31st Annual Meeting of the DPS, October 1999
Session 38. The Moon and Mercury
Contributed Oral Parallel Session, Wednesday, October 13, 1999, 11:00am-12:00noon, Sala Pietro d'Abano

[Previous] | [Session 38] | [Next]


[38.02] Automatic classification of spectral units in the Aristarchus plateau

S. Erard, S. Le Mou\'{e}lic, Y. Langevin (IAS, Orsay)

A reduction scheme has been recently proposed for the NIR images of Clementine (Le Mouélic et al, JGR 1999). This reduction has been used to build an integrated UVvis-NIR image cube of the Aristarchus region, from which compositional and maturity variations can be studied (Pinet et al, LPSC 1999). We will present an analysis of this image cube, providing a classification in spectral types and spectral units. The image cube is processed with Gmode analysis using three different data sets:

Normalized spectra provide a classification based mainly on spectral slope variations (ie. maturity and volcanic glasses). This analysis discriminates between craters plus ejecta, mare basalts, and DMD. Olivine-rich areas and Aristarchus central peak are also recognized.

Continuum-removed spectra provide a classification more related to compositional variations, which correctly identifies olivine and pyroxenes-rich areas (in Aristarchus, Krieger, Schiaparelli\ldots).

A third analysis uses spectral parameters related to maturity and Fe composition (reflectance, 1 \mum band depth, and spectral slope) rather than intensities. It provides the most spatially consistent picture, but fails in detecting Vallis Schroeteri and DMDs. A supplementary unit, younger and rich in pyroxene, is found on Aristarchus south rim.

In conclusion, Gmode analysis can discriminate between different spectral types already identified with more classic methods (PCA, linear mixing\ldots). No previous assumption is made on the data structure, such as endmembers number and nature, or linear relationship between input variables. The variability of the spectral types is intrinsically accounted for, so that the level of analysis is always restricted to meaningful limits. A complete classification should integrate several analyses based on different sets of parameters. Gmode is therefore a powerful light toll to perform first look analysis of spectral imaging data.

This research has been partly founded by the French Programme National de Planétologie.


If you would like more information about this abstract, please follow the link to www.ias.fr/cdp/Clementine/clementine.html. This link was provided by the author. When you follow it, you will leave the Web site for this meeting; to return, you should use the Back comand on your browser.

[Previous] | [Session 38] | [Next]