Project 27: Improving Gravitational Wave Detection with Neural Networks
Apply

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

School: http://www.cs.sjtu.edu.cn/PeopleDetail.aspx?id=87