• About
• Projects
• Publications
• Teaching

Active Projects:

• Anomaly and Novelty Detection in Large Data Sets Show/hide details

  We employ anomaly and novelty detection methods to support science investigations, enabling subsequent review to separate anomalies of potential scientific interest (and follow-up) from those that indicate artifacts or noise in the data.

  • Integrating Novelty Detection Capabilities with MSL Mastcam Operations to Enhance Data Analysis.
    Paul Horton, Hannah R. Kerner, Samantha Jacob, Ernest Cisneros, Kiri L. Wagstaff, and James Bell.
    Proceedings of the IEEE Aerospace Conference, 2021.
  • Novelty-Driven Onboard Target Selection in Grayscale and Color Mars Rover Images. (Poster)
    Hannah R. Kerner, Kiri L. Wagstaff, Steven Lu, Raymond Francis, and Shakshum Kulshrestha.
    52nd Lunar and Planetary Science Conference, Abstract #2618, March 2021.
    • Rovers are searching / Color images reveal / Novel rocks and veins
  • Novelty-Driven Onboard Targeting for Mars Rovers.
    Kiri L. Wagstaff, Raymond Francis, Hannah Kerner, Steven Lu, Favour Nerrise, James F. Bell III, Gary Doran, and Umaa Rebbapragada.
    Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space, 2020.
  • Comparison of Novelty Detection Methods for Multispectral Images in Rover-based Planetary Exploration Missions.
    Hannah R. Kerner, Kiri L. Wagstaff, Brian D. Bue, Danika F. Wellington, Samantha Jacob, Paul Horton, James F. Bell III, Chiman Kwan, and Heni Ben Amor.
    Data Mining and Knowledge Discovery, vol. 34(6), p. 1652-1675, 2020, DOI 10.1007/s10618-020-00697-6.
    • We compare multiple novelty detection methods on multispectral (6-channel) images collected by a Mars rover. We find that some methods are more sensitive to spectral (compositional) novelty, while others are more sensitive to morphological (shape-based) novelty.
    • Code: Novelty Detection in Multispectral Mastcam Images (github)
    • Data: Mars novelty detection Mastcam labeled dataset
  • Toward Generalized Change Detection on Planetary Surfaces with Convolutional Autoencoders and Transfer Learning.
    Hannah R. Kerner, Kiri L. Wagstaff, Brian D. Bue, Patrick C. Gray, James F. Bell III, and Heni Ben Amor.
    Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, issue 10, p. 3900-3918, 2019.
  • Toward Generalized Change Detection on Planetary Surfaces with Deep Learning.
    Hannah R. Kerner, Kiri Wagstaff, Brian D. Bue, Patrick C. Gray, James F. Bell, and Heni Ben Amor.
    Fall Meeting of the American Geophysical Union, December 2019.
  • Enabling Onboard Detection of Events of Scientific Interest for the Europa Clipper Spacecraft.
    Kiri Wagstaff, Gary Doran, Ashley Davies, Saadat Anwar, Srija Chakraborty, Marissa Cameron, Ingrid Daubar, and Cynthia Phillips.
    Proceedings of the 25th International Conference on Knowledge Discovery and Data Mining (KDD), p. 2191-2201, August 2019.
    • We make a case for the utility of onboard analysis of data collected by Europa Clipper (future mission to Europa) to enable prioritization of data for downlink. We describe three onboard detection algorithms to address the science goals detecting thermal anomalies (hot spots), compositional anomalies, and active plumes. We also report lessons learned from developing and evaluating these methods in the context of an onboard computing environment and mission acceptance.
  • Comparison of Novelty Detection Methods for Multispectral Images from the Mastcam Instrument onboard Mars Science Laboratory.
    Hannah R. Kerner, Kiri L. Wagstaff, Brian Bue, Danika Wellington, Samantha Jacob, James F. Bell III, and Heni Ben Amor.
    Fourth Planetary Data Workshop, Abstract #7115, June 2019.
    • We describe experiments with different novelty detection methods applied to rover images to aid in directing attention to the images most likely to be of interest to mission scientists and planners. These include images of meteorites, rock veins, broken rocks, and other surface features with unusual mineralogy. We found that a convolutional autoencoder had the best overall precision@N performance. However, individual classes showed different behavior, with a standard SVD yielding the best AUC for naturally occurring features (broken rocks, float rocks, and meteorites) and a generative adversarial network (GAN) yielding the best performance for novel features created by the rover itself (drill holes, brush spots, and dump piles).
  • An Anomaly Catalog for the Dark Energy Survey.
    Umaa Rebbapragada, Eric Huff, and Kiri Wagstaff.
    JPL Data Science Showcase, Poster 68, April 2019.
  • Spectral Anomaly Detection for the Mapping Imaging Spectrometer for Europa (MISE).
    Kiri L. Wagstaff, Diana L. Blaney, Srija Chakraborty, Steve A. Chien, Ashley G. Davies, Serina Diniega, and Gary Doran.
    50th Lunar and Planetary Science Conference, Abstract #1604, March 2019.
    • We apply anomaly detection methods to NIMS observations of Europa and describe how they could be used onboard the upcoming Europa Clipper mission by the MISE instrument for in-situ detections. See also the poster.
  • Novelty Detection for Multispectral Images with Application to Planetary Exploration.
    Hannah R. Kerner, Danika F. Wellington, Kiri L. Wagstaff, James F. Bell, and Heni Ben Amor.
    Proceedings of the Thirty-First Annual Conference on Innovative Applications of Artificial Intelligence, 2019.
    • We use an autoencoder to detect unusual image content, such as meteorites on the Martian surface, in multispectral images.
    • Data set (labeled images):
  • Novelty Detection for Multispectral Planetary Images.
    Hannah Rae Kerner, Danika F. Wellington, Kiri Wagstaff, Samantha Jacob, James F. Bell III, and Heni Ben Amor.
    Fall Meeting of the American Geophysical Union, Abstract #IN14A-01, December 2018.
  • Onboard Detection of Thermal Anomalies for Europa Clipper.
    Gary Doran, Ashley G. Davies, Kiri L. Wagstaff, Saadat Anwar, Diana L. Blaney, Steve Chien, Phil Christensen, and Serina Diniega.
    European Planetary Science Congress, Abstract #528, September 2018.
  • Interpretable Discovery in Large Image Data Sets.
    Kiri L. Wagstaff and Jake Lee.
    Proceedings of the ICML Workshop on Human Interpretability in Machine Learning (WHI), p. 107-113, 2018.
    • We combine novelty detection with CNN image features to achieve rapid discovery with interpretable explanations of novel image content.
    • Visit the paper website for code, data, etc.
    • Watch the 10-minute talk
  • Cloud Filtering and Novelty Detection using Onboard Machine Learning for the EO-1 Spacecraft.
    Kiri L. Wagstaff, Alphan Altinok, Steve Chien, Umaa Rebbapragada, Steve Schaffer, David R. Thompson, and Daniel Tran.
    IJCAI 2017 Workshop on AI in the Oceans and Space, 2017.
  • Guiding Scientific Discovery with Explanations using DEMUD (pdf, 7 pages, 291K).
    Kiri L. Wagstaff, Nina L. Lanza, David R. Thompson, Thomas G. Dietterich, and Martha S. Gilmore.
    Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI-13), p. 905-911, 2013.
    • DEMUD is an algorithm for quickly finding interesting novelties or anomalies in large data sets. Uniquely, it also provides explanations for why each item is considered interesting. We report on experiments with hyperspectral data from Mars orbit and the Martian surface, finding that DEMUD indeed discovers items of scientific interest, and that the explanations are useful: with them, a scientist's ability to classify spectra doubled.
  • Semi-Supervised Eigenbasis Novelty Detection.
    David R. Thompson, Walid A. Majid, Colorado J. Reed, and Kiri L. Wagstaff.
    Statistical Analysis and Data Mining, 2012.
    • This is an extended version of our CIDU 2011 paper, which offers two improvements: modeling local context around known false alarms, and employing a sparse PCA for better interpretability of the results.
  • Semi-Supervised Novelty Detection with Adaptive Eigenbases, and Application to Radio Transients (pdf, 11 pages, 625K). [Slides (pdf, 12 pages, 4M)] Received the Best Paper Award.
    David R. Thompson, Walid A. Majid, Colorado J. Reed, and Kiri L. Wagstaff.
    Proceedings of the Conference on Intelligent Data Understanding, 2011.
    • How to do novelty detection while ignoring anomalies you already know about and don't think are interesting.
• Responsive Onboard Science for the Europa Clipper Mission Show/hide details

