用于改进的自动P相到达检测的地震记录的高阶统计量（RHOS）值中的比率

P-wave arrival picking and first-motion polarity determination with deep learning

Determining earthquake hypocenters and focal mechanisms requires precisely measured P-wave arrival times and first-motion polarities. Automated algorithms for estimating these quantities have been less accurate than estimates by human experts, which is problematic for processing large data volumes. Here, we train convolutional neural networks to measure both quantities, which learn directly from seismograms without the need for feature extraction. The networks are trained on 18.2 million manually picked seismograms for the southern California region. Through cross-validation on 1.2 million ind…

Automatic picking of P and S arrivals using a minimal uncertainty wavelet approach

The so-called "minimum uncertainty" or mu-wavelet approach has been shown to be very effective. Prior work has shown that using special algorithms based on a mu-wavelet decomposition of a seismic signal allows for arrival detection of various waves on a single-component seismogram with good precision. However, the question of interpretation of the type of wave arriving has not been addressed. The problem lies in the fact that the algorithm detects more than two arrivals even on seismograms with little noise, the peaks corresponding to P and S wave arrivals on the indicator function are not alw…

Sequencing seismograms: A panoptic view of scattering in the core-mantle boundary region

Scattering of seismic waves can reveal subsurface structures but usually in a piecemeal way focused on specific target areas. We used a manifold learning algorithm called "the Sequencer" to simultaneously analyze thousands of seismograms of waves diffracting along the core-mantle boundary and obtain a panoptic view of scattering across the Pacific region. In nearly half of the diffracting waveforms, we detected seismic waves scattered by three-dimensional structures near the core-mantle boundary. The prevalence of these scattered arrivals shows that the region hosts pervasive lateral heterogen…

用于多台站地震震相拾取的相位神经算子

Phase Neural Operator for Multi-Station Picking of Seismic Arrivals

本文提出基于神经算子的全台网震相拾取算法PhaseNO，利用时空上下文信息对任意台网几何结构同时拾取震相，在检测地震数量、拾取震相数量和测量精度上均优于现有基线方法。

基于Transformer架构的三分量地震图数据驱动预测

Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures

提出基于Transformer的自回归模型SeismoGPT，通过物理约束的延续问题框架直接预测三分量地震波形，在合成数据上实现中位数归一化互相关>0.93，证明了Transformer序列模型可学习地震波场的稳定动力学延续。

Applying deep learning to teleseismic phase detection and picking: PcP and PKiKP cases

The availability of a tremendous amount of seismic data demands seismological researchers to analyze seismic phases efficiently. Recently, deep learning algorithms exhibit a powerful capability of detecting and picking on P- and S-wave phases. However, it is still a challenge to process teleseismic phases fast and accurately. In this study, we detect and pick the PcP and PKiKP phases from a Hinet dataset with 7386 seismograms by applying a deep-learning-based scheme. The scheme consists of three steps: first, we prepare latent phase data, which is truncated from the whole seismogram with the t…