing of biogenic indicators is of considerable interest. Previous work has been performed in the generation and execution of an onboard SVM (support vector machine) classifier to autonomously identify the presence of sulfur compounds associated with the activity of microbial life. However, those results were severely limited in the number of positive examples available to be labeled. In this paper we extend the sample size from 1 to 7 example scenes between 2006 and 2008, corresponding to a change from 18 to 235 positive labels. We also explore nonlinear SVM kernels as an extension of our onboard capability.

[1]  Stephen G. Ungar,et al.  Overview of the Earth Observing One (EO-1) Mission , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[2]  Rebecca Castano,et al.  Improving onboard analysis of Hyperion images by filtering mislabeled training data examples , 2009, 2009 IEEE Aerospace conference.

[3]  Lawrence Ong,et al.  Onboard classification of hyperspectral data on the Earth Observing One mission , 2009, 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[4]  Umaa Rebbapragada,et al.  Onboard detection of natural sulfur on a glacier via a SVM and Hyperion data , 2009, 2009 IEEE Aerospace conference.

[5]  Rebecca Castano,et al.  Onboard Detection of Active Canadian Sulfur Springs: A Europa Analogue , 2008 .