122 results about "Bayesian inversion" patented technology

The invention provides a river water quality parameter supervision method and system based on deep learning. The method comprises the steps of self-calibration multi-source data acquisition, diffusive water quality prediction, extreme water quality parameter simulation, reverse diffusion pollution positioning and water quality parameter intelligent supervision. The invention relates to the technical field of river water quality supervision, in particular to a river water quality parameter supervision method and system based on deep learning. By introducing a graph convolutional neural network and a physical diffusion constraint model, space-time diffusion trend modeling of pollutants in a river channel is realized; constructing an extreme pollution event simulation and attribution mechanism by combining a generative adversarial network and physical verification; further adopting a multi-modal Bayesian inversion model and a graph deconvolution structure to realize accurate source tracing of the pollution source; the system can dynamically sense hydrological changes, construct an adaptive threshold judgment mechanism, realize prediction, tracking and response to pollution risks, and provide efficient and intelligent technical support for river ecological safety management.

The invention relates to the technical field of data processing, and discloses a method and a system for detecting a soil body around a pipeline based on a ground penetrating radar. The method comprises the following steps: performing generalized reflection coefficient modeling on soil layer distribution data to obtain reflection coefficient model data, and calculating the reflection coefficient model data through a Bayesian inversion framework to obtain soil dielectric characteristic data; performing feature parameter extraction on the dielectric feature data of the soil body to obtain feature vector data of the soil body, and performing anomaly identification on the feature vector data of the soil body to obtain data of an abnormal region of the soil body; and performing fuzzy hierarchy analysis on the soil body abnormal region data to obtain risk index data, and performing correlation analysis on the risk index data and the pipeline position feature data to obtain risk assessment data of the soil body around the pipeline. Based on the obtained quantification result of the dielectric parameters of the soil body, the accuracy of abnormal region identification is improved, and the accuracy of detection of the soil body around the pipeline by the ground penetrating radar is further improved.

The invention relates to the technical field of geophysical electromagnetic data exploration, in particular to a fast Bayesian inversion method based on machine learning. Acquiring aviation electromagnetic model data for electromagnetic forward modeling; establishing a candidate forward modeling model for training according to the aviation electromagnetic model information, and obtaining electromagnetic response data obtained by forward modeling; preprocessing the aviation electromagnetic model data and the electromagnetic response data; constructing an optimized neural network, taking the preprocessed aviation electromagnetic model data as input, taking the electromagnetic response data as output, and training the neural network; according to the trained neural network, obtaining a weight and a bias coefficient used for fitting forward modeling calculation, and obtaining an optimized forward modeling fitting matrix; and obtaining forward modeling data according to the optimized forward modeling fitting matrix, establishing a Bayesian inversion model, and performing Bayesian inversion according to the forward modeling data. According to the method, the fitting matrix after machine learning is used for replacing a forward modeling calculation process, and the efficiency of variable-dimension Bayesian inversion can be effectively improved.

The invention discloses an orthogonal fractured reservoir frequency variation AVO inversion and parameter prediction method, and relates to the technical field of exploration geophysics, and the method comprises the steps: deducing and reconstructing a fluid saturation horizontal-vertical orthogonal fractured medium rock physical model based on a multi-group fracture-pore medium Chapman model, realizing fluid saturation rock physical modeling containing two groups of orthogonal fracture media; based on an anisotropic reflectivity algorithm and a fluid saturation horizontal-vertical orthogonal fractured medium rock physical model, realizing frequency variation AVO forward modeling of the fractured reservoir, and calculating a frequency variation AVO reflection coefficient and a synthetic seismic record of the fractured reservoir under the interface reflection model; a frequency-varying AVO inversion theory based on a Bayesian framework is constructed by taking a forward modeling process of the frequency-varying AVO as a drive, and the frequency-varying AVO inversion based on the Bayesian inversion framework is realized and reservoir parameter prediction is carried out by utilizing pre-stack seismic AVO data and introducing a simulated annealing-particle swarm algorithm in an inversion process. The method provides a new method and a new means for fine description and prediction of the fractured reservoir.

