105 results about "Earthquake prediction" patented technology

The invention relates to the technical field of earthquake prediction, in particular to a three-dimensional earthquake motion field rapid prediction method based on deep learning and physical constraint, and the method comprises the following steps: S1, data collection: obtaining original data related to an earthquake event in real time; s2, data preprocessing and multi-modal data fusion: preprocessing the original data, and fusing the preprocessed original data into multi-modal data; s3, spatial interpolation: realizing seismic oscillation feature interpolation prediction of the epicentral region, and outputting spatial spectrum data; s4, time sequence prediction and physical information optimization: generating a seismic oscillation time domain prediction sequence, and correcting errors by using an SVM model; s5, real-time reasoning and emergency response: realizing real-time minute-level response under the GPU architecture, and outputting three-dimensional seismic motion field data; according to the method, high-precision minute-level prediction of the three-dimensional seismic motion field is realized, and the efficiency and reliability of post-earthquake emergency response are remarkably improved.

The invention provides a TLF-GV signal correlation earthquake magnitude prediction method and system, and a medium, belongs to the technical field of earthquake prediction, and aims at solving the problems that a traditional magnitude prediction model lacks physical constraints, TLF-GV features are not fully utilized, the interpretability is poor, and cooperation with a preorder technology is lacked. Comprising the following steps: extracting a multi-source feature vector of a TLF-GV signal containing a gravity component absolute amplitude, a vibration component relative amplitude and a signal phase; based on the G-R law, constructing the positive correlation physical characteristics log10 (GVCIpeak) and BF * Tanomal of the abnormal intensity and the magnitude of the TLF-GV signal; weighting the features according to a Bayesian factor BF value; fitting according to historical samples to obtain a physical empirical formula of positive correlation of GVCI peak logarithm and magnitude as a physical constraint, and constructing a loss function by taking the physical constraint as a regularization item and combining with a mean square error of a magnitude prediction task; and constructing an XGBoost model, and training according to the training set to obtain a prediction model for earthquake magnitude prediction. According to the method, quantitative prediction of earthquake magnitude is realized based on multi-source features of TLF-GV signals in combination with a physically constrained XGBoost regression model.

The invention relates to the technical field of earthquake monitoring, and discloses a comprehensive earthquake prediction method, which comprises the following steps of: acquiring a continuous micro-motion data sequence to reconstruct an empirical green function sequence, and dividing the empirical green function sequence into a compression phase subset and a stretching phase subset by utilizing a synchronously acquired theoretical earth tide stress phase; respectively extracting a causal branch waveform corresponding to the positive time axis and a non-causal branch waveform corresponding to the negative time axis, and determining a weight index for inhibiting the non-structural interference by calculating a reciprocity residual error between a causal wave velocity offset and a non-causal wave velocity offset; correcting a wave velocity offset mean value by using the weight index to obtain a stress sensitivity coefficient reflecting the stress state of the earth crust medium; according to the method, a physical criterion is established by using an elastic wave propagation reciprocity principle, decoupling of medium attribute change and noise source spatial drift is realized, and visual wave velocity offset induced by environmental interference is eliminated.

The invention discloses an earthquake forecasting and tsunami early warning method and system, and the method comprises the steps: monitoring the earth electromagnetic field data in real time, and recognizing and extracting a regional transient electromagnetic signal which accords with a preset abnormal feature as an earthquake precursor signal; taking the position of the precursor signal as a reference, and predicting the earthquake generation time, the magnitude and the potential influence area based on an earth crust stress wave propagation model; when the early warning condition is met, earthquake early warning information containing risk avoiding guidance is generated and issued, and if the prediction area relates to the coastal area and the earthquake magnitude reaches a threshold value, tsunami early warning information is synchronously generated and issued. The corresponding system comprises a geomagnetic monitoring module, a forecast analysis module and an early warning issuing module. According to the method, pre-earthquake prediction based on the physical precursor is realized, the prediction time is remarkably prolonged, the problems that earthquake and tsunami early warning information is separated and published lags are solved, and the disaster response capability is improved.

The invention provides a TLF-GV signal correlation earthquake three-element joint probability prediction method and system, belongs to the technical field of earthquake prediction, and aims to solve the problems that traditional three-element prediction lacks joint fusion, evidence conflicts are difficult to process, and weights are fixed. Comprising the following steps: extracting physical features of TLF-GV signals, carrying out preorder three-element prediction results and model credibility parameters, splicing the physical features into feature vectors, inputting the feature vectors into a dynamic weight prediction model constructed by a shallow MLP, and outputting time, magnitude and position weights; dividing the three elements into 3 * 3 * 3 = 27'time-magnitude-position 'propositions, generating basic probability assignment (BPA) of each proposition based on weights, and quantifying evidence contradictions through a conflict coefficient K; and adopting a Dempster combination rule to obtain a joint BPA, calculating a mean value of a reliability function and a likelihood function of each proposition as a comprehensive probability, and extracting a maximum probability proposition as a coupling result. According to the method, the scientificity and practicability of strong earthquake short-term and temporary prediction are remarkably improved.

The invention provides an earthquake quantitative prediction method for the compaction effect intensity of carbonate rocks, and the method comprises the following steps: (1) carrying out the statistics and analysis of logging data and core analysis data of a compacted stratum in a to-be-analyzed region, and building a fitting relation between the apparent compaction rate and the longitudinal wave speed; (2) performing phase-control frequency-division inversion in combination with the seismic response characteristics, and then calculating and analyzing the actual longitudinal wave speed of the to-be-analyzed region; and (3) determining the distribution of the apparent compaction rate according to the fitting relation between the apparent compaction rate and the longitudinal wave speed obtained in the step (1) and the actual longitudinal wave speed obtained in the step (2). According to the carbonate rock diagenesis strength earthquake prediction method based on the apparent compaction rate, the problem that quantitative prediction of the carbonate rock compaction strength is difficult is solved, the distribution characteristics of different compaction strength in space are defined, and the exploration and development success rate can be improved.

The invention provides a gas field reservoir lithology earthquake prediction method based on CCIDI cleaning and TransMSAE, and the method comprises the steps: constructing a CCIDI cleaning module, and employing a well-divided lithology-divided strategy: employing IQR to remove statistical anomalies, employing DBSCAN to remove boundary noise, employing Isolation Forest to remove high-dimensional residual noise, and forming a high-quality logging data set; the method comprises the following steps: constructing a TransMSAE model: pre-standardizing a Transform encoder to capture long-range dependence, and providing robust time sequence representation; multi-scale convolution is introduced into the MSCCAM to extract a local-global mode, and cross attention is fused to improve complex deposition dynamic perception; aMFEM gating residual self-adaptively enhances minority class features, and minority class recognition is remarkably improved; designing NAFL-ProtoLoss mixed loss: NAFL focus inhibition easy-to-classify samples, ecological niche punishment over-confidence prevention, ProtoLoss zoom-in class inward pushing-out between classes, and optimization of unbalanced classification; finally, training and reasoning are carried out based on the model, and high-precision lithology prediction is achieved. The method provided by the invention has high generalization and accuracy, and has excellent reservoir prediction performance in a complex geological environment.

The invention provides a geological disaster identification method based on seismic wave dynamics and kinematics characteristics, the geological disaster is mountain torrent or debris flow, and the method comprises the following steps: collecting seismic signals in a geological disaster potential risk area; the seismic signals are preprocessed; extracting early warning parameters from the pre-processed seismic signal, wherein the early warning parameters comprise a long and short time window energy ratio, a time-frequency spectrum parameter, a power spectrum density and a seismic signal duration; establishing an earthquake prediction model of the single-measuring-point geological disaster according to the extracted early warning parameters; fusing the earthquake prediction models of the geological disasters at multiple measuring points, and judging whether the earthquake signals are earthquake signals triggered by the geological disasters or not; and when it is judged that the seismic signal is triggered by the geological disaster flow, real-time early warning information issuing is carried out on the downstream risk area. The method can be applied to monitoring and early warning of geological disasters caused by artificial or natural activities such as mountain torrents, dam break, landslides, collapse and the like, and has wide engineering technology application and scientific research prospects.

The application discloses a coalbed methane enrichment area prediction method based on multiple geological parameter constraints, determines a research area, analyzes geological features of the research area to determine lithology, physical property features and elastic parameters of rock strata, predicts geological elements of a coalbed methane enrichment area of the research area, and establishes a nonlinear mapping relationship between main geological parameters of the coalbed methane and enrichment characteristics of the coalbed methane, namely, a geological attribute discrimination mode of the coalbed methane enrichment area, by means of artificial neural network method and constraint of the geological parameters. The method for predicting the coalbed methane enrichment area under the constraint of multiple geological parameters simultaneously controls the convergence direction of the solution of the enrichment area by multiple mutually irrelevant geological parameters, reduces the prediction scale of the enrichment unit to obtain an optimal solution, avoids the uncertainty of single parameter prediction, improves the accuracy of the prediction result, and solves the technical problem that the method for predicting the coalbed gas content by single seismic attribute or parameter in the prior art has strong multiple solutions, thereby leading to inaccurate prediction results.

