Detection of gravitational waves using topological data analysis and convolutional neural network: An improved approach
This provides an incremental improvement for astrophysicists detecting gravitational waves in noisy data.
The paper tackles gravitational wave detection by combining persistent homology feature extraction with convolutional neural networks to improve noise resilience and reduce training requirements, achieving unspecified performance gains over CNN-only approaches.
The gravitational wave detection problem is challenging because the noise is typically overwhelming. Convolutional neural networks (CNNs) have been successfully applied, but require a large training set and the accuracy suffers significantly in the case of low SNR. We propose an improved method that employs a feature extraction step using persistent homology. The resulting method is more resilient to noise, more capable of detecting signals with varied signatures and requires less training. This is a powerful improvement as the detection problem can be computationally intense and is concerned with a relatively large class of wave signatures.