The invention provides an aviation transient electromagnetic fast Bayesian inversion method, device and equipment, and relates to the technical field of geophysical signal processing and analysis, and the aviation transient electromagnetic fast Bayesian inversion method comprises the steps: obtaining a resistivity model and the height of a transmitting coil; the resistivity model and the transmitting coil height serve as input data, electromagnetic response data serve as output data, a deep learning network model is trained, and a forward modeling model is obtained; coupling the forward modeling simulation model to a parallel Bayesian inversion framework to generate a target network model; and performing resistivity inversion and quantitative uncertainty analysis on to-be-analyzed aviation transient electromagnetic data based on the target network model to obtain an analysis result. By integrating a deep learning forward simulator into a Bayesian inversion framework, rapid Bayesian inversion and quantitative uncertainty estimation of aviation transient electromagnetic data can be realized, and the inversion efficiency is greatly improved.

The invention relates to the technical field of meteorological remote sensing, in particular to a self-adaptive partition water vapor chromatography method and system based on multi-scale Bayesian prior, and the method comprises the steps: S1, obtaining and processing multi-source observation data of a to-be-analyzed region; s2, constructing a multi-scale grid of the tomographic inversion region; s3, multi-scale representation of the water vapor density is established, and a Bayesian prior constraint model is constructed; s4, constructing a three-dimensional chromatography inversion equation set; and S5, carrying out Bayesian inversion solution. According to the method, global navigation satellite system observation data, meteorological station data and sounding station data are fused, Bayesian prior constraints are constructed, and a multi-scale representation and self-adaptive partitioning method is adopted, so that the number of parameters is effectively reduced, and the stability, precision and calculation efficiency of tomography inversion are improved.

The invention discloses an InSAR (Interferometric Synthetic Aperture Radar) deformation monitoring system for landslide and a method thereof, and relates to the field of geological disaster monitoring. The method has a high-precision deformation monitoring effect, through multi-source SAR data fusion, interference pair screening optimization and multi-source error correction (such as troposphere and ionosphere delay correction), the fidelity of a deformation phase sequence is remarkably improved, and the precision limitation under a complex terrain is overcome; the method has an intelligent geological constraint inversion capability, introduces geological prior knowledge (such as fault and fracture characteristics), enables a deformation field to better conform to the actual geomechanical law through deep learning semantic segmentation and a Bayesian inversion model, and reduces misinformation and missing report. The method has self-adaptive landslide recognition, adopts deformation gradient field calculation and a dynamic threshold segmentation algorithm, automatically recognizes a potential sliding zone boundary, improves the landslide partitioning efficiency, and is suitable for large-range monitoring.

The invention discloses an offshore wind turbine foundation scouring full-period intelligent monitoring method and system based on multi-source data fusion and a dynamic coupling model, and relates to the technical field of intelligent monitoring, and the method comprises the steps: deploying a multi-source monitoring module, and constructing a finite element model; carrying out load calculation and parameter inversion; and training full-cycle dynamic updating of the washout failure function model. According to the method, a self-adaptive Kriging-Bayesian method is adopted, a Bayesian inversion framework and a self-adaptive agent model are fused to solve optimal soil body parameters, full-period model dynamic updating based on dynamic monitoring data is achieved, a multi-fidelity deep kernel learning model is adopted, three types of data are fused into a training set, full-period intelligent monitoring of offshore wind turbine foundation scouring is achieved, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. The dynamic identification of soil parameters is realized by combining a self-adaptive inversion framework with a displacement error closed-loop optimization mechanism, and the technical problem that a traditional static model cannot adapt to the spatial-temporal variability of seabed geology is solved.