  We are developing and evaluating onboard data analysis methods for use by the Europa Clipper spacecraft, a future mission that will make 40+ flybys of Europa. These methods include onboard detection of thermal anomalies (hot spots) on the surface, areas of unusual mineralogical composition, active plumes erupting from the surface, and more. These methods must be highly efficient to operate within the limited computational and memory resources available onboard.

  • Unsupervised Detection of Saturn Magnetic Field Boundary Crossings From Plasma Spectrometer Data.
    Ameya Daigavane, Kiri L. Wagstaff, Gary Doran, Corey Cochrane, Caitriona M. Jackman, and Abigail Rymer.
    Computers & Geosciences, vol. 161, 2022, DOI 10.1016/j.cageo.2022.105040.
  • Detection of Environment Transitions in Time Series Data for Responsive Science.
    Ameya Daigavane, Kiri Wagstaff, Gary Doran, Corey Cochrane, Caitriona Jackman, and Abigail Rymer.
    6th KDD Workshop on Mining and Learning for Time Series, 2020.
  • Assessing the Susceptibility of Europa Clipper Onboard Thermal Anomaly Detection to Radiation.
    G. Doran, K. L. Wagstaff, J. Bapst, A. G. Davies, and S. Anwar.
    51st Lunar and Planetary Science Conference, Abstract #2193, March 2020.
  • Opportunities for Increased Data Return through Coordinated Instrument Observations on Europa Clipper.
    Marissa Cameron, Kiri Wagstaff, Gary B. Doran, and Ashley G. Davies.
    Fall Meeting of the American Geophysical Union, December 2019.
  • Enabling Onboard Detection of Events of Scientific Interest for the Europa Clipper Spacecraft.
    Kiri Wagstaff, Gary Doran, Ashley Davies, Saadat Anwar, Srija Chakraborty, Marissa Cameron, Ingrid Daubar, and Cynthia Phillips.
    Proceedings of the 25th International Conference on Knowledge Discovery and Data Mining (KDD), p. 2191-2201, August 2019.
    • We make a case for the utility of onboard analysis of data collected by Europa Clipper (future mission to Europa) to enable prioritization of data for downlink. We describe three onboard detection algorithms to address the science goals detecting thermal anomalies (hot spots), compositional anomalies, and active plumes. We also report lessons learned from developing and evaluating these methods in the context of an onboard computing environment and mission acceptance.
  • Automatic Plume Detection for the Europa Imaging System.
    Gary Doran, Kiri L. Wagstaff, Marissa Cameron, Ingrid Daubar, and Cynthia Phillips.
    Fourth Planetary Data Workshop, Abstract #7026, June 2019.
    • We apply image analysis and adaptive thresholding methods to detect the target body's limb and determine whether there is evidence for an active plume. This technology could potentially be used to detect plumes in situ within images of Europa obtained by the Europa Imaging System (EIS) instrument on the upcoming Europa Clipper mission.
    • Data set (labeled images with and without plumes):
  • Responsive Onboard Science for the Europa Clipper Mission.
    Kiri Wagstaff, Gary Doran, Ashley Davies, Saadat Anwar, Srija Chakraborty, Diana Blaney, Marissa Cameron, Jonathan Bapst, Steve Chien, Corey Cochrane, Ingrid Daubar, Serina Diniega, Cynthia Phillips, and Sylvain Piqueux.
    JPL Data Science Showcase, Poster 29, April 2019.
  • Spectral Anomaly Detection for the Mapping Imaging Spectrometer for Europa (MISE).
    K. L. Wagstaff, D. L. Blaney, S. Chakraborty, S. A. Chien, A. G. Davies, S. Diniega, and G. Doran.
    50th Lunar and Planetary Science Conference, Abstract #1604, March 2019.
    • We apply anomaly detection methods to NIMS observations of Europa and describe how they could be used onboard the upcoming Europa Clipper mission by the MISE instrument for in-situ detections.
  • Responsive Onboard Science for Europa Clipper.
    Kiri L. Wagstaff, Ashley Davies, Gary Doran, Srija Chakraborty, Saadat Anwar, Diana L. Blaney, Steve Chien, Philip R. Christensen, and Serina Diniega.
    Outer Planets Assessment Group meeting, September 2018.
  • Onboard Detection of Thermal Anomalies for Europa Clipper.
    Gary Doran, Ashley G. Davies, Kiri L. Wagstaff, Saadat Anwar, Diana L. Blaney, Steve Chien, Phil Christensen, and Serina Diniega.
    European Planetary Science Congress, Abstract #528, September 2018.
• Image Classification for Planetary Science Data Show/hide details

  We employ image classification to data collected by spacecraft (e.g., Mars orbiters and rovers) to enable content-based search (e.g., "all images containing craters").

  • Tutorial: How to Access, Process, and Label PDS Image Data for Machine Learning.
    Steven Lu, Kiri Wagstaff, Rafael Alanis, Gary Doran, Kevin Grimes, and Jordan Padams.
    Chapter in Machine Learning for Planetary Science, 2022.
  • Content-Based Classification of Mars Exploration Rover Pancam Images. (Poster)
    Steven Lu, Brandon Zhao, Kiri L. Wagstaff, Shoshanna B. Cole, and Kevin Grimes.
    52nd Lunar and Planetary Science Conference, Abstract #1779, March 2021.
  • Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
    (IAAI Deployed Application Award).
    Kiri Wagstaff, Steven Lu, Emily Dunkel, Kevin Grimes, Brandon Zhao, Jesse Cai, Shoshanna B. Cole, Gary Doran, Raymond Francis, Jake Lee, and Lukas Mandrake.
    Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence, 2021.
    • We report on updates to Mars image classifiers deployed at the NASA Planetary Data System, for orbital and rover images, and lessons learned that inform ongoing activities to build new classifiers for additional missions.
  • Content-Based Classification of Mars Exploration Rover Pancam Images. (Poster)
    Steven Lu, Brandon Zhao, Kiri L. Wagstaff, Shoshanna B. Cole, and Kevin Grimes.
    52nd Lunar and Planetary Science Conference, Abstract #1779, March 2021.
  • Using Machine Learning to Complement New Martian Crater Inventories. (Poster)
    Annabelle Gao, Ingrid J. Daubar, Daniel Wexler, Kiri L. Wagstaff, Valentin Bickel, and Gary Doran.
    52nd Lunar and Planetary Science Conference, Abstract #1674, March 2021.
    • Machine learning finds / Fresh impacts on Mars that we / Missed before, what now?
  • Press release (Oct. 1, 2020): AI Is Helping Scientists Discover Fresh Craters on Mars
  • Large-Scale Automated Detection of Fresh Impacts on Mars Using Machine Learning with CTX Observations.
    Michael J. Munje, Ingrid J. Daubar, Gary Doran, Kiri Wagstaff, and Lukas Mandrake.
    11th Planetary Crater Consortium, Abstract #2065, August 2020.
  • Efficient Active Learning in New Domains.
    Kiri Wagstaff and Steven Lu.
    ICML Workshop on Real World Experiment Design and Active Learning, 2020.
    • Data set (labeled Mars rover images):
  • Visualizing Image Content to Explain Novel Image Discovery (free view-only access to full text).
    Jake H. Lee and Kiri L. Wagstaff.
    Data Mining and Knowledge Discovery, 34(6), p. 1777-1804, 2020, DOI 10.1007/s10618-020-00700-0.
    • We combine novelty detection with CNN image features to achieve rapid discovery with interpretable explanations of novel image content. We also report on a user study of explanation utility.
    • Visit the paper website for code, data, etc.
  • COSMIC: Content-based Onboard Summarization to Monitor Infrequent Change.
    Gary Doran, Steven Lu, Maria Liukis, Lukas Mandrake, Umaa Rebbapragada, Kiri L. Wagstaff, Jimmie Young, Erik Langert, Anneliese Braunegg, Paul Horton, Daniel Jeong, and Asher Trockman.
    Proceedings of the IEEE Aerospace Conference, 2020.
  • Content-based Classification of Mars Imagery for the PDS Image Atlas.
    Steven Lu, Kiri Wagstaff, Jesse Cai, Gary B. Doran, Kevin Grimes, Jake Lee, and Lukas Mandrake.
    Fall Meeting of the American Geophysical Union, December 2019.
  • Improved Content-Based Image Classifiers for the PDS Image Atlas.
    Steven Lu, Kiri L. Wagstaff, Jesse Cai, Gary Doran, Kevin Grimes, Jake Lee, Lukas Mandrake, and Yisong Yue.
    Fourth Planetary Data Workshop, Abstract #7028, June 2019.
    • We report on several improvements to the classifiers we developed to assign content labels to NASA images collected by Mars rovers and orbiters. The improvements include data augmentation, classifier calibration, and updates to the fine-tuning methodology.
    • Data set (labeled HiRISE images, V3):
  • Deep Mars: A CNN Approach that Enables Image Content-Based Search for PDS Image Atlas. Steven Lu, Kiri Wagstaff, Kevin Grimes, Gary Doran, Lukas Mandrake, Jake Lee, and Jesse Cai.
    JPL Data Science Showcase, Poster 35, April 2019.
  • Content-based Onboard Summarization to Monitor Infrequent Change (COSMIC) - An Ultra-Low Bandwidth, Autonomous System to Globally Monitor Mars for Dynamic Events.
    Lukas Mandrake, Kiri Wagstaff, Gary Doran, Steven Lu, Erik Langert, and Jimmie Young.
    JPL Data Science Showcase, Poster 14, April 2019.
  • Deep Mars: CNN Classification of Mars Imagery for the PDS Imaging Atlas.
    Kiri L. Wagstaff, You Lu, Alice Stanboli, Kevin Grimes, Thamme Gowda, and Jordan Padams.
    Proceedings of the Thirtieth Annual Conference on Innovative Applications of Artificial Intelligence, p. 7867-7872, 2018.
    • Data set (labeled HiRISE images, V1):
    • Data set (labeled Mars rover images):
  • Automated Content Detection for Cassini Images.
    Alice Stanboli, Brian Bue, Kiri Wagstaff, and Alphan Altinok.
    Third Planetary Data Workshop, Abstract #7048, June 2017.
  • Landmark Classification and Content-Based Search for Mars Orbital Imagery.
    Kiri L. Wagstaff, Gary B. Doran, Ravi Kiran, Lukas Mandrake, Norbert Schorghofer, and Alice Stanboli.
    2nd Planetary Data Workshop, June 2015.
• Mars Target Encyclopedia Show/hide details

  We are creating an automated system that scans through scientific publications about Mars to extract information about named surface targets (rocks, soils, etc.) and their composition. The extracted information is compiled into a searchable encyclopedia. You can access MTE data at these locations:

  • Mars Pathfinder, Mars Phoenix Lander, and Mars Exploration Rover targets
  • Mars Science Laboratory targets through the MSL Analyst's Notebook (click "Search", then "Targets")

  Publications:

