Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network

Abstract

Precise real time estimates of earthquake magnitude and location are essential for early warning and rapid response. While recently multiple deep learning approaches for fast assessment of earthquakes have been proposed, they usually rely on either seismic records from a single station or from a fixed set of seismic stations. Here we introduce a new model for real-time magnitude and location estimation using the attention based transformer networks. Our approach incorporates waveforms from a dynamically varying set of stations and outperforms deep learning baselines in both magnitude and location estimation performance. Furthermore, it outperforms a classical magnitude estimation algorithm considerably and shows promising performance in comparison to a classical localization algorithm. In this work, we furthermore conduct a comprehensive study of the requirements on training data, the training procedures and the typical failure modes using three diverse and large scale data sets. Our analysis gives several key insights. First, we can precisely pinpoint the effect of large training data; for example, a four times larger training set reduces the required time for real time assessment by a factor of four. Second, the basic model systematically underestimates large magnitude events. This issue can be mitigated by incorporating events from other regions into the training through transfer learning. Third, location estimation is highly precise in areas with sufficient training data, but is strongly degraded for events outside the training distribution. Our analysis suggests that these characteristics are not only present for our model, but for most deep learning models for fast assessment published so far. They result from the black box modeling and their mitigation will likely require imposing physics derived constraints on the neural network.

arXiv comment24 pages main text, 20 pages appendix. This article has been accepted for publication in Geophysical Journal International Published by Oxford University Press on behalf of the Royal Astronomical Society

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• An Overview of Multi-Task Learning in Deep Neural Networks
• On Calibration of Modern Neural Networks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• A Machine-Learning Approach for Earthquake Magnitude Estimation
• Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
• Rapid Prediction of Earthquake Ground Shaking Intensity Using Raw Waveform Data and a Convolutional Neural Network
• The transformer earthquake alerting model: A new versatile approach to earthquake early warning

Cited by in corpus (9)

• Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data
• Earthquake Phase Association with Graph Neural Networks
• CREIME: A Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation
• Earthquake Location and Magnitude Estimation with Graph Neural Networks
• Generalized Neural Networks for Real-Time Earthquake Early Warning
• A probabilistic view on rupture predictability: all earthquakes evolve similarly
• Full-waveform earthquake source inversion using simulation-based inference
• RNN-DAS: A New Deep Learning Approach for Detection and Real-Time Monitoring of Volcano-Tectonic Events Using Distributed Acoustic Sensing
• Real-Time Earthquake Magnitude Classification from Initial P-Waves: Models, Dataset, and Comparative Analysis for South Asia