Skip Links

USGS - science for a changing world

Open-File Report 03–478

Interim Progress Report on the Application of an Independent Components Analysis-based Spectral Unmixing Algorithm to Beowulf Computers

By George Lemeshewsky

Thumbnail of and link to report PDF (563 KB)Introduction

This report describes work done to implement an independent-components-analysis (ICA) -based blind unmixing algorithm on the Eastern Region Geography (ERG) Beowulf computer cluster. It gives a brief description of blind spectral unmixing using ICA-based techniques and a preliminary example of unmixing results for Landsat-7 Thematic Mapper multispectral imagery using a recently reported1,2,3 unmixing algorithm. Also included are computer performance data. The final phase of this work, the actual implementation of the unmixing algorithm on the Beowulf cluster, was not completed this fiscal year and is addressed elsewhere. It is noted that study of this algorithm and its application to land-cover mapping will continue under another research project in the Land Remote Sensing theme into fiscal year 2004.

First posted 2003

Part or all of this report is presented in Portable Document Format (PDF); the latest version of Adobe Reader or similar software is required to view it. Download the latest version of Adobe Reader, free of charge.

Suggested citation:

Lemeshewsky, George, 2003, Interim progress report on the application of an independent components analysis-based spectral unmixing algorithm to Beowulf computers: U.S. Geological Survey Open-File Report 03–478, 5 p., available only online at

Accessibility FOIA Privacy Policies and Notices logo U.S. Department of the Interior | U.S. Geological Survey
Page Contact Information: Contact USGS
Page Last Modified: Thursday, August 01, 2013, 02:37:52 PM