Seismicity anomalies before the great earthquake of M_S=8.1 in the Kunlun Pass and its significance to earthquake prediction

A great earthquake of MS=8.1 took place in the west of Kunlun Pass on November 14, 2001. The epicenter is lo-cated at 36.2N and 90.9E. The analysis shows that some main precursory seismic patterns appear before the great earthquake, e.g., seismic gap, seismic band, increased activity, seismicity quiet and swarm activity. The evolution of the seismic patterns before the earthquake of MS=8.1 exhibits a course very similar to that found for earthquake cases with MS7. The difference is that anomalous seismicity before the earthquake of MS=8.1 involves in the lar-ger area coverage and higher seismic magnitude. This provides an evidence for recognizing precursor and fore-casting of very large earthquake. Finally, we review the rough prediction of the great earthquake and discuss some problems related to the prediction of great earthquakes.

Seismicity Quantification and Its Application to Medium-term Earthquake Prediction

Bed on the analysis of each parameter describing seismicity,we think A(b)-value can betterquantitatively describe the feature of the enhancement and quietness of seismicity in this paper. Thedata of moderate or small earthquakes during 1972～1996 in North China are used in space scanningof A(b)-value. The result shows that 2～3 years before most strong earthquakes there wereObviously anomaly zones of A(b)-value with very good prediction effect. Some problems about themedium-term prediction by using A(b)-value are also discussed.

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.

Application of consequence-based design criteria in regions of moderate seismicity

Current design criteria and prineiples of earthquake engineering design are reviewed,including safety factors, probabilistic approach,and two-level and muhi-level functional design ideas.The modern multi-functional idea is discussed in greater details.When designing a structure,its resistance to and the intensity of the earthquake action are considered. The consequence of failure of the structure is considered only through a rough and empirical factor of importance,ranging usually from 1.0 to 1.5.This paper suggests a method of'consequence-based design,'which considers the consequences of malfunctioning instead of simply an importance factor.The main argument for this method is that damage to a structure located in different types of societies may have very different consequences,which are depeudant on its value and usefulness to the society and the seismicity in the region.

Prediction of maximum magnitude and original time of reservoir induced seismicity

This paper deals with the prediction of potentially maximum magnitude and origin time for reservoir induced seismicity (RIS). The factor and sign of seismology and geology of RIS has been studied, and the information quantity for magnitude of induced seismicity provided by them has been calculated. In terms of information quan-tity the biggest possible magnitude of RIS is determined. The changes of seismic frequency with time are studied using grey model method, and the time of the biggest change rate is taken as original time of the main shock. The feasibility of methods for predicting magnitude and time has been tested for the reservoir induced seismicity in the Xinfengjiang reservoir, China and the Koyna reservoir, India.

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.

Study of the Seismicity of Strong Earthquakes in the Yunnan Area

Yunnan is located in the east margin of the collision zone between the India Plate and the Eurasian Plate on the Chinese Continent, where crustal movement is violent and moderatestrong earthquakes are frequent. In addition, the area features marked active block movement. Therefore, Yunnan is a perfect place for research on strong earthquake activity. Through the study on the temporal and spatial distribution of the M ≥ 6.7 earthquakes and the related earthquake dynamics in Yunnan in the last century, we conclude that the four seismically active periods, which are characterized by alternative activity in the east and the west part of Yunnan, possibly result from a combination of active and quiescent periods in each of the east and west part. And for every 100 years, there may be a period in which strong earthquakes occur in the east and west parts simultaneously. In addition, the seismicity of strong earthquakes in Yunnan corresponds well to that in the peripheral region. The seismicity of the great earthquakes in the Andaman-Myanmar Tectonic Arc belt indicates, to some extent, the beginning of a seismically active period in Yunnan. The seismicity of strong earthquakes in east Yunnan is closely related to that in Sichuan. Strong earthquakes in Sichuan often occur later than those in Yunnan. Furthermore, in the east part of Ynnnan, the three procedures including continuous occurrence of moderate-strong earthquake, quiescent period, and the occurrence of the first strong earthquake may be the style of the beginning of the earthquake active period. The above cognition is helpful to the study of earthquake prediction, seismogenic mechanism, and the dynamics of the plate margin in Yunnan.

The NE Directed Seismicity Belt in Tibet after the M_S8.1 Nepal Earthquake and Its Predictive Significance

After the 2015 M_S8. 1 Nepal earthquake,a strong and moderate seismicity belt has formed in Tibet gradually spreading along the northeast direction. In this paper,we attempt to summarize the features and investigate the primary mechanism of this behavior of seismic activity,using a 2-D finite element numerical model with tectonic dynamic settings and GPS horizontal displacements as the constraints. In addition,compared with the NEtrending seismicity belt triggered by the 1996 Xiatongmoin earthquake,we discuss the future earthquake hazard in and around Tibet. Our results show that: the NE-directed seismicity belt is the response of enhanced loading on the anisotropic Qinghai-Tibetan plateau from the Indian plate and earthquake thrusting. Also,this possibly implies that a forthcoming strong earthquake may fill in the gaps in the NE-directed seismicity belt or enhance the seismic hazard in the eastern( the north-south seismic zone) and western( Tianshan tectonic region) parts near the NE-directed belt.

Mining-Induced Seismicity in the Kola Peninsula Mines

Mining-induced seismicity is a reflection of rock geomechanical evolution of geological environment in the natural and man-made systems and in the mining-technical systems. In order to predict and prevent mining-induced seismicity, it is necessary to research geodynamics and stress state of intact rock mass, to determine possible deformations and additional stresses as a result of large-scale rock extraction, conditions of accumulated energy release. For that a geodynamical monitoring is required on every stage of deposit development and a closing. The report considers principal influencing factors of preparation and occurrence of mining-induced earthquakes. Also it estimates precursors and indicators of rock mass breaking point, and experience concerning prediction and prevention of mining-induced seismicity in the Khibiny apatite mines in the Murmansk region, which is the largest mining province.

State Vectors—A New Method for Seismicity Analysis

The concept of state vector stems from statistical physics, where it is usually used to describe the evolution of a continuum field in its way of coarse-graining. In this paper, the state vector is employed to depict the evolution of seismicity quantitatively, and some interesting results are presented. The authors investigated some famous earthquake cases (e.g., the Haicheng earthquake, the Tangshan earthquake, the west Kunlun Mountains earthquake, etc.) and found that the state vectors evidently change prior to the occurrence of large earthquakes. Thus it is believed that the state vector can be used as a kind of precursor to predict large earthquakes.

Preliminary Study on the Seismicity Trend of the Shanxi Seismic Belt

In this paper,according to the geological structure and the data on seismicity in the Shanxi seismic belt,the tectonic stress field of this belt is numerically imitated by using the finite element method,and by analyzing synthetically the characteristics of seismogeoiogical structure,seismicity and tectonic stress field,the trend of the coming macroseism in the Shanxi seismic belt can be roughly assessed.The main estimate is as follows.From 1993 to 2015,a strong earthquake with Ms=6.2±0.4 may occur in the Shanxi seismic belt,and there are 3 possible locations for earthquake occurrence,if we arrange according to the order of possibility of earthquake occurrence,the location of a coming earthquake would be(1)the region between Huoxian and Hongdong;(2)the region surrounded by Datong,Huairen,Yingxian and Hunyuan,and(3)the region surrounded by eastern Lingqiu to both ends of the Laiyuan fault.

The role of artificial intelligence and IoT in prediction of earthquakes:Review

Earthquakes are classified as one of the most devastating natural disasters that can have catastrophic effects on the environment,lives,and properties.There has been an increasing interest in the prediction of earthquakes and in gaining a comprehensive understanding of the mechanisms that underlie their generation,yet earthquakes are the least predictable natural disaster.Satellite data,global positioning system,interferometry synthetic aperture radar(InSAR),and seismometers such as microelectromechanical system,seismometers,ocean bottom seismometers,and distributed acoustic sensing systems have all been used to predict earthquakes with a high degree of success.Despite advances in seismic wave recording,storage,and analysis,earthquake time,location,and magnitude prediction remain difficult.On the other hand,new developments in artificial intelligence(AI)and the Internet of Things(IoT)have shown promising potential to deliver more insights and predictions.Thus,this article reviewed the use of AI-driven Models and IoT-based technologies for the prediction of earthquakes,the limitations of current approaches,and open research issues.The review discusses earthquake prediction setbacks due to insufficient data,inconsistencies,diversity of earthquake precursor signals,and the earth’s geophysical composition.Finally,this study examines potential approaches or solutions that scientists can employ to address the challenges they face in earthquake prediction.The analysis is based on the successful application of AI and IoT in other fields.

An adaptive physics-informed deep learning method for pore pressure prediction using seismic data

Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.

Geophysical prediction of organic matter abundance in source rocks based on geochemical analysis:A case study of southwestern Bozhong Sag,Bohai Sea,China

The Bozhong Sag is the largest petroliferous sag in the Bohai Bay Basin,and the source rocks of Paleogene Dongying and Shahejie Formations were buried deeply.Most of the drillings were located at the structural high,and there were few wells that met good quality source rocks,so it is difficult to evaluate the source rocks in the study area precisely by geochemical analysis only.Based on the Rock-Eval pyrolysis,total organic carbon(TOC)testing,the organic matter(OM)abundance of Paleogene source rocks in the southwestern Bozhong Sag were evaluated,including the lower of second member of Dongying Formation(E_(3)d2L),the third member of Dongying Formation(E_(3)d_(3)),the first and second members of Shahejie Formation(E_(2)s_(1+2)),the third member of Shahejie Formation(E_(2)s_(3)).The results indicate that the E_(2)s_(1+2)and E_(2)s_(3)have better hydrocarbon generative potentials with the highest OM abundance,the E_(3)d_(3)are of the second good quality,and the E_(3)d2L have poor to fair hydrocarbon generative potential.Furthermore,the well logs were applied to predict TOC and residual hydrocarbon generation potential(S_(2))based on the sedimentary facies classification,usingΔlogR,generalizedΔlogR,logging multiple linear regression and BP neural network methods.The various methods were compared,and the BP neural network method have relatively better prediction accuracy.Based on the pre-stack simultaneous inversion(P-wave impedance,P-wave velocity and density inversion results)and the post-stack seismic attributes,the three-dimensional(3D)seismic prediction of TOC and S_(2)was carried out.The results show that the seismic near well prediction results of TOC and S_(2)based on seismic multi-attributes analysis correspond well with the results of well logging methods,and the plane prediction results are identical with the sedimentary facies map in the study area.The TOC and S_(2)values of E_(2)s_(1+2)and E_(2)s_(3)are higher than those in E_(3)d_(3)and E_(3)d_(2)L,basically consistent with the geochemical analysis results.This method makes up the deficiency of geochemical methods,establishing the connection between geophysical information and geochemical data,and it is helpful to the 3D quantitative prediction and the evaluation of high-quality source rocks in the areas where the drillings are limited.

Machine learning for carbonate formation drilling: Mud loss prediction using seismic attributes and mud loss records

Due to the complexity and variability of carbonate formation leakage zones, lost circulation prediction and control is one of the major challenges of carbonate drilling. It raises well-control risks and production expenses. This research utilizes the H oilfield as an example, employs seismic features to analyze mud loss prediction, and produces a complete set of pre-drilling mud loss prediction solutions. Firstly, 16seismic attributes are calculated based on the post-stack seismic data, and the mud loss rate per unit footage is specified. The sample set is constructed by extracting each attribute from the seismic trace surrounding 15 typical wells, with a ratio of 8:2 between the training set and the test set. With the calibration results for mud loss rate per unit footage, the nonlinear mapping relationship between seismic attributes and mud loss rate per unit size is established using the mixed density network model.Then, the influence of the number of sub-Gausses and the uncertainty coefficient on the model's prediction is evaluated. Finally, the model is used in conjunction with downhole drilling conditions to assess the risk of mud loss in various layers and along the wellbore trajectory. The study demonstrates that the mean relative errors of the model for training data and test data are 6.9% and 7.5%, respectively, and that R2is 90% and 88%, respectively, for training data and test data. The accuracy and efficacy of mud loss prediction may be greatly enhanced by combining 16 seismic attributes with the mud loss rate per unit footage and applying machine learning methods. The mud loss prediction model based on the MDN model can not only predict the mud loss rate but also objectively evaluate the prediction based on the quality of the data and the model.

Machine learning prediction models for ground motion parameters and seismic damage assessment of buildings at a regional scale

This study examines the feasibility of using a machine learning approach for rapid damage assessment of rein-forced concrete(RC)buildings after the earthquake.Since the real-world damaged datasets are lacking,have limited access,or are imbalanced,a simulation dataset is prepared by conducting a nonlinear time history analy-sis.Different machine learning(ML)models are trained considering the structural parameters and ground motion characteristics to predict the RC building damage into five categories:null,slight,moderate,heavy,and collapse.The random forest classifier(RFC)has achieved a higher prediction accuracy on testing and real-world damaged datasets.The structural parameters can be extracted using different means such as Google Earth,Open Street Map,unmanned aerial vehicles,etc.However,recording the ground motion at a closer distance requires the installation of a dense array of sensors which requires a higher cost.For places with no earthquake recording station/device,it is difficult to have ground motion characteristics.For that different ML-based regressor models are developed utilizing past-earthquake information to predict ground motion parameters such as peak ground acceleration and peak ground velocity.The random forest regressor(RFR)achieved better results than other regression models on testing and validation datasets.Furthermore,compared with the results of similar research works,a better result is obtained using RFC and RFR on validation datasets.In the end,these models are uti-lized to predict the damage categories of RC buildings at Saitama University and Okubo Danchi,Saitama,Japan after an earthquake.This damage information is crucial for government agencies or decision-makers to respond systematically in post-disaster situations.

Facies-controlled prediction of dolomite reservoirs in the Middle Permian Qixia Formation in Shuangyushi,northwestern Sichuan Basin

The Middle Permian Qixia Formation in the Shuangyushi area,northwestern Sichuan Basin,develops shoal-facies dolomite reservoirs.To pinpoint promising reservoirs in the Qixia Formation,deep thin shoal-facies dolomite reservoirs were predicted using the techniques of pre-stack Kirchhoff-Q compensation for absorption,inverse Q filtering,low-to high-frequency compensation,forward modeling,and facies-controlled seismic meme inversion.The results are obtained in six aspects.First,the dolomite reservoirs mainly exist in the middle and lower parts of the second member of Qixia Formation(Qi2 Member),which coincide with the zones shoal cores are developed.Second,the forward modeling shows that the trough energy at the top and bottom of shoal core increases with increasing shoal-core thickness,and weak peak reflections are associated in the middle of shoal core.Third,five types of seismic waveform are identified through waveform analysis of seismic facies.Type-Ⅰ and Type-Ⅱ waveforms correspond to promising facies(shoal core microfacies).Fourth,vertically,two packages of thin dolomite reservoirs turn up in the sedimentary cycle of intraplatform shoal in the Qi2 Member,and the lower package is superior to the upper package in dolomite thickness,scale and lateral connectivity.Fifth,in plane,significantly controlled by sedimentary facies,dolomite reservoirs laterally distribute with consistent thickness in shoal cores at topographical highs and extend toward the break.Sixth,the promising prospects are the zones with thick dolomite reservoirs and superimposition of horstegraben structural traps.

Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.

Research on Fracture Prediction Method Based on Multi-Source Information Fusion

Machine learning is a good method for predicting fracture by integrating multi-source information. Post-stack seismic attributes are commonly used to predict medium to large fractures, while pre-stack seismic attributes are proven to be more sensitive to small and micro sized fractures through forward modeling. Using machine learning algorithm to fuse information from different scales to predict fracture can greatly improve the accuracy of fracture prediction. On the basis of In-Situ stress prediction, the paper conducted post-stack seismic attribute analysis and pre-stack seismic attribute analysis, further studied on the sensitivity of seismic attributes to fracture and selected sensitive attributes, used the sensitivity log of well-bore fractures as the target log for learning, ultimately obtained a comprehensive body of fracture. Through blind well verification, the prediction results match well with the we1l data and the prediction results is highly consistent with the production data. The results of fracture prediction are reliable, and the research method has certain reference significance for fracture prediction.