The invention relates to the technical field of tunnel defect identification, in particular to a tunnel defect identification method based on a dielectric distribution diagram. According to the method, on the basis of AI rock-soil perspective radar field monitoring, gprMax simulation and laboratory electromagnetic data, a two-dimensional dielectric distribution diagram is generated through variational Bayesian inversion fusion. Through multi-scale spectral clustering and expert knowledge, a potential abnormal region is automatically identified, and then accurate classification and identification of a defect region are realized by adopting graph form constraint propagation and integrating a Transform-graph neural network model. And finally, projecting an identification result to an original image, and generating a visual defect labeling layer and a structured report. According to the invention, high-precision, automatic, visual and structured detection of tunnel structure defects is realized, the intelligent level and risk early warning capability of tunnel safety operation and maintenance are significantly improved, and the digitization and intelligent process of tunnel operation and maintenance management is promoted.

The invention discloses a post-earthquake railway structure state evaluation method and system based on multi-source data fusion. The method comprises the steps that a finite element model is constructed according to the structure of a regional railway network, a simulation data set is generated, a physical information neural network model is trained, and a proxy model library is formed; acquiring multi-source observation data, and performing inversion according to the Bayesian theory, the structural damage parameters of the physical information neural network agent model and the multi-source observation data to obtain complete posterior probability distribution of the damage parameters; according to the method, statistical characteristics of damage parameters are extracted from posterior probability distribution, probability grading is carried out on the damage degree of the structure, driving constraint suggestions are generated according to the combination of damage probability grading and specifications, and Bayesian inversion time is reduced from several days to several hours through a physical information neural network agent model, so that the evaluation efficiency is improved; the output of the Bayesian method is probability distribution, the uncertainty range of the evaluation result is clearly displayed, and the uncertainty is quantified.

The invention provides a crustal stress prediction method and device, electronic equipment and a storage medium, and relates to the technical field of seismic survey. The method comprises the following steps: obtaining observation seismic data of seismic wavelets in a strong VTI medium, and constructing a to-be-inverted parameter matrix based on a PP wave reflection coefficient corresponding to the strong VTI medium; constructing a posterior probability function obeyed by an inversion parameter matrix corresponding to the to-be-inverted parameter matrix based on a Bayesian inversion theory and observation seismic data, and determining a target functional based on a prior probability function and a likelihood function corresponding to the posterior probability function; determining medium density and each stiffness matrix coefficient based on an inversion parameter matrix solving result of the target functional, and determining a flexibility matrix of the strong VTI medium based on each stiffness matrix coefficient; and predicting the ground stress distribution of the target profile in the strong VTI medium based on the medium density and the positive strain matrix and the flexibility matrix corresponding to the strong VTI. Therefore, the crustal stress prediction accuracy under the strong VTI medium is improved.

The invention provides a fracturing crack real-time monitoring method and system based on time-varying electric field dynamic data, and the method specifically comprises the steps: obtaining an electric field data sequence which changes with time and is collected by an electric field sensor disposed in a fracturing work area; for each monitoring time step k in the electric field data sequence, executing the following sequential Bayesian inversion: a, constructing state parameter prior distribution of the time step k by adopting kernel density estimation based on a sample of crack state parameter posteriori distribution of the time step k-1; b, establishing a target posterior probability density function composed of prior distribution, a likelihood function and a physical regularization item; c, in Markov chain Monte Carlo iteration, sampling is carried out on the target posterior probability density function; and d, after iteration is finished, taking a sample set output by the Markov chain as crack state parameter posteriori distribution of the time step k, and extracting crack three-dimensional geometrical morphology and distribution information from the sample set.

The invention discloses a large recreation facility safety detection method and system based on multiple sensors, and relates to the technical field of data encryption, and the method comprises the steps: based on a multi-modal data set, extracting vibration signal time-frequency features through fast Fourier transform and wavelet analysis, and generating a fault analysis report in combination with a support vector machine algorithm; based on the comprehensive characteristic spectrum, carrying out recreation facility health state quantitative evaluation through a Bayesian inversion algorithm, and generating a health state diagnosis report; based on a differential detection scheme, multi-source information fusion decision making is carried out through a D-S evidence theory, and graded safety early warning is generated. According to the method, the time-frequency characteristics of the vibration signals are extracted through fast Fourier transform and wavelet analysis, and a fault analysis report is generated in combination with a support vector machine algorithm, so that accurate analysis of the vibration state of the recreation facility is realized; and the accuracy of fault diagnosis is improved.

The invention is suitable for the field of extra-deep and ultra-deep geotechnical engineering and petroleum engineering, and particularly relates to an extra-deep stratum parameter inversion and fracture prediction method based on Bayesian. By constructing a Bayesian inversion method combining a gradient lifting regression (GBR) machine learning model and a Markov chain Monte Carlo (MCMC) algorithm, deep rock mass mechanical parameter field distribution considering cross correlation among parameters is efficiently obtained, and accurate prediction of a well wall surrounding rock fracture area is achieved. Compared with the prior art, the method has the advantages of being high in prediction precision, wide in application range, high in calculation efficiency and the like, and reliable technical guarantee is provided for safe and efficient construction of ultra-deep drilling engineering.

The invention belongs to the technical field of geophysical exploration, and relates to an underground water magnetic resonance longitudinal relaxation time detection method, which comprises the following steps: laying a magnetic resonance detection coil on the ground, fixing a short emission time, changing a current amplitude, emitting a plurality of short pulses, and collecting a short pulse observation signal generated by each short pulse; fixing a long emission time, re-emitting a series of long pulses with different current amplitudes, and collecting a long pulse observation signal generated by each long pulse; inverting the short pulse observation signal to obtain water content and transverse relaxation time distribution of underground water at different depths; and taking the water content and the transverse relaxation time distribution of the underground water at different depths as prior data of Bayesian inversion, and analyzing the long pulse observation signal by adopting Bayesian inversion to obtain longitudinal relaxation time distribution. According to the invention, a complex excitation sequence form is not needed, and a longitudinal relaxation signal of a short relaxation sample with a fast attenuation speed can be captured. The method is suitable for a high-power scene of field ground magnetic resonance detection.

The invention provides a tunnel activity measurement method with a bidirectional loading demand, and belongs to the technical field of tunnel activity measurement, and the method comprises the steps: collecting a multi-dimensional force signal and a displacement signal, carrying out the digital processing, building a mechanical coupling tensor matrix, and obtaining a preliminary decoupling force component through a condition number adaptive inversion strategy; tensor network high-order correlation modeling and density matrix reforming swarm optimization are utilized for optimization to obtain an accurate decoupling force component, a simulated annealing particle swarm optimization algorithm is combined for solving a non-convex optimization objective function to obtain real mechanical response parameters, defects are identified through ultrasonic detection, and an influence coefficient matrix is established; a Bayesian inversion algorithm is adopted to remove defect influence to obtain corrected tunnel activity parameters, tunnel safety monitoring is finally realized through time sequence analysis and stress redistribution evaluation, and the technical problem of insufficient measurement precision caused by multi-dimensional force signal coupling interference is solved.

The present disclosure provides a shale reservoir fracture and brittleness prediction method based on Bayesian inversion, including: obtaining azimuth partial angle stacking seismic data, azimuth seismic wavelet and model parameter low-frequency model; obtaining prediction results based on the obtained azimuth partial angle stacking seismic data, azimuth seismic wavelet and model parameter low-frequency model, and a preset shale reservoir fracture and brittleness prediction model; wherein, the shale reservoir fracture and brittleness prediction model is established in the following process: deriving an approximate equation of the HTI medium longitudinal wave azimuth reflection coefficient containing a new brittleness indicator factor and fracture density; and establishing a shale reservoir fracture and brittleness prediction model based on the above relationship and the Bayesian AVAZ inversion method. The present disclosure effectively avoids the cumulative error in the indirect parameter conversion process and improves the accuracy of shale reservoir fracture and brittleness prediction.

The invention discloses a port area flexible load millisecond-level cooperative suppression method based on magnetic flux jump prediction, and the method comprises the steps: obtaining the external vibration and electrical data of a transformer, combining the Bayesian inversion of physical constraint, and reconstructing an internal three-dimensional magnetic flux field; based on time sequence evolution of the magnetic flux field, a dual-mode self-adaptive prediction algorithm is adopted, and a magnetic flux jump early warning vector containing jump time, amplitude and position is generated; and according to the early warning vector, through a multi-layer cooperative control strategy of time sequence decoupling, a control instruction for the flexible load of the harbor district is generated and executed. Advanced early warning and millisecond-level active suppression of the potential magnetic saturation risk are realized, and the operation reliability and equipment safety of a harbor district power distribution system are improved.

The invention discloses an ancient building durability monitoring system based on micro-deformation monitoring and machine learning, which is used for predicting the water content of a wood structure of an ancient building through monitoring local wood grain micro-deformation of the wood structure of the ancient building and machine learning based on a multi-Fick coupling unsteady state water transfer model and Bayesian inversion, and further monitoring the durability of the ancient building. According to the method, digital image correlation is used, the sub-pixel precision is considered, and the machine learning model is corrected through temperature and humidity, so that the durability of the ancient building is monitored more accurately.

The invention discloses a small watershed nitrogen and phosphorus load accounting method based on key process parameter calibration, and the method comprises the steps: obtaining the basic geographic hydrological data of a target small watershed, the data comprising the areas of different land utilization types in the watershed, the flow length of a water collection region river channel, and the average flow velocity; based on the hydrology and water quality monitoring data of the long-time sequence of the catchment area, adopting a Bayesian inversion model to quantitatively identify the nitrogen and phosphorus output coefficient of each land utilization type; calculating a soil nitrogen and phosphorus output load in the catchment area, determining a natural reduction coefficient of a nitrogen and phosphorus first-order river, and calculating transport time of nitrogen and phosphorus from a starting point of a river channel of the catchment area to a water outlet and transport time of soil output nitrogen and phosphorus from a tributary estuary to the water outlet of the catchment area; and calculating the water collection area outlet nitrogen and phosphorus load. According to the method, the overestimation error caused by the fact that a production and pollution discharge coefficient method is adopted in a traditional method is remarkably reduced through fusion of'pollution source nitrogen and phosphorus entering the river-remaining soil output-along-the-way natural reduction 'ternary accounting, the accuracy of load accounting is improved, the feasibility and advantages of the technical scheme are verified, and the method is particularly suitable for small watersheds with deficient basic data.

The invention discloses a pre-stack waveform inversion method based on a viscoelastic layered medium, which relates to the field of geophysical exploration of petroleum, and comprises the following steps: carrying out forward modeling based on a viscoelastic reflection matrix method, and accurately simulating the propagation characteristics of seismic waves in the viscoelastic layered medium, thereby effectively improving the inversion prediction precision. According to the method, the elastic characteristic and the attenuation characteristic of the stratified medium are considered at the same time in the seismic wave propagation process, the P-wave speed, the S-wave speed, the density, the P-wave quality factor and the S-wave quality factor can be inverted at the same time, the precision of the inversion result is improved through fine simulation of the underground reservoir medium, and the method has the advantages of being high in practicability and the like. The multi-parameter inversion method has the advantages that strong support is provided for reservoir prediction, a Bayesian inversion framework is adopted, a multi-parameter inversion process is optimized by fusing prior information, robustness and noise immunity of the inversion method are improved, and stability and accuracy of the multi-parameter inversion method in actual seismic data application are guaranteed.