The invention discloses an earthquake monitoring and early warning method and system based on an earthquake precursor, and relates to the technical field of earthquake forecasting, and the method comprises the steps: collecting the core data and auxiliary state data of the earthquake precursor, marking a sample label, and forming a training data set; establishing a core parameter screening model, and training the core parameter screening model by using the training data set to obtain core parameters; constructing a typical working condition library, calculating an Euclidean distance between a real-time data point and a historical working condition sample point, selecting first K neighbor points, and returning a working condition category with the highest frequency as a current operation working condition; corresponding anomaly prediction models are established according to the different operation conditions, and anomaly types under the different current operation conditions are predicted according to the anomaly prediction models; an EWI index is calculated through the core parameters, and when the EWI index is larger than an index threshold value, earthquake early warning is triggered; otherwise, continuously monitoring. According to the invention, real-time early warning of the earthquake precursor is realized under the condition that the equipment is abnormal.

The invention discloses a TLF-GV-based earthquake prediction signal anomaly detection method and system, and relates to the technical field of earthquake monitoring and prediction, and the method comprises the steps: collecting TLF-GV original time sequence signals; decomposing the TLF-GV original time sequence signal to obtain an IMF component; a gravity-related IMF component and a vibration-related IMF component of a frequency band corresponding to the TLF-GV original time sequence signal are screened out from the IMF components, and noise reduction and reconstruction are carried out respectively; performing physical enhancement processing on the reconstructed dynamic gravity signal and vibration signal; calculating a gravity-vibration contribution index GVCI and a Bayesian factor BF; effective abnormal points are screened out through three-level abnormal detection; according to the method, aliasing-free separation of dynamic gravity and vibration is realized, the signal separation precision is improved, a mode number does not need to be preset, and the method adapts to the aperiodic characteristics of TLF-GV signals.

The invention provides a coal seam high-precision identification and positioning method based on dynamic modeling and real-time updating to solve the problems that coal seam conditions are complex and changeable, data processing of a coal mining guiding system is insufficient in data precision, data visualization is not comprehensive enough, and a real-time dynamic monitoring system is not perfect enough. Through collection, arrangement and analysis of related data of a working face, geostatistics inversion prediction of a coal seam is carried out, and then geological guarantee and coal mining guidance system platform construction are carried out. On the basis of collected related geological data and provided three-dimensional earthquake prediction coal seam interface data, fine modeling of an initial three-dimensional geological model is carried out, the sampling precision of the model is improved, and then high-precision geological model data is imported into a constructed geological guarantee and coal mining guidance system platform. By tracking the mining condition of a coal mining machine, collecting and returning coal seam top and bottom interface data in real time, geological tracking and updating of a coal seam interface are realized by utilizing geological guarantee and an internal algorithm of a coal mining guidance system, and the difference and regularity between the actually measured coal seam interface and predicted coal seam model data are compared and analyzed, so that the coal seam interface is accurately and accurately measured. And correcting and updating the subsequent coal mining route of the coal mining machine in real time. According to the method, the coal seam can be accurately positioned, the coal mining scheme can be quickly updated and optimized, the path planning precision of the coal mining machine is remarkably improved, geological risks are reduced, and intelligent mining is promoted.

The present application provides a kind of reservoir brittleness index seismic prediction method, device, computer readable storage medium and electronic equipment, the method comprises: according to the relationship of the elastic parameter of target area rock with the change of pressure Determine the relationship of the reservoir brittleness index of target area with the change of effective confining pressure;By inversion, determine the reservoir brittleness index data volume of target area without considering the influence of effective confining pressure;Based on the well logging data and seismic data of target area, calculate the formation pressure of target area, and determine the effective confining pressure data volume of target area according to the formation pressure;Based on the reservoir brittleness index data volume of target area without considering the influence of effective confining pressure, the effective confining pressure data volume of target area, according to the relationship of the reservoir brittleness index of target area with the change of effective confining pressure, determine the reservoir brittleness index data volume of target area considering the influence of effective confining pressure.The technical scheme of the present application improves the accuracy and rationality of reservoir brittleness index seismic prediction, especially provides technical support for guiding deep shale gas well site deployment and well trajectory design.