  • Targets from the Spirit Mars Exploration Rover in the Mars Target Encyclopedia. (Poster)
    Kiri L. Wagstaff, Raymond Francis, Matthew Golombek, Steven Lu, Ellen Riloff, Leslie Tamppari, Yuan Zhuang, and Thomas Stein.
    53rd Lunar and Planetary Science Conference, Abstract #1231, March 2022.
    • What's in twenty years / Of talk about Mars targets? / Olivine and more!
    • The MTE database is available at the PDS: Mars Target Encyclopedia
  • The Mars Target Encyclopedia Now Includes Mars Pathfinder and Mars Phoenix Targets. (Poster)
    Kiri L. Wagstaff, Raymond Francis, Matthew Golombek, Steven Lu, Ellen Riloff, Leslie Tamppari, and Thomas C. Stein.
    52nd Lunar and Planetary Science Conference, Abstract #1278, March 2021.
    • What about Yogi? / Mars mission targets abound / You can find them here
    • The MTE database is now available at the PDS: Mars Target Encyclopedia
  • MER Contact Science Targets: Archived Database and Inclusion in the Analyst's Notebook.
    T. C. Stein, R. E. Arvidson, S. J. Van Bommel, K. L. Wagstaff, E. Riloff, F. Zhou, and E. A. Guinness.
    51st Lunar and Planetary Science Conference, Abstract #1942, March 2020.
  • MSL Analyst's Notebook: Improved Connections between Targets, Data, and Published Literature.
    Thomas C. Stein, Raymond E. Arvidson, Kiri L. Wagstaff, and Feng Zhou.
    Fourth Planetary Data Workshop, Abstract #7027, June 2019.
  • MSL Analyst's Notebook: Curiosity APXS Concentration Data Integration and Mars Target Encyclopedia and Interface Updates.
    T. C. Stein, R. E. Arvidson, S. J. Van Bommel, K. L. Wagstaff, and F. Zhou.
    50th Lunar and Planetary Science Conference, Abstract #1820, March 2019.
  • PDS Analyst's Notebook: Curiosity ChemCam RMI Mosaic and Mars Target Encyclopedia Integration and Interface Updates.
    T. C. Stein, R. E. Arvidson, W. Rapin, K. L. Wagstaff, D. Delapp, R. C. Wiens, O. Gasnault.
    49th Lunar and Planetary Science Conference, Abstract #1248, March 2018.
  • Mars Target Encyclopedia: Rock and Soil Composition Extracted from the Literature.
    Kiri L. Wagstaff, Raymond Francis, Thamme Gowda, You Lu, Ellen Riloff, Karanjeet Singh, and Nina L. Lanza.
    Proceedings of the Thirtieth Annual Conference on Innovative Applications of Artificial Intelligence, 2018.
    • Data set (annotated documents):
  • Mars Target Encyclopedia: Information Extraction for Planetary Science.
    Kiri L. Wagstaff, Raymond Francis, Thamme Gowda, You Lu, Ellen Riloff, and Karanjeet Singh.
    Third Planetary Data Workshop, Abstract #7031, June 2017.
  • Creating a Mars Target Encyclopedia by Extracting Information from the Planetary Science Literature (pdf, 5 pages, 421K) [Slides (pptx, 5.4M)].
    Kiri L. Wagstaff, Ellen Riloff, Nina L. Lanza, Chris A. Mattmann, and Paul M. Ramirez.
    AAAI-16 Workshop on Workshop on Knowledge Extraction from Text, Feb. 2016.
• On-board Data Analysis: Show/hide details

  This has been a focus of my research since I joined JPL, and (not coincidentally) it is a major emphasis of my group's work in general. I have looked at methods for on-board analysis for Earth orbiters, Mars orbiters (to detect thermal anomalies, track the CO2 polar caps, and estimate the dust and water ice content of the atmosphere), Mars landers/rovers (to detect dust devils), and a hypothetical mission to Enceladus (to detect plumes).

  Most of this work is cutting-edge in terms of the problems we tackle and the restrictions of the computing environment, rather than in terms of novel machine learning methods. Thus, most of the publications we've had are in science venues, in which we seek to publicize the benefits of machine learning technology for spacecraft.

  • Novelty-Driven Onboard Targeting for Mars Rovers.
    Kiri L. Wagstaff, Raymond Francis, Hannah Kerner, Steven Lu, Favour Nerrise, James F. Bell III, Gary Doran, and Umaa Rebbapragada.
    Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space, 2020.
  • Cloud Filtering and Novelty Detection using Onboard Machine Learning for the EO-1 Spacecraft.
    Kiri L. Wagstaff, Alphan Altinok, Steve Chien, Umaa Rebbapragada, Steve Schaffer, David R. Thompson, and Daniel Tran.
    IJCAI 2017 Workshop on AI in the Oceans and Space, 2017.
  • Scientist-Guided Autonomy for Self-Reliant Rovers.
    Gary Doran, Umaa Rebbapragada, Eugenie Song, Kiri Wagstaff, Daniel Gaines, Robert Anderson, and Ashwin Vasavada.
    IJCAI 2017 Workshop on AI in the Oceans and Space, 2017.
  • Onboard Autonomy on the Intelligent Payload EXperiment CubeSat Mission.
    Steve Chien, Joshua Doubleday, David R. Thompson, Kiri L. Wagstaff, John Bellardo, Craig Francis, Eric Baumgarten, Austin Williams, Edmund Yee, Eric Stanton, and Jordi Piug-Suari.
    Journal of Aerospace Information Systems, vol. 14, no. 6, p. 307-315, 2017.
  • Robotic Space Exploration Agents.
    Steve Chien and Kiri L. Wagstaff.
    Science Robotics, 2(7), eaan4831, 2017.
    
