Project 27: Improving Gravitational Wave Detection with Neural Networks
Contact Information:
Prof. Yuan Luo
Email: yuanluo@sjtu.edu.cn
Project Description and Objectives:
Sensitive gravitational wave (GW) detectors such as that of the Laser Interferometer Gravitational-wave Observatory (LIGO) realize the direct observation of GW signals that confirm Einstein’s general theory of relativity. However, it remains challenging to quickly detect faint GW signals from a large number of time series with background noise under unknown probability distributions. Traditional methods such as matched-filtering in general assume Additive White Gaussian Noise (AWGN) are far from being real-time due to its high computational complexity. To avoid these weaknesses, one-dimensional (1D) Convolutional Neural Networks (CNNs) are introduced to achieve fast online detection in milliseconds. However, they do not allow enough consideration on the trade-off between the frequency and time features, which will be revisited in this project through data pre-processing and subsequent two-dimensional (2D) CNNs during offline training to improve the online detection sensitivity.
Eligibility Requirements:
Good English communication skills.
Theoretical analysis ability, logical thinking ability, teamwork ability.
Software: Machine Learning Software.
Interest in Computer Science, Astronomy, Physics or Mathematics.
Main Tasks:
Feature extraction analysis.
Sensitivity performance analysis under real noise.
Interpretability analysis.
Website:
Lab: N/A