A system and methods are disclosed. The method includes obtaining a seismic dataset including a plurality of recorded multiple events, generating a predicted multiple model using a multiple prediction method and the seismic dataset, and estimating a set of initial matching filters using a matching method, to match the plurality of estimated and recorded multiple events. The method further includes generating a tensor field based on the predicted multiple model, determining a set of structure-oriented matching filters based on the set of initial matching filters and the tensor field, generating a filtered multiple model based on the predicted multiple model and the set of structure-oriented matching filters, and generating a multiple-attenuated seismic dataset based on the filtered multiple model and the seismic dataset, forming a seismic image based, at least in part, on the multiple-attenuated seismic dataset, and determining a location of a hydrocarbon reservoir based on the seismic image.

The invention discloses an earthquake numerical value prediction method based on kernel density and machine learning, and belongs to the technical field of earthquake prediction. The method comprises the steps of performing magnitude standardization and energy association processing on original seismic directory data to form standard seismic directory data, performing completeness processing on the standard seismic directory data to determine a minimum complete magnitude, and performing screening to obtain a complete seismic directory; determining a first bandwidth and a second bandwidth for the complete seismic directory through a nuclear density bandwidth sensitivity test, calculating seismic frequency and energy nuclear density distribution of the target area in combination with a time and magnitude sliding window, and obtaining nuclear density anomaly distribution data by making a difference between the seismic frequency and energy nuclear density distribution and long-term average nuclear density distribution; and inputting the kernel density abnormal distribution data of the target magnitude range under multiple time scales into a pre-trained random forest model, and outputting an occurrence prediction result of a target magnitude earthquake in the target region. According to the method, the spatial accuracy and timeliness of earthquake prediction are improved, and technical support is provided for earthquake disaster risk prevention and control.

The invention belongs to the technical field of oil-gas exploration and development, and provides a deep carbonate reservoir azimuth pre-stack depth domain earthquake prediction method and device, and the method comprises the steps: employing OVT domain pre-stack pre-stack depth domain trace gather data, combining with the stress distribution characteristics of a target region, generating sector azimuth pre-stack depth domain trace gather data, retaining azimuth anisotropy information, and obtaining a deep carbonate reservoir azimuth pre-stack depth domain earthquake prediction result. And optimal orientation sensitive attribute pairs and multi-transformation coefficient solving are carried out, the porosity of the deep carbonate reservoir is predicted, and deep carbonate reservoir prediction is completed. The method mainly comprises the following steps: generating a sector azimuth pre-stack depth migration gather; performing sector azimuth pre-stack depth domain gather seismic attribute processing; preferably selecting sensitive seismic attribute pairs; solving multiple equation coefficients; and calculating a reservoir porosity three-dimensional data volume, and completing earthquake prediction of a favorable reservoir. The method not only solves the problem of resolution reduction caused by high-frequency information loss of a time domain, but also facilitates characterization of anisotropy information of the reservoir, can predict the anisotropy thin reservoir, improves thin layer identification precision, and effectively guides well location deployment.

The invention discloses a tectonic geochemical earthquake precursor anomaly discrimination index extraction method and device, and the method comprises the steps: obtaining monitoring data of a monitored target fault zone, carrying out the analysis of the monitoring data based on a tectonic geochemical method, determining the cross-fault soil gas spatio-temporal evolution characteristic data of the monitored target fault zone, and carrying out the analysis of the cross-fault soil gas spatio-temporal evolution characteristic data of the monitored target fault zone. And according to the monitored cross-fault soil gas spatio-temporal evolution characteristic data of the target fault zone and the response change relationship of the cross-fault soil gas concentration intensity of the fault zone to the earthquake, extracting an earthquake precursor anomaly discrimination index. Monitoring data of a target fault zone are analyzed based on a tectonic geochemical method, and then the fault zone is analyzed according to the analyzed cross-fault soil gas spatio-temporal evolution data and the response change relation of the cross-fault soil gas concentration intensity of the fault zone to an earthquake, which is obtained through a solid body earthquake-inducing mode. According to the invention, data quantification of the earthquake precursor anomaly discrimination index can be realized, the problem that only the earthquake precursor anomaly index can be qualitatively researched at present is solved, and the accuracy of earthquake prediction is improved.