  • Onboard Machine Learning Classification of Images by a Cubesat in Earth Orbit.
    David R. Thompson, Alphan Altinok, Ben Bornstein, Steve A. Chien, Joshua Doubleday, John Bellardo, and Kiri L. Wagstaff.
    AI Matters, 1(4), 38-40, 2015.
  • Enhanced Flyby Science with Onboard Computer Vision: Tracking and Surface Feature Detection at Small Bodies.
    Thomas Fuchs, David R. Thompson, Brian Bue, Julie Castillo, Steve Chien, Dero Gharibian, and Kiri Wagstaff.
    Earth and Space Science, 2(10), 417-434, 2015.
  • Autonomous Onboard Surface Feature Detection for Flyby Missions.
    Thomas J. Fuchs, Brian D. Bue, Julie Castillo-Rogez, Kiri Wagstaff, David R. Thompson.
    Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space, 2014.
  • Smart, Texture-sensitive Instrument Classification for In Situ Rock And Layer Analysis.
    Kiri L. Wagstaff, David R. Thompson, William Abbey, Abigail Allwood, Dmitriy L. Bekker, Nathalie A. Cabrol, Thomas Fuchs, and Kevin Ortega.
    Geophysical Research Letters, 40(16):4188-4193, doi:10.1002/grl.50817, 2013.
  • Surface Sulfur Detection via Remote Sensing and Onboard Classification.
    Lukas Mandrake, Umaa Rebbapragada, Kiri L. Wagstaff, David Thompson, Steve Chien, Daniel Tran, Robert T. Pappalardo, Damhnait Gleeson, and Rebecca Castano.
    ACM Transactions on Intelligent Systems and Technology, 2012.
  • Machine Learning in Space: Extending Our Reach.
    Amy McGovern and Kiri L. Wagstaff.
    Machine Learning, 84(3):335-340, doi:10.1007/s10994-011-5249-4, 2011.
  • Mars Coordinated Science Networking Demonstration (pdf, 9 pages, 1.1M).
    Ross Jones, Andre Girerd, Kiri Wagstaff, Charles Baker, Rashied Amini, and Debarati Chattopadhyay.
    JPL Technical Report, 2009.
  • Progressive Refinement for Support Vector Machines.
    Kiri L. Wagstaff, Michael Kocurek, Dominic Mazzoni, and Benyang Tang. Data Mining and Knowledge Discovery, DOI 10.1007/s10618-009-0149-y, 2009.
  • Improving Onboard Analysis of Hyperion Images by Filtering Mislabeled Training Data Examples (pdf, 9 pages, 751K).
    Umaa Rebbapragada, Lukas Mandrake, Kiri L. Wagstaff, Damhnait Gleeson, Rebecca Castano, Steve Chien, and Carla E. Brodley.
    Proceedings of the 30th IEEE Aerospace Conference, 2009.
  • Onboard Detection of Natural Sulfur on a Glacier via a SVM and Hyperion Data (pdf, 14 pages, 7.5M).
    Lukas Mandrake, Kiri L. Wagstaff, Damhnait Gleeson, Umaa Rebbapragada, Daniel Tran, Rebecca Castano, Steven Chien, and Robert Pappalardo.
    Proceedings of the 30th IEEE Aerospace Conference, 2009.
  • Observations of the North Polar Water Ice Annulus on Mars using THEMIS and TES.
    Kiri L. Wagstaff, Timothy N. Titus, Anton B. Ivanov, and Rebecca Castano.
    Planetary and Space Science, v. 56, p. 256-265, 2008.
  • Onboard Detection of Active Canadian Sulfur Springs (pdf, 8 pages, 235k).
    Rebecca Castano, Kiri Wagstaff, Damhnait Gleeson, Robert Pappalardo, Steve Chien, Daniel Tran, Lucas Scharenbroich, Benyang Tang, Brian Bue, and Thomas Doggett.
    Proceedings of the 9th International Symposium on Artificial Intelligence, Robotics, and Automation in Space, 2008.
  • On-board Analysis of Uncalibrated Data for a Spacecraft at Mars (pdf, 9 pages, 849k).
    Rebecca Castano, Kiri L. Wagstaff, Steve Chien, Timothy M. Stough, and Benyang Tang.
    Proceedings of the Thirteenth International Conference on Knowledge Discovery and Data Mining (KDD), 2007.
  • Automatic Onboard Detection of Planetary Volcanism from Images (pdf, 2 pages, 173k).
    Brian Bue, Kiri L. Wagstaff, Rebecca Castano, and Ashley Davies.
    38th Lunar and Planetary Science Conference, 2007.
  • NASA Tech Brief: Estimating Dust and Water Ice Content of the Martian Atmosphere From THEMIS Data, 2007.
  • Real-Time, In-Situ Detection of Dust Devils using Pressure Sensors (html).
    Kiri L. Wagstaff, Rebecca Castano, and Steve Chien.
    Eos Transactions of the American Geophysical Union, 87(52), Fall Meeting Supplement, Abstract #IN52A-03, 2006.
  • Automatic Plume Detection for Planetary Bodies (html).
    Brian Bue, Kiri L. Wagstaff, Rebecca Castano, and Ashley Davies.
    Eos Transactions of the American Geophysical Union, 87(52), Fall Meeting Supplement, Abstract #IN52A-04, 2006.
  • Automating the Detection of Enceladus-Style Plumes (html).
    Kiri L. Wagstaff, Becky Castano, Ashley Davies, and Brian Bue.
    Division for Planetary Sciences meeting #38, Bulletin of the American Astronomical Society, Vol. 38, p. 522, 2006.
  • Detecting Dust Storms and Water Ice Clouds Onboard THEMIS (html -- note incorrect citation; should be Spring 2006, not Fall 2007 meeting).
    Kiri L. Wagstaff, Joshua L. Bandfield, Rebecca Castano, Steve Chien, Michael D. Smith, and Timothy M. Stough.
    Spring AGU Joint Assembly, Revolutionary Space Exploration Concepts using Onboard Computing, 2006.
  • Dust Storms and Water Ice Clouds: Feature Detection for Use Onboard THEMIS (pdf, 2 pages, 216k).
    Kiri L. Wagstaff, Joshua L. Bandfield, Rebecca Castano, Steve Chien, and Michael D. Smith.
    37th Lunar and Planetary Science Conference, 2006.
  • An Onboard Data Analysis Method to Track the Seasonal Polar Caps on Mars (pdf, 8 pages, 2.8M).
    Kiri L. Wagstaff, Rebecca Castano, Steve Chien, Anton B. Ivanov, and Timothy N. Titus.
    Proceedings of the International Symposium on Artificial Intelligence, Robotics, and Automation in Space, 2005.
  • Revolutionising Science-Driven Deep Space Mission Operations Using Autonomously-Operating Spacecraft as Demonstrated with ASE on EO-1 (html).
    Davies, Chien, Doggett, Ip, Dohm, Greeley, Baker, Castano, Sherwood, and Wagstaff.
    Eos Transactions of the American Geophysical Union, 86(52), Fall Meeting Supplement, Abstract #P41A-0924, 2005.
  • Towards Onboard Orbital Tracking of Seasonal Polar Volatiles on Mars (pdf, 2 pages, 115k).
    Kiri L. Wagstaff, Rebecca Castano, Steve Chien, Anton B. Ivanov, and Timothy N. Titus.
    36th Lunar and Planetary Science Conference, 2005.
  • Tracking Retreat of the North Seasonal Ice Cap on Mars: Results from the THEMIS Investigation (pdf, 2 pages, 860k).
    Anton B. Ivanov, Kiri L. Wagstaff, and Timothy N. Titus.
    36th Lunar and Planetary Science Conference, 2005.

Past Projects:

• Adaptive Data Processing for Fast Radio Transient Detection Show/hide details

  We are developing new algorithms to quickly detect transient (very short-duration) events in radio astronomy data, to enable archiving the raw data for only events of interest. We have an operational system (V-FASTR) at the 10-station Very Long Baseline Array (VLBA) and ultimately aim to support the ambitious plans of the 3,000-antenna Square Kilometer Array (SKA). You can see the latest V-FASTR activity and detections here.

  • Limits on Fast Radio Bursts from Four Years of the V-FASTR Experiment.
    Sarah Burke-Spolaor, Cathryn M. Trott, Walter F. Brisken, Adam T. Deller, Walid A. Majid, Divya Palaniswamy, David R. Thompson, Steven J. Tingay, Kiri L. Wagstaff, and Randall B. Wayth.
    The Astrophysical Journal, 826(2), doi:10.3847/0004-637X/826/2/223, 2016.
  • A Machine Learning Classifier for Fast Radio Burst Detection at the VLBA.
    Kiri L. Wagstaff, Benyang Tang, David R. Thompson, Shakeh Khudikyan, Jane Wyngaard, Adam T. Deller, Divya Palaniswamy, Steven J. Tingay, and Randall B. Wayth.
    Publications of the Astronomical Society of the Pacific, 128:966(084503), 2016.
  • A Framework for Collaborative Review of Candidate Events in High Data Rate Streams: The V-FASTR Experiment as a Case Study.
    Andrew F. Hart, Luca Cinquini, Shakeh E. Khudikyan, David R. Thompson, Chris A. Mattmann, Kiri Wagstaff, Joseph Lazio, and Dayton Jones.
    Astronomical Journal, 149(1), 2015.
  • Astronomical Data Triage for Rapid Science Return.
    Brian D. Bue, Kiri L. Wagstaff, Umaa D. Rebbapragada, David R. Thompson, and Benyang Tang.
    Proceedings of the Big Data from Space Conference, 2014.
  • Supporting Distributed, Collaborative Review and Classification of Fast Transient Events.
    A. F. Hart, L. Cinquini, S. E. Khudikyan, D. R. Thompson, C. A. Mattmann, K. L. Wagstaff, J. Lazio, and D. Jones.
    Computer, 47(9), 65-66, 2014.
  • Real-Time Adaptive Event Detection in Astronomical Data Streams.
    Randall B. Wayth, Kiri L. Wagstaff, Steven J. Tingay, Walid A. Majid, Divya Palaniswamy, Adam T. Deller, David R. Thompson, and Sarah Burke-Spolaor. IEEE Intelligent Systems, 29(1):48-55, 2014.
  • Online Classification for Time-Domain Astronomy.
    Kitty K. Lo, Tara Murphy, Umaa Rebbapragada, and Kiri L. Wagstaff.
    Proceedings of the Astroinformatics workshop, IEEE International Conference on Data Mining, December 2013.
  • A Framework for Interpreting Fast Radio Transients Search Experiments: Application to the V-FASTR Experiment.
    Cathryn M. Trott, Steven J. Tingay, Randall B. Wayth, David R. Thompson, Adam T. Deller, Walter F. Brisken, Kiri L. Wagstaff, Walid A. Majid, Sarah Burke-Spolaor, Jean-Pierre R. Macquart, and Divya Palaniswamy.
    The Astrophysical Journal, 767, 4, doi: 10.1088/0004-637X/767/1/4, 2013.
  • Limits on the event rates of fast radio transients from the V-FASTR experiment.
    Randall B. Wayth, Steven J. Tingay, Adam T. Deller, Walter F. Brisken, David R. Thompson, Kiri L. Wagstaff, and Walid A. Majid.
    The Astrophysical Journal Letters, 753(2), doi: 10.1088/2041-8205/753/2/L36, 2012 (arXiv version).
  • Semi-Supervised Eigenbasis Novelty Detection.
    David R. Thompson, Walid A. Majid, Colorado J. Reed, and Kiri L. Wagstaff.
    Statistical Analysis and Data Mining, 2012.
  • Offline and Online Classification of Simulated VAST Transients (pdf, 18 pages, 3M).
    Umaa Rebbapragada, Kitty Lo, Kiri L. Wagstaff, Colorado Reed, and Tara Murphy.
    VAST Memo 5, 2012.
  • Big Data Challenges for Large Radio Arrays (pdf, 6 pages, 1.2M).
    Dayton L. Jones, Kiri Wagstaff, David R. Thompson, Larry D'Addario, Robert Navarro, Chris Mattmann, Walid Majid, Joseph Lazio, Robert Preston, and Umaa Rebbapragada.
    Proceedings of the 33rd IEEE Aerospace Conference, March 2012.
  • Semi-Supervised Novelty Detection with Adaptive Eigenbases, and Application to Radio Transients (pdf, 11 pages, 625K). [Slides (pdf, 12 pages, 4M)] Received the Best Paper Award. David R. Thompson, Walid A. Majid, Colorado J. Reed, and Kiri L. Wagstaff. Proceedings of the Conference on Intelligent Data Understanding, 2011.
  • V-FASTR: The VLBA Fast Radio Transients Experiment.
    Randall B. Wayth, Walter F. Brisken, Adam T. Deller, Walid A. Majid, David R. Thompson, Steven J. Tingay, and Kiri L. Wagstaff.
    The Astrophysical Journal, 735(2), doi: 10.1088/0004-637X/735/2/97, 2011.
  • Detection of fast radio transients with multiple stations: A case study using the Very Long Baseline Array.
    David R. Thompson, Kiri L. Wagstaff, Walter Brisken, Adam T. Deller, Walid A. Majid, Steven J. Tingay, and Randall B. Wayth.
    The Astrophysical Journal, 735(2), doi: 10.1088/0004-637X/735/2/98, 2011.
  • The Commensal Real-time ASKAP Fast Transients (CRAFT) survey.
    Jean-Pierre Macquart and the CRAFT collaboration: M. Bailes, N.D.R. Bhat, G.C. Bower, J.D. Bunton, S. Chatterjee, T. Colegate, J.M. Cordes, L. D'Addario, A. Deller, R. Dodson, R. Fender, K. Haines, P. Hall, C. Harris, A. Hotan, S. Johnston, D.L. Jones, M. Keith, J.Y. Koay, T.J.W. Lazio, W. Majid, T. Murphy, R. Navarro, C. Phillips, P. Quinn, R.A. Preston, B. Stansby, I. Stairs, B. Stappers, L. Staveley-Smith, S. Tingay, D. Thompson, W. van Straten, K. Wagstaff, M. Warren, R. Wayth, L. Wen.
    Publications of the Astronomical Society of Australia, 27(3), p. 272-282, 2010.
• Automated Code Generation for Flight Software: Show/hide details

  Ensuring that an implementation exactly matches the specification is challenging, but particularly critical in flight software systems. We advocate the use of state-based software system modeling for use in flight software development, in which the system behavior is encoded in a UML state diagram, then converted into C or C++ code using the JPL Autocoder.

  We demonstrated this approach by encoding part of the Proximity-1 communications protocol, used by the Mars Reconnaissance Orbiter (MRO) and the Mars Exploration Rovers, into a state chart that we then converted into C code. We linked this code in with the MRO flight software for its Electra radio and successfully demonstrated that the auto-generated code passed all relevant flight software tests. In addition, we demonstrated the benefits of this development process, which include reduced development time, earlier detection of errors, and ease of communicating system design. As a result, a simplified version of the Autocoder was adopted by the Mars Science Laboratory software team, and we received follow-on funding to produce a full reference implementation of Proximity-1, using the same process, for use testing future radios in the JPL Protocol TestLab.

  • From Protocol Specification to Statechart to Implementation (pdf, 13 pages, 560k).
    Kiri L. Wagstaff, Ken Peters, and Lucas Scharenbroich.
    JPL Technical Report, 2008.
  • Automatic Code Generation for Instrument Flight Software (pdf, 8 pages, 289k).
    Kiri L. Wagstaff, Edward Benowitz, DJ Byrne, Ken Peters, and Garth Watney.
    Proceedings of the 9th International Symposium on Artificial Intelligence, Robotics, and Automation in Space, 2008.
• Biogenicity Analysis of Images: Show/hide details

  I completed a Master's degree in Geological Sciences from the University of Southern California in December, 2008. This work has focused on what methods from information theory can tell us about the potential biogenicity (created by life) of a sample may be.

