Monitoring seismicity in the southern Sichuan Basin using a machine learning workflow

Monitoring seismicity in real time provides significant benefits for timely earthquake warning and analyses.In this study,we propose an automatic workflow based on machine learning(ML)to monitor seismicity in the southern Sichuan Basin of China.This workflow includes coherent event detection,phase picking,and earthquake location using three-component data from a seismic network.By combining Phase Net,we develop an ML-based earthquake location model called Phase Loc,to conduct real-time monitoring of the local seismicity.The approach allows us to use synthetic samples covering the entire study area to train Phase Loc,addressing the problems of insufficient data samples,imbalanced data distribution,and unreliable labels when training with observed data.We apply the trained model to observed data recorded in the southern Sichuan Basin,China,between September 2018 and March 2019.The results show that the average differences in latitude,longitude,and depth are 5.7 km,6.1 km,and 2 km,respectively,compared to the reference catalog.Phase Loc combines all available phase information to make fast and reliable predictions,even if only a few phases are detected and picked.The proposed workflow may help real-time seismic monitoring in other regions as well.

Dynamically triggered seismicity on a tectonic scale:A review

Earthquakes triggered by dynamic disturbances have been confirmed by numerous observations and experiments.In the past several decades,earthquake triggering has attracted increasing attention of scholars in relation to exploring the mechanism of earthquake triggering,earthquake prediction,and the desire to use the mechanism of earthquake triggering to reduce,prevent,or trigger earthquakes.Natural earthquakes and large‐scale explosions are the most common sources of dynamic disturbances that trigger earthquakes.In the past several decades,some models have been developed,including static,dynamic,quasi‐static,and other models.Some reviews have been published,but explosiontriggered seismicity was not included.In recent years,some new results on earthquake triggering have emerged.Therefore,this paper presents a new review to reflect the new results and include the content of explosion‐triggered earthquakes for the reference of scholars in this area.Instead of a complete review of the relevant literature,this paper primarily focuses on the main aspects of dynamic earthquake triggering on a tectonic scale and makes some suggestions on issues that need to be resolved in this area in the future.

The seismicity in the middle section of the Altyn Tagh Fault system revealed by a dense nodal seismic array

The left-lateral Altyn Tagh Fault(ATF) system is the northern boundary of the Qinghai-Xizang Plateau, separating the Tarim Basin and the Qaidam Basin. The middle section of ATF has not recorded any large earthquakes since1598 AD, so the potential seismic hazard is unclear. We develope an earthquake catalog using continuous waveform data recorded by the Tarim-Altyn-Qaidam dense nodal seismic array from September 17 to November23, 2021 in the middle section of ATF. With the machine learning-based picker, phase association, location, match and locate workflow, we detecte 233 earthquakes with M_L-1–3, far more than 6 earthquakes in the routine catalog. Combining with focal mechanism solutions and the local fault structure, we find that seismic events are clustered along the ATF with strike-slip focal mechanisms and on the southern secondary faults with thrusting focal mechanisms. This overall seismic activity in the middle section of the ATF might be due to the northeastward transpressional motion of the Qinghai-Xizang Plateau block at the western margin of the Qaidam Basin.

South China Sea Typhoon Hagibis enhanced Xinfengjiang Reservoir seismicity

There was an evident increase in the number of earthquakes in the Xinfengjiang Reservoir from June to July 2014 after the landing of Typhoon Hagibis.To understand the spatial and temporal evolution of this microseismicity,we built a high-precision earthquake catalog for 2014 and relocated 2275 events using recently developed methods for event picking and catalog construction.Seismicity occurred in the southeastern part of the reservoir,with the preferred fault plane orientation aligned along the Heyuan Fault.The total seismic energy peaked when the typhoon passed through the reservoir,and seismicity correlated with typhoon energy.In contrast,a limited seismic response was observed during the later Typhoon Rammasun.Combining data regarding the water level in the Xinfengjiang Reservoir and seismicity frequency changes in the Taiwan region during these two typhoon events,we suggest that typhoon activity may increase microseism energy by impacting fault stability around the Xinfengjiang Reservoir.Whether a fault can be activated also depends on how close the stress accumulation is to its failure point.

