CN111597753B - Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system - Google Patents
Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system Download PDFInfo
- Publication number
- CN111597753B CN111597753B CN202010269141.9A CN202010269141A CN111597753B CN 111597753 B CN111597753 B CN 111597753B CN 202010269141 A CN202010269141 A CN 202010269141A CN 111597753 B CN111597753 B CN 111597753B
- Authority
- CN
- China
- Prior art keywords
- resistivity
- data
- inversion
- adaptive
- self
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Measurement Of Resistance Or Impedance (AREA)
Abstract
The present disclosure provides a two-dimensional resistivity inversion method and system with self-adaptive data depth change characteristics, which constructs data sets of apparent resistivity-resistivity model data pairs of different earth models; constructing an adaptive convolution network with adaptively variable convolution kernel amplitudes and offsets of different horizon depths according to resistivity depth change characteristics; constructing an inversion loss function carrying the vertical weight of the resistivity data item, training the self-adaptive convolution network controlled by the inversion loss function by utilizing the data set, and establishing a mapping relation between apparent resistivity data and a resistivity model; the observation apparent resistivity data is input into the trained self-adaptive convolution network, the resistivity imaging result is output through the established mapping relation, the earth surface two-dimensional resistivity deep learning inversion is realized, and the inversion quality, particularly the inversion precision of a deep region, can be effectively improved.
Description
Technical Field
The disclosure belongs to the technical field of two-dimensional resistivity inversion, and relates to a two-dimensional resistivity inversion method and system with self-adaptive data depth change characteristics.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Earth's surface two-dimensional resistivity detection is a common geophysical prospecting method. Resistivity inversion imaging is a process of reversely calculating the resistivity distribution of the underground medium through apparent resistivity data obtained through observation, and is a core problem of resistivity detection. The resistivity inversion is a typical nonlinear problem, and the existing general mature method solves the problem that the resistivity inversion is easily trapped into local optimum, the initial model has strong dependence, the inversion precision is insufficient and the like by omitting a higher-order term of an objective function and converting the higher-order term into a linear problem. Aiming at the problems of the existing method, starting from the nonlinear nature of resistivity inversion, the imaging quality of the resistivity inversion is improved by utilizing the strong complex function nonlinear fitting capability of the emerging depth neural network, so that the imaging quality becomes a brand new scheme for solving the difficult problem of resistivity inversion.
According to the knowledge of the inventor, the current deep learning inversion scheme is not developed and popularized in the resistivity inversion field, and the core difficulty is that a deep convolution network for natural image processing has weight sharing property and fixed convolution kernel amplitude. The apparent resistivity data is different from the natural image, and the abnormal response characteristic of the apparent resistivity data changes along with the change of the depth position, namely the apparent resistivity data has the depth change characteristic. The depth change characteristic of apparent resistivity data directly results in: (1) abnormal features are difficult to effectively capture and distinguish, network output is fuzzy, and accurate inversion imaging is difficult to achieve; (2) the abnormal characteristics of the deep region are not obvious, and the inversion effect of the deep abnormal body is not good.
Disclosure of Invention
In order to solve the problems, the disclosure provides a two-dimensional resistivity inversion method and a two-dimensional resistivity inversion system with self-adaptive data depth change characteristics, and the inversion quality, particularly the inversion precision of a deep region, can be effectively improved.
According to some embodiments, the present disclosure employs the following technical solutions:
a data depth change characteristic self-adaptive two-dimensional resistivity inversion method comprises the following steps:
constructing data sets of apparent resistivity-resistivity model data pairs of different ground models;
constructing an adaptive convolution network with adaptively variable convolution kernel amplitudes and offsets of different horizon depths according to resistivity depth change characteristics;
constructing a resistivity deep learning inversion loss function carrying the vertical weight of the data item;
training the self-adaptive convolution network controlled by the inversion loss function by utilizing the data set, and establishing a mapping relation between apparent resistivity data and a resistivity model;
and inputting the observation apparent resistivity data into a trained self-adaptive convolution network, and outputting a resistivity imaging result through the established mapping relation to realize the earth surface two-dimensional resistivity deep learning inversion.
According to the technical scheme, the convolutional neural network is controlled through the inversion loss function carrying the vertical weight of the data item, the convolutional neural network is trained by utilizing the data set of the typical electric model, the depth change characteristics of the apparent resistivity can be self-adapted, meanwhile, the network learning capacities of different depth positions are adjusted according to the data characteristics, and the end-to-end mapping relation between the apparent resistivity data and the inversion result is directly established through the depth characteristic self-adaptive deep learning inversion method.
Alternatively, the ground model is a single or a plurality of high-resistance/low-resistance abnormal body combinations with different forms.
As an alternative embodiment, the depth variation feature adaptive convolutional network includes:
the self-adaptive convolution aiming at the depth change characteristics of the apparent resistivity learns the convolution kernel amplitude and the offset of different depth positions through network training, and the self-adaptive convolution kernel with the depth change characteristics with the flexibility matched with the depth change characteristics is:
wherein alpha (h) k ，β(h) k ，A(h) k Adapting parameters, alpha (h), to the depth change characteristics to be learned k And beta (h) k Is the horizontal and vertical position of network node k, A (h) k Is the convolution kernel w c For a convolution kernel of size k and an input of vertical length h, a total of 3 x k x h of additional parameters is assigned.
As an alternative embodiment, the resistivity deep learning inversion loss function carrying the vertical weights of the data items includes:
and applying the vertical weight of the data item in the deep learning inversion loss function to carry out targeted training standard allocation on the depth change characteristics of the apparent resistivity data.
As a further embodiment, the data item vertical weight dw is in the form of:
wherein m is i，j Is a predicted value of the resistivity model position (i, j), λ is a constant related to the electrode device size and the current electrode position, and the parameter β depends on the data type and the dimensionality of the problem.
As a further embodiment, the resistivity deep learning inversion loss function carrying the vertical weights of the data items is:
wherein the inversion resistivity value is
The resistivity model value is m i,j 。
In the inversion process, the resistivity deep learning inversion loss function carrying the vertical weight of the data item aims at attenuation characteristics of the surface excitation electric field at different vertical direction positions, and the purpose of controlling the self-adaptive convolution network is achieved by weighting and differentiating measurement on the inconsistency degree of model predicted values and true values of different vertical direction positions.
A data depth variation feature adaptive two-dimensional resistivity inversion system, comprising:
a dataset construction module configured to construct datasets of apparent resistivity-resistivity model data pairs of different earth models;
a network model building module configured to construct an adaptive convolutional network with adaptively variable convolutional kernel amplitudes and offsets for different horizon depths according to resistivity depth variation characteristics;
the inversion loss function construction module is configured to construct a resistivity deep learning inversion loss function carrying the vertical weight of the data item;
the training module is configured to train the adaptive convolution network controlled by the inversion loss function by utilizing the data set, and establish a mapping relation between apparent resistivity data and a resistivity model;
the inversion module is configured to input the observation apparent resistivity data into the trained self-adaptive convolution network, and output a resistivity imaging result through the established mapping relation to realize the earth surface two-dimensional resistivity deep learning inversion.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the steps of the one data depth variation feature adaptive two-dimensional resistivity inversion method.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of the one data depth variation feature adaptive two-dimensional resistivity inversion method.
Compared with the prior art, the beneficial effects of the present disclosure are:
the method adopts the self-adaptive convolution kernel of the resistivity data depth change characteristic, namely, the amplitude and the offset of the convolution kernel which are self-adaptively convolved into different horizon depths are self-adaptively variable according to the resistivity depth change characteristic, the coverage area of the convolution kernel for the deep abnormal characteristic is wider, the problems that the abnormal characteristic is difficult to effectively capture and distinguish, and the output of a depth inversion network is fuzzy are solved, and the inversion quality is effectively improved.
According to the method and the device, the resistivity deep learning inversion loss function carrying the vertical weight of the data item is adopted to conduct network capacity redistribution, inversion effect of a deep region is effectively improved, the vertical weight of the data item redistributes the network learning capacity according to the resistivity deep variation characteristics, and therefore the network inputs more abnormal characteristic learning capacity into the deep region.
