13 results about "Bayesian inversion" patented technology

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.

This invention relates to the field of numerical simulation and computational technology for seismic wave propagation, and discloses a method and apparatus for generating seismic ground motions based on target spectra and Green's functions. It aims to address the difficulty in achieving a balance between physical consistency, computational efficiency, and spectral compatibility in existing methods. The scheme mainly includes: preprocessing environmental noise records and extracting empirical Green's functions through unsupervised clustering; constructing a spatially continuous propagation tensor by performing depth correction and gradient interpolation based on surface wave eigenfunctions; discretizing the kinematically finite fault model into sub-source units and generating long-period seismic ground motions including path effects using propagation tensor convolution; optimizing source parameters through Bayesian inversion using the GMPE target spectrum as a constraint; and finally generating high-frequency components and fusing them with the long-period waveform to obtain a broadband seismic ground motion time history. This invention achieves a unification of physical propagation mechanisms and statistical spectral constraints, significantly improving computational efficiency while ensuring spectral compatibility, and is particularly suitable for basin areas.

This application provides a dynamic simulation system and method for coupled soil organic carbon and inorganic carbon. The system utilizes an internal observation data input layer, a mechanistic model layer with a coupled carbon model deployed in the system, a Bayesian inversion layer, and a posterior analysis and application layer. The coupled carbon model is used to describe the co-evolution process of organic carbon and inorganic carbon. Thus, the system provides an automated and reproducible modeling framework from observation → mechanistic constraints → posterior learning → future prediction → uncertainty quantification. It realizes a closed-loop process of parameter estimation, mechanism analysis, and scenario prediction of the coupled carbon model, thereby obtaining a carbon change prediction system for experimental sites with mechanistic interpretability and risk quantification capabilities, which can improve the prediction accuracy and decision interpretability of carbon change.

The application discloses a full waveform inversion method based on a deep generative model and a stochastic gradient variational inference, and belongs to the technical field of seismic exploration data processing. The application constructs a Bayesian inversion framework, adopts a deep generative model to reduce high-dimensional velocity modeling to low-dimensional hidden space, introduces a convolution type robust loss function to improve the resistance to noise and phase mismatch, realizes efficient posterior approximation and uncertainty quantification through the stochastic gradient variational inference, designs a multi-scale special network structure to balance the inversion stability and resolution, and realizes physical driving gradient calculation in combination with the adjoint state method to ensure that the inversion conforms to the wave field propagation law. Through the above process, the computational amount can be significantly reduced, the robustness and precision can be improved, the uncertainty distribution map can be simultaneously output to quantize uncertainty, and the application is suitable for large-scale seismic data high-precision velocity modeling and geological imaging.

This invention discloses a method, apparatus, and medium for cross-dimensional Bayesian inversion of Rayleigh surface wave dispersion curves, relating to the field of surface wave exploration technology. This invention introduces a Dix-type physically guided soft prior, using a reference shear wave velocity profile as a probability anchor point to construct a Gaussian probability field around this profile. This guides the cross-dimensional Bayesian inversion to quickly enter a high-probability physically reasonable region in a probabilistic sense, thereby upgrading the Dix non-iterative inversion results from "fixed initial values / hard constraints" to "Gaussian probability anchor point soft priors." Simultaneously, based on the formation depth value corresponding to the subsurface shear wave velocity parameters to be inverted, a depth-related prior standard deviation of the Gaussian probability field is set to ensure the soft prior operates within the physical boundaries. This makes the final inversion results naturally biased towards the physically reasonable model region in a probabilistic sense, and physical boundary constraints are applied, eliminating systematic biases in the Dix inversion and ultimately obtaining inversion results consistent with actual geology.

This invention discloses a Bayesian inversion extraction method for the equilibrium signal of wide-span altimeter data. The method involves acquiring and preprocessing sea surface height anomaly sequences from radar interferometers and nadir altimeters. A normalized sine square window function is applied for windowing, and multidimensional spatial averaging is used to estimate the one-dimensional wavenumber power spectrum. A piecewise power law-based equilibrium signal spectrum model and a noise spectrum model constrained by dynamic sea state are constructed, and the set of spectral parameters is extracted through logarithmic domain weighted least squares fitting. A set of spatial covariance matrices is constructed using cosine integral transform and Abelian forward and inverse transforms. A graphics processor is scheduled to perform batch matrix decomposition and singular fault-tolerant regularized inversion to solve for the posterior mean vector and posterior covariance matrix of the target equilibrium signal. Window fusion and index mapping are applied to fill the gaps in nadir observations. Geostrophic dynamics parameters are calculated, uncertainty quantification is performed based on the linear error propagation law, and the knowledge base is updated based on the exponential moving average algorithm. This invention achieves suppression of observation noise and physical filling of observation gaps, improving the adaptability of the inversion system to environmental changes while preserving non-Gaussian dynamic characteristics.

