Toward path-invariant embeddings for local distance source characterization

TL;DR

This paper introduces a seismic source characterization method using a Barlow Twins-inspired model to achieve path-invariant embeddings, improving event discrimination and uncertainty estimation.

Contribution

It adapts the Barlow Twins architecture for seismic data, demonstrating improved discrimination and uncertainty estimation in source characterization tasks.

Findings

10-12% improvement in event discrimination

More reliable predictive uncertainty estimates

Dataset scale influences performance more than architecture

Abstract

This work builds on recent advances in foundation models in the language and image domains to explore similar approaches for seismic source characterization. We rely on an architecture called Barlow Twins, borrowed from an understanding of the human visual cortical system and originally envisioned for the image domain and adapt it for learning path invariance in seismic event time series. Our model improves the performance on event characterization tasks such as source discrimination across catalogs by 10-12% and provides more reliable predictive uncertainty estimates. We suggest that dataset scale and diversity more than architecture may determine aspects of the current ceiling on performance. We leverage decision trees, linear models, and visualization to understanding the dependencies in learned representations.