用自监督学习训练地震波形基础模型，可高效完成震源检测等任务。
SeisLM: a Foundation Model for Seismic Waveforms
- 基于对比学习预训练，从无标注地震数据中学习通用波形模式。
- 微调后在事件检测、震相拾取等任务上表现优异，提升准确率。
- 适合地震监测、地质研究者使用，开源代码便于复现与应用。
我们提出地震语言模型（SeisLM），一种用于分析地震波形的基础模型，地震波形是地球振动产生的信号，如地震引发的波动。SeisLM 在大规模开源地震数据集上通过自监督对比损失进行预训练，类似于自然语言处理中的 BERT 模型。该方法使模型无需依赖特定下游任务即可从无标签数据中学习地震波形的通用特征。微调后，SeisLM 在地震事件检测、震相拾取、初至时间回归以及前震-余震分类等任务中表现出色。相关代码已公开于 https://github.com/liutianlin0121/seisLM。
原文摘要 · Abstract (English)
We introduce the Seismic Language Model (SeisLM), a foundational model designed to analyze seismic waveforms -- signals generated by Earth's vibrations such as the ones originating from earthquakes. SeisLM is pretrained on a large collection of open-source seismic datasets using a self-supervised contrastive loss, akin to BERT in language modeling. This approach allows the model to learn general seismic waveform patterns from unlabeled data without being tied to specific downstream tasks. When fine-tuned, SeisLM excels in seismological tasks like event detection, phase-picking, onset time regression, and foreshock-aftershock classification. The code has been made publicly available on https://github.com/liutianlin0121/seisLM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。