Open Access

The rapid characterisation of earthquake parameters such as its magnitude is at the heart of Earthquake Early Warning (EEW). In traditional EEW methods the robustness in the estimation of earthquake parameters have been observed to increase with the length of input data. Since time is a crucial factor in EEW applications, in this paper we propose a deep learning based magnitude classifier and, further we investigate the effect of using five different durations of seismic waveform data after first P wave arrival of length 1s, 3s, 10s, 20s and 30s. This is accomplished by testing the performance of the proposed model that combines Convolution and Bidirectional Long-Short Term Memory units to classify waveforms based on their magnitude into three classes "noise", "low magnitude events" and "high magnitude events". Herein, any earthquake signal with magnitude equal to or above 5.0 is labelled as high magnitude. We show that the variation in the results produced by changing the length of the data, is no more than the inherent randomness in the trained models, due to their initialisation.

Highlights • We use 1D-ResNet-based architecture for seismic phase detection. • We report a 4% improvement in earthquake detection as compared to previous methods. • We show the model generalization ability on the STanford EArthquake Dataset (STEAD). • We show its robustness by masking phases of low magnitude with various noise levels. Abstract Reliable seismic phase identification is often challenging especially in the circumstances of low-magnitude events or poor signal-to-noise ratio. With improved seismometers and better global coverage, a sharp increase in the volume of recorded seismic data has been achieved. This makes handling seismic data rather daunting by using traditional approaches and therefore fuels the need for more robust and reliable methods. In this study, we develop 1D deep Residual Neural Network (ResNet), for tackling the problem of seismic signal detection and phase identification. This method is trained and tested on the dataset recorded by the Southern California Seismic Network. Results demonstrate that the proposed method can achieve robust performance for the detection of seismic signals and the identification of seismic phases. Compared to previously proposed deep learning methods, the introduced framework achieves around 4% improvement in earthquake detection and a slightly better performance in seismic phase identification on the dataset recorded by Southern California Earthquake Data Center. The model generalizability is also tested further on the STanford EArthquake Dataset. In addition, the experimental result on the same subset of the STanford EArthquake Dataset, when masked by different noise levels, demonstrates the model’s robustness in identifying the seismic phases of small magnitude.

Earthquake detection and seismic phase picking not only play a crucial role in travel time estimation of body waves(P and S waves) but also in the localisation of the epicenter of the corresponding event. Generally, manual phase picking is a trustworthy and the optimum method to determine the phase arrival time, however, its capacity is restricted by available resources and time. Moreover, noisy seismic data renders an additional critical challenge for fast and accurate phase picking. In this study, a deep learning based model, EPick, is proposed which benefits both from U shaped neural network (also called UNet)and attention mechanism, as a strong alternative for seismic event detection and phase picking. On one hand, the utilization of UNet structure enables addressing different levels of deep features. On the other hand, attention mechanism promotes the decoder in the UNet structure to focus on the efficient exploitation of the low-resolution features learned from the encoder part to achieve precise phase picking. Extensive experimental results demonstrate that EPick achieves better performance over the benchmark method, and show the models robustness when tested on a different seismic dataset.

Abstract The detection and rapid characterization of earthquake parameters such as magnitude are important in real-time seismological applications such as Earthquake Monitoring and Earthquake Early Warning (EEW). Traditional methods, aside from requiring extensive human involvement can be sensitive to signal-to-noise ratio leading to false/missed alarms depending on the threshold. We here propose a multitasking deep learning model—the Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation (CREIME) that: (a) detects the earthquake signal from background seismic noise, (b) determines the first P wave arrival time, and (c) estimates the magnitude using the raw three-component waveforms from a single station as model input. Considering, that speed is essential in EEW, we use up to 2 s of P wave information which, to the best of our knowledge, is a significantly smaller data window compared to the previous studies. To examine the robustness of CREIME, we test it on two independent data sets and find that it achieves an average accuracy of 98% for event versus noise discrimination and can estimate first P-arrival time and local magnitude with average root mean squared errors of 0.13 s and 0.65 units, respectively. We compare CREIME with traditional methods such as short-term-average/long-term-average (STA/LTA) and show that CREIME has superior performance, for example, the accuracy for signal and noise discrimination is higher by 4.5% and 11.5%, respectively, for the two data sets. We also compare the architecture of CREIME with the architectures of other baseline models, trained on the same data, and show that CREIME outperforms the baseline models. Key Points * We use a novel sequence-to-sequence mapping to train a deep learning model to detect an earthquake, pick the P-wave arrival and estimate its magnitude * The proposed model can perform reasonably well with 5 s windows containing only up to 2 s of P wave data * We show that our model can outperform traditional methods like short-term-average/long-term-average (STA/LTA) and the existing deep learning models Plain Language Summary The detection of earthquakes and rapid determination of parameters such as magnitude is crucial in Earthquake Monitoring and Earthquake Early Warning (EEW). Existing methods used to make such estimations are empirical and require expert analysts to define involved parameters, which is quite challenging. They are also sensitive to noise, which could lead to erroneous results. In this paper, we propose the Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation (CREIME) which is capable to detect an earthquake within 2 s of the first P wave arrival and provides a first estimate for its magnitude. We test the model on two independent data sets to demonstrate its generalizability. CREIME successfully discriminates between seismic events and noise with an average accuracy of 98% and can estimate first P-arrival time and local magnitude with average root mean squared errors of 0.13 s and 0.65 units, respectively. We also show that CREIME can perform better than traditional methods like STA/LTA and previously published deep learning architectures in the context of rapid characterization.

We revise the high pressure, high temperature phase diagram of CaCO3 using Raman spectroscopy in conjunction with laser heated diamond anvil cell experiments. We confirm numerous aspects of earlier studies, including a recent X-ray diffraction study about the stability field of CaCO3-VII. Our Raman results show that CaCO3-VII is stable in the lower mantle at a depth of 690–1010 km. Our DFT calculations show that the phase transition from aragonite to CaCO3-VII at ≈25 GPa and from CaCO3-VII to post-aragonite at ≈40 GPa are accompanied by density changes of 2% and 3.5%, respectively. Shear sound velocities change by 9% and −12% across the transitions, respectively. Hence, a sufficient amount, at least locally, of CaCO3 in the Earth’s mantle can be detectable by an increase of the shear velocity at 690 km and a decrease of the shear velocity at 1010 km depths.