Enhancing the reliability of machine learning for gravitational wave parameter estimation with attention-based models

TL;DR

This paper presents attention-based models using Vision Transformers to improve the reliability of gravitational wave parameter estimation, providing interpretability and glitch impact analysis.

Contribution

Introduces attention map techniques in machine learning models for gravitational wave analysis to enhance interpretability and reliability.

Findings

Models focus on physically meaningful features

Attention maps reveal bias from glitches

Potential to distinguish reliable from unreliable estimates

Abstract

We introduce a technique to enhance the reliability of gravitational wave parameter estimation results produced by machine learning. We develop two independent machine learning models based on the Vision Transformer to estimate effective spin and chirp mass from spectrograms of gravitational wave signals from binary black hole mergers. To enhance the reliability of these models, we utilize attention maps to visualize the areas our models focus on when making predictions. This approach enables demonstrating that both models perform parameter estimation based on physically meaningful information. Furthermore, by leveraging these attention maps, we demonstrate a method to quantify the impact of glitches on parameter estimation. We show that as the models focus more on glitches, the parameter estimation results become more strongly biased. This suggests that attention maps could potentially be used to distinguish between cases where the results produced by the machine learning model are reliable and cases where they are not.