Search

Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real‐time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR‐GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine‐Learning Assessed Rapid Geodetic Earthquake model (M‐LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M‐LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real‐time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes. Plain Language Summary: Earthquake Early Warning (EEW) systems can evaluate the shaking impact soon after an earthquake occurs and send alerts to areas where strong shaking has not yet arrived. However, predicting shaking intensity for large earthquakes face challenges such as magnitude underestimation and rupture complexity, leading to inaccurate prediction. In our previous study, we proposed a machine learning model, called M‐LARGE, which can predict the magnitude of large earthquakes accurately and rapidly by utilizing surface deformation patterns recorded by HR‐GNSS. Here, we expand the M‐LARGE model to also predict the source location and fault size. This capability allows us to construct a fault, enabling forecasts of strong shaking 35–40 s before the shaking onset, longer than other similar methods. Our approach has the potential to improve the accuracy of EEW and reduce the impact of seismic hazards. Because the model is fully trained with simulated data, the successful prediction of real Chilean earthquakes indicates that our assumptions in simulating large earthquakes are sufficiently consistent with the rupture dynamics of actual events. Key Points: We train a ML model that utilizes HR‐GNSS data to predict source parameters and shaking intensity for large (M7.0+) earthquakesThe model yields a long median warning time of 35–40 s for MMI 4+ when tested on synthetic and real HR‐GNSS recordsOur model fills a critical gap in current EEW systems for large events and can operate in parallel with other methods for better warnings [ABSTRACT FROM AUTHOR]

Low‐frequency earthquakes are a seismic manifestation of slow fault slip. Their emergent onsets, low amplitudes, and unique frequency characteristics make these events difficult to detect in continuous seismic data. Here, we train a convolutional neural network to detect low‐frequency earthquakes near Parkfield, CA using the catalog of Shelly (2017), https://doi.org/10.1002/2017jb014047 as training data. We explore how varying model size and targets influence the performance of the resulting network. Our preferred network has a peak accuracy of 85% and can reliably pick low‐frequency earthquake (LFE) S‐wave arrival times on single station records. We demonstrate the abilities of the network using data from permanent and temporary stations near Parkfield, and show that it detects new LFEs that are not part of the Shelly (2017), https://doi.org/10.1002/2017jb014047 catalog. Overall, machine‐learning approaches show great promise for identifying additional low‐frequency earthquake sources. The technique is fast, generalizable, and does not require sources to repeat. Plain Language Summary: Low‐frequency earthquakes are an enigmatic seismic signal that often accompany slow earthquakes in many tectonic environments. They are weak seismic signals, and, as such, are challenging to find using routine approaches to earthquake detection. In this study, we use machine learning, a type of artificial intelligence, to discover low‐frequency earthquakes that are hidden in continuous seismic data. This approach is computationally efficient and is capable of identifying both known and new earthquake sources. This new approach to low‐frequency earthquake detection has the potential to discover many more earthquakes than traditional approaches which may help scientists better understand slow earthquakes. Key Points: We trained different variations of a U‐shaped convolutional neural network to detect low‐frequency earthquakes on the San Andreas faultThe model identifies known and new low‐frequency earthquakes in continuous seismic data, including data from stations not used in trainingThe preferred model has a peak accuracy of 85%, does not require repeating sources, and is a fast way to identify low‐frequency earthquakes [ABSTRACT FROM AUTHOR]

• We invert GPS, strong motion, and tide gauge records to determine the slip distribution of the 2018 May 4 Hawai'i event. • This earthquake likely ruptured through an adjacent region that regularly hosts slow slip. • Effective stress levels can control the extent to which coseismic slip can penetrate into regions hosting slow slip. Earthquakes and slow slip are different faulting processes that release accumulated stress on different time scales. Despite nearly two decades of study, it is still unclear whether the same section of fault is capable of hosting both slow, aseismic and fast, seismic slip. Here, we jointly invert GPS, strong motion records, and empirically corrected tsunami waveforms for the 2018 M7.1 Hawai'i earthquake. Our inversion results suggest the earthquake had a slow rupture speed of 1.2 km/s with a maximum slip of ∼3 m South-East of the hypocenter extending to the South-West through an area known to regularly host slow slip events. After exploring how the choice of fault geometry and regularization parameters affect the slip distributions of the earthquake and slow slip events we find strong evidence of overlap between the two. Additionally, we perform numerical modeling to simulate fast and slow slip behavior. Due to the homogeneity of the Hawaiian décollement differences in effective stress are likely an important factor that causes the diversity of slip. We find that an earthquake can completely penetrate into the slow slip zone provided the effective stress differences between fast and slow slip zones is large enough to facilitate this. Our results reinforce the idea that an individual section of fault is capable of hosting a variety of distinct slip behaviors. This is important for estimating earthquake rupture extent and for better ground motion and tsunami hazard assessment. [ABSTRACT FROM AUTHOR]