Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

GR: Fachverband Gravitation und Relativitätstheorie

GR 11: BH Physics II, GW IV

GR 11.4: Vortrag

Donnerstag, 3. April 2025, 15:15–15:35, ZHG007

Forecasting Seismic Noise with Deep Learning for Gravitational Wave Detection — •Waleed Esmail¹, Alexander Kappes¹, Stuart Russell², and Christine Thomas² — ¹Institut für Kernphysik, Universität Münster, 48149 Münster, Germany — ²Institut für Geophysik, Universität Münster, 48149 Münster, Germany

The Einstein Telescope (ET) is a third-generation gravitational wave observatory. As a ground-based detector, it is susceptible to seismic noise, particularly at low frequencies. Accurately predicting seismic waveforms can help mitigate the impact of seismic noise, thereby enhancing the detector's sensitivity. This study utilizes the power of deep learning algorithms for their ability to model complex systems, to precisely predict the 3-component seismic waveforms. Our approach focuses on training a model to use initial earthquake waves (P-waves) to predict subsequent, more destructive waves (S-waves and surface waves). The training process utilizes synthetic seismograms embedded in realistic noise, with the synthetic data generated using realistic source parameters and Green*s function databases derived from a 1D Earth model.