NASA's Stardust mission utilized a sample collector composed of aerogel and aluminum foil to return cometary and interstellar particles to Earth. Analysis of the aluminum foil begins with locating craters produced by hypervelocity impacts of cometary and interstellar dust. Interstellar dust craters are typically less than one micrometer in size and are sparsely distributed, making them difficult to find. In this paper, we describe a convolutional neural network based on the VGG16 architecture that achieves high specificity and sensitivity in locating impact craters in the Stardust interstellar collector foils. Finally, we evaluate its implications for current and future analyses of Stardust samples.
Jaeger, Logan, et al. "Automatic detection of impact craters on Al foils from the Stardust interstellar dust collector using convolutional neural networks." Meteoritics and Planetary Science, vol. 56, no. 10, Sep. 2021. https://doi.org/10.1111/maps.13747
Jaeger, Logan, Butterworth, Anna L., Gainsforth, Zack, Lettieri, Robert, Zevin, Dan, Ardizzone, Augusto, Capraro, Michael, Burchell, Mark, Wozniakiewicz, Penny, Ogliore, Ryan C., De Gregorio, Bradley T., Stroud, Rhonda M., & Westphal, Andrew J. (2021). Automatic detection of impact craters on Al foils from the Stardust interstellar dust collector using convolutional neural networks. Meteoritics and Planetary Science, 56(10). https://doi.org/10.1111/maps.13747
Jaeger, Logan, Butterworth, Anna L., Gainsforth, Zack, et al., "Automatic detection of impact craters on Al foils from the Stardust interstellar dust collector using convolutional neural networks," Meteoritics and Planetary Science 56, no. 10 (2021), https://doi.org/10.1111/maps.13747
@article{osti_1982916,
author = {Jaeger, Logan and Butterworth, Anna L. and Gainsforth, Zack and Lettieri, Robert and Zevin, Dan and Ardizzone, Augusto and Capraro, Michael and Burchell, Mark and Wozniakiewicz, Penny and Ogliore, Ryan C. and others},
title = {Automatic detection of impact craters on Al foils from the Stardust interstellar dust collector using convolutional neural networks},
annote = {NASA's Stardust mission utilized a sample collector composed of aerogel and aluminum foil to return cometary and interstellar particles to Earth. Analysis of the aluminum foil begins with locating craters produced by hypervelocity impacts of cometary and interstellar dust. Interstellar dust craters are typically less than one micrometer in size and are sparsely distributed, making them difficult to find. In this paper, we describe a convolutional neural network based on the VGG16 architecture that achieves high specificity and sensitivity in locating impact craters in the Stardust interstellar collector foils. Finally, we evaluate its implications for current and future analyses of Stardust samples.},
doi = {10.1111/maps.13747},
url = {https://www.osti.gov/biblio/1982916},
journal = {Meteoritics and Planetary Science},
issn = {ISSN 1086-9379},
number = {10},
volume = {56},
place = {United States},
publisher = {Wiley},
year = {2021},
month = {09}}
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). Advanced Light Source (ALS); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). Molecular Foundry
Sponsoring Organization:
USDOE; National Aeronautics and Space Administration (NASA)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1982916
Alternate ID(s):
OSTI ID: 1827744
Journal Information:
Meteoritics and Planetary Science, Journal Name: Meteoritics and Planetary Science Journal Issue: 10 Vol. 56; ISSN 1086-9379