¹Logan Jaeger et al. (>10)
Meteoritics & Planetary Science (in Press) Link to Article [https://doi.org/10.1111/maps.13747]
¹Space Sciences Laboratory, University of California at Berkeley, Berkeley, California, 94720 USA
Published by arrangement with John Wiley & Sons

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. We evaluate its implications for current and future analyses of Stardust samples.