Onboard classifiers for science event detection on a remote sensing spacecraft
Typically, data collected by a spacecraft is downlinked to Earth and pre-processed before any analysis is performed. We have developed classifiers that can be used onboard a spacecraft to identify high priority data for downlink to Earth, providing a method for maximizing the use of a potentially ba...
Main Authors: | , , , , , , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
2006
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.5074 http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.415.5074 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.415.5074 2023-05-15T18:18:38+02:00 Onboard classifiers for science event detection on a remote sensing spacecraft Rebecca Castano Dominic Mazzoni Nghia Tang Ron Greeley Thomas Doggett Ben Cichy Steve Chien Ashley Davies The Pennsylvania State University CiteSeerX Archives 2006 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.5074 http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.5074 http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf General Terms Algorithms Performance Experimentation Human Factors Keywords Classification Support Vector Machine Constrained processing text 2006 ftciteseerx 2016-01-08T03:37:01Z Typically, data collected by a spacecraft is downlinked to Earth and pre-processed before any analysis is performed. We have developed classifiers that can be used onboard a spacecraft to identify high priority data for downlink to Earth, providing a method for maximizing the use of a potentially bandwidth limited downlink channel. Onboard analysis can also enable rapid reaction to dynamic events, such as flooding, volcanic eruptions or sea ice break-up. Four classifiers were developed to identify cryosphere events using hyperspectral images. These classifiers include a manually constructed classifier, a Support Vector Machine (SVM), a Decision Tree and a classifier derived by searching over combinations of thresholded band ratios. Each of the classifiers was designed to run in the computationally constrained operating environment of the spacecraft. A set of scenes was hand-labeled to provide training and testing data. Performance results on the test data indicate that the SVM and manual classifiers outperformed the Decision Tree and band-ratio classifiers with the SVM yielding slightly better classifications than the manual classifier. The manual and SVM classifiers have been uploaded to the EO-1 spacecraft and have been running onboard the spacecraft for over a year. Results of the onboard analysis are used by the Autonomous Sciencecraft Experiment (ASE) of NASA’s New Millennium Program onboard EO-1 to automatically target the spacecraft to collect follow-on imagery. The software demonstrates the potential for future deep space missions to use onboard decision making to capture short-lived science events. Text Sea ice Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
topic |
General Terms Algorithms Performance Experimentation Human Factors Keywords Classification Support Vector Machine Constrained processing |
spellingShingle |
General Terms Algorithms Performance Experimentation Human Factors Keywords Classification Support Vector Machine Constrained processing Rebecca Castano Dominic Mazzoni Nghia Tang Ron Greeley Thomas Doggett Ben Cichy Steve Chien Ashley Davies Onboard classifiers for science event detection on a remote sensing spacecraft |
topic_facet |
General Terms Algorithms Performance Experimentation Human Factors Keywords Classification Support Vector Machine Constrained processing |
description |
Typically, data collected by a spacecraft is downlinked to Earth and pre-processed before any analysis is performed. We have developed classifiers that can be used onboard a spacecraft to identify high priority data for downlink to Earth, providing a method for maximizing the use of a potentially bandwidth limited downlink channel. Onboard analysis can also enable rapid reaction to dynamic events, such as flooding, volcanic eruptions or sea ice break-up. Four classifiers were developed to identify cryosphere events using hyperspectral images. These classifiers include a manually constructed classifier, a Support Vector Machine (SVM), a Decision Tree and a classifier derived by searching over combinations of thresholded band ratios. Each of the classifiers was designed to run in the computationally constrained operating environment of the spacecraft. A set of scenes was hand-labeled to provide training and testing data. Performance results on the test data indicate that the SVM and manual classifiers outperformed the Decision Tree and band-ratio classifiers with the SVM yielding slightly better classifications than the manual classifier. The manual and SVM classifiers have been uploaded to the EO-1 spacecraft and have been running onboard the spacecraft for over a year. Results of the onboard analysis are used by the Autonomous Sciencecraft Experiment (ASE) of NASA’s New Millennium Program onboard EO-1 to automatically target the spacecraft to collect follow-on imagery. The software demonstrates the potential for future deep space missions to use onboard decision making to capture short-lived science events. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Rebecca Castano Dominic Mazzoni Nghia Tang Ron Greeley Thomas Doggett Ben Cichy Steve Chien Ashley Davies |
author_facet |
Rebecca Castano Dominic Mazzoni Nghia Tang Ron Greeley Thomas Doggett Ben Cichy Steve Chien Ashley Davies |
author_sort |
Rebecca Castano |
title |
Onboard classifiers for science event detection on a remote sensing spacecraft |
title_short |
Onboard classifiers for science event detection on a remote sensing spacecraft |
title_full |
Onboard classifiers for science event detection on a remote sensing spacecraft |
title_fullStr |
Onboard classifiers for science event detection on a remote sensing spacecraft |
title_full_unstemmed |
Onboard classifiers for science event detection on a remote sensing spacecraft |
title_sort |
onboard classifiers for science event detection on a remote sensing spacecraft |
publishDate |
2006 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.5074 http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.5074 http://ml.jpl.nasa.gov/public/mls/papers/castano/kdd-2006-eo1-castano.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766195284388347904 |