Machine learning opportunities to conduct high-fidelity earthquake simulations in multi-scale heterogeneous geology

Abstract

The 2019 Le Teil earthquake is an illustrative example of a moderate (MW 4.9) yet damaging event, occurring at shallow depth (≈1 km) in a region with little to no geophysical data available. Therefore, using a high-fidelity wave propagation code, we performed numerical simulations of the Le Teil earthquake in a highly uncertain framework, investigating several seismic sources and geological set-ups. With respect to the former aspect, a point-source model and an extended kinematic fault model were compared. The latter aspect was investigated by comparing a 1D-layered to a 3D geological model. Those models were enhanced with random fluctuations, in order to obtain three alternative non-stationary random geological fields. The synthetic waveforms obtained from regional geophysical models were globally coherent with the recorded ones. The extended fault source model seemed more realistic than the point-source model. In addition, some geological random fields improved the synthetics’ agreement with the recordings. However, the three random field samplings led to a high variability in induced ground motion responses. Given the computational burden of high-fidelity simulations, we used two dimensionality reduction methods, namely the Principal Component Analysis (PCA) and a deep neural network (3D UNet), to investigate this variability. The methods were applied to a database of 40,000 3D geological random fields. Both the PCA and the 3D UNet condensed the variability of the 3D geological fields into a few components. These were sufficient to reconstruct the original fields with great accuracy. More importantly, the seismic response arising from the propagation throughout the reconstructed fields was in excellent agreement with the response of the original geological fields in more than 75% of the dataset. By building a structured ensemble of complex geological fields from their reduced representation, it may become possible to find a relationship between the reduced representation and the generated ground motion. Thus, our study proves the interest of dimensionality reduction to perform uncertainty analyses in complex geological media.

Synthetic ground motions in heterogeneous geologies: the HEMEW-3D dataset for scientific machine learning

“…The geological database was used to study dimensionality reduction methods such as the PCA and a 3D autoencoder (Lehmann et al, 2022). It was shown that at least 1000 PCA components should be preserved to reconstruct a geological model whose heterogeneities are not too smoothed.…”

“…Since extensive geophysical investigations are needed to obtain 3D geological models, they are rare, and when existing, they are still limited by epistemic uncertainties. Therefore, when trying to reproduce an earthquake with physics-based numerical simulations, uncertainties can be represented by random heterogeneities added to the reference model to introduce variability (Chaljub et al, 2021;Lehmann et al, 2022).…”

Fourier Neural Operator Surrogate Model to Predict 3d Seismic Waves Propagation

“…Our geological database represents 3D S-wave velocity fields in a 9.6 km × 9.6 km × 9.6 km cube. This database is built from layered random fields to provide a general decomposition basis to any 3D material [30]. Each geology contains a homogeneous bottom layer with constant velocity V S =4500 m/s.…”