  • Detecting Structural Microbial Biosignatures in Digital Images.
    Kiri L. Wagstaff and Frank A. Corsetti.
    Astrobiology, 10(4), p. 363-379, doi:10.1089/ast.2008.0301, May 2010.
  • Biogenicity Analysis for Stromatolite Structures (full text from the USC library).
    Kiri L. Wagstaff.
    Master's Thesis, University of Southern California, 2008.
• Collaborative Learning for Sensor Networks:
  (Synergistic Machine Learning, Collaboration and Topology Exploitation in Dynamic Environments) Show/hide details

  We seek to develop methods by which the individual nodes in a sensor network can collaboratively learn new concepts, by querying each other and sharing data and learned information.

  Funded by a four-year grant from the NSF's Robust Intelligence Program (NSF award number IIS-0705681), this project is a collaboration with Terran Lane of UNM.

  • Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data (pdf, 6 pages 275K).
    Umaa Rebbapragada and Kiri L. Wagstaff.
    Proceedings of the ICML Workshop on Combining Learning Strategies to Reduce Label Cost, 2011.
  • NSF RI Year 3 Project Report (pdf, 6 pages, 97K).
    Covers the period June 2009 - May 2010.
  • Progressive Refinement for Support Vector Machines.
    Kiri L. Wagstaff, Michael Kocurek, Dominic Mazzoni, and Benyang Tang, Data Mining and Knowledge Discovery, 20(1), p. 53-69, doi:10.1007/s10618-009-0149-y, 2010.
  • NSF award abstract
• Constrained Clustering: Show/hide details

  Constrained clustering was an idea I invented for my dissertation at Cornell University (Ph.D. 2002). Unsatisfied with the peformance of regular clustering on the challenging task of noun phrase clustering, I suggested that we might be able to build in our existing domain knowledge as constraints on the clustering process. Others have since taken up this idea and extended it in many directions.

  • Constrained Clustering: Advances in Algorithms, Theory, and Applications.
    Edited by Sugato Basu, Ian Davidson, and Kiri L. Wagstaff, 2008.
  • Value, Cost, and Sharing: Open Issues in Constrained Clustering (pdf, 10 pages, 384K).
    Kiri L. Wagstaff.
    Proceedings of the Fifth International Workshop on Knowledge Discovery in Inductive Databases (KDID 2006), LNCS 4747, p. 1-10, 2007.
  • Measuring Constraint-Set Utility for Partitional Clustering Algorithms (pdf, 12 pages, 276K).
    Ian Davidson, Kiri L. Wagstaff, and Sugato Basu.
    Proceedings of the Tenth European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), p. 115-126, 2006.
  • When is Constrained Clustering Beneficial, and Why? (pdf, 2 pages, 71K).
    Kiri L. Wagstaff, Sugato Basu, and Ian Davidson.
    AAAI Member Abstracts and Posters, Proceedings of the Twenty-first National Conference on Artificial Intelligence (AAAI), 2006.
  • Active Constrained Clustering by Examining Spectral Eigenvectors (pdf, 14 pages, 681K).
    Qianjun Xu, Marie desJardins, and Kiri L. Wagstaff.
    Proceedings of the Eighth International Conference on Discovery Science, 2005.
  • Constrained Spectral Clustering under a Local Proximity Structure (pdf, 2 pages, 55K).
    Qianjun Xu, Marie desJardins, and Kiri Wagstaff.
    Proceedings of the 18th International Florida Artificial Intelligence Research Society (FLAIRS) Conference, 2005.
  • Intelligent Clustering with Instance-Level Constraints
    (link is to a more detailed page with individual chapters, not to the whole thing).
    Kiri Wagstaff. Ph.D. Dissertation, 2002.
  • Constrained K-means Clustering with Background Knowledge (ps, 8 pages, 225K; [pdf version]).
    Kiri Wagstaff, Claire Cardie, Seth Rogers, and Stefan Schroedl.
    Proceedings of the International Conference on Machine Learning (ICML), p. 577-584, 2001.
  • Clustering with Instance-level Constraints (ps, 8 pages, 224K; [pdf version]).
    Kiri Wagstaff and Claire Cardie.
    Proceedings of the International Conference on Machine Learning (ICML), p. 1103-1110, 2000.
• HARVIST (Heterogeneous Agricultural Research Via Interactive, Scalable Technology): Show/hide details

  We developed and demonstrated an interactive machine learning analysis toolkit for use with remote sensing data. In particular, the PixelLearn system provides SVM classification, SVM regression, and clustering methods and supports a range of different remote sensing data types (for imagers and spectrometers).

  In this project, we sought to identify connections between weather and agriculture (e.g., crop yield). We integrated data from orbiting satellites, weather stations on the ground, and historical crop yield archives to generate crop yield predictions in California and Kansas, for wheat and corn.

  Funded by a two-year grant from NASA's Earth Science Technology Office (grant number AIST-QRS-04-3004), then extended an additional 9 months by an ATI infusion grant, this project was a collaboration with Dominic Mazzoni of JPL and Stephan Sain of NCAR.

  • Multiple-Instance Regression with Structured Data (pdf, 10 pages, 307k).
    Kiri L. Wagstaff, Terran Lane, and Alex Roper.
    Proceedings of the 4th International Workshop on Mining Complex Data, 2008.
  • County-Level Crop Yield Prediction Using Remote Sensing Data.
    Kiri L. Wagstaff, Alex Roper, and Terran Lane.
    Eos Transactions of the American Geophysical Union, 88(52), Fall Meeting Supplement, Abstract #B13D-1526, 2007.
  • Salience Assignment for Multiple-Instance Regression (pdf, 6 pages, 223k).
    Kiri L. Wagstaff and Terran Lane.
    Proceedings of the ICML 2007 Workshop on Constrained Optimization and Structured Output Spaces, 2007.
  • Recent HARVIST Results: Classifying Crops from Remote Sensing Data (pdf, 5 pages, 197k).
    Kiri Wagstaff and Dominic Mazzoni.
    Proceedings of the Second NASA Data Mining Workshop, 2006.
  • Fast, Interactive Analysis of Remote Sensing Data with the HARVIST System (html).
    Michael J. Kocurek, Kiri L. Wagstaff, Dominic Mazzoni, Stephan R. Sain, Lucas Scharenbroich, and Timothy M. Stough.
    Eos Transactions of the American Geophysical Union, 87(52), Fall Meeting Supplement, Abstract #IN21A-1204, 2006.
  • HARVIST: A System for Agricultural and Weather Studies Using Advanced Statistical Models (pdf, 5 pages, 3.5Mb).
    Kiri L. Wagstaff, Dominic Mazzoni, and Stephan Sain.
    Proceedings of the Earth-Sun Systems Technology Conference, 2005.
• KEDS (Knowledge-Enhanced Discovery Systems): Show/hide details

  We seek to develop classification, clustering, and preference modeling methods that can take advantage of existing domain knowledge.

  Funded by a five-year grant from the NSF's Information Technology Research Program (NSF award number ITR-0325329), this project is a collaboration with Marie desJardins of UMBC.

