K-means in space: a radiation sensitivity evaluation

Spacecraft increasingly employ onboard data analysis to inform further data collection and prioritization decisions. However, many spacecraft operate in high-radiation environments in which the reliability of dataintensive computation is not known. This paper presents the first study of radiation sensitivity for k-means clustering. Our key findings are 1) k-means data structures differ in sensitivity, which is not determined solely by the amount of memory exposed; 2) no special radiation protection is needed below a dataset-dependent radiation threshold, enabling the use of faster, smaller, and cheaper onboard memory; and 3) subsampling improves radiation tolerance slightly, but the use of kdtrees unfortunately reduces tolerance. Our conclusions can help tailor k-means for use in future high-radiation environments.

• Type: Conference
• Year: 2009
• Where: ICML
• Authors: Kiri L. Wagstaff, Benjamin Bornstein
• Keywords: ICML 2009, Improves Radiation Tolerance, K-means Data Structures, Machine Learning, Radiation Sensitivity