Implications for fault reactivation and seismicity induced by hydraulic fracturing

Evaluating the physical mechanisms that link hydraulic fracturing(HF) operations to induced earthquakes and the anticipated form of the resulting events is significant in informing subsurface fluid injection operations. Current understanding supports the overriding role of the effective stress magnitude in triggering earthquakes, while the impact of change rate of effective stress has not been systematically addressed. In this work, a modified critical stiffness was brought up to investigate the likelihood, impact,and mitigation of induced seismicity during and after hydraulic fracturing by developing a poroelastic model based on rate-and-state fraction law and linear stability analysis. In the new criterion, the change rate of effective stress was considered a key variable to explore the evolution of this criterion and hence the likelihood of instability slip of fault. A coupled fluid flow-deformation model was used to represent the entire hydraulic fracturing process in COMSOL Multiphysics. The possibility of triggering an earthquake throughout the entire hydraulic fracturing process, from fracturing to cessation, was investigated considering different fault locations, orientations, and positions along the fault. The competition between the effects of the magnitude and change rate of effective stress was notable at each fracturing stage. The effective stress magnitude is a significant controlling factor during fracturing events, with the change rate dominating when fracturing is suddenly started or stopped. Instability dominates when the magnitude of the effective stress increases(constant injection at each fracturing stage) and the change rate of effective stress decreases(the injection process is suddenly stopped). Fracturing with a high injection rate, a fault adjacent to the hydraulic fracturing location and the position of the junction between the reservoir and fault are important to reduce the Coulomb failure stress(CFS) and enhance the critical stiffness as the significant disturbance of stresses at these positions in the coupled process. Therefore,notable attention should be given to the injection rate during fracturing, fault position, and position along faults as important considerations to help reduce the potential for induced seismicity. Our model was verified and confirmed using the case of the Longmaxi Formation in the Sichuan Basin, China, in which the reported microseismic data were correlated with high critical stiffness values. This work supplies new thoughts of the seismic risk associated with HF engineering.

Seismicity patterns before the 2021 Fin (Iran) doublet earthquakes using the region-time-length and time-to-failure methods

Knowledge regarding earthquake hazards and seismicity is crucial for crisis management, and the occurrence of foreshocks, seismic activity patterns, and spatiotemporal variations in seismic activity have been studied. Furthermore, the estimation of the region-time-length (RTL) parameter has been proposed to detect seismic quiescence before the occurrence of a large earthquake. In addition, the time-to-failure method has been used to estimate the time occurrence of large earthquakes. Hence, in this study, to gain deeper insight into seismic activity in the southern Zagros region, we utilized the RTL algorithm to identify the quiescence and activation phases leading to the Fin doublet earthquakes. Temporal variations in the RTL parameter showed two significant anomalies. One corresponded to the occurrence time of the first earthquake (2017-12-12);the other anomaly was associated with the occurrence time of the second event (2021-11-14). Based on a negative value of the RTL parameter observed in the vicinity of the Fin epicenters (2021), seismic quiescence (a decrease in seismicity compared to the preceding background rate) was identified. The spatial distribution of the RTL prognostic parameters confirms the appearance of seismic quiescence surrounding the epicenter of the Fin doublet earthquakes (2021). The time-to-failure method was designed using precursory events that describe the acceleration of the seismic energy release before the mainshock. Using the time-to-failure method for the earthquake catalog, it was possible to estimate both the magnitude and time of failure of the Fin doublet. Hence, the time-tofailure technique can be a useful supplementary method to the RTL algorithm for determining the characteristics of impending earthquakes.

Assessing current faulting behaviors and seismic risk of the Anninghe-Zemuhe fault zone from seismicity parameters

Using the data of regional seismic network, this paper analyzes the current faulting behaviors of different segments of the Anninghe-Zemuhe fault zone, western Sichuan, and identifies the likely risky segments for potential large earthquakes. The authors map the probable asperities from the abnormally low b-value distribution, develop and employ a method for identifying current faulting behaviors of individual fault segment from the combinations of multiple seismicity parameter values, and make an effort to estimate the average recurrence intervals of character-istic earthquakes by using the parameters of magnitude-frequency relationship of the asperity segment. The result suggests that the studied fault zone contains 5 segments of different current faulting behaviors. Among them, the Mianning-Xichang segment of the Anninghe fault has been locked under high stress, its central part is probably an asperity with a relatively large scale. The Xichang-Puge segment of the Zemuhe fault displays very low seismicity under low stress. Both the locked segment and the low-seismicity segment can be outlined on the across-profile of relocated hypocenter depths. The Mianning-Xichang segment is identified to be the one with potential large earth-quake risk, for which the average recurrence interval between the latest M = 6.7 earthquake in 1952 and the next characteristic event is estimated to be 55 to 67 years, and the magnitude of the potential earthquake between 7.0 and 7.5. Also, it has been preliminarily suggested that for a certain fault segment, its faulting behaviors may change and evolve with time gradually.

