Physics-informed deep learning links geodetic data and fault friction

TL;DR

This paper introduces a physics-informed neural network approach to link geodetic data with fault friction heterogeneity, enabling more accurate fault slip modeling and forecasting of slow slip events.

Contribution

It develops a novel PINN-based method to estimate spatially variable fault friction from geodetic observations, integrating fault mechanics into the inversion process.

Findings

Successfully modeled the 2010 Bungo SSE and its propagation.

Reproduced observed surface displacements with high accuracy.

Predicted future fault slip evolution across multiple SSE cycles.

Abstract

Fault slip modeling, based on laboratory-derived friction laws, has significantly enhanced our understanding of fault mechanics. Agreement between model predictions and observations supports the hypothesis that observed slip diversity, including fast earthquakes and slow transient slips (Slow Slip Events; SSEs), originates from frictional heterogeneity. However, quantitative assessments of frictional heterogeneity from geodetic observations while fully incorporating fault mechanics are lacking due to the difficulties of high-dimensional optimization. In this study, we aim to address this gap using Physics-Informed Neural Networks (PINNs) to link frictional heterogeneity with geodetic observations. PINNs employ a neural network to represent the spatially variable frictional properties, making their estimation feasible. Targeting the 2010 Bungo SSE in southwest Japan, our estimation reveals heterogeneous friction coinciding with localized SSE nucleation in southwest Shikoku, and subsequent westward propagation. The calculated fault slip of SSE successfully reproduces the spatio-temporal pattern of observed surface displacements. This PINN-based inversion provides a mechanically consistent fault slip model validated through quantitative comparison with observations. Furthermore, we predict the future fault slip evolution, demonstrating the importance of assimilating observations spanning multiple SSE cycles. Our results demonstrate the potential of PINN for advancing understanding of fault mechanics and enabling physics-based fault slip forecasting.