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.

The present application relates to the field of geophysical exploration technology, and particularly relates to a method for well leakage early warning by using seismic prediction results, comprising: basic data acquisition, regional geological condition analysis, seismic data preprocessing, small fracture and fracture-vug body seismic fine delineation, and shadow relief display of the delineation result. The present application improves the basic data quality by introducing anisotropic diffusion and three-dimensional multi-level median joint filtering technology, and carries out multi-attribute fusion based on adjustable parameters by combining pre-stack multi-azimuth frequency attenuation gradient fracture prediction and post-stack structural coherent tensor, finally realizes spatial display of the multi-attribute fusion result by using shadow relief technology, improves the accuracy of small fracture and fracture-vug body delineation, and more directly shows the spatial form of the fracture and fracture-vug body, which can effectively guide well location design, drilling design and drilling trajectory optimization.

The invention discloses a maximum aftershock prediction method based on online enhancement, and belongs to the technical field of earthquake prediction. The core of the method is that a personalized prediction model is dynamically generated for a current event through online retrieval of similar historical sequences and data enhancement aiming at a newly occurring main earthquake. Firstly, a historical seismic database is constructed from a global seismic directory, and an initial prediction model is trained. When a new main earthquake occurs, an online process is triggered immediately: based on the characteristics of the new main earthquake, K most similar sequences are quickly retrieved from historical data; then, the similar sequence data are enhanced (such as noise adding and interpolation), so that a diversified enhanced training set is constructed; and finally, performing rapid fine adjustment on the initial model by using the enhancement set to obtain an optimization model for the current main earthquake, and predicting the maximum aftershock magnitude. According to the method, the limitation of one-time cutting of the existing static model is overcome, the problem of inaccurate prediction in an earthquake small sample scene is effectively solved, and the accuracy, robustness and timeliness of prediction are remarkably improved.

The invention relates to a dual-pore structure factor permeability earthquake prediction method and system, a medium and equipment. The method comprises the following steps: acquiring logging data, core experiment data and earthquake data of a target area; performing inversion based on the rock physical model to obtain pore structure parameters and a dynamic soft / hard pore aspect ratio; performing model construction according to the porosity, the pore structure parameters and the dynamic soft / hard pore aspect ratio to obtain a multivariate nonlinear regression model; training and verifying the multivariate nonlinear regression model and the neural network by using a training set in the logging data to obtain a permeability regression model; and carrying out inversion based on the seismic data to obtain inversion data, and carrying out prediction on the inversion data and the permeability regression model to obtain a permeability body. According to the method, three-dimensional quantitative prediction of the permeability of the low porosity and permeability reservoir is realized on the basis of the double-pore structure factors in combination with the pre-stack seismic inversion and neural network technologies, the prediction precision can be remarkably improved, and reliable basis and technical support are provided for efficient development of oil and gas reservoirs.

The invention discloses a short critical strong earthquake occurrence time prediction method and device, a medium and equipment, and relates to the technical field of earthquake prediction. The method comprises the following steps: performing standardized preprocessing on an atmospheric tidal gravity signal in a preset time window, and after an atmospheric tidal gravity abnormal event is detected, inputting a plurality of target days into a pre-constructed prediction model respectively to obtain the probability of strong shock in each target day after the atmospheric tidal gravity abnormal event occurs; the prediction model is obtained by training according to statistical correlation characteristics between the occurrence time of the atmospheric tidal gravity abnormal event and the occurrence time of the strong earthquake; the strong earthquakes represent earthquakes of which the magnitude is greater than a preset threshold value; and determining a strong earthquake occurrence time prediction result according to the probability of occurrence of the strong earthquake in each target day after the abnormality occurs. According to the method, quantitative probability prediction of the strong earthquake occurrence time is realized, and the method has the advantages of interpretability, calibration and online updating.

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.

The invention relates to the technical field of oil exploration and development, and discloses a stratum collapse pressure earthquake prediction method and device based on rock mechanics nonlinear variation, and the method comprises the steps: carrying out the nonlinear fitting of compressive strength with rock cohesion and an internal friction angle through a triaxial mechanics experiment, and obtaining a corresponding fitting relation; then, through seismic inversion, a rock mechanical attribute body, an overlying stratum pressure body, a pore pressure body, a maximum horizontal principal stress body, a minimum horizontal principal stress body, and three-dimensional space rock cohesion distribution and internal friction angle distribution are obtained through calculation; and finally, according to the pore pressure body, the maximum horizontal principal stress body, the minimum horizontal principal stress body, the three-dimensional space rock cohesion distribution and the three-dimensional space rock internal friction angle distribution, predicting stratum three-dimensional collapse pressure body data in combination with a collapse pressure calculation model. By means of the method, the formation collapse pressure can be predicted more accurately, geological disasters caused by improper drilling operation can be reduced, and therefore the geological environment is protected, and potential influences on the earth surface and underground water resources are reduced.

The invention discloses a method and device for predicting artificial fractures in oil reservoir development, and belongs to the technical field of oil reservoir development fracturing. The method comprises the following steps: constructing an artificial fracture theoretical model according to well drilling and oil testing data of a target block; obtaining an earthquake elastic parameter body and a stress field parameter body according to the earthquake data of the target block in combination with logging data, logging data and rock physics related test parameter data of the target block; and correcting the artificial fracture theoretical model based on the earthquake elastic parameter body and the stress field parameter body, and taking the corrected artificial fracture theoretical model as an earthquake prediction artificial fracture model. The method can realize fine prediction of artificial fractures, and can effectively guide development and production of oil reservoirs.

The invention discloses a method for determining a geologic horizon of a PSV wave seismic event, and relates to the technical field of petroleum and natural gas exploration and development, and the method comprises the following steps: S1, carrying out the rotation orientation processing of a horizontal component and a vertical component; s2, extracting an upgoing wave field of the PSV wave; s3, non-zero offset PSV wave imaging and non-zero offset PSV wave corridor superposition are carried out; s4, determining the geologic horizon of the PSV wave corridor stacked section; and S5, determining the geologic horizon of the three-dimensional seismic PSV wave event. According to the method, a high-precision extraction method of the non-zero offset PSV upgoing wave field is innovated, and effective separation of the complex wave field is ensured; meanwhile, a new corridor stacked section manufacturing method and a new geologic horizon determining method are created, the situation that logging curve missing and environmental quality affect the reliability of geologic horizon determination is avoided, the problem that calibration difficulty is large due to the fact that zero-offset PSV wave signals are weak is solved, more reasonable PSV wave geologic horizon determination can be obtained, and the accuracy of geologic horizon determination is improved. And a basic guarantee is provided for multi-wave multi-component oil gas earthquake prediction application.

The invention belongs to the technical field of petroleum and natural gas seismic exploration, and particularly discloses a deep learning-based micro fault displacement seismic calculation method, device and equipment and a medium. The method provided by the invention sequentially comprises the following steps: S1, calculating a micro fault displacement; S2, depicting a micro-amplitude structural form of a target stratum; S3, finely explaining three-dimensional seismic data; S4, carrying out deep learning to predict a micro fault; the invention provides a new earthquake prediction method for calculating the micro fault displacement by utilizing earthquake data, actual drilling fracture statistics and deep learning to predict the micro fracture and accurately predict and calculate the fault displacement by fracture modeling, can quantitatively predict the micro fault displacement, improves the drilling efficiency and the shale gas recovery rate, and has a good application prospect. The method is suitable for quantitative prediction of the tiny fault displacement in shale gas exploration and development.

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.

The application discloses a kind of earthquake precursor information extraction method, device, equipment and storage medium, it is related to earthquake monitoring technical field, including the following steps: the dynamic gravity signal of the region to be measured is continuously collected;The amplitude of dynamic gravity signal and abnormal early warning threshold are different to obtain the first difference, the amplitude of dynamic gravity signal and abnormal noise threshold are different to obtain the second difference;When the first difference and the second difference are in abnormal interval, start abnormal detection time window to detect the amplitude of dynamic gravity signal, when the duration reaches the set value, the number of times that the amplitude of dynamic gravity signal is in abnormal interval is counted, and the total number of times counted is used as early warning number;If early warning number is greater than set number, calculate the dispersion coefficient of the amplitude of dynamic gravity signal in abnormal interval, and output the amplitude data with dispersion coefficient less than 1 as earthquake precursor information.The application first collects the dynamic gravity signal related to earthquake precursor, then sets multiple control variables, judges the disturbance signal in dynamic gravity signal through multiple control variables, and obtains the judgment result, i.e., earthquake precursor information.The method of the application can accurately obtain earthquake precursor information, and provide research data for earthquake prediction work.