56 results about "Three dimensional inversion" patented technology

The invention relates to the field of geological exploration, in particular to an intelligent prospecting prediction method and system for an ore deposit three-dimensional geological model, a terminal and a medium. The method comprises the steps of obtaining multi-source geological data of a target area to construct an ore deposit three-dimensional geological model, inputting the ore deposit three-dimensional geological model into a trained intelligent prospecting prediction model for ore-forming potential analysis, and optimizing the model or generating an intelligent prospecting prediction scheme according to a predicted resource quantity confidence degree condition; when the model is constructed, three-dimensional inversion calculation, element anomaly field construction and the like are carried out, the model can be optimized through transfer learning, exploration data can be accessed in real time to realize dynamic updating, and a multi-target optimization model is established to output an exploration scheme; the invention also relates to a corresponding system, a terminal and a storage medium. The method achieves the technical effects of improving the accuracy and efficiency of prospecting prediction, dynamically optimizing the model according to the actual situation, reasonably planning the exploration scheme, and reducing the exploration cost and risk.

The invention discloses a seismic data constrained direct current method three-dimensional inversion method, which relates to the field of geophysical exploration and comprises the steps of processing seismic data and performing inversion processing on resistivity data. The seismic wave layer velocity information is used for constraining high-density electrical method inversion, so that a supplement effect to a certain degree can be achieved, three-dimensional seismic image information can be used for supplementing the resolution ratio of resistivity inversion, the boundary of an underground electrical anomalous body is reflected, and meanwhile, through the comprehensive geological-geophysical information, the electrical anomalous body can be accurately determined. And boundary features of the anomalous body can be further depicted. Seismic data constraints are applied to three-dimensional resistivity inversion, numerical simulation and inversion processing are performed on electrical method data under rugged topography according to finite volume method numerical simulation and a Gaussian-Newton inversion method, and meanwhile, seismic anisotropic velocity tensor constraints are introduced to perform inversion, so that the problem of multiplicity of solutions of inversion of a single method is reduced, and the inversion accuracy is improved. A more accurate three-dimensional underground electrical structure is obtained, and the resolution of inversion to a longitudinal boundary is improved.

The invention discloses an electromagnetic detection data efficient three-dimensional inversion method based on operator learning, and belongs to the technical field of geophysical inversion, and the method comprises the steps: constructing an operator learning data set which comprises a plurality of electromagnetic forward modeling models and forward modeling responses of the electromagnetic forward modeling models; performing aviation electromagnetic frequency domain forward calculation training based on the operator learning data set by using a DeepONet network to obtain a trained aviation electromagnetic three-dimensional forward operator; inputting the initial uniform half-space model, replacing a generator with an aviation electromagnetic three-dimensional positive operator, and constructing a WGAN network by taking a KAN network as a discriminator to carry out aviation electromagnetic three-dimensional inversion; training is carried out based on the loss function and the data fitting difference convergence condition to update the KAN network and the uniform half-space model, and finally the updated uniform half-space model is obtained to serve as an inversion result. According to the method, more efficient and accurate three-dimensional aviation electromagnetic inversion can be realized, and the method is more suitable for geophysical inversion application under complex data distribution.

A 3D inversion method of DC method using seismic data constraints is disclosed, comprising processing of seismic data and inversion processing of resistivity data; by utilizing seismic wave interval velocity information to constrain the high-density electrical inversion, which can play a complementary role to a certain extent, it is beneficial to supplement the resolution of resistivity inversion with 3D seismic image information, reflect a boundary of subsurface electrical anomalous body, and further characterizes the boundary characteristics of anomalous body through comprehensive geological-geophysical analysis. Seismic data constraints are applied to 3D resistivity inversion, performing numerical simulation and inversion of electrical data under undulating terrain using the finite volume method and Gauss-Newton inversion method. Furthermore, the seismic anisotropic velocity tensor constraint is introduced for inversion to mitigate the non-uniqueness inherent in single-method inversion, yielding a more accurate 3D subsurface electrical structure and improving the resolution of longitudinal boundaries.