The present disclosure avoids higher order omission of the linear method by a fully nonlinear deep neural network inversion method.
Aiming at the deep change characteristics that the apparent resistivity data response characteristics are increased along with the increase of depth, the characteristic boundaries are not obvious, and the abnormal response is not easy to identify, the amplitudes and the offsets of convolution kernels at different depth positions are changed through the self-adaptive convolution kernels of the resistivity data depth change characteristics, so that the coverage areas of the convolution kernels at different depth positions are increased and are self-adaptive to the change of the deep characteristics, the abnormal response characteristics are more comprehensively captured, and the variable scale learning of the abnormal response characteristics of the resistivity data with the deep change characteristics is realized, thereby effectively improving the inversion precision.
According to the method and the device, the network learning capacity is redistributed through the resistivity deep learning inversion loss function carrying the vertical weight of the data item, and the network capacity is concentrated to the deep region of electric field attenuation, so that inversion accuracy of the deep region is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
FIG. 1 is a flow chart of a two-dimensional resistivity deep learning inversion method with adaptive data depth variation characteristics;
FIG. 2 is a schematic diagram of a ground model in the database established in the present embodiment;
fig. 3 is a deep learning inversion result in the present embodiment.
The specific embodiment is as follows:
the disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
A data depth change characteristic self-adaptive two-dimensional resistivity deep learning inversion method comprises the following steps:
constructing a massive typical ground model data set, wherein the typical ground model is a single or a plurality of high-resistance/low-resistance abnormal body combinations with different forms, and the data set comprises apparent resistivity-resistivity model data pairs of different ground models;
and constructing a depth change characteristic self-adaptive convolution network, wherein the self-adaptive convolution is that the convolution kernel amplitude and the offset of different horizon depths are self-adaptively variable according to the resistivity depth change characteristic, and the convolution kernel coverage area of the deep abnormal characteristic is wider.
And constructing a resistivity deep learning inversion loss function carrying data item vertical weights, wherein the data item vertical weights redistribute the network learning capacity according to the resistivity deep variation characteristics, so that the network inputs more abnormal characteristic learning capacity into a deep region.
The method comprises the steps of training a massive typical electric model data set through a depth change characteristic self-adaptive convolution network controlled by a resistivity deep learning inversion loss function carrying data item vertical weight, and establishing a complex mapping relation between apparent resistivity data and a resistivity model by the network.
And inputting observation apparent resistivity data, and outputting a resistivity imaging result through established network mapping to realize earth surface two-dimensional resistivity deep learning inversion.
Further, the depth variation feature adaptive convolutional network includes:
the self-adaptive convolution aiming at the depth change characteristics of the apparent resistivity learns the convolution kernel amplitude and the offset of different depth positions through network training, and the self-adaptive convolution kernel with the depth change characteristics with the flexibility matched with the depth change characteristics is:
wherein alpha (h) k ，β(h) k ，A(h) k Adapting parameters, alpha (h), to the depth change characteristics to be learned k And beta (h) k Is the horizontal and vertical position of network node k, A (h) k Is the convolution kernel w c Is set in the above-described range.
The total amount of additional parameters is assigned 3 x k x h for a convolution kernel of size k and an input of vertical length h.
Further, the resistivity deep learning inversion loss function carrying the vertical weights of the data items includes:
and applying the vertical weight of the data item in the deep learning inversion loss function to carry out targeted training standard allocation on the depth change characteristics of the apparent resistivity data. The data item vertical weight dw is in the form of:
wherein m is i，j Is a predicted value of the resistivity model location (i, j). Lambda is a constant related to the size of the electrode assembly and the position of the current electrode. The parameter β depends on the data type and the dimensionality of the problem.
The resistivity deep learning inversion loss function carrying the vertical weight of the data item is as follows:
wherein the inversion resistivity value is
The resistivity model value is m i,j 。
As a typical implementation manner, the present embodiment discloses a two-dimensional resistivity deep learning inversion method with adaptive data depth change characteristics, as shown in fig. 1, including the following steps:
step one, constructing a mass typical electric model data set through finite element forward modeling.
