Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability
作者: Wei Quan, Denise Gorse
分类: cs.LG
发布日期: 2026-06-12
💡 一句话要点
结合地震统计特征与VQ-VAE提升地震性预测能力
🎯 匹配领域: 支柱四:生成式动作 (Generative Motion) 支柱八:物理动画 (Physics-based Animation)
关键词: 地震预测 统计特征 深度学习 VQ-VAE 局部化预测 特征工程 灾害预警
📋 核心要点
- 现有方法在地震预测中面临区域预测精度不足的挑战,尤其是局部事件的预测能力较弱。
- 本文提出通过局部化预测和结合VQ-VAE生成的二维地震图特征,来提升地震性预测的准确性。
- 实验结果表明,局部化预测的AUC值与整体区域预测相当,且新特征的引入进一步提升了模型性能。
📝 摘要(中文)
本文在之前研究的基础上,利用XGBoost和来自日本及智利的地震目录数据,证明了60个地震统计特征(SSF)在预测价值上显著优于tsfresh包中的428个通用时间序列特征。我们将研究扩展至两个关键方面:首先,从整体区域预测转向局部化预测,限制特征计算和预测区域在候选事件周围24公里的圆内,结果显示性能依然优秀。其次,将基于一维数据的SSF与通过训练VQ-VAE模型获得的二维地震图特征结合,发现新特征的引入显著提升了预测性能,并几乎完全取代了传统计算的$b$-值。
🔬 方法详解
问题定义:本文旨在解决地震预测中局部事件预测精度不足的问题。现有方法主要依赖于整体区域预测,难以捕捉局部地震活动的特征。
核心思路:通过局部化预测,限制特征计算和预测区域在候选事件周围24公里内,同时引入基于VQ-VAE模型生成的二维地震图特征,以增强预测能力。
技术框架:整体架构包括数据预处理、特征提取(包括SSF和VQ-VAE特征)、模型训练(使用深度学习自编码器)和性能评估四个主要模块。
关键创新:最重要的创新在于结合了传统的地震统计特征与新生成的空间特征,尤其是VQ-VAE模型生成的二维地震图特征,显著提升了预测性能。
关键设计:在模型设计中,采用了特定的损失函数以优化预测精度,并通过SHAP分析确定了新特征的重要性,确保模型的可解释性和有效性。
🖼️ 关键图片
📊 实验亮点
实验结果显示,局部化预测的AUC值与之前整体区域研究相当,最高可达0.85。同时,VQ-VAE生成的特征在SHAP分析中排名最高,显著提升了模型性能,几乎完全取代了传统的$b$-值计算,展示了新特征的有效性。
🎯 应用场景
该研究的潜在应用领域包括地震监测、灾害预警和城市规划等。通过提高地震预测的准确性,可以有效降低地震带来的损失,增强公众安全意识,并为相关政策制定提供科学依据。未来,随着数据和模型的进一步优化,该方法有望在全球范围内推广应用。
📄 摘要(原文)
In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package. We here extend this previous work in two key ways, focusing on data from Japan as a large dataset is necessary in order to allow for the training of a deep learning (autoencoder) model. First, we move from whole-region prediction (considering, for each candidate event, the likelihood of an event M $\geq$ 5.0 anywhere in the region in the next 15 days) to localised predictions in which both the region of feature computation and the region of prediction are restricted to a circle of radius 24 km around the candidate event, and we show that performance remains excellent, similar to our previous whole-region study for the same area. Second, we here couple this proven set of SSFs, based on one-dimensional (catalogue) data, with a novel feature based on two-dimensional seismic maps, obtained by training a VQ-VAE model to reproduce such maps as output and identifying a measure of its error in doing so with a localised build-up of crustal stress. We show that while localised prediction based on SSFs can be effective alone, with test AUC values as high as those obtained in the case of Japan in our previous whole-region study, the inclusion of the new natively-spatial VQ-VAE-derived feature, top-ranked by SHAP analysis, can enhance performance and additionally appears to near-wholly replace the traditionally-computed $b$-value in terms of feature usage.