Abstract
Precisely measuring seismic arrival times is a labor-intensive task but is critical for both earthquake monitoring and subsurface imaging. Recently published deep learning models have demonstrated superior performance compared to traditional automatic approaches for picking arrival times. Although existing deep learning models have shown promising results, further advancements are necessary as their performance is not yet satisfactory especially when applied to new regions and station networks. Increasing model size has led to improved performance in other machine learning applications. We aimed to investigate whether enlarging deep learning models can increase performance on accepted benchmarks. We trained three models of varying sizes, small (1X), medium (4X), and large (16X), using globally distributed local and regional earthquake signals and background noise waveforms from a benchmark dataset, Stanford Earthquake Dataset. Our results indicate that the largest model (PickerXL) outperforms both the smaller models and Seisbench implementation of the PhaseNet model, which has the same number of parameters as our small model. The PickerXL model’s enhanced capacity to extract complex patterns from seismograms contributes to its superior arrival picking abilities compared to the smaller model.
| Original language | English |
|---|---|
| Pages (from-to) | 2394-2404 |
| Number of pages | 11 |
| Journal | Seismological Research Letters |
| Volume | 96 |
| Issue number | 4 |
| DOIs | |
| State | Published - Jul 2025 |
Funding
The authors would like to acknowledge the U.S. Department of Energy, National Nuclear Security Administration’s Office of Defense Nuclear Nonproliferation Research and Development for supporting this work. This work has been authored in part by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the U.S. Department of Energy (DOE). The U.S. Government and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this article, or allow others to do so, for U.S. Government purposes. The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S. Government. This research used resources of the Compute and Data Environment for Science (CADES) and Oak Ridge Leadership Computing Facility at ORNL, which is supported by the DOE Office of Science under Contract Number DE-AC05-00OR22725. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan can be accessible http://energy.gov/downloads/doe-publicaccess-plan there are no conflicts of interest recorded. The authors thank Jason Hite for his contributions to an early version of the source code. The authors acknowledge helpful suggestions from Erin Cunningham. The authors thank Editor-in-Chief Allison Bent, an anonymous Associate Editor, Jannes Münchmeyer, and an anonymous reviewer for their constructive comments. worldwide license to publish or reproduce the published form of this article, or allow others to do so, for U.S. Government purposes. The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S. Government. This research used resources of the Compute and Data Environment for Science (CADES) and Oak Ridge Leadership Computing Facility at ORNL, which is supported by the DOE Office of Science under Contract Number DE-AC05-00OR22725. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan can be accessible http://energy.gov/downloads/doe-public-access-plan (last accessed July 2024). The authors acknowledge that there are no conflicts of interest recorded. The authors thank Jason Hite for his contributions to an early version of the source code. The authors acknowledge helpful suggestions from Erin supporting this work. This work has been authored in part by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the U.S. Department of Energy (DOE). The U.S. Government and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable,