You only thermoelastically deform once: point absorber detection in LIGO test masses with YOLO
Date
2025
Authors
Goode, S.R.
Schiworski, M.
Brown, D.
Thrane, E.
Lasky, P.D.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Optics Express, 2025; 33(8):17601-17616
Statement of Responsibility
Simon R. Goode, Mitchell Schiworski, Daniel Brown, Eric Thrane, and Paul D. Lasky
Conference Name
Abstract
Current and future gravitational-wave observatories rely on large-scale, precision interferometers to detect the gravitational-wave signals. However, microscopic imperfections on the main interferometer mirrors, known as point absorbers, cause problematic heating of the optic via absorption of the high-power laser beam, which results in diminished sensitivity, loss of interferometer lock, or even permanent damage. Consistent monitoring of these mirrors is crucial for detecting, characterizing, and ultimately removing point absorbers. We present a machine-learning algorithm for detecting point absorbers based on the object-detection algorithm You Only Look Once (YOLO). The algorithm can perform this task in situ while the detector is in operation. We validate our algorithm by comparing it with past reports of point absorbers identified by humans at LIGO. The algorithm confidently identifies the same point absorbers as humans with minimal false positives. It also identifies some point absorbers previously not identified by humans, which we confirm with human follow-up. We highlight the potential of machine learning in detector commissioning efforts.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement