Potential of the Arkhangelsk seismic network for European Arctic monitoring

The Arkhangelsk Seismic Network(ASN)of the N.Laverov Federal Center for Integrated Arctic Research of the Ural Branch of the Russian Academy of Sciences,founded in 2003,includes 10 permanent seismic stations located on the coasts of the White,Barents,and Kara Seas and on the Arctic archipelagos of Novaya Zemlya,Franz Josef Land,and Severnaya Zemlya.The network is registered with the International Federation of Digital Seismograph Networks and the International Seismological Center.We used not only ASN data to process earthquakes but also the waveforms of various international seismic stations.The 13,000 seismic events were registered using ASN data for 2012-2022,and for 5,500 of them,we determined the parameters of the earthquake epicenters from the European Arctic.The spatial distribution of epicenters shows that the ASN monitors not only the main seismically active zones but also weak seismicity on the shelf of the Barents and Kara Seas.The representative magnitude of ASN was ML,rep=3.5.The level of microseismic noise has seasonal variations that affect the registration capabilities of each station included in the ASN and the overall sensitivity of the network as a whole.In summer,the sensitivity of the ASN decreased owing to the increasing microseismic and ambient noises,whereas in winter,the sensitivity of the ASN increased significantly because of the decrease.

Assessment of earthquake location uncertainties for the design of local seismic networks

The ability to estimate earthquake source locations,along with the appraisal of relevant uncertainties,is paramount in monitoring both natural and human-induced micro-seismicity.For this purpose,a monitoring network must be designed to minimize the location errors introduced by geometrically unbalanced networks.In this study,we first review different sources of errors relevant to the localization of seismic events,how they propagate through localization algorithms,and their impact on outcomes.We then propose a quantitative method,based on a Monte Carlo approach,to estimate the uncertainty in earthquake locations that is suited to the design,optimization,and assessment of the performance of a local seismic monitoring network.To illustrate the performance of the proposed approach,we analyzed the distribution of the localization uncertainties and their related dispersion for a highly dense grid of theoretical hypocenters in both the horizontal and vertical directions using an actual monitoring network layout.The results expand,quantitatively,the qualitative indications derived from purely geometrical parameters(azimuthal gap(AG))and classical detectability maps.The proposed method enables the systematic design,optimization,and evaluation of local seismic monitoring networks,enhancing monitoring accuracy in areas proximal to hydrocarbon production,geothermal fields,underground natural gas storage,and other subsurface activities.This approach aids in the accurate estimation of earthquake source locations and their associated uncertainties,which are crucial for assessing and mitigating seismic risks,thereby enabling the implementation of proactive measures to minimize potential hazards.From an operational perspective,reliably estimating location accuracy is crucial for evaluating the position of seismogenic sources and assessing possible links between well activities and the onset of seismicity.

Benchmark on the accuracy and efficiency of several neural network based phase pickers using datasets from China Seismic Network

Seismic phase pickers based on deep neural networks have been extensively used recently,demonstrating their advantages on both performance and efficiency.However,these pickers are trained with and applied to different data.A comprehensive benchmark based on a single dataset is therefore lacking.Here,using the recently released DiTing dataset,we analyzed performances of seven phase pickers with different network structures,the efficiencies are also evaluated using both CPU and GPU devices.Evaluations based on F1-scores reveal that the recurrent neural network(RNN)and EQTransformer exhibit the best performance,likely owing to their large receptive fields.Similar performances are observed among PhaseNet(UNet),UNet++,and the lightweight phase picking network(LPPN).However,the LPPN models are the most efficient.The RNN and EQTransformer have similar speeds,which are slower than those of the LPPN and PhaseNet.UNet++requires the most computational effort among the pickers.As all of the pickers perform well after being trained with a large-scale dataset,users may choose the one suitable for their applications.For beginners,we provide a tutorial on training and validating the pickers using the DiTing dataset.We also provide two sets of models trained using datasets with both 50 Hz and 100 Hz sampling rates for direct application by end-users.All of our models are open-source and publicly accessible.

Sparse Seismic Data Reconstruction Based on a Convolutional Neural Network Algorithm

At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.

Earthquake disaster chain model based on complex networks for urban engineering systems

According to news reports on severe earthquakes since 2008,a total of 51 cases with magnitudes of 6.0 or above were analyzed,and 14 frequently occurring secondary disasters were identified.A disaster chain model was developed using principles from complex network theory.The vulnerability and risk level of each edge in this model were calculated,and high-risk edges and disaster chains were identified.The analysis reveals that the edge“floods→building collapses”has the highest vulnerability.Implementing measures to mitigate this edge is crucial for delaying the spread of secondary disasters.The highest risk is associated with the edge“building collapses→casualties,”and increased risks are also identified for chains such as“earthquake→building collapses→casualties,”“earthquake→landslides and debris flows→dammed lakes,”and“dammed lakes→floods→building collapses.”Following an earthquake,the prompt implementation of measures is crucial to effectively disrupt these chains and minimize the damage from secondary disasters.

Review of Artificial Intelligence for Oil and Gas Exploration: Convolutional Neural Network Approaches and the U-Net 3D Model

Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.

Effect of seismic retrofit of bridges on transportation networks

The objective of this research is to determine the effect earthquakes have on the performance of transportation network systems.To do this,bridge fragility curves,expressed as a function of peak ground acceleration(PGA)and peak ground velocity(PGV),were developed.Network damage was evaluated under the 1994 Northridge earthquake and scenario earthquakes.A probabilistic model was developed to determine the effect of repair of bridge damage on the improvement of the network performance as days passed after the event.As an example,the system performance degradation measured in terms of an index,'Drivers Delay,'is calculated for the Los Angeles area transportation system,and losses due to Drivers Delay with and without retrofit were estimated.

Fractured reservoir modeling by discrete fracture network and seismic modeling in the Tarim Basin,China

Fractured reservoirs are an important target for oil and gas exploration in the Tarim Basin and the prediction of this type of reservoir is challenging.Due to the complicated fracture system in the Tarim Basin,the conventional AVO inversion method based on HTI theory to predict fracture development will result in some errors.Thus,an integrated research concept for fractured reservoir prediction is put forward in this paper.Seismic modeling plays a bridging role in this concept,and the establishment of an anisotropic fracture model by Discrete Fracture Network （DFN） is the key part.Because the fracture system in the Tarim Basin shows complex anisotropic characteristics,it is vital to build an effective anisotropic model.Based on geological,well logging and seismic data,an effective anisotropic model of complex fracture systems can be set up with the DFN method.The effective elastic coefficients,and the input data for seismic modeling can be calculated.Then seismic modeling based on this model is performed,and the seismic response characteristics are analyzed.The modeling results can be used in the following AVO inversion for fracture detection.

Seismic impedance inversion based on cycle-consistent generative adversarial network

Deep learning has achieved great success in a variety of research fields and industrial applications.However,when applied to seismic inversion,the shortage of labeled data severely influences the performance of deep learning-based methods.In order to tackle this problem,we propose a novel seismic impedance inversion method based on a cycle-consistent generative adversarial network(Cycle-GAN).The proposed Cycle-GAN model includes two generative subnets and two discriminative subnets.Three kinds of loss,including cycle-consistent loss,adversarial loss,and estimation loss,are adopted to guide the training process.Benefit from the proposed structure,the information contained in unlabeled data can be extracted,and adversarial learning further guarantees that the prediction results share similar distributions with the real data.Moreover,a neural network visualization method is adopted to show that the proposed CNN model can learn more distinguishable features than the conventional CNN model.The robustness experiments on synthetic data sets show that the proposed method can achieve better performances than other methods in most cases.And the blind-well experiments on real seismic profiles show that the predicted impedance curve of the proposed method maintains a better correlation with the true impedance curve.

Earth slope reliability analysis under seismic loadings using neural network

A new method was proposed to cope with the earth slope reliability problem under seismic loadings. The algorithm integrates the concepts of artificial neural network, the first order second moment reliability method and the deterministic stability analysis method of earth slope. The performance function and its derivatives in slope stability analysis under seismic loadings were approximated by a trained multi-layer feed-forward neural network with differentiable transfer functions. The statistical moments calculated from the performance function values and the corresponding gradients using neural network were then used in the first order second moment method for the calculation of the reliability index in slope safety analysis. Two earth slope examples were presented for illustrating the applicability of the proposed approach. The new method is effective in slope reliability analysis. And it has potential application to other reliability problems of complicated engineering structure with a considerably large number of random variables.