The application discloses a reservoir quantitative prediction method, electronic equipment, a storage medium and a device. The method comprises the following steps: establishing a double-factor control initial model based on seismic facies attribute information, fracture attribute information and low-frequency framework information of a target layer; performing synchronous compression transformation frequency division on seismic data of the target layer to obtain a plurality of different frequency band data bodies; sequentially performing Bayesian inversion on each frequency band data body in the order from low to high based on the double-factor control initial model and the frequency band data bodies; iteratively inverting the next frequency band data body based on the inversion result of the previous frequency band data body as the initial constraint; and completing the Bayesian inversion of all the frequency band data bodies to complete reservoir quantitative prediction. The application can effectively reduce the interference caused by horizontal layering seismic reflection on inversion, improve the accuracy of reservoir quantitative prediction, enhance the reservoir detail accuracy and lateral heterogeneity description capability, and provide a reliable reference for high-quality reservoir development area description and well location deployment.

This invention discloses an online intelligent assessment system for urban land value based on big data analysis, comprising: a data normalization module for acquiring and preprocessing multi-source heterogeneous data; an association mapping module for performing temporal registration, using data components as graph nodes and calculating association weights to construct a value association graph; a propagation solution module for locating nodes to be assessed, iteratively updating access probabilities along node connections to obtain an association propagation state sequence; an evolution and recombination module for performing multi-scale time window rearrangement, elevating to a linear evolution space and recursively recombinating to obtain the value evolution state; an inversion assessment module for variational Bayesian inversion, filtering out posterior state components and retaining posterior parameters to obtain the value assessment result; and an incremental update module for acquiring feedback data and incrementally updating the value association graph. This invention enables online intelligent assessment of urban land value, improving the accuracy of value assessment.

The application discloses a kind of underground engineering construction scheme dynamic optimization method, system and computer readable storage medium, including integration geometry information, geology parameter space distribution, supporting structure parameter and history monitoring data constructs initial digital twin model;In construction process, the posterior distribution of surrounding rock mechanics parameters is dynamically revised based on Bayesian inversion method using real-time monitoring data;Define trigger threshold and comprehensive trigger index, when inversion parameter deviation exceeds threshold, automatically trigger scheme dynamic adjustment;According to the weight of the comprehensive trigger index dynamic adjustment geology adaptability index, make the scheme optimization result more close to the current actual geological conditions;While outputting the adjusted scheme, automatically generate transition path and standardized construction instruction and issue to field management system, form "monitoring→inversion→adjustment→construction" full-automatic closed loop.The application improves the construction safety and scheme adaptability of tunnel reconstruction and expansion project.

The wheel-soil model small sample phased Bayesian inversion method solves the problems of serious parameter coupling, poor distinguishability and difficult quantification of uncertainty in the wheel-soil model parameter inversion process under small sample conditions, and belongs to the field of planetary exploration robot ground mechanics parameter identification. The model distinguishability is improved through parameter reconstruction, and the inversion process is divided into multiple stages according to the slip working conditions: first, the pressure-related parameters are estimated using low-slip data, then the shear-related parameters are estimated using high-slip data, and the uncertainty is propagated across stages. Through the above mechanism, the influence of parameter coupling can be effectively reduced under small sample conditions, and the parameter estimation results with physical interpretability and containing confidence information can be achieved, thereby providing reliable support for the motion control and environment adaptation of the exploration vehicle.

This invention provides a method for igneous rock facies classification and prediction based on multi-physics discriminant factors, relating to the field of oil and gas field exploration and development technology. The method includes: S1: Constructing a multi-dimensional facies classification model based on diagenesis, integrating lithology index and structural maturity index to quantitatively classify geological facies; S2: Performing principal component analysis on well logging curves to select sensitive well logging curves and construct a sensitive well logging dataset; S3: Constructing rock physical facies factors through Fisher discriminant analysis; S4: Projecting known facies samples onto the rock physical facies factor space, training a classification model using a support vector machine algorithm, and generating a facies identification map; S5: Substituting target well data into the model to complete single-well facies identification; S6: Establishing the correlation between rock physical facies factors and seismic elastic parameters, inverting the seismic data volume into a three-dimensional attribute volume of rock physical facies factors based on a Bayesian inversion framework, fusing them to generate a three-dimensional facies model, thus realizing facies prediction from well point to three-dimensional space.

This invention relates to the field of numerical simulation and computational technology for seismic wave propagation, and discloses a method and apparatus for generating seismic ground motions based on target spectra and Green's functions. It aims to address the difficulty in achieving a balance between physical consistency, computational efficiency, and spectral compatibility in existing methods. The scheme mainly includes: preprocessing environmental noise records and extracting empirical Green's functions through unsupervised clustering; constructing a spatially continuous propagation tensor by performing depth correction and gradient interpolation based on surface wave eigenfunctions; discretizing the kinematically finite fault model into sub-source units and generating long-period seismic ground motions including path effects using propagation tensor convolution; optimizing source parameters through Bayesian inversion using the GMPE target spectrum as a constraint; and finally generating high-frequency components and fusing them with the long-period waveform to obtain a broadband seismic ground motion time history. This invention achieves a unification of physical propagation mechanisms and statistical spectral constraints, significantly improving computational efficiency while ensuring spectral compatibility, and is particularly suitable for basin areas.