The invention discloses a complex medium controllable source electromagnetic multi-parameter three-dimensional inversion method and system, and the method comprises the steps: carrying out the three-dimensional space discretization of an exploration region, and carrying out the multi-time iteration inversion of a discrete exploration region through initializing a multi-parameter geologic model based on a multi-parameter inversion target function, and obtaining a multi-parameter three-dimensional inversion result; wherein the multi-parameter inversion objective function comprises a data fitting constraint, a model constraint and a cross gradient constraint, and the multi-parameter model comprises resistivity, magnetic conductivity, a charging rate, a frequency correlation coefficient and a time constant; and a hexahedral mesh discrete calculation region is adopted in inversion, and a finite element linear equation set is obtained through a vector finite element method, so that multi-parameter three-dimensional forward modeling calculation is realized. According to the method, the induced polarization effect and the magnetic conductivity influence are considered at the same time, multi-parameter three-dimensional inversion is achieved, the application precision and reliability of the controllable source electromagnetic method under the complex geological condition are remarkably improved, and rich geophysical basis is provided.

The invention discloses a magnetotelluric sounding measurement method for multidirectional aggregation observation, and the method comprises the steps: building a novel device layout: designing a reasonable measurement point layout scheme according to geological features and electromagnetic response distribution; processing data and establishing an unstructured grid: acquiring an electromagnetic field component, completing data acquisition, and inputting the processed electromagnetic field data into an unstructured grid model; impedance tensor calculation: on the basis of the unstructured grid, performing impedance calculation by utilizing multi-component electromagnetic field data and combining an interpolation idea, and constructing an extended impedance tensor of an electromagnetic field component to obtain an impedance value component; and three-dimensional inversion and visualization: performing three-dimensional inversion through a vector finite element method to obtain an inversion result. According to the method, richer observation data are provided for deep geologic structure inversion.

The invention relates to the field of inversion, in particular to a three-dimensional inversion method for gravity multi-scale data, which comprises the following steps of: thinning gravity abnormal data in different scales to obtain multi-scale gravity data; and judging whether the scale of the gravity anomaly is appropriate or not, setting a subdivision unit for the gravity anomaly of the appropriate scale, and accumulating all the previous structure information in each Gramer gradient inversion as a constraint condition for current scale inversion. Applying the inversion result of the current scale to the initial model of the next scale to obtain a target function; and carrying out inversion calculation on the target function by adopting a Grubm gradient method and combining with the adaptive depth weight to obtain a three-dimensional high-resolution density result. In practical application, on the premise that original data do not need to be reconstructed, the deep geologic body inversion resolution is improved by conducting multi-scale collaborative inversion on the gravity data. In practical application, higher inversion resolution and field source depicting capability can be obtained by processing gravity abnormal data.

An aeroelectromagnetic data inversion method and a system based on an approximate Jacobian matrix are provided. The method includes following steps: dividing an inversion target area into grids, and setting an initial underground space model based on divided grids; constructing an aerial transient electromagnetic three-dimensional inversion target function based on the initial underground space model, and calculating a weighting term of the model based on observation data and the inversion target function; constructing the approximate Jacobian matrix, calculating an iterative equation set based on the approximate Jacobian matrix, and updating the inversion target function based on the iterative equation set to obtain an inversion model; and inputting aerial transient electromagnetic observation data into the inversion model for inversion to obtain inversion results of each induced polarization parameter.

According to the oil and gas pipeline defect three-dimensional imaging method and system based on magnetic flux leakage detection, original data are converted into magnetic field intensity units with physical significance, physical coordinates are calculated, meanwhile, an automatic defect detection and merging algorithm is adopted, abnormal areas can be accurately recognized, and independent defect marks can be formed. In the detection process, through an overall three-dimensional view, a defect thermodynamic diagram and three-dimensional imaging of a specific defect area, the position, form and magnetic field signal characteristics of the defect can be visually displayed, the defect size can be further quantified in combination with a defect three-dimensional inversion function, and a reliable basis is provided for accurate evaluation and maintenance of oil and gas pipeline defects.

The invention provides a semi-aviation transient electromagnetic rapid inversion method and system based on multi-GPU parallel, and relates to the technical field of semi-aviation transient electromagnetic inversion. Comprising the following steps: determining a calculation task of a Jacobian matrix based on necessary initial information and an initial model; splitting a Jacobian matrix calculation task into a plurality of sub-tasks on a CPU memory, transmitting the plurality of sub-tasks to corresponding GPUs respectively, and executing calculation of the sub-tasks in parallel on the GPUs; results of all the subtasks are spliced into a complete Jacobian matrix in a CPU memory; obtaining an update model based on the complete Jacobian matrix; and performing forward modeling calculation on the updated model until the root-mean-square error meets a threshold value, thereby obtaining a final model which is a three-dimensional inversion result. According to the method, a Jacobian matrix calculation task is split into a plurality of sub-tasks on a CPU memory, the plurality of sub-tasks are allocated to a plurality of corresponding GPU graphics cards, and the process of solving an inversion model is accelerated through a multi-GPU parallel calculation scheme.

Described herein are systems and techniques for monitoring for monitoring and evaluating conditions associated with a wellbore and wellbore operations that use neural operators instead of computationally intensive iterative differential equations. Such systems and techniques allow for determinations to be made as operations associated with a wellbore are performed. Instead of having to wait for computationally intensive tasks to be performed or take risks of proceeding with a wellbore operation without real-time evaluations being performed, these wellbore operations may be continued while determinations are timely made, thus improving operation of computing systems that perform evaluations and that make decisions regarding safely and efficiently performing wellbore operations such as drilling a wellbore, cementing wellbore casings in place, or injecting fluids into formations of the Earth.

The invention relates to the technical field of geophysics, in particular to an electromagnetic method three-dimensional inversion method and system based on a convolutional neural network, and the method comprises the following steps: firstly, achieving the end-to-end nonlinear mapping through a three-dimensional CNN processing module, and obtaining a corresponding three-dimensional resistivity model; the three-dimensional CNN processing module comprises an encoder used for extracting multi-scale features through a 3D convolution layer and down-sampling, a decoder used for recovering spatial resolution through a 3D deconvolution layer and jump connection, and a processor used for processing the multi-scale features through the decoder. And the output layer is used for restraining the resistivity range through a Sigmoid activation function. And then multi-frequency electromagnetic field data is used as joint input of a three-dimensional resistivity model, and TV regularization and physical property range constraint are introduced into a loss function to realize three-dimensional inversion. According to the method, efficient, high-precision and low-cost electromagnetic method three-dimensional inversion is realized through a three-dimensional CNN architecture, multi-frequency data fusion and physical constraint design, and the method is remarkably superior to a traditional iteration method.

The invention discloses a rockburst risk identification method based on a dynamic interference compensation algorithm and quasi-three-dimensional high-resolution imaging. The rockburst risk identification method comprises the following steps: separating construction noise and a rock mass fracture signal in real time by adopting a variational mode decomposition-particle swarm optimization algorithm; a high-frequency tunnel electromagnetic signal and a rock mass fracture signal are obtained, and an inversion imaging image is obtained through quasi-three-dimensional inversion of multi-band data fusion; and according to the inversion imaging image, the fracture density and the extension direction are extracted, and the trained LSTM model is used to carry out rockburst risk identification. Through the scheme, the method has the advantages of simple logic, accuracy, reliability and the like, and has very high practical value and popularization value in the technical field of tunnel construction safety monitoring.

The invention relates to the technical field of exploration, and discloses an SATEM transverse constraint quasi-two-dimensional inversion method based on Occam. Firstly, one-dimensional SATEM forward modeling is carried out, and the precision of a numerical solution is verified. And then adding a transverse constraint weight factor in the inversion objective function, and adjusting the continuity strength of the electrical units of the adjacent measuring points. Setting a three-dimensional theoretical model, calculating three-dimensional forward modeling response, and selecting a plurality of sections for inversion; by adjusting the transverse constraint weight factor, the influence of the transverse constraint weight factor on the inversion effect is analyzed, and an inversion result is obtained. Compared with three-dimensional inversion, the method is higher in efficiency and lower in hardware requirement, has important value for preliminarily understanding underground structures and providing an initial model for three-dimensional inversion, and has better recovery capability for structures with high transverse continuity and stratified stratums.

The invention discloses a high-density electrical method infiltration surface three-dimensional inversion method based on multi-source data collaboration, and the method comprises the steps: constructing a multi-source heterogeneous data collection network, synchronously obtaining four types of data of a dam body monitoring region, and achieving the unification of coordinates and time scales of the four types of data through a space-time registration algorithm; establishing a multi-scale coupling model; on this basis, a deep learning inversion framework fused with physical constraints is developed; an inversion result is optimized through a self-adaptive dynamic correction module; and outputting the corrected three-dimensional distribution model of the infiltration surface. According to the method, a resistivity-moisture content-pore structure-fluid pressure quaternary coupling equation is macroscopically established through a multi-scale coupling model, pressure data are obtained in real time in combination with optical fiber sensing, pressure and pore deformation are correlated through a mesomechanical equation, a physical mechanism is fully fused, resistivity deviation caused by pressure is eliminated, and the resistivity is measured. The three-dimensional form of the infiltration surface is more suitable for the real situation, and an accurate position basis is provided for dam body permeability stability evaluation.

The present application belongs to the technical field of geophysical electromagnetic inversion, and specifically relates to an airborne electromagnetic three-dimensional inversion method based on compressed sensing and preconditioned random gradient, and comprises the following steps: step one, screening of available data in airborne electromagnetic measured data for inversion; step two, random sampling of measuring points by using a Poisson disc sampling method, forward calculation of the sampling points by using a finite volume method to obtain predicted data of the random measuring points, and reconstruction of the predicted data of all measuring points by using a compressed sensing method; and step three, data fitting of the measured data of step one and the predicted data of step two, and construction of an objective function of airborne electromagnetic three-dimensional regularization inversion in combination with model roughness, wherein the convergence speed can be comparable to that of traditional full-batch data three-dimensional inversion, and the inversion calculation efficiency is greatly improved while ensuring inversion accuracy.

The invention relates to a transient electromagnetic three-dimensional inversion method and device, computer equipment and a storage medium. The method comprises the following steps: decoupling a forward modeling grid and an inversion grid, independently generating a vertical self-adaptive layered special forward modeling grid for each time channel according to the skin depth of the time channel, and remarkably reducing the calculation dimension while keeping the horizontal discrete consistency; an equivalent circuit method is innovatively adopted to achieve high-precision mapping of model parameters from an inversion space to a forward modeling space, a plurality of inversion grid units arranged in the current magnetic field component direction are regarded as series connection, and a plurality of inversion grid units arranged in the direction perpendicular to the current magnetic field component direction are regarded as parallel connection. The equivalent conductivity in the control volume is accurately calculated by using a series-parallel resistance formula, and the precision defect of a traditional method in a complex electrical structure is effectively solved. According to the method, the calculation efficiency and the numerical precision are effectively balanced, and the optimal discretization modeling of the transient electromagnetic response is realized.

This invention discloses a method and system for predicting reservoir types, comprising: obtaining a cross-interpretation chart of sandstone and mudstone transverse and longitudinal wave impedances based on the lithological distribution information, P-wave impedance curves, and S-wave impedance curves of the target layer in the target well; constructing new elastic impedance curves for distinguishing sandstone and mudstone based on P-wave and S-wave characteristics using principal component analysis based on the sandstone and mudstone transverse and longitudinal wave impedances in the cross-interpretation chart; constructing a new three-dimensional elastic impedance data volume based on the new elastic impedance curves and the three-dimensional inversion data volume of transverse and longitudinal wave impedances; and predicting the reservoir type of the entire well section of the target well based on the new three-dimensional inversion data volume of elastic impedances. This invention can construct elastic impedance attributes more suitable for reservoir identification based on transverse and longitudinal wave impedances, and can realize reservoir interpretation using a single parameter, overcoming the problem of low sandstone identification accuracy under impedance overlap, and improving the accuracy and efficiency of sandstone reservoir identification.

The application discloses a kind of electric source short offset distance transient electromagnetic pseudo three-dimensional inversion method, system, equipment and medium, and it is related to geophysical prospecting technical field.The method includes: the multiple source data is normalized, and based on the data after pre-processing, underground space is divided and valued using Gaussian difference method, and initial three-dimensional model is constructed;Based on the initial three-dimensional model, nonlinear conjugate gradient algorithm is used for pseudo three-dimensional inversion, and the value of transverse and longitudinal constraint factor is adaptively adjusted in the inversion process, and inversion data is obtained;According to the inversion data, the three-dimensional imaging information of underground electrical structure is extracted;The three-dimensional imaging information is used for geological interpretation and resource assessment.The application can establish initial three-dimensional model by Gaussian interpolation, carry out efficient inversion calculation using nonlinear conjugate gradient algorithm, and adaptively adjust transverse and longitudinal constraint factor in the inversion process, to realize high-precision pseudo three-dimensional imaging of underground electrical structure.

The invention relates to the field of geophysics and discloses a three-dimensional magnetotelluric inversion method for block-by-block continuous variation of conductivity. The method includes adding a model constraint term based on the conductivity of an unstructured tetrahedral grid node to an objective function to obtain an inversion objective function expression. The model constraint term is solved by minimizing the norm of the conductivity variation between a unit and surrounding units to obtain a model constraint term based on the conductivity of the tetrahedral grid node. The inversion objective function expression is gradient-solved. Specific expressions of elements in the stiffness matrix gradient under four different conditions are solved and the gradient components of the stiffness matrix corresponding to all nodes are solved, thereby achieving the solution of the objective function gradient in magnetotelluric inversion. The method realizes the updating of the node conductivity model during three-dimensional underground medium inversion, greatly reduces the unknowns generated in the inversion process, improves the uniqueness of the solution, and greatly shortens the time required for the inversion process to obtain a better inversion effect.

The present disclosure discloses a three-dimensional inversion method of airborne transient electromagnetics based on deep learning. The method of the present disclosure proposes two strategies that focus on training datasets, to improve the performance of deep learning models, including divide and conquer strategy and random models generating. Through a large of reasonable structural models, appropriate network setups, a more generalized result can be obtained through our proposed U-Net framework, which has been demonstrated to be effective on both synthetic and field data. This scheme can realize the rapid prospecting of three-dimensional resistivity structure in large-area target region, and solve the problem of low efficiency of traditional three-dimensional inversion calculation of ATEM and poor migration ability of three-dimensional inversion based on deep learning developed by predecessors.

The invention discloses a three-dimensional resistivity imaging method for fracture development of a strip mine dumping site, and belongs to the technical field of strip mine dumping site fracture development detection. The method comprises the following steps: S1, topographic survey and electrode layout; s2, acquiring potential data; s3, carrying out data processing and three-dimensional inversion; s4, evaluating an inversion result; s5, analyzing the resistivity distribution model; and S6, performing safety assessment and engineering management. According to the three-dimensional resistivity imaging method for fracture development of the strip mine dumping site, the detection capability and efficiency of fracture development of the strip mine dumping site are remarkably improved by combining data processing and an inversion algorithm, and technical support is provided for safety management and disaster prevention of the dumping site.

This application belongs to the technical field of geophysical methods, and specifically discloses a geophysical electromagnetic method data inversion method and system based on entropy constraint. The method includes: setting conductivity values after dividing the inversion space to construct an initial inversion model; constructing a magnetotelluric regularization inversion objective function based on entropy constraint; using the Gauss-Newton method to minimize the magnetotelluric regularization inversion objective function, updating the initial inversion model, and obtaining a conductivity model to achieve three-dimensional magnetotelluric inversion. This application can achieve the effect of focused inversion to obtain a high-resolution conductivity model with clear boundaries, serving fields such as oil and mineral resource exploration.

The invention relates to an efficient forward modeling transient electromagnetic three-dimensional inversion method and device and computer equipment. The method comprises the following steps: randomly generating a plurality of transient electromagnetic three-dimensional geoelectric models, carrying out emission source decomposition on each three-dimensional geoelectric model, constructing an independent sub-grid for each independent source and each receiving point according to the skin depth of each time channel, converting a large-scale global problem into a large number of small-scale sub-problems, and generating a plurality of transient electromagnetic three-dimensional geoelectric models; and the sub-problems are efficiently distributed to a large number of computing cores for parallel processing. Based on the efficient parallel forward modeling capability, it is possible to construct a large-scale and high-density three-dimensional training data set, and a foundation is laid for subsequent application of a deep learning model. And then, a high-precision prior model of deep learning prediction is used as a hot start initial model, and is introduced into a traditional inversion process based on a Gaussian Newton method, so that rapid, stable and high-resolution transient electromagnetic three-dimensional inversion is realized. According to the invention, the precision and efficiency of underground structure imaging are significantly improved.

