26 results about "Earthquake prediction" patented technology

The application relates to the technical field of earthquake prediction, and particularly provides a lightweight on-site ground motion parameter prediction model construction method and an earthquake early warning system. The lightweight on-site ground motion parameter prediction model construction method comprises the following steps: training an initial prediction model according to acceleration waveform data when a P wave of an earthquake arrives, to obtain a pre-training prediction model; taking the pre-training prediction model as a teacher model, and transferring the knowledge of the teacher model to a student model through distillation; and constructing a lightweight on-site ground motion parameter prediction model based on the student model. The method can reduce the complexity and calculation amount of the student model by transferring the knowledge in the pre-training prediction model to the student model through distillation; and the lightweight on-site ground motion parameter prediction model can be constructed based on the student model, so that the demand of the model for hardware resources can be reduced while the on-site ground motion parameter prediction efficiency is ensured, and the deployable scene of the model is expanded.

This invention relates to the field of earthquake prediction, specifically to a method, system, device, and medium for earthquake parameter prediction based on spatial Bayesian Copula. The method includes obtaining the coupling relationship between the earthquake parameters to be predicted and multivariate environmental test data based on pre-constructed Copula models of known sites in a target area; solving for the prior distribution of parameters of the Copula model of the site to be predicted using a general Kriging model based on the spatial correlation and coupling relationship between the multivariate environmental test data of each site; updating the prior distribution of the solved parameters using a Bayesian update method to obtain a Bayesian posterior Copula model; and predicting the earthquake parameters of the site to be predicted using the Bayesian posterior Copula model with local observed earthquake data of the site as variables. This invention can dynamically predict earthquake parameters, significantly improving the spatial consistency and prediction accuracy of earthquake risk assessment.

This invention discloses a seismic prediction method for gravity-induced geostress parameters in TTI media. The specific process includes: Step 1, establishing calculation models for the minimum and maximum horizontal stresses and DHSR of the TTI media; Step 2, performing discrete Fourier transform on partially stacked seismic data from different azimuths to obtain zero-order and second-order Fourier coefficient data volumes; Step 3, predicting TTI media model parameters: performing Bayesian Fourier coefficient inversion to predict P-wave and S-wave moduli, densities, fracture densities, and dip fracture parameters; and calculating fracture dip angles; Step 4, calculating TTI media geostress parameters: substituting the predicted TTI media model parameters into the calculation model established in Step 1 to calculate the minimum and maximum horizontal stresses and DHSR of the TTI media. This invention can provide stable and reliable prediction results for TTI media geostress parameters, which helps guide fracturing development operations in unconventional reservoirs.

This invention provides a method, system, and medium for predicting earthquake source locations using TLF-GV signals, belonging to the field of earthquake prediction technology. The method includes: constructing a U-Net++ model, where multiple encoding blocks are used to sequentially generate feature maps of different spatial scales based on the gradient tensors extracted from TLF-GV; multiple decoding blocks are used to decode and output earthquake source probability heatmaps based on the feature maps at different spatial scales; obtaining active fault distribution maps, and constructing a geological prior penalty term based on the distance from each grid cell in the earthquake source probability heatmap to the nearest active fault, and constructing a loss function by combining the cross-entropy loss between the probability heatmap and the actual source mask; constructing a training set, using the concatenated features of the gradient tensors extracted from the gravity gradient grid and the fault binary mask as input to train and obtain the prediction model. This method utilizes the spatial grid features of the TLF-GV gravity gradient, combined with the small-scale feature capture capability of U-Net++, to effectively improve the accuracy of earthquake source location prediction.

This invention discloses a plate motion analysis method based on GNSS and SLR stations of the Eurasian Plate, belonging to the field of geodesy and surveying engineering technology. The method includes: acquiring raw coordinate time-series data from GNSS and SLR stations and preprocessing them; decomposing the preprocessed sequence using singular spectrum analysis (SSA) to reconstruct and separate trend, periodic, and noise terms; performing Fast Fourier Transform (FFT) on the reconstructed signal to extract frequency domain features; establishing a comprehensive model of linear velocity plus periodic correction by combining time and frequency domain features; and analyzing the motion characteristics of the Eurasian Plate based on this model to achieve motion trend prediction and anomaly detection. This invention, through the combination of SSA and FFT, significantly improves the accuracy of motion parameter estimation and the ability to identify weak signals, providing a reliable method for plate motion analysis and earthquake prediction.

