Gast ::
| Hauptseite > Publikationsdatenbank > FPGA Prototype of Seismic Signal Prediction from an Accelerometer Array towards Online Newtonian Noise Mitigation |
| Hauptseite > Publikationsdatenbank > FPGA Prototype of Seismic Signal Prediction from an Accelerometer Array towards Online Newtonian Noise Mitigation |
| Poster (After Call) | FZJ-2026-04121 |
; ; ; ; ; ;
2026
This record in other databases:
Please use a persistent id in citations: doi:10.34734/FZJ-2026-04121
Abstract: Seismic and environmental noise, particularly Newtonian noise, constitute a fundamentallimitation for the Einstein Telescope, motivating the development ofadvanced, data-driven approaches for noise mitigation to improve the sensitivityand operational stability of its interferometric systems. Real-time compensationof Newtonian noise can improve sensitivity of the sensor and allow rapidtriggering of multi-messenger observations when a gravitational wave signal isdetected.A neural network is trained to reconstruct the waveform of a target sensorbased on measurements from neighboring nodes. The method considers an arrayof N three-axis accelerometers, sampled at rates of up to 4,000 Hz. Correlationanalysis is used to identify suitable data preprocessing techniques and to determinethe optimal input window length for the neural network. The networkand data preprocessing is aimed to be implemented on an FPGA to achievereal-time signal processing. For this purpose, tools such as hls4ml or similarframeworks will be used.The approach is first evaluated using publicly available seismic datasets.This is followed by experimental validation using an FPGA-based sensor networkwith micro-electromechanical systems (MEMS) accelerometers, which collectseismic data and transmit it to a central FPGA for real-time predictionof target sensor measurements. Data compression techniques will be used tooptimize communication between FPGA nodes.
|
The record appears in these collections: |
PDF
Volltext