The MARS Journal Vol 4, pp 33-55 - Comprehensive mapping of spectral classes in the imager for Mars Pathfinder Super Pan

Classification image obtained from Imager for Mars Pathfinder "right eye" multispectral data.
(full-resolution, 1.3mb)

Science

Comprehensive mapping of spectral classes in the imager for Mars Pathfinder Super Pan

William H. Farrand¹, Erzsébet Merényi², Jeffrey R. Johnson³ and James F. Bell III⁴
¹Space Science Institute, 4750 Walnut Street #205, Boulder, CO 80301 USA
²Department of Electrical Engineering, Rice University, Houston, TX 77005 USA
³Astrogeology Team, U.S. Geological Survey, Flagstaff, AZ 86001 USA
⁴Department of Astronomy, Cornell University, Ithaca, NY 14853 USA

Citation: Mars 4, 33-55, 2008; doi:10.1555/mars.2008.0004

History: Submitted: November 9, 2007; Reviewed: April 21, 2008; Revised: April 21, 2007; Accepted: June 5, 2008; Published: July 11, 2008

Summary: This paper details the application of an artificial neural network classification architecture to the Mars Pathfinder Super Pan. Comprehensive class maps and new information about those classes are presented.

PDF (5.4mb) Full-text printable manuscript with links to online supporting data. Best viewed using Adobe Reader 7. Links to supporting data are active when viewed online in your web browser.

Directory of all files Access to all supporting data.

Zip archive (12.6mb) All files, including pdf manuscript and supporting data, in zip archive format. Allows linked access to all supporting data on your local computer.

tar.gz archive (12.6mb) All files, including pdf manuscript and supporting data, in tar.gz archive format. Allows linked access to all supporting data on your local computer.

Note: Mars Journal papers consist of PDF manuscripts with links to author-supplied supporting data, which may include full-resolution images, text files, databases, and code. Download time will depend on the speed of your internet connection.

The MARS Journal Home News Contents Search About The MARS Journal Submit Help Comments

Last Updated: June 14, 2010 The MARS Journal is an open-access publication distributed under the terms of a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.