WaveCastNet: Rapid Wavefield Forecasting for Earthquake Early Warning via Deep Sequence to Sequence Learning

TL;DR

WaveCastNet is a deep learning model that rapidly forecasts earthquake wavefields in real time, improving early warning systems by modeling complex seismic patterns efficiently and accurately without relying on traditional estimation methods.

Contribution

It introduces WaveCastNet, a novel deep sequence-to-sequence model with shared weights, enabling fast, accurate, and generalizable earthquake wavefield predictions without traditional parameter estimation.

Findings

Accurately predicts ground motion intensity and timing in real time.

Demonstrates zero-shot generalization to real earthquake data.

Requires fewer parameters than transformer-based models.

Abstract

We propose a new deep learning model, WaveCastNet, to forecast high-dimensional wavefields. WaveCastNet integrates a convolutional long expressive memory architecture into a sequence-to-sequence forecasting framework, enabling it to model long-term dependencies and multiscale patterns in both space and time. By sharing weights across spatial and temporal dimensions, WaveCastNet requires significantly fewer parameters than more resource-intensive models such as transformers, resulting in faster inference times. Crucially, WaveCastNet also generalizes better than transformers to rare and critical seismic scenarios, such as high-magnitude earthquakes. Here, we show the ability of the model to predict the intensity and timing of destructive ground motions in real time, using simulated data from the San Francisco Bay Area. Furthermore, we demonstrate its zero-shot capabilities by evaluating WaveCastNet on real earthquake data. Our approach does not require estimating earthquake magnitudes and epicenters, steps that are prone to error in conventional methods, nor does it rely on empirical ground-motion models, which often fail to capture strongly heterogeneous wave propagation effects.