The application provides a carbon dioxide underground storage range earthquake prediction method, and the earthquake prediction method comprises the following steps: S1, obtaining an injection layer isobath structure map according to seismic data and injection well calibration data; S2, obtaining an amplitude variation curve of the injection layer according to prestack gather seismic data; S3, calculating a slope variation rate attribute according to the amplitude variation curve, and determining a threshold value of the slope variation rate attribute of a gas injection area; and S4, determining a final carbon dioxide gas injection area plane distribution range according to the prestack gather seismic data. The application provides a theoretical basis for predicting a carbon dioxide oil displacement range by using three-dimensional seismic data after gas injection, and the earthquake prediction method serves as a prerequisite for the above research method, so as to provide scientific guidance for safe implementation of carbon dioxide oil displacement in a research area.

The application discloses a short-term strong earthquake occurrence time prediction method and device, medium and equipment, and relates to the technical field of earthquake prediction. The method performs standardization preprocessing on atmospheric tide gravity signals in a preset time window, inputs a plurality of target days into a prediction model constructed in advance after detecting an atmospheric tide gravity anomaly event, and obtains the probability of strong earthquakes occurring in each target day after the atmospheric tide gravity anomaly event. The prediction model is trained according to the statistical correlation characteristics between the atmospheric tide gravity anomaly event occurrence time and the strong earthquake occurrence time. The strong earthquake refers to an earthquake with a magnitude greater than a preset threshold. According to the probability of strong earthquakes occurring in each target day after the anomaly, the strong earthquake occurrence time prediction result is determined. The method realizes quantitative probability prediction of the strong earthquake occurrence time, and has the advantages of being interpretable, calibratable and online updatable.

The application discloses a kind of according to nuclear density and machine learning Seismic Numerical Prediction Method, belong to the technical field of earthquake prediction.The method includes: the original earthquake catalogue data is standardized and energy correlation is handled, and standard earthquake catalogue data is formed, and the minimum complete magnitude is determined by completeness processing to standard earthquake catalogue data, and the complete earthquake catalogue is obtained by screening;The first and second bandwidth are determined by nuclear density bandwidth sensitivity test to the complete earthquake catalogue, the time and magnitude sliding window are combined, the seismic frequency and energy nuclear density distribution of target area are calculated, and the nuclear density anomaly distribution data is obtained by difference with long-term average nuclear density distribution;The nuclear density anomaly distribution data of target magnitude range under multiple time scales is input into pre-training random forest model, and the occurrence prediction result of target magnitude earthquake in target area is output.The method improves the spatial accuracy and timeliness of earthquake prediction, and provides technical support for earthquake disaster risk prevention and control.

This invention discloses an earthquake prediction method, system, device, and storage medium, relating to the field of earthquake prediction technology. The method includes the following steps: determining a corresponding dedicated kernel function based on the proportion of different heterogeneous feature types in the current multidimensional heterogeneous features; mapping the current multidimensional heterogeneous features to a high dimension using the dedicated kernel function to obtain a mapping vector; assigning different weights to different earthquake precursor data based on the correlation between different multidimensional heterogeneous features and the earthquake prediction target; linearly fusing multiple mapping vectors with multiple weights to obtain a preliminary fusion vector; reducing the dimensionality of the preliminary fusion vector to obtain a fusion feature vector; and inputting the fusion feature vector into sub-models corresponding to different earthquake prediction targets to obtain the probability values ​​of the corresponding prediction results. This invention can dynamically adapt to the differences in importance of multi-source features, weighting the mapping vector with corresponding weights to achieve linear fusion of heterogeneous features and improve the accuracy of earthquake prediction.

The application discloses a kind of biological limestone reservoir seismic prediction methods, comprising the following steps: according to the possibility of whether the research target has biological limestone reservoir development of geological understanding of research area judgment;Rock physics analysis is carried out to the biological limestone reservoir section and its surrounding rock of well logging data of research area, the applicability of longitudinal wave impedance, P-S wave velocity ratio in biological limestone reservoir prediction is studied;The velocity spectrum and velocity profile characteristics of biological limestone reservoir are analyzed, to determine whether the possible biological limestone reservoir development area is low-speed characteristic compared with surrounding rock, to further reduce the multiple solutions of reservoir prediction;Forward modeling is carried out, the corresponding relationship between the distribution characteristics of biological limestone reservoir in forward model and seismic profile is discussed, and the possibility of biological limestone reservoir development is verified;Using the seismic data collected in the research area, prestack inversion and bayesian discriminant analysis based thereon are carried out, and the planar and profile distribution of biological limestone reservoir is predicted by longitudinal wave impedance and P-S wave velocity ratio double parameters.

The application discloses a strong earthquake prediction method and device based on earthquake precursor information, a medium and equipment, and relates to the technical field of earthquake prediction. When the atmospheric tidal gravity signal is determined to be an atmospheric tidal gravity anomaly signal, the atmospheric tidal gravity anomaly signal is input to a gradient boosting machine model constructed in advance, the research area is simulated by spatial partitioning, and the simulated magnitude of each partition is obtained. Then, the energy loss of the signal in the complex medium propagation is compensated by using an attenuation function, and the actual magnitude of each partition is obtained. Further, in combination with the spatial distribution characteristics of regional earthquakes, the distribution of the source risk area is determined, and the strong earthquake prediction result of the research area is output accordingly. On this basis, by introducing a feature contribution degree analysis method, the physical interpretability of the model output is tested, and the influence mechanism of the key features of the abnormal signal on the prediction result is determined. The method improves the accuracy of quantitative prediction of strong earthquakes.

This invention relates to a seismic prediction method for fractures and fissures in folded belt formations, belonging to the field of oil and gas exploration and development technology. The seismic prediction method for fractures and fissures in folded belt formations of this invention, by dividing the boundary points of the axial and limb regions, performing planar phase-controlled seismic adjacent channel gradient scanning, calculating the seismic trend volume of the formation, and then predicting the development of fractures and fissures in the formation, determines the distribution of fractures and fissures throughout the folded belt. This seismic prediction method for fractures and fissures in folded belt formations of this invention can reduce the impact of seismic axial deformation and large phase differences on the calculated fractures in the axial and limb regions, improve the influence of small phase changes and frequency decay, and mitigate the impact of discontinuities in the seismic phase axis caused by non-fracture factors due to the large slope of the limb slope, thus presenting the development information of fractures and fissures in the axial and limb regions of the folded belt formations.

This invention provides a method and system for joint probabilistic prediction of three earthquake elements associated with TLF-GV signals, belonging to the field of earthquake prediction technology. It aims to solve the problems of traditional three-element prediction lacking joint fusion, difficulty in handling evidence conflicts, and fixed weights. The method includes: extracting the physical characteristics of the TLF-GV signal, taking the prediction results of the previous three elements and model confidence parameters, concatenating them into a feature vector, inputting it into a dynamic weighted prediction model constructed by a shallow MLP, and outputting time, magnitude, and location weights; dividing the three elements into 3×3×3=27 "time-magnitude-location" propositions, generating a basic probability assignment (BPA) for each proposition based on the weights, and quantifying evidence contradictions through a conflict coefficient K; obtaining the joint BPA using the Dempster combination rule, calculating the mean of the confidence function and likelihood function of each proposition as the comprehensive probability, and extracting the proposition with the highest probability as the coupling result. This method significantly improves the scientific rigor and practicality of short-term strong earthquake prediction.

The application discloses a mine earthquake prediction method and system coupling surface subsidence and dynamic rock stratum moving angle, and relates to the technical field of mining engineering and mine safety monitoring. The method first obtains a surface subsidence curve evolving with dynamic mining of a working face through monitoring; a dynamic rock stratum moving angle calculation model is established based on the geometric relation between the real-time mining position of the working face in a geological profile and the intersection point of the surface basin edge; the dynamic evolution law of the rock stratum moving angle is extracted to determine that the system enters a high-risk energy accumulation stage, and mine earthquake early warning information is issued. The application uses macroscopic deformation indexes to accurately represent deep rock stratum activities, effectively makes up for the early warning blind area of microseismic monitoring in the "energy silent period", and improves the advance and reliability of mine earthquake prediction.

This application discloses a method and system for inferring and predicting fault instability states, relating to the fields of earthquake prediction and geophysics. The method includes: acquiring a time-series dataset from laboratory fault stick-slip experiments, including acoustic emission signals and shear stress signals; constructing a deep learning model based on the Transformer architecture, and training the model using the time-series dataset to optimize its parameters; after training, by inputting real-time or historical acoustic emission signal sequences or shear stress signal sequences, the model can directly output inference or prediction results of fault instability states. This application utilizes the self-attention mechanism of the Transformer model to effectively capture long-range dependencies in time-series data, achieving end-to-end learning of fault instability patterns from raw data, improving the accuracy and timeliness of fault activity monitoring and early warning, and providing dynamic and continuous decision support for earthquake risk assessment.