A deep learning network for estimation of seismic local slopes

The local slopes contain rich information of the reflection geometry,which can be used to facilitate many subsequent procedures such as seismic velocities picking,normal move out correction,time-domain imaging and structural interpretation.Generally the slope estimation is achieved by manually picking or scanning the seismic profile along various slopes.We present here a deep learning-based technique to automatically estimate the local slope map from the seismic data.In the presented technique,three convolution layers are used to extract structural features in a local window and three fully connected layers serve as a classifier to predict the slope of the central point of the local window based on the extracted features.The deep learning network is trained using only synthetic seismic data,it can however accurately estimate local slopes within real seismic data.We examine its feasibility using simulated and real-seismic data.The estimated local slope maps demonstrate the succes sful performance of the synthetically-trained network.

A hybrid approach for evaluating CPT-based seismic soil liquefaction potential using Bayesian belief networks

Discernment of seismic soil liquefaction is a complex and non-linear procedure that is affected by diversified factors of uncertainties and complexity.The Bayesian belief network(BBN)is an effective tool to present a suitable framework to handle insights into such uncertainties and cause–effect relationships.The intention of this study is to use a hybrid approach methodology for the development of BBN model based on cone penetration test(CPT)case history records to evaluate seismic soil liquefaction potential.In this hybrid approach,naive model is developed initially only by an interpretive structural modeling(ISM)technique using domain knowledge(DK).Subsequently,some useful information about the naive model are embedded as DK in the K2 algorithm to develop a BBN-K2 and DK model.The results of the BBN models are compared and validated with the available artificial neural network(ANN)and C4.5 decision tree(DT)models and found that the BBN model developed by hybrid approach showed compatible and promising results for liquefaction potential assessment.The BBN model developed by hybrid approach provides a viable tool for geotechnical engineers to assess sites conditions susceptible to seismic soil liquefaction.This study also presents sensitivity analysis of the BBN model based on hybrid approach and the most probable explanation of liquefied sites,owing to know the most likely scenario of the liquefaction phenomenon.

NEURAL NETWORKS PREDICTION FOR SEISMIC RESPONSE OF STRUCTURE UNDER THE LEVENBERG-MARQUARDT ALGORITHM

Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural networks for nonlinear systems, and combined with LM algorithm, a multi layer forward networks is adopted to predict the seismic responses of structure. The networks is trained in batch by the shaking table test data of three floor reinforced concrete structure firstly, then the seismic responses of structure are predicted under the unused excitation data, and the predict responses are compared with the experiment responses. The error curves between the prediction and the experimental results show the efficiency of the method. Conclusion LM algorithm has very good convergence rate, and the neural networks can predict the seismic response of the structure well.

Seismic reliability analysis of urban water distribution network

An approach to analyze the seismic reliability of water distribution networks by combining a hydraulic analysis with a first-order reliability method （FORM）, is proposed in this paper. The hydraulic analysis method for normal conditions is modified to accommodate the special conditions necessary to perform a seismic hydraulic analysis. In order to calculate the leakage area and leaking flow of the pipelines in the hydraulic analysis method, a new leakage model established from the seismic response analysis of buried pipelines is presented. To validate the proposed approach, a network with 17 nodes and 24 pipelines is investigated in detail. The approach is also applied to an actual project consisting of 463 nodes and 767 pipelines. The results show that the proposed approach achieves satisfactory results in analyzing the seismic reliability of large-scale water distribution networks.

Serviceability evaluation of water supply networks under seismic loads utilizing their operational physical mechanism

The serviceability of water supply networks(WSNs)under seismic loads has significant importance for estimating the probable losses and the impact of diminished functionality on affected communities.The innovation presented in this paper is suggesting a new strategy to evaluate the seismic serviceability of WSNs,utilizing their operational physical mechanism.On one hand,this method can obtain the seismic serviceability of each node as well as entire WSNs.On the other hand,this method can dynamically reflect the propagation of randomness from ground motions to WSNs.First,a finite element model is established to capture the seismic response of buried pipe networks,and a leakage model is suggested to obtain the leakage area of WSNs.Second,the transient flow analysis of WSNs with or without leakage is derived to obtain dynamic water flow and pressure.Third,the seismic serviceability of WSNs is analyzed based on the probability density evolution method(PDEM).Finally,the seismic serviceability of a real WSN in Mianzhu city is assessed to illustrate the method.The case study shows that randomness from the ground motions can obviously affect the leakage state and the probability density of the nodal head during earthquakes.

Seismic signal recognition using improved BP neural network and combined feature extraction method

Seismic signal is generally employed in moving target monitoring due to its robust characteristic.A recognition method for vehicle and personnel with seismic signal sensing system was proposed based on improved neural network.For analyzing the seismic signal of the moving objects,the seismic signal of person and vehicle was acquisitioned from the seismic sensor,and then feature vectors were extracted with combined methods after filter processing.Finally,these features were put into the improved BP neural network designed for effective signal classification.Compared with previous ways,it is demonstrated that the proposed system presents higher recognition accuracy and validity based on the experimental results.It also shows the effectiveness of the improved BP neural network.

Inversion of Oceanic Parameters Represented by CTD Utilizing Seismic Multi-Attributes Based on Convolutional Neural Network

In Recent years,seismic data have been widely used in seismic oceanography for the inversion of oceanic parameters represented by conductivity temperature depth(CTD).Using this technique,researchers can identify the water structure with high horizontal resolution,which compensates for the deficiencies of CTD data.However,conventional inversion methods are modeldriven,such as constrained sparse spike inversion(CSSI)and full waveform inversion(FWI),and typically require prior deterministic mapping operators.In this paper,we propose a novel inversion method based on a convolutional neural network(CNN),which is purely data-driven.To solve the problem of multiple solutions,we use stepwise regression to select the optimal attributes and their combination and take two-dimensional images of the selected attributes as input data.To prevent vanishing gradients,we use the rectified linear unit(ReLU)function as the activation function of the hidden layer.Moreover,the Adam and mini-batch algorithms are combined to improve stability and efficiency.The inversion results of field data indicate that the proposed method is a robust tool for accurately predicting oceanic parameters.

Plastic-Flow/Seismic" Network Systems and Tectonic Units in Central-Eastern Asia

The study of the netlike earthquake distribution indicates that in the central-eastern part of Asia continent there are two network systems: the central-eastern Asia system and the southeastern China system.As interpreted by the multilayer tectonic model,they might be a manifestation of the plastic-flow network systems in the lower lithosphere,including the lower crust and the mantle lid.Each network system is enclosed by different types of boundaries,including one driving boundary and some constraining and releasing boundaries.The two plastic-flow network systems with the Himalayan and Taiwan arcs as their driving boundaries play the role of controlling the intraplate tectonic deformation,stress field,seismicity,and subdivision of tectonic units.

Estimation of reservoir porosity using probabilistic neural network and seismic attributes

Porosity is one of the most important properties of oil and gas reservoirs. The porosity data that come from well log are only available at well points. It is necessary to use other method to estimate reservoir porosity.Seismic data contain abundant lithological information. Because there are inherent correlations between reservoir property and seismic data,it is possible to estimate reservoir porosity by using seismic data and attributes.Probabilistic neural network is a powerful tool to extract mathematical relation between two data sets. It has been used to extract the mathematical relation between porosity and seismic attributes. Firstly,a seismic impedance volume is calculated by seismic inversion. Secondly,several appropriate seismic attributes are extracted by using multi-regression analysis. Then a probabilistic neural network model is trained to obtain a mathematical relation between porosity and seismic attributes. Finally,this trained probabilistic neural network model is implemented to calculate a porosity data volume. This methodology could be utilized to find advantageous areas at the early stage of exploration. It is also helpful for the establishment of a reservoir model at the stage of reservoir development.

Detectability and reliability analysis of the local seismic network in Pakistan

The detectability and reliability analysis for the local seismic network is performed employing by Bungum and Husebye technique. The events were relocated using standard computer codes for hypocentral locations. The detectability levels are estimated from the twenty-five years of recorded data in terms of 50%, 90% and 100% cumulative detectability thresholds, which were derived from frequency-magnitude distribution. From this analysis the 100% level of detectability of the network is M L=1.7 for events which occur within the network. The accuracy in hypocentral solutions of the network is investigated by considering the fixed real hypocenter within the network. The epicentral errors are found to be less than 4 km when the events occur within the network. Finally, the problems faced during continuous operation of the local network, which effects its detectability, are discussed.