Assessing current faulting behaviors and seismic risk of the Anninghe-Zemuhe fault zone from seismicity parameters

Using the data of regional seismic network, this paper analyzes the current faulting behaviors of different segments of the Anninghe-Zemuhe fault zone, western Sichuan, and identifies the likely risky segments for potential large earthquakes. The authors map the probable asperities from the abnormally low b-value distribution, develop and employ a method for identifying current faulting behaviors of individual fault segment from the combinations of multiple seismicity parameter values, and make an effort to estimate the average recurrence intervals of character-istic earthquakes by using the parameters of magnitude-frequency relationship of the asperity segment. The result suggests that the studied fault zone contains 5 segments of different current faulting behaviors. Among them, the Mianning-Xichang segment of the Anninghe fault has been locked under high stress, its central part is probably an asperity with a relatively large scale. The Xichang-Puge segment of the Zemuhe fault displays very low seismicity under low stress. Both the locked segment and the low-seismicity segment can be outlined on the across-profile of relocated hypocenter depths. The Mianning-Xichang segment is identified to be the one with potential large earth-quake risk, for which the average recurrence interval between the latest M = 6.7 earthquake in 1952 and the next characteristic event is estimated to be 55 to 67 years, and the magnitude of the potential earthquake between 7.0 and 7.5. Also, it has been preliminarily suggested that for a certain fault segment, its faulting behaviors may change and evolve with time gradually.

Fault activation and induced seismicity in geological carbon storage--Lessons learned from recent modeling studies

In the light of current concerns related to induced seismicity associated with geological carbon sequestration(GCS),this paper summarizes lessons learned from recent modeling studies on fault activation,induced seismicity,and potential for leakage associated with deep underground carbon dioxide(CO2) injection.Model simulations demonstrate that seismic events large enough to be felt by humans require brittle fault properties and continuous fault permeability allowing pressure to be distributed over a large fault patch to be ruptured at once.Heterogeneous fault properties,which are commonly encountered in faults intersecting multilayered shale/sandstone sequences,effectively reduce the likelihood of inducing felt seismicity and also effectively impede upward CO2leakage.A number of simulations show that even a sizable seismic event that could be felt may not be capable of opening a new flow path across the entire thickness of an overlying caprock and it is very unlikely to cross a system of multiple overlying caprock units.Site-specific model simulations of the In Salah CO2storage demonstration site showed that deep fractured zone responses and associated microseismicity occurred in the brittle fractured sandstone reservoir,but at a very substantial reservoir overpressure close to the magnitude of the least principal stress.We conclude by emphasizing the importance of site investigation to characterize rock properties and if at all possible to avoid brittle rock such as proximity of crystalline basement or sites in hard and brittle sedimentary sequences that are more prone to injection-induced seismicity and permanent damage.

Comparative Study of Global Seismicity on the Hot Engine Belt and the Cooling Seismic Belt—Improvement on Research Ideas of Earthquake Prediction

The study in this paper analyzes and compares the distribution on the global engine active seismic zone and cooling seismic belt basing on the ANSS earthquake catalog from Northern California Earthquake Data Center. An idea of the seismogenesis and earthquake prediction research is achieved by showing the stratigraphic structure in the hot engine belt. The results show that the main engine and its seismic cones are the global seismic activity area, as well as the subject of global geological disaster. Based on the conjecture of other stratum structure, the energy of crustal strong earthquake and volcano activities probably originates from the deep upper mantle. It is suggested that the research on earthquake and volcano prediction should focus on the monitor and analysis on the sub-crustal earthquake activities.

A classification of induced seismicity

In order to adopt the best safety procedures, man-made earthquakes should be differentiated as a function of their origin. At least four different types of settings can be recognized in which anthropogenic activities may generate seismicity:(I) fluid removal from a stratigraphic reservoir in the underground can trigger the compaction of the voids and the collapse of the overlying volume, i.e., graviquakes; the deeper the reservoir, the bigger the volume and the earthquake magnitude;(II) wastewater or gas reinjection provides the reduction of friction in volumes and along fault planes, allowing creep or sudden activation of tectonic discontinuities, i.e., reinjection quakes;(III) fluid injection at supra-lithostatic pressure generates hydrofracturing and micro-seismicity, i.e., hydrofracturing quakes;(IV) fluid extraction or fluid injection,filling or unfilling of artificial lakes modifies the lithostatic load, which is the maximum principal stress in extensional tectonic settings, the minimum principal stress in contractional tectonic settings, and the intermediate principal stress in strike-slip settings, i.e., load quakes; over given pressure values, the increase of the lithostatic load may favour the activation of normal faults, whereas its decrease may favour thrust faults. For example, the filling of an artificial lake may generate normal fault-related seismicity.Therefore, each setting has its peculiarities and the knowledge of the different mechanisms may contribute to the adoption of the appropriate precautions in the various industrial activities.

The seismicity research in the sub-regions of Chinese mainland using strain accumula-ting and releasing model

The sub-regions are divided for the seismicity of the Chinese mainland based on the hypothesis of the active crustal blocks and the division of the active boundaries. On this result, the seismicity of each active crustal blocks are studied by calculating the accumulated and released strain of the earthquakes based on strain accumulating and releasing model, and the different seismicity stages of the sub-regions are discussed basically. Finally we have discussed the premise of the model application and the potential problems of the model results.

A limit equilibrium fracture zone model to investigate seismicity in coal mines

This paper explores possible synergies between techniques used to minimise seismicity in deep South African gold mines and their applicability to control coal bumps. The paper gives a summary of the techniques used in the deep gold mines and a critical appraisal if these are useful in coal mines. The techniques typically include control of mining rate, preconditioning, optimisation of extraction sequences and centralised blasting. Of particular interest to the coal bump problem is an experimental limit equilibrium fracture zone model implemented in a displacement discontinuity code. This was recently developed for the gold mines to enable the interactive analysis of complex tabular mine layout extraction sequences. The model specifically accommodates energy dissipation computations in the developing fracture zone near the edges of these excavations. This allows the released energy to be used as a surrogate measure of ongoing seismic activity and addresses a number of the weaknesses in the traditional usage of this quantity as a criterion for the design of seismically active layouts. This paper investigates the application of the model to a hypothetical coal longwall layout and the specific problem of coal bumps.

Seismicity,structure and tectonics in the Arctic region

The "Arctic" region,where the North Pole occupies the center of the Arctic Ocean,has been affecting the environmental variation of the Earth from geological time to the present.However,the seismic activities in the area are not adequately monitored.Therefore,by conducting long term monitoring of seismic phenomenon as sustainable parameters,our understanding of both the tectonic evolution of the Earth and the dynamic interaction between the cryosphere and geosphere in surface layers of the Earth will increase.In this paper,the association of the seismicity and structure of the Arctic region,particularly focused on Eurasian continent and surrounding oceans,and its relationship with regional evolution during the Earth’s history is studied.The target areas cover representative tectonic provinces in the Eurasian Arctic,such as the wide area of Siberia,Baikal Rift Zone.Far East Russia,Arctic Ocean together with Greenland and Northern Canada.Based on discussion including characteristics of seismicity,heterogeneous structure of the crust and upper mantle,tectonic history and recent dynamic features of the Earth’s surface in the Arctic are summarized.

Regional seismicity triggered by the M_s=7.8 Tangshan event on July 28, 1976 and the stati cstress field change

We studied the seismicity before and after the M_s=7.8 Tangshan event on July 28, 1976 (39°28'N, 1 18° 11'E) and the results show that in 3 regions outside of the source zone, seismicity rate increasing were observed, which was significant in 0.99 significance level using Z-statistic test and was proposed to be triggered by the M_s=7.8 Tangshan earthquake. The magnitude of the greatest triggered event was 5.5. The epicenter distances of these earthquakes were several ten kilometers to 300 km. The static stress change △CFS of Coulomb failure was calculated using an elastic dislocation model in half space and the △CFS on the major rupture directions in these three regions were positive.

Generalized Rydelek-Sacks test for distinguishing between periodic and randompatterns in seismicity

For distinguishing the periodicity of strong earthquakes on the time scale of decades, we generalized the Rydelek-Sacks test (R) delek. Sacks. 1989) to explore whether a time series is modulated by a periodic process or not. Thetest is conducted by comparing the total phasor of seismicity with that produced by a random Brownian motion.The phdse angle is defined by the origin time of earthquakes relative to a reference time scale. Using this methodwe tested two hypotheses in geodynamics and earthquake prediction study. One is the hypothesis of Romanowicz( 1993 ) who proposed that the great earthquakes alternate in a predictable fashion between strike-slip and thrustingmechanisms oil a 20~30 years cycle. The other hypothesis is that the strong earthquakes in and around China havean active period of about ten years. The test obtains a negative conclusion for the former hypothesis and a positiveconclusion for the latter at the 93% confidence level.

Development of a new high resolution waveform migration location method and its applications to induced seismicity

Locating seismic events is a central task for earthquake monitoring.Compared to arrival-based location methods,waveformbased location methods do not require picking phase arrivals and are more suitable for locating seismic events with noisy waveforms.Among waveform-based location methods,one approach is to stack different attributes of P and S waveforms around arrival times corresponding to potential event locations and origin times,and the maximum stacking values are assumed to indicate the correct event location and origin time.In this study,to obtain a high-resolution location image,we improve the waveform-based location method by applying a hybrid multiplicative imaging condition to characteristic functions of seismic waveforms.In our new stacking method,stations are divided into groups;characteristic functions of seismic waveforms recorded at stations in the same group are summed,and then multiplied among groups.We find that this approach can largely eliminate the cumulative effects of noise in the summation process and thus improve the resolution of location images.We test the new method and compare it to three other stacking methods,using both synthetic and real datasets that are related to induced seismicity occurring in petroleum/gas production.The test results confirm that the new stacking method can provide higher-resolution location images than those derived from currently used methods.

Seismicity acceleration model and its application to several earthquake regions in China

With the theory of subcritical crack growth, we can deduce the fundamental equation of regional seismicity acceleration model. Applying this model to intraplate earthquake regions, we select three earthquake subplates: North China Subplate, Chuan Dian Block and Xinjiang Subplate, and divide the three subplates into seven researched regions by the difference of seismicity and tectonic conditions. With the modified equation given by Sornette and Sammis (1995), we analysis the seismicity of each region. To those strong earthquakes already occurred in these region, the model can give close fitting of magnitude and occurrence time, and the result in this article indicates that the seismicity acceleration model can also be used for describing the seismicity of intraplate. In the article, we give the magnitude and occurrence time of possible strong earthquakes in Shanxi, Ordos, Bole Tuokexun, Ayinke Wuqia earthquake regions. In the same subplate or block, the earthquake periods for each earthquake region are similar in time interval. The constant α in model can be used to describe the intensity of regional seismicity, and for the Chinese Mainland, α is 0.4 generally. To the seismicity in Taiwan and other regions with complex tectonic conditions, the model does not fit well at present.

On the physical model of earthquake precursor fields and the mechanism of precursors＇timespace distribution（Ⅲ）──anomalies of seismicity and crustal deformation and their mechanisms when a strong earthquake is in prep

By studying the seismicity pattern before 37 earthquakes with M≥6. 0 in North China and the pattern of crustal deformation in the Capital Area from 1954 to 1992, some abnormal characteristics of these patterns before strong earthquakes have been extracted. A comparison has been made between the anomalies of these two kinds of Patterns. From the results we can know the following. ① Before a strong earthquake, the seismicity will strengthen and the crustal deformation rate will increase. ② Several years before a strong earthquake, there will be seismic gaps and deformation gaps around the epicenter of the quake. ③ The dynamic parameters of patterns all show a decrease in information dimension. This means that the crustal deformation has become more and more localized with time and it gives an important indication showing that a strong earthquake is in preparation. At the end of the paper, the physical mechanisms of the abnormal patterns of seismicity and crustal deformationhave been explained in a unified way in terms of the earthquake-generating model of a inhomogeneous strongbody in inhmogeneous media.

Seismicity gap and seismic quiescence before 1999 Jiji(Chi-Chi) M_W7.6 earthquake

The September 21, 1999, Jiji （Chi-Chi） Mw7.6 earthquake is the strongest event occurred since 1900 in Taiwan of China. It is located in the middle segment of the western seismic zone of Taiwan. Based on several versions of China earthquake catalogue this study found that a seismic gap of M≥5 earthquakes appeared, in and around the epicenter region, 24 years before and lasted up to the mainshock occurrence. This study also noticed that there existed a lager seismically quiet region of M≥4 earthquakes, which lasted for about 2.5 years before the mainshock occurrence, The spatial variation pattern of regional seismicity before the mainshock seems to match with its coseismic source rupture process. The mentioned seismicity gap and seismic quiescence might be an indication of the preparation process of the Jiji strong earthquake.