The application belongs to the technical field of earthquake monitoring, and discloses an adjustable gas collecting device and a hot spring fluid collecting and analyzing method. The adjustable gas collecting device comprises a gas collecting support, a lifting adjusting assembly and a gas collecting assembly. The hot spring fluid collecting and analyzing method comprises the following steps: S1, dipping a gas collecting cover and a gas guide pipe into hot spring water, and collecting hot spring gas through a gas outlet pipe and conveying the hot spring gas to a pretreatment module; S2, stably conveying the gas sample by the pretreatment module, and providing a required gas sample to a TCD chromatographic analysis system; S3, analyzing the chemical components of the gas sample by the TCD chromatographic analysis system, and conveying the chemical component content data of the gas sample to an analysis and prediction model; S4, forming a data set by the analysis and prediction model, extracting features, and constructing an earthquake prediction model; S5, inputting the analysis and prediction system to transmit data outward; and S6, generating an earthquake pre-monitoring report. The application is convenient for stably and accurately collecting hot spring fluid.

The application discloses a method for monitoring and predicting earthquakes based on abnormal electromagnetic satellite plasma observation data, and relates to the technical field of earthquake ionospheric plasma abnormal signal identification, and comprises the following steps: constructing a main earthquake data set and a plasma observation abnormal data set, establishing the space-time correlation characteristics of earthquake events and abnormal disturbance events based on the main earthquake data set and the plasma observation abnormal data set, training a multi-dimensional earthquake monitoring and prediction model based on the space-time correlation characteristics, inputting plasma observation data obtained in real time by an electromagnetic satellite into the trained multi-dimensional earthquake monitoring and prediction model, and obtaining potential dangerous earthquake prediction information. The application establishes the space-time correlation characteristics of earthquake events and ionospheric plasma abnormal disturbance events, trains a multi-dimensional earthquake monitoring and prediction model, and realizes effective identification and limitation of the occurrence time, direction and magnitude of a potential dangerous earthquake based on electromagnetic satellite plasma observation data.

The application provides an orthogonal medium seismic prediction method based on a model parameterization and a step-by-step inversion strategy, relates to the technical field of seismic inversion, and comprises the following steps: constructing a first forward model and a second forward model based on a preset P-wave reflection coefficient model; solving the first forward model by using crack normal plane seismic data to obtain target crack normal plane S-wave modulus and target crack normal plane P-wave velocity; solving the second forward model by using crack plane seismic data to obtain target crack plane S-wave modulus and target crack plane P-wave velocity; and calculating target crack parameters and target P-wave impedance parameters based on the above parameters. The preset P-wave reflection coefficient model contains five to-be-inverted parameters, and compared with a conventional P-wave reflection coefficient model which needs to calculate nine parameters, the number of to-be-calculated parameters is greatly reduced, and the inversion efficiency is improved. The step-by-step inversion mode is adopted to calculate parameters in different directions and properties step by step, the multi-solution property of parameter inversion is reduced, the stability of parameter inversion is improved, and the seismic inversion efficiency is improved.

This disclosure provides a method, apparatus, equipment, and medium for multi-scale seismic prediction of shale fractures, relating to the field of oil and gas geophysical exploration technology. The method includes: calculating seismic coherence attributes based on post-stack seismic data using the Gradient Structure Tensor (GST) algorithm; probabilistically inferring the seismic coherence attributes to obtain the prior distribution of fracture parameters; determining the azimuth elastic impedance characterized by the fracture parameters based on azimuth seismic data and well logging data; establishing a target functional for fracture parameters based on seismic geometric attribute constraints based on the prior distribution of fracture parameters and the azimuth elastic impedance characterized by the fracture parameters; and optimally solving the target functional using a Bayesian direct inversion framework to obtain the prediction result. The embodiments of this disclosure effectively combine the response of seismic coherence and other attribute parameters to fracture development, further constraining the pre-stack seismic inversion of fracture parameters, reducing the ambiguity of fracture parameter inversion, and improving the accuracy of the inversion results.

The present application belongs to the technical field of unconventional natural gas exploitation, and specifically provides a braided river sand body scale prediction method, which solves the problem of the braided river sand body in the existing research area, which is multi-layer superimposed, frequent river channel migration and thin sand body thickness, increases the difficulty of predicting the reservoir scale of seismic data, and urgently needs a new sandstone reservoir scale prediction method and means; according to the characteristics of the braided river and the actual gas field development, the present application screens out the relationship between the sand body thickness drilled by the block well and the corresponding well spacing and two parameters of the river channel swing angle, predicts the river channel sand body scale, perfects the sand body prediction method, establishes a set of braided river sand body scale prediction mode suitable for the whole basin, has good effect, is a good supplement to the seismic prediction of the sand body scale, and provides technical support for the deployment and effective exploitation of the natural gas well.