The invention provides a three-dimensional underground model electromagnetic data intelligent inversion method based on deep learning, and the method comprises the following steps: synthesizing a three-dimensional underground model, and automatically and rapidly generating a large number of electromagnetic data samples; performing rapid three-dimensional inversion on the electromagnetic data by using a deep learning neural network; and comparing with three-dimensional inversion in a traditional mode to obtain a result. According to the method, a Monte Carlo and Gaussian filtering combined method is adopted as a generation theory of an underground model, a large number of data models are generated, then three-dimensional forward modeling is performed on the data models to obtain electromagnetic data sample pairs, and the problem of insufficient samples in deep learning training is solved. And meanwhile, training of deep learning is carried out by using the generated samples. Compared with a three-dimensional inversion result of a traditional method, the definition and the accuracy of the method are almost the same as those of a traditional inversion mode, but the inversion speed is greatly improved, and it is also proved that the method has practical value in actual three-dimensional model electromagnetic data inversion.

This invention relates to the field of controlled-source electromagnetic inversion technology, and more particularly to a controlled-source electromagnetic three-dimensional inversion method based on anisotropic media. Based on the method defined by Tikhonov, this invention constructs an anisotropic objective function for the inversion model from observational data, without requiring additional construction or the use of independent preconditioning operators, thus effectively improving the efficiency of anisotropic inversion calculations. Furthermore, this invention first takes the natural logarithm of the model conductivity before inversion, effectively avoiding the problem of negative conductivity values ​​during the inversion process, thereby ensuring the physical rationality of the inversion results. Simultaneously, this invention effectively suppresses the multiple solutions in anisotropic inversion through forward and inversion grid decoupling technology, improving the reliability of anisotropic inversion.

The application discloses a low-density electrical property reconstruction data body mixed weight constraint inversion imaging method, which comprises the following steps: deploying an electrical monitoring system at a downhole working face; establishing an inversion grid for an observation area; determining observation point weights; determining depth weights; fusing the observation point weights and the depth weights to form mixed weights; constructing a diagonal matrix as a mixed weight matrix; applying prior constraint information to a target function; linearizing and minimizing the target function to which the prior constraint is applied to obtain a model update formula to which mixed weight constraints are applied, which is an inversion problem to which mixed weight constraints are applied; and solving the inversion problem to which the mixed weight constraints are applied by using an inversion algorithm to realize three-dimensional inversion imaging of a low-density electrical property reconstruction data body in a coal mine downhole.

Described herein are systems and techniques for monitoring for monitoring and evaluating conditions associated with a wellbore and wellbore operations that use neural operators instead of computationally intensive iterative differential equations. Such systems and techniques allow for determinations to be made as operations associated with a wellbore are performed. Instead of having to wait for computationally intensive tasks to be performed or take risks of proceeding with a wellbore operation without real-time evaluations being performed, these wellbore operations may be continued while determinations are timely made, thus improving operation of computing systems that perform evaluations and that make decisions regarding safely and efficiently performing wellbore operations such as drilling a wellbore, cementing wellbore casings in place, or injecting fluids into formations of the Earth.

A method that may include disposing an electromagnetic (EM) logging tool in a wellbore. The EM logging tool may include one or more transmitters disposed on the EM logging tool and one or more receivers disposed on the EM logging tool. The method may further include transmitting an electromagnetic field from the transmitter into one or more tubulars to energize the one or more tubulars with the electromagnetic field thereby producing an eddy current that emanates from the one or more tubulars, measuring the eddy current in the one or more tubulars with the at least one receiver on at least one channel to obtain a plurality of measurements and sending the plurality of measurements to an information handling system. The information handling system may be configured to utilize a multi-dimensional computational model to simulate sensor responses and may apply an inversion to estimate one or more anomaly parameters.