We have successfully applied full‐3‐D tomography (F3DT) based on a combination of the scattering‐integral method (SI‐F3DT) and the adjoint‐wavefield method (AW‐F3DT) to iteratively improve a 3‐D starting model, the Southern California Earthquake Center (SCEC) Community Velocity Model version 4.0 (CVM‐S4). In F3DT, the sensitivity (Fréchet) kernels are computed using numerical solutions of the 3‐D elastodynamic equation and the nonlinearity of the structural inversion problem is accounted for through an iterative tomographic navigation process. More than half‐a‐million misfit measurements made on about 38,000 earthquake seismograms and 12,000 ambient‐noise correlagrams have been assimilated into our inversion. After 26 F3DT iterations, synthetic seismograms computed using our latest model, CVM‐S4.26, show substantially better fit to observed seismograms at frequencies below 0.2 Hz than those computed using our 3‐D starting model CVM‐S4 and the other SCEC CVM, CVM‐H11.9, which was improved through 16 iterations of AW‐F3DT. CVM‐S4.26 has revealed strong crustal heterogeneities throughout Southern California, some of which are completely missing in CVM‐S4 and CVM‐H11.9 but exist in models obtained from previous crustal‐scale 2‐D active‐source refraction tomography models. At shallow depths, our model shows strong correlation with sedimentary basins and reveals velocity contrasts across major mapped strike‐slip and dip‐slip faults. At middle to lower crustal depths, structural features in our model may provide new insights into regional tectonics. When combined with physics‐based seismic hazard analysis tools, we expect our model to provide more accurate estimates of seismic hazards in Southern California.

Seismograms are convolution results between seismic sources and the media that seismic waves propagate through, and, therefore, the primary observations for studying seismic source parameters and the Earth interior. The routine earthquake location and travel‐time tomography rely on accurate seismic phase picks (e.g., P and S arrivals). As data increase, reliable automated seismic phase‐picking methods are needed to analyze data and provide timely earthquake information. However, most traditional autopickers suffer from low signal‐to‐noise ratio and usually require additional efforts to tune hyperparameters for each case. In this study, we proposed a deep‐learning approach that adapted soft attention gates (AGs) and recurrent‐residual convolution units (RRCUs) into the backbone U‐Net for seismic phase picking. The attention mechanism was implemented to suppress responses from waveforms irrelevant to seismic phases, and the cooperating RRCUs further enhanced temporal connections of seismograms at multiple scales. We used numerous earthquake recordings in Taiwan with diverse focal mechanisms, wide depth, and magnitude distributions, to train and test our model. Setting the picking errors within 0.1 s and predicted probability over 0.5, the AG with recurrent‐residual convolution unit (ARRU) phase picker achieved the F1 score of 98.62% for P arrivals and 95.16% for S arrivals, and picking rates were 96.72% for P waves and 90.07% for S waves. The ARRU phase picker also shown a great generalization capability, when handling unseen data. When applied the model trained with Taiwan data to the southern California data, the ARRU phase picker shown no cognitive downgrade. Comparing with manual picks, the arrival times determined by the ARRU phase picker shown a higher consistency, which had been evaluated by a set of repeating earthquakes. The arrival picks with less human error could benefit studies, such as earthquake location and seismic tomography.

Summary. We have developed an automated procedure to resolve fault-plane ambiguity for small to medium-sized earthquakes (2.5 ≤ML≤ 5) using synthetic Green's t

Accurate and (near) real‐time earthquake monitoring provides the spatial and temporal behaviors of earthquakes for understanding the nature of earthquakes, and also helps in regional seismic hazard assessments and mitigations. Because of the increase in both the quality and quantity of seismic data, an automated earthquake monitoring system is needed. Most of the traditional methods for detecting earthquake signals and picking phases are based on analyses of features in recordings of an individual earthquake and/or their differences from background noises. When seismicity is high, the seismograms are complicated, and, therefore, traditional analysis methods often fail. With the development of machine learning algorithms, earthquake signal detection and seismic phase picking can be more accurate using the features obtained from a large amount of earthquake recordings. We have developed an attention recurrent residual U‐Net algorithm, and used data augmentation techniques to improve the accuracy of earthquake detection and seismic phase picking on complex seismograms that record multiple earthquakes. The use of probability functions of P and S arrivals and potential P and S arrival pairs of earthquakes can increase the computational efficiency and accuracy of backprojection for earthquake monitoring in large areas. We applied our workflow to monitor the earthquake activity in southern California during the 2019 Ridgecrest sequence. The distribution of earthquakes determined by our method is consistent with that in the Southern California Earthquake Data Center (SCEDC) catalog. In addition, the number of earthquakes in our catalog is more than three times that of the SCEDC catalog. Our method identifies additional earthquakes that are close in origin times and/or locations, and are not included in the SCEDC catalog. Our algorithm avoids misidentification of seismic phases for earthquake location. In general, our algorithm can provide reliable earthquake monitoring on a large area, even during a high seismicity period.

Seismological data plays a crucial role in timely slope failure hazard assessments. However, identifying rockfall waveforms from seismic data poses challenges due to their high variability across different events and stations. To address this, we propose RockNet, a deep-learning-based multitask model capable of detecting both rockfall and earthquake events at both the single-station and local seismic network levels. RockNet consists of two sub-models: the single-station model, which computes waveform masks for earthquake and rockfall signals and performs earthquake P and S phase picking simultaneously on single-station seismograms, and the association model, which determines the occurrences of local seismic events by aggregating hidden feature maps from the trained single-station model across all stations. Since rockfall data is relatively scarce and may not be sufficient to train a deep learning model effectively, we augment the dataset with abundant non-rockfall data and add additional tasks to promote shared interpretability and robustness. RockNet is trained and tested on a local dataset collected from the Luhu tribe in Miaoli, Taiwan, achieving macro F1-scores of 0.983 and 0.990 for the single-station model and the association model, respectively. Furthermore, we evaluate RockNet on an independent dataset collected from the Super-Sauze unstable slope region in France, and it demonstrates good generalization performance in discriminating earthquake, rockfall, and noise with a macro F1-score of 0.927. This study highlights the potential of deep learning in leveraging diverse types of inputs for seismic signal detection even with limited training data.

Summary. In seismic waveform analysis and inversion, data functionals can be used to quantify the misfit between observed and model-predicted (synthetic) seism