We provide the system. [Solution] A means for collecting earthquake-related data in real time, Means of obtaining earthquake-related information in real time, A method for analyzing acquired information and predicting earthquake occurrences using a deep learning algorithm, Based on the prediction results, a means of notifying potentially affected users of the warning, A means to achieve integration with the urban environment and automatically manage infrastructure facilities, A means of providing evacuation orders and information on evacuation facilities based on earthquake predictions, A system that includes this.

This invention relates to a method for estimating fracture parameters in wells containing inclined fractures based on inversion-assisted modeling, belonging to the field of geophysics. First, an isotropic background framework containing both soft and hard pores is constructed using inclusion theory. Second, based on an improved Hudson and Schoenberg fracture model and Bond transform, the stiffness coefficient perturbation caused by inclined fractures is established and introduced into the background medium to establish a rock physics model of the TTI medium containing inclined fractures. Then, a step-by-step inversion strategy is adopted. First, the clay content is inverted using density and P-wave and S-wave velocities as known quantities. Then, the inclusion content, fracture density, and fracture dip angle are inverted using P-wave and S-wave velocities as constraints. Finally, the inverted parameters are used to correct the model, and the fracture normal and tangential weaknesses are estimated. This invention, through the combination of refined modeling and step-by-step inversion, provides a new method for estimating fracture parameters and fracture elastic parameters in wells, laying a data foundation for subsequent fracture seismic prediction.

The present disclosure relates to an earthquake prediction network design that is formed by the coordinated operation of an IoT (I)-based radon measurement / prediction network, in which the radon concentrations in outdoor environments and / or in soil gas near active fault lines are continuously monitored from a central location and in which the next radon level can be automatically predicted before measurement by means of the prediction algorithms used, together with seismographs that measure ground movements, and that comprises an early warning system in which the authorities (Y) are automatically informed in cases where earthquake risk is detected.

The application belongs to the technical field of earthquake prediction, and particularly relates to an earthquake prediction method, device, medium, equipment and program product. The earthquake prediction method comprises the following steps: acquiring each item of first earthquake observation data of a target region and each item of second earthquake observation data of a region related to the target region according to required data of a preset earthquake prediction model; determining node values of each basic node in the earthquake prediction model according to each item of the first earthquake observation data and the second earthquake observation data; determining activation probabilities of each type of node in the earthquake prediction model according to each node value; determining earthquake occurrence probabilities of each grade of earthquake of the target region according to the activation probabilities of each type of node; and predicting whether each grade of earthquake will occur in the target region according to the earthquake occurrence probabilities. The probability of each grade of earthquake of the target region is predicted.

The present application belongs to the technical field of rock mechanics and induced earthquake prediction, and particularly relates to a water injection induced earthquake risk prediction and prevention method based on hydraulic diffusion characteristics, comprising: obtaining basic information of a target fault; based on the basic information, injecting fluid upstream of the target fault and synchronously monitoring pore pressure evolution downstream to obtain hydraulic diffusion response data of the target fault; according to the time difference of the upstream and downstream pore pressures and the critical pressure characteristics in the hydraulic diffusion response data, calculating diffusion lag time and fluid overpressure ratio; according to the quantitative correlation of the diffusion lag time and the fluid overpressure ratio with the interface topography of the target fault, inversely obtaining the real contact area ratio of the target fault; and bringing the real contact area ratio into a modified earthquake moment scale law prediction model to obtain the maximum earthquake moment. The present application does not need to drill for coring and indoor testing, can realize in-situ, non-destructive and low-cost characterization of the fault contact state, and at the same time solves the prediction deviation problem caused by the homogeneity assumption of the traditional earthquake moment model.

The method for predicting river sand body by using geological pattern and seismic waveform dual constraints in dense well pattern relates to the field of reservoir geophysics, and solves the problem of uncertainty in interwell prediction caused by strong heterogeneity of reservoir and interference of thin layer in the process of seismic reservoir prediction. The method comprises the following steps: S1, analyzing and evaluating the quality of seismic data to determine the tuning thickness of the target layer; S2, establishing a geological-seismic knowledge base of river sand body; S3, classifying the geological response mode of reservoir based on the established geological-seismic knowledge base of river sand body; S4, establishing a geological-seismic response model of reservoir based on the classification of the geological response mode of reservoir; S5, selecting sensitive seismic attributes of different types of sand body; S6, analyzing and evaluating the prediction effect. The method improves the prediction accuracy of interwell river sand body.