  • Data Clustering.
    Kiri L. Wagstaff.
    Chapter in Advances in Machine Learning and Data Mining for Astronomy, Chapman & Hall/CRC Press, 2011.
  • NSF ITR Year 7 Project Report (pdf, 6 pages, 91K).
    Covers the period Sept. 2009 - Aug. 2010.
  • Confidence-Based Feature Acquisition to Minimize Training and Test Costs (pdf, 11 pages, 624K).
    Marie desJardins, James MacGlashan, and Kiri L. Wagstaff.
    Proceedings of the SIAM Conference on Data Mining, p. 514-524, 2010.
  • Modeling and Learning Preferences over Sets.
    Kiri L. Wagstaff, Marie desJardins, and Eric Eaton.
    Journal of Experimental and Theoretical Artificial Intelligence, doi:10.1080/09528130903119336, 2009.
  • Learning User Preferences for Sets of Objects (pdf, 8 pages, 270k).
    Marie desJardins, Eric Eaton, and Kiri L. Wagstaff.
    Proceedings of the Twenty-Third International Conference on Machine Learning, p. 273-280, 2006.
  • Active Constrained Clustering by Examining Spectral Eigenvectors (pdf, 14 pages, 681K).
    Qianjun Xu, Marie desJardins, and Kiri L. Wagstaff.
    Proceedings of the Eighth International Conference on Discovery Science, 2005.
  • DD-PREF: A Language for Expressing Preferences Over Sets (pdf, 7 pages, 597K).
    Marie desJardins and Kiri L. Wagstaff.
    Proceedings of the Twentieth National Conference on Artificial Intelligence, p. 620-626, 2005.
  • Constrained Spectral Clustering under a Local Proximity Structure (pdf, 2 pages, 55K).
    Qianjun Xu, Marie desJardins, and Kiri Wagstaff.
    Proceedings of the 18th International Florida Artificial Intelligence Research Society (FLAIRS) Conference, 2005.
  • A Context-Sensitive and User-Centric Approach to Developing Personal Assistants (pdf, 3 pages, 40K).
    Marie desJardins, Eric Eaton, and Kiri Wagstaff.
    Persistent Assistants: Living and Working with AI (AAAI Spring Symposium), 2005.
  • Making the Most of Missing Values: Object Clustering with Partial Data in Astronomy (pdf, 5 pages, 85K).
    Kiri Wagstaff and Victoria G. Laidler.
    Astronomical Data Analysis Software and Systems XIV (ADASS), ASP Conference Series, Vol. 347, 2005.
  • Clustering with Missing Values: No Imputation Required (pdf, 10 pages, 244K).
    Kiri Wagstaff.
    Classification, Clustering, and Data Mining Applications (Proceedings of the Meeting of the International Federation of Classification Societies), p. 649-658, 2004.
• Radiation-Tolerant Machine Learning : Show/hide details

  Computing in a high-radiation environment, such as in orbit, can be risky; data can be corrupted by radiation during the course of a long computation. As we seek to have more data analysis done onboard spacecraft, this issue becomes more critical. Radiation-hardened hardware lags behind the "soft" state of the art by years, and is orders of magnitude slower and more expensive. In this project, we investigated alternative ways to compute safely in a high-radiation environment, using software solutions rather than specialized hardware. We also designed and built a software simulator that can subject a program to a simulated high-radiation environment by injecting "bit flips" into RAM while the program is running.

  • Simulating and Detecting Radiation-Induced Errors for Onboard Machine Learning (pdf, 7 pages, 243K).
    Robert Granat, Kiri L. Wagstaff, Benjamin Bornstein, Benyang Tang, and Michael Turmon.
    Proceedings of the Third IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT), p. 125-131, 2009.
  • How much Memory Radiation Protection do Onboard Machine Learning Algorithms Require? (pdf, 7 pages, 645K).
    Kiri L. Wagstaff and Benjamin Bornstein.
    Proceedings of the IJCAI-09/SMC-IT-09/IWPSS-09 Workshop on Artificial Intelligence in Space, 2009.
  • K-means in Space: A Radiation Sensitivity Evaluation (pdf, 8 pages, 283K). (Or watch the video)
    Kiri L. Wagstaff and Benjamin Bornstein.
    Proceedings of the Twenty-Sixth International Conference on Machine Learning (ICML), p. 1097-1104, 2009.
    [Note: An error in units conversion causes the experiments in this paper to over-estimate the impact of radiation. See "How Much Memory Radiation Protection do Onboard Machine Learning Algorithms Require?" above for updated results.]
  • NASA Tech Brief: Injecting Artificial Memory Errors Into a Running Computer Program, 2008: describes BITFLIPS (Basic Instrumentation Tool for Fault Localized Injection of Probabilistic SEUs)
• Surface Change Detection from Images: Show/hide details

  Currently, most analysis of images collected by orbiters around other planets proceeds manually. Interesting features, such as craters, fissures, gullies, and volcanoes are annotated in a painstaking process. We seek to provide automated means to annotate these features of interest, and particularly to detect any surface changes. These changes include the appearance or disappearance of the mysterious dark slope streaks on Mars as well as dust devil tracks and any other new discoveries we may uncover. Our approach focuses on the automated identification of "landmarks", which are statistically salient features within an image, and the subsequent detection of any changes.

  Funded by a three-year grant from NASA's Applied Information Systems Research (AISR) Program, this project is a collaboration with Ron Greeley of ASU and Norbert Schorghofer of the Univ. of Hawaii.

  • Dynamic Landmarking for Surface Feature Identification and Change Detection.
    Kiri L. Wagstaff, Julian Panetta, Adnan Ansar, Ronald Greeley, Mary Pendleton Hoffer, Melissa Bunte, and Norbert Schorghofer.
    ACM Transactions on Intelligent Systems and Technology, vol. 3, issue 3, article number 49, 2012.
  • Change Detection in Mars Orbital Images using Dynamic Landmarking (pdf, 2 pages, 596K).
    Kiri L. Wagstaff, Julian Panetta, Adnan Ansar, Melissa Bunte, Ronald Greeley, Mary Pendleton Hoffer, and Norbert Schorghofer.
    41st Lunar and Planetary Science Conference, March 2010.
  • Automatic Landmark Identification in Mars Orbital Imagery.
    Kiri L. Wagstaff, Julian Panetta, Ron Greeley, Norbert Schorghofer, Melissa Bunte, Mary Pendleton Hoffer, and Adnan Ansar.
    Eos Transactions of the American Geophysical Union, 89(53), Fall Meeting Supplement, Abstract #P53C-1469, 2008.
  • Surface Change Detection from Mars Orbital Imagery.
    Baback Moghaddam, Brian D. Bue, Rebecca Castano, and Kiri L. Wagstaff.
    Eos Transactions of the American Geophysical Union, 88(52), Fall Meeting Supplement, Abstract #P33A-1020, 2007.