The invention discloses a finite aperture elastic wave underground buried object reconstruction method based on Bayesian inversion, and belongs to the technical field of data processing. The method comprises the following steps of: firstly, performing structured reconstruction on non-phase scattering data collected under a finite aperture condition by utilizing the redundancy and multi-resolution characteristic of framework reconstruction; then, posterior distribution of anomalous body shape parameters is obtained by constructing prior distribution and a likelihood function, efficient sampling is carried out on the anomalous body shape parameters by adopting a precondition Crank-Nicolson parallel annealing (pCN-PT) algorithm, and robust reconstruction of the positions and the geometrical shapes of the underground buried objects is achieved. According to the method, the problem of data missing caused by the finite aperture is effectively solved through frame reconstruction, and the sampling efficiency and convergence performance of Bayesian inversion are improved in combination with the pCN-PT algorithm, so that the precision and reliability of underground buried object detection under the condition of finite aperture elastic waves are remarkably improved.

The present application provides a method and device for directly predicting pore parameters of deep coalbed methane reservoirs, which belongs to the field of coalbed development technology, including obtaining prior data of pore parameters at the target coalbed methane reservoir location and actual observed seismic data; simulating and generating simulated seismic data based on the prior data of pore parameters and the linear mapping relationship between pre-constructed seismic data and pore parameters; performing iterative inversion using a pre-constructed Bayesian inversion objective function based on the actual observed seismic data, simulated seismic data and prior data of pore parameters to determine the minimum objective function value; and directly determining the target pore parameters based on the simulated seismic data corresponding to the minimum objective function value and the mapping relationship between seismic data and pore parameters. The present invention directly inverts the pore parameters through the mapping relationship between pre-constructed seismic data and pore parameters, reducing the cumulative error generated by intermediate conversion and greatly improving the prediction accuracy of the pore parameters.

The invention provides a seismic inversion method based on horizontal well information explicit constraint and a related device. The method comprises the following steps: calculating corresponding wave impedance data by acquiring longitudinal wave velocity curve and density curve data of a whole well section of a horizontal well in a target work area; generating a synthetic seismic record according to the longitudinal wave impedance data corresponding to the vertical well section and the longitudinal wave impedance data corresponding to the inclined well section, and performing well-seismic calibration to obtain a well-seismic calibration result; establishing a logging response forward modeling equation set by combining the wave impedance data; establishing a seismic response forward equation set according to the convolution theoretical model; forming a well-seismic combined vertical wave impedance forward modeling equation set by combining the two equation sets; constructing a low-frequency longitudinal wave impedance model according to the well seismic calibration result, the wave impedance data and preset seismic horizon interpretation; performing seismic inversion on the well-seismic combined vertical wave impedance forward equation set and the low-frequency longitudinal wave impedance model by using a Bayesian inversion theory to obtain a wave impedance inversion solution; therefore, the accuracy of seismic inversion is improved.

The present invention discloses a method for modeling an oilfield area by integrating InSAR three-dimensional deformation and a geophysical model, belonging to the technical field of surface deformation monitoring and physical model inversion. The present invention solves the problem of how to provide a method for acquiring three-dimensional deformation of an oilfield area without sacrificing resolution and accuracy. The present invention comprises the following steps: S1: selecting ascending and descending SAR observation data to obtain vertical and east-west deformation components; S2: obtaining north-south deformation components; S3: using the geophysical model integrating the orthogonal rectangular model as a physical inversion model, and introducing it into the nonlinear Bayesian physical parameter inversion of the underground oilfield; S4: using the extracted vertical, east-west, and north-south three-dimensional displacement fields of the oilfield as inversion observations, and utilizing a nonlinear Bayesian inversion method to achieve modeling of the three-dimensional deformation of the underground oilfield. The present invention provides a favorable basis for analyzing the multi-dimensional deformation mechanism and dynamic spatiotemporal evolution of the oilfield.

The invention relates to the technical field of aviation electromagnetic detection, in particular to a rapid time domain aviation electromagnetic data variable-dimension Bayesian inversion method, system and device and a medium. According to the method, a mapping relation between geoelectric model parameters and time domain electromagnetic response data is constructed by adopting a one-dimensional convolutional neural network according to a deep learning network, and rapid prediction of the time domain aviation electromagnetic response data in a variable-dimension Bayesian inversion process is realized; secondly, during parallel calculation, only one Markov chain is operated in the preheating period, and N Markov chains are executed in parallel after the preheating period is ended, so that the parallel strategy can avoid the problems that the N Markov chains are executed in parallel from the beginning of the preheating period, and the sampling of the Markov chains is not convergent and the calculation time is wasted due to a relatively poor initial state; the condition that Markov chain sampling is not convergent can be found in time in the sampling process of the preheating period, so that the next operation is stopped, and wrong calculation is avoided.

The application provides a fracturing fracture real-time monitoring method and system based on time-varying electric field dynamic data, and specifically, time-varying electric field data sequences collected by electric field sensors arranged in a fracturing working area are acquired; for each monitoring time step k in the electric field data sequences, the following sequential Bayesian inversion is performed: a. based on samples of a fracture state parameter posterior distribution of a time step k-1, a state parameter prior distribution of a time step k is constructed by using kernel density estimation; b. a target posterior probability density function composed of a prior distribution, a likelihood function and a physical regularization term is established; c. in Markov chain Monte Carlo iteration, the target posterior probability density function is sampled; d. after iteration, a sample set output by the Markov chain is taken as a fracture state parameter posterior distribution of the time step k, and fracture three-dimensional geometric morphology and distribution information is extracted from the sample set.

The present disclosure provides a shale lamination density prediction method and related equipment based on statistical rock physics, which relates to the field of geophysical exploration technology. The method includes: performing rock physics intersection analysis on the lamination density in the logging data to determine the sensitive elastic parameters of the lamination density; establishing a linear relationship between the lamination density and the sensitive elastic parameters through statistical analysis; substituting the linear relationship into the normalized azimuthal anisotropic elastic impedance equation to establish a statistical rock physics model; substituting the statistical rock physics model into the Bayesian inversion framework, and directly inverting the lamination density using Bayesian to obtain the final inversion result. According to the embodiment of the present disclosure, the lamination density of the shale reservoir can be directly predicted, and the prediction accuracy is significantly improved compared to the indirect prediction of its anisotropic parameters.

This invention discloses a seismic inversion method for inclined fracture parameters and brittleness indicator factors, comprising the following steps: (1) calculating Young's modulus and brittleness indicator factors; calculating two inclined fracture parameters using fracture density and fracture dip angle; performing interpolation and extrapolation based on seismic stratigraphic data and well logging data to obtain an initial model of Young's modulus, brittleness indicator factors, density, fracture density, and two inclined fracture parameters; (2) extracting azimuth angle seismic wavelets; (3) combining azimuth partial angle superimposed seismic data, azimuth angle seismic wavelets, and the initial model, obtaining Young's modulus, brittleness indicator factors, density, fracture density, and two inclined fracture parameters through Bayesian inversion; calculating the fracture dip angle based on the inverted two inclined fracture parameters. This invention can provide stable and reliable prediction results for brittleness indicator factors, fracture density, and fracture dip angle, which is helpful for conducting seismic characterization of brittleness and inclined fractures in shale gas reservoirs.

The invention relates to the technical field of vehicle-mounted mobile meteorological detection, in particular to a vehicle-mounted mobile meteorological detection system and method. The method comprises the following steps: activating a laser radar system of a vehicle-mounted end to collect back scattering signals of a target air mass corresponding to each collection point on a voyage route, performing inversion based on the back scattering signals to obtain an extinction coefficient of the target air mass, and determining the boundary of the target air mass based on the variation of the extinction coefficient of the target air mass on the voyage route; determining a wind field vertical profile of the target air mass based on the heterodyne spectrum; and obtaining a posterior failure probability of the moving trend of the target air mass based on Bayesian inversion analysis, and predicting the moving trend of the target air mass based on the posterior failure probability. According to the method, the air mass boundary can be accurately determined, the height of the vertical profile of the wind field is calculated, the air mass moving trend is analyzed and predicted through Bayesian inversion, and the accuracy of air mass moving trend prediction is improved.