CN112463776A - Seismic data feature extraction and clustering method and device based on depth self-encoder - Google Patents
Seismic data feature extraction and clustering method and device based on depth self-encoder Download PDFInfo
- Publication number
- CN112463776A CN112463776A CN202011205663.9A CN202011205663A CN112463776A CN 112463776 A CN112463776 A CN 112463776A CN 202011205663 A CN202011205663 A CN 202011205663A CN 112463776 A CN112463776 A CN 112463776A
- Authority
- CN
- China
- Prior art keywords
- data
- layer data
- interlayer
- seismic
- layer
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000000605 extraction Methods 0.000 title claims abstract description 32
- 239000010410 layer Substances 0.000 claims abstract description 232
- 239000011229 interlayer Substances 0.000 claims abstract description 111
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000013075 data extraction Methods 0.000 claims description 22
- 238000011176 pooling Methods 0.000 claims description 21
- 230000003044 adaptive effect Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012952 Resampling Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 239000000872 buffer Substances 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 208000035126 Facies Diseases 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a seismic data feature extraction and clustering method and device based on a depth self-encoder, wherein the method comprises the following steps: acquiring seismic data, and extracting interlayer data between target layers according to the seismic data and target level information; bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model; extracting the seismic data through the feature model to obtain feature data; and carrying out clustering analysis on the characteristic data to obtain characteristic points, and reducing the characteristic points into an original two-dimensional plane to obtain a waveform clustering result.
Description
Technical Field
The invention relates to seismic signal processing and interpretation technology, in particular to a method and a device for extracting and clustering seismic data features based on a depth self-encoder.
Background
Conventionally, when waveform clustering is performed, a time window is generally selected along a time domain layer, a section of data is taken out for waveform clustering, or Fourier transform is performed on the data for cluster analysis in a frequency domain. However, the data waveform extracted by selecting the time window may not be representative and is often not a real representation of the destination layer; meanwhile, the extracted single-channel waveform data has too many characteristic points and serious data redundancy, so that the instability and complexity of a waveform clustering algorithm are increased; the spectrum method is easily interfered by noise, and has great influence on data with low signal-to-noise ratio.
Disclosure of Invention
The invention aims to provide a seismic data feature extraction and clustering method and device based on a depth self-encoder, which are used for realizing seismic data compression and feature extraction of important bases of seismic facies analysis and improving waveform clustering effect.
To achieve the above object, the present invention provides a method for extracting and clustering seismic data features based on a depth self-encoder, which specifically comprises: acquiring seismic data, and extracting interlayer data between target layers according to the seismic data and target level information; bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model; extracting the seismic data through the feature model to obtain feature data; and carrying out clustering analysis on the characteristic data to obtain characteristic points, and reducing the characteristic points into an original two-dimensional plane to obtain a waveform clustering result.
In the above seismic data feature extraction and clustering method based on the depth self-encoder, extracting interlayer data between target layers according to the seismic data and target level information includes: extracting top layer data and bottom layer data according to the seismic data and the target level; acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data; and acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data.
In the above seismic data feature extraction and clustering method based on the depth self-encoder, preferably, the obtaining interlayer data between target layers by calculating according to the top layer data, the bottom layer data and corresponding coordinate data includes: obtaining whole data in the seismic data by taking the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data as boundaries; and setting the data above the top layer and below the bottom layer in each data of the whole block of data to zero to obtain the interlayer data between the target layers.
In the above seismic data feature extraction and clustering method based on the depth self-encoder, preferably, the obtaining interlayer data between target layers by calculating according to the top layer data, the bottom layer data and corresponding coordinate data includes: obtaining the minimum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; and performing adaptive pooling on each data between the top layer data and the bottom layer data by taking the minimum interlayer spacing as an adaptive pooling output value to obtain interlayer data between target layers.
In the above seismic data feature extraction and clustering method based on the depth self-encoder, preferably, the obtaining interlayer data between target layers by calculating according to the top layer data, the bottom layer data and corresponding coordinate data includes: obtaining the maximum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data; and comparing the output data with the maximum interlayer spacing, and when the comparison result shows that the output data is consistent in size, acquiring interlayer data between target interlayers according to the output data.
In the seismic data feature extraction and clustering method based on the depth self-encoder, preferably, the step of bringing the interlayer data into the depth self-encoder network for unsupervised training to obtain the feature model comprises the following steps: and carrying out unsupervised training by bringing the interlayer data into a convolution self-encoder or a full-connection self-encoder to obtain a feature model.
The invention also provides a seismic data feature extraction and clustering device based on the depth self-encoder, which comprises a data extraction module, a model training module, a feature extraction module and a clustering module; the data extraction module is used for acquiring seismic data and extracting interlayer data between target layers according to the seismic data and target level information; the model training module is used for bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model; the characteristic extraction module is used for extracting characteristic data from the seismic data through the characteristic model; the clustering module is used for carrying out clustering analysis on the characteristic data to obtain characteristic points, and restoring the characteristic points to an original two-dimensional plane to obtain a waveform clustering result.
In the seismic data feature extraction and clustering device based on the depth self-encoder, preferably, the data extraction module includes an interlayer data extraction unit, and the interlayer data extraction unit is configured to extract top layer data and bottom layer data according to the seismic data and a target level; acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data; and acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data.
In the seismic data feature extraction and clustering device based on the depth self-encoder, preferably, the interlayer data extraction unit is configured to obtain whole block data from the seismic data by taking coordinate data corresponding to the top layer data and coordinate data corresponding to the bottom layer data as boundaries; and setting the data above the top layer and below the bottom layer in each data of the whole block of data to zero to obtain the interlayer data between the target layers.
In the seismic data feature extraction and clustering device based on the depth self-encoder, preferably, the interlayer data extraction unit is configured to obtain a minimum interlayer distance between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; and performing adaptive pooling on each data between the top layer data and the bottom layer data by taking the minimum interlayer spacing as an adaptive pooling output value to obtain interlayer data between target layers.
In the seismic data feature extraction and clustering device based on the depth self-encoder, preferably, the interlayer data extraction unit is configured to obtain a maximum interlayer distance between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data; and comparing the output data with the maximum interlayer spacing, and when the comparison result shows that the output data is consistent in size, acquiring interlayer data between target interlayers according to the output data.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
The invention has the beneficial technical effects that: based on an unsupervised deep neural network, the seismic data are compressed and feature extracted by using a self-encoder network, the data dimension is reduced, the data redundancy is removed, the horizon feature is extracted, and particularly, the seismic data with different thicknesses among layers can be compressed and feature extracted; and performing cluster analysis on the extracted characteristic data to provide reliable support for subsequent seismic facies analysis and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic flow chart of a seismic data feature extraction and clustering method based on a depth self-encoder according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of interlayer data acquisition according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating a process of acquiring interlayer data by a zero padding method according to an embodiment of the present invention;
fig. 4 is a schematic flowchart illustrating a process of acquiring interlayer data by an adaptive pooling method according to an embodiment of the present invention;
fig. 5 is a schematic flow chart illustrating a process of obtaining interlayer data by an interpolation/resampling method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating an application flow of a depth self-encoder-based seismic data feature extraction and clustering method according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an encoder according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating feature point compression results provided by an embodiment of the present invention;
fig. 9 is a schematic diagram of a feature point clustering result according to an embodiment of the present invention;
FIG. 10 is a diagram illustrating a waveform clustering result according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a seismic data feature extraction and clustering device based on a depth self-encoder according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the invention;
fig. 13 is a schematic diagram of a network structure according to an embodiment of the present invention;
fig. 14 is a schematic diagram of a waveform clustering result according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, unless otherwise specified, the embodiments and features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
Referring to fig. 1, a method for extracting and clustering seismic data features based on a depth self-encoder provided by the present invention specifically includes:
s101, acquiring seismic data, and extracting interlayer data between target layers according to the seismic data and target level information;
s102, bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model;
s103, extracting the seismic data through the feature model to obtain feature data;
s104, carrying out clustering analysis on the feature data to obtain feature points, and reducing the feature points into an original two-dimensional plane to obtain a waveform clustering result.