The ground model is shown in fig. 2 and is formed by combining one or more regular or irregular high/low resistance abnormal bodies.
The model size of the embodiment is 6.3m×1.2m, the electrode points are 64, the electrode distance is 0.1m, the inversion grid size is 0.05m×0.05m, the low-resistance abnormal body resistivity values are respectively 10 ohm meters and 30 ohm meters, the high-resistance abnormal body resistivity values are respectively 950 ohm meters and 1000 ohm meters, and the background resistivity is 500 ohm meters;
the forward apparent resistivity data of each ground model and the temperature-Shi Lunbei are two groups of forward data under the observation device;
the database of this embodiment includes 29160 sets of two-dimensional apparent resistivity profile-resistivity model data pairs, wherein the rule anomaly score 14580 sets, the anomaly score 14580 sets, and the test set, validation set, and training set ratio is 1:1:10.
And secondly, constructing a visual resistivity data depth change characteristic self-adaptive convolutional neural network.
The adaptive convolution of the data depth change features of the embodiment is applied to a network architecture based on U-Net, the number of network layers is 5, the number of input channels is 1, the convolution kernel sizes are 3×3, and the depth change modes of the data are captured by constructing two vertical adaptive convolution layers, so that distinguishable features for the convolution layers are generated.
And thirdly, adding a data item vertical weight for adjusting the resistivity detection deep area network learning capability into the loss function.
The loss function calculation formula used in this embodiment is:
wherein v is a data value term; alpha is a smoothing factor, and the value is 0.2; lambda is 8; beta is 1.
And step four, training a depth inversion network.
The main network parameters and hardware conditions in this embodiment are: the calculation is implemented using a monolithic NVIDIATITANXp. Based on the PyTorch platform, the network is built, the batch processing capacity (batch size) of the SGD optimizer is 5, the learning rate (learning rate) is 0.1, the momentum (momentum) is 0.9, the weight decay (weight decay) is 1e-4, and the working times (epoch) of the learning algorithm in the whole training data set is 500.
And fifthly, inputting apparent resistivity data in the trained network, and obtaining a more accurate inversion result as shown in fig. 3. The method can be used for accurately inverting the position and the form of the target body, and has a good inversion effect even in the region with deeper burial depth of the abnormal body.
It will be apparent to those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
While the specific embodiments of the present disclosure have been described above with reference to the drawings, it should be understood that the present disclosure is not limited to the embodiments, and that various modifications and changes can be made by one skilled in the art without inventive effort on the basis of the technical solutions of the present disclosure while remaining within the scope of the present disclosure.
Claims (7)
1. A data depth change characteristic self-adaptive two-dimensional resistivity inversion method is characterized by comprising the following steps of: the method comprises the following steps:
constructing data sets of apparent resistivity-resistivity model data pairs of different ground models;
constructing an adaptive convolutional network with adaptively variable convolution kernel amplitudes and offsets for different horizon depths according to resistivity depth variation characteristics, the adaptive convolutional network with adaptively variable resistivity depth variation characteristics comprising:
the self-adaptive convolution learns the amplitudes and the offsets of the convolution kernels at different depth positions through network training, and the self-adaptive convolution kernels with depth change characteristics with the flexibility of matching with the depth change characteristics are as follows:
wherein alpha (h) k ，β(h) k ，A(h) k Adapting parameters, alpha (h), to the depth change characteristics to be learned k And beta (h) k Is the horizontal and vertical position of network node k, A (h) k Is the convolution kernel w c，k B is the offset;
constructing a resistivity deep learning inversion loss function carrying a vertical weight of a data item, wherein the vertical weight dw of the data item is in the form of:
wherein m is i，j Is a predicted value of the resistivity model location (i, j), λ is a constant related to the electrode device size and the current electrode location, and the parameter β depends on the data type and the dimensionality of the problem;
the resistivity deep learning inversion loss function carrying the vertical weight of the data item is as follows:
wherein the inversion resistivity value is
Resistivity ofModel value of m i,j ；
Training the self-adaptive convolution network controlled by the inversion loss function by utilizing the data set, and establishing a mapping relation between apparent resistivity data and a resistivity model;
and inputting the observation apparent resistivity data into a trained self-adaptive convolution network, and outputting a resistivity imaging result through the established mapping relation to realize the earth surface two-dimensional resistivity deep learning inversion.
2. A method of two-dimensional resistivity inversion with adaptive data depth variation characteristics as claimed in claim 1, wherein: the ground model is a single or a plurality of high-resistance/low-resistance abnormal body combinations with different forms.
3. A method of two-dimensional resistivity inversion with adaptive data depth variation characteristics as claimed in claim 1, wherein: for a convolution kernel of size k and an input of vertical length h, a total of 3 x k x h additional parameters are assigned.
4. A method of two-dimensional resistivity inversion with adaptive data depth variation characteristics as claimed in claim 1, wherein: the resistivity deep learning inversion loss function carrying the vertical weight of the data item comprises:
and applying the vertical weight of the data item in the deep learning inversion loss function to carry out targeted training standard allocation on the depth change characteristics of the apparent resistivity data.
5. A data depth change characteristic self-adaptive two-dimensional resistivity inversion system is characterized in that: comprising the following steps:
a dataset construction module configured to construct datasets of apparent resistivity-resistivity model data pairs of different earth models;
a network model building module configured to construct an adaptive convolutional network with adaptively variable convolutional kernel amplitudes and offsets for different horizon depths according to resistivity depth variation characteristics, the adaptive convolutional network with adaptively variable resistivity depth variation characteristics comprising:
the self-adaptive convolution learns the amplitudes and the offsets of the convolution kernels at different depth positions through network training, and the self-adaptive convolution kernels with depth change characteristics with the flexibility of matching with the depth change characteristics are as follows:
wherein alpha (h) k ，β(h) k ，A(h) k Adapting parameters, alpha (h), to the depth change characteristics to be learned k And beta (h) k Is the horizontal and vertical position of network node k, A (h) k Is the convolution kernel w c，k B is the offset;
the inversion loss function construction module is configured to construct a resistivity deep learning inversion loss function carrying a vertical weight of a data item, and the vertical weight dw of the data item is as follows:
wherein m is i，j Is a predicted value of the resistivity model location (i, j), λ is a constant related to the electrode device size and the current electrode location, and the parameter β depends on the data type and the dimensionality of the problem;
the resistivity deep learning inversion loss function carrying the vertical weight of the data item is as follows:
wherein the inversion resistivity value is
The resistivity model value is m i,j ；
The training module is configured to train the adaptive convolution network controlled by the inversion loss function by utilizing the data set, and establish a mapping relation between apparent resistivity data and a resistivity model;
the inversion module is configured to input the observation apparent resistivity data into the trained self-adaptive convolution network, and output a resistivity imaging result through the established mapping relation to realize the earth surface two-dimensional resistivity deep learning inversion.
6. A computer-readable storage medium, characterized by: in which instructions are stored which are adapted to be loaded by a processor of a terminal device and to perform the steps of a data depth change feature adaptive two-dimensional resistivity inversion method according to any of the claims 1-4.
7. A terminal device, characterized by: comprising a processor and a computer-readable storage medium, the processor configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the steps of a data depth variation feature adaptive two-dimensional resistivity inversion method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269141.9A CN111597753B (en) | 2020-04-08 | 2020-04-08 | Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269141.9A CN111597753B (en) | 2020-04-08 | 2020-04-08 | Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111597753A CN111597753A (en) | 2020-08-28 |
| CN111597753B true CN111597753B (en) | 2023-06-30 |
Family
ID=72188685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010269141.9A Active CN111597753B (en) | 2020-04-08 | 2020-04-08 | Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597753B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199887A (en) * | 2020-09-30 | 2021-01-08 | 山东大学 | Semi-supervised resistivity inversion method and system based on countermeasure generation network and pseudo-labeling |
| CN112364911B (en) * | 2020-11-06 | 2022-11-11 | 东北石油大学 | Resistivity imaging inversion method and device and storage medium |
| CN115755201A (en) * | 2022-11-21 | 2023-03-07 | 深蓝感知(杭州)物联科技有限公司 | Method for calculating towed transient electromagnetic apparent resistivity based on neural network model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017113205A1 (en) * | 2015-12-30 | 2017-07-06 | 中国科学院深圳先进技术研究院 | Rapid magnetic resonance imaging method and apparatus based on deep convolutional neural network |
| CN110333543A (en) * | 2019-07-03 | 2019-10-15 | 山东大学 | Post non of low resistance body explanation and imaging method and system based on reflection coefficient analysis |
| CN110888172A (en) * | 2019-11-11 | 2020-03-17 | 吉林大学 | Coarse medium electromagnetic response resistivity imaging method based on neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109212617B (en) * | 2018-08-24 | 2020-09-08 | 中国石油天然气股份有限公司 | Automatic identification method and device for electric imaging logging phase |
-
2020
- 2020-04-08 CN CN202010269141.9A patent/CN111597753B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017113205A1 (en) * | 2015-12-30 | 2017-07-06 | 中国科学院深圳先进技术研究院 | Rapid magnetic resonance imaging method and apparatus based on deep convolutional neural network |
| CN110333543A (en) * | 2019-07-03 | 2019-10-15 | 山东大学 | Post non of low resistance body explanation and imaging method and system based on reflection coefficient analysis |
| CN110888172A (en) * | 2019-11-11 | 2020-03-17 | 吉林大学 | Coarse medium electromagnetic response resistivity imaging method based on neural network |
Non-Patent Citations (2)
| Title |
|---|
| Bin Liu 等.Full waveform inversion based on inequality constraint for cross-hole radar.Journal of Applied Geophysics.2019,118-127. * |
| 刘斌等.基于自适应加权光滑约束与PCG算法的三维电阻率探测反演成像.岩土工程学报.2012,(第09期),92-99. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111597753A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111597753B (en) | Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system | |
| CN111126591B (en) | Magnetotelluric deep neural network inversion method based on space constraint technology | |
| US10439594B2 (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| WO2022227206A1 (en) | Fully convolutional neural network-based magnetotelluric inversion method | |
| Yassin et al. | Binary particle swarm optimization structure selection of nonlinear autoregressive moving average with exogenous inputs (NARMAX) model of a flexible robot arm | |
| Jiang et al. | Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks | |
| Aranha et al. | Optimization of oil reservoir models using tuned evolutionary algorithms and adaptive differential evolution | |
| CN113255230A (en) | Gravity model forward modeling method and system based on MQ radial basis function | |
| CN109800517B (en) | Improved reverse modeling method for magnetorheological damper | |
| WO2020257263A1 (en) | Systems and methods for solving geosteering inverse problems in downhole environments using a deep neural network | |
| CN116384244A (en) | Electromagnetic field prediction method based on physical enhancement neural network | |
| Setiyoko et al. | Minimax approach for semivariogram fitting in ordinary kriging | |
| CN109711051B (en) | Pile top displacement nonlinear prediction method considering sliding bed rock mass structure characteristics | |
| CN109712207B (en) | V-Net depth imaging method | |
| CN111158059B (en) | Gravity inversion method based on cubic B spline function | |
| CN105277974A (en) | Stratum data interpolation method | |
| CN116011338A (en) | Full waveform inversion method based on self-encoder and deep neural network | |
| CN116577821A (en) | Time-lapse earthquake prediction method and system based on neural network | |
| CN112016956B (en) | Ore grade estimation method and device based on BP neural network | |
| Tang et al. | Fundamental matrix estimation by multiobjective genetic algorithm with Taguchi's method | |
| CN111597752B (en) | Cross-hole resistivity CT deep learning inversion method and system for balancing sensitivity among holes | |
| Berretta et al. | Adaptive Environmental Sampling: The Interplay Between Geostatistics and Geometry. | |
| CN117010260A (en) | Automatic history fit model prediction method, system and equipment for fractured reservoir | |
| CN110794469B (en) | Gravity inversion method based on minimum geological feature unit constraint | |
| CN112649869A (en) | Reservoir characteristic parameter prediction method and system based on GA-WNN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |