Data mining and machine learning improve gravitational-wave detector sensitivity
G. Vajente
Abstract
Application of data mining and machine learning techniques can significantly improve the sensitivity of current interferometric gravitational-wave detectors. Such instruments are complex multi-input single-output systems, with close-to-linear dynamics and hundreds of active feedback control loops. We show how the application of brute-force data-mining techniques allows us to discover correlations between auxiliary monitoring channels and the main gravitational-wave output channel. We also discuss the result of the application of a parametric and time-domain noise subtraction algorithm, that allows a significant improvement of the detector sensitivity at frequencies below 30 Hz.
Topics & Concepts
Sensitivity (control systems)DetectorGravitational waveSubtractionNoise (video)Computer scienceParametric statisticsInterferometryPhysicsChannel (broadcasting)Frequency domainAlgorithmArtificial intelligenceElectronic engineeringOpticsComputer visionTelecommunicationsMathematicsArithmeticEngineeringStatisticsImage (mathematics)AstrophysicsPulsars and Gravitational Waves ResearchGeophysics and Gravity MeasurementsModel Reduction and Neural Networks