Further, referring to fig. 2, in the above embodiment, extracting interlayer data between target layers according to the seismic data and the target level information includes:
s201, extracting top layer data and bottom layer data according to the seismic data and the target level;
s202, acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data;
s203, acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data.
In practical work, the seismic data feature extraction and clustering method based on the depth self-encoder provided by the invention can be mainly divided into the following three parts, and the whole flow is shown in fig. 6:
1. interlayer data extraction:
in order to perform waveform clustering, firstly, a waveform of each trace between target layers needs to be extracted from seismic data, which is different from a traditional method for extracting a seismic trace waveform by opening a time window, and in an embodiment of the invention, the following three ways are mainly provided for extracting interlayer data:
referring to fig. 3, in an embodiment of the present invention, the obtaining interlayer data between target layers according to the top layer data, the bottom layer data and corresponding coordinate data includes:
s301, obtaining whole data from the seismic data by taking the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data as boundaries;
s302, data above the top layer and below the bottom layer in each data of the whole block of data are set to be zero, and interlayer data between target layers are obtained.
Specifically, the above embodiment is a zero padding method, that is, after two given levels are given, data between given levels are extracted by using the zero padding method; firstly, reading data of the top layer and the bottom layer of the target area and coordinates in a corresponding matrix. Taking the top layer minimum coordinate and the bottom layer maximum coordinate as boundaries to take out whole data; and setting zero to the data above the top layer and below the bottom layer of each channel of the taken data to obtain the required interlayer data.
Referring to fig. 4, in an embodiment of the present invention, the obtaining interlayer data between target layers according to the top layer data, the bottom layer data and corresponding coordinate data includes:
s401, obtaining the minimum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data;
s502, taking the minimum interlayer spacing as a self-adaptive pooling output value to perform self-adaptive pooling on each data between the top layer data and the bottom layer data, so as to obtain interlayer data between target layers.
Specifically, the above embodiment is an adaptive pooling method, i.e. after two horizons are given, data between given horizons are processed using adaptive pooling; firstly, the minimum distance between the top and bottom layers is (or is smaller) obtained as the size of the self-adaptive pooling output, and the same size is obtained by each channel between the top and bottom layers through the self-adaptive pooling, so that the data between the top and bottom layers can be obtained. Adaptive pooling can pool different sizes of tensors to the same size, the principle of which is:
kernel_size＝(input_size+2*padding)-(output_size-1)*stride；
wherein, kernel _ size is the size of the pooled window, stride is the step size of the window movement, padding is the number of layers of each input variable supplement 0, input _ size is the size of the input tensor, and output _ size is the size of the output tensor.
Referring to fig. 5, in an embodiment of the present invention, the obtaining interlayer data between target layers according to the top layer data, the bottom layer data and corresponding coordinate data includes:
s501, obtaining the maximum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data;
s502, carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data;
s503, comparing the output data with the maximum interlayer distance, and when the comparison result is that the output data is consistent in size, obtaining interlayer data between target interlayers according to the output data.
Specifically, the above embodiment is an interpolation/resampling method, that is, after two horizons are given, given interlayer data is processed by using the interpolation/resampling method; firstly, acquiring the maximum (or larger) distance between the top and the bottom as the output size, and carrying out interpolation/resampling processing on each channel between the top and the bottom to obtain data with consistent output size, namely the required interlayer data; a variety of methods may be used for interpolation/resampling and will not be described in detail herein.
2. Data compression and feature extraction:
the method for constructing the feature model by using the auto encoder network, namely bringing the interlayer data into the deep auto encoder network for unsupervised training to obtain the feature model comprises the following steps: carrying out unsupervised training on the interlayer data in a convolution self-encoder or a full-connection self-encoder to obtain a characteristic model; in practical work, the self-encoder comprises an encoding (encoder) part and a decoding (decoder) part, and the convolution self-encoder and the full-connection self-encoder have good results; the fully-connected self-encoder (as shown in fig. 7) is composed of a fully-connected layer and an active layer, and the convolution self-encoder is composed of a convolution layer, a pooling layer, an active layer, a fully-connected layer and the like.
Then, putting the interlayer data obtained by the calculation into a self-encoder for unsupervised training, setting the output of the encoder to be a specified size to obtain compressed data (as shown in fig. 8), wherein the compressed data comprises the characteristics in the original data and simultaneously removes data redundancy; and the output of the coding part after the network training is stable is the compressed seismic data and contains the extracted characteristic data of the original data.
3. Clustering analysis:
the compressed feature data is subjected to clustering analysis (as shown in fig. 9) by using a clustering method (K-means, Mean Shift, etc.), and the result is projected back to the original two-dimensional plane, so that a waveform clustering result (as shown in fig. 10) can be obtained.
To further improve the effect of clustering, we introduce an Adaptive Gaussian Mixture Model (Adaptive Gaussian Mixture Model) layer to perform clustering analysis on the data. The adaptive Gaussian mixture model can automatically determine the number of the clustering categories, and can be combined with the self-encoder structure in the step 2 to form a new network (as shown in FIG. 13), and the trainable parameters of the self-encoder and the clustering layer are dynamically adjusted, so that the waveform clustering accuracy is improved (as shown in FIG. 14).
The adaptive gaussian mixture model can be defined by the following formula:
wherein q isij(x|θi) Is a kernel for measuring similarity, m is the mean vector, ΣjIs a covariance matrix, LcIs the loss function of the cluster layer and KL represents the KL divergence.
To more clearly illustrate the combination and application manner of the above embodiments, please refer to fig. 6 again, the specific implementation flow of the seismic data feature extraction and clustering method based on the depth self-encoder provided by the present invention can be as follows:
1. acquiring data of a top layer h1 and a bottom layer h2 and coordinates thereof in seismic data;
2. and acquiring interlayer data. Taking the minimum coordinates of the top layer and the maximum coordinates of the bottom layer as boundaries to take out whole data, and setting zero for the taken out data in each channel of data above the top layer and below the bottom layer to obtain required inter-layer data; or obtaining the minimum distance between the top and bottom layers as the size of the self-adaptive pooling output (or smaller), and obtaining the same size of each channel between the top and bottom layers through self-adaptive pooling; or acquiring the maximum (or larger) distance between the top and the bottom as the output size, and carrying out interpolation/resampling processing on each channel between the top and the bottom to obtain data with consistent output size;
3. putting the interlayer data into a self-encoder network for training;
4. outputting the result of the encoder by using the trained self-encoding network model, inputting the result into a clustering layer, and dynamically adjusting the encoding result and the clustering result through cyclic iterative training;
5. performing clustering analysis;
6. and reducing the clustered points into an original two-dimensional plane to obtain a waveform clustering result.
Referring to fig. 11, the present invention further provides a seismic data feature extraction and clustering device based on a depth self-encoder, where the device includes a data extraction module, a model training module, a feature extraction module, and a clustering module; the data extraction module is used for acquiring seismic data and extracting interlayer data between target layers according to the seismic data and target level information; the model training module is used for bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model; the characteristic extraction module is used for extracting characteristic data from the seismic data through the characteristic model; the clustering module is used for carrying out clustering analysis on the characteristic data to obtain characteristic points, and restoring the characteristic points to an original two-dimensional plane to obtain a waveform clustering result.
In the above embodiment, the data extraction module includes an interlayer data extraction unit, and the interlayer data extraction unit is configured to extract top layer data and bottom layer data according to the seismic data and a target level; acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data; and acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data. The interlayer data extraction unit is used for obtaining whole data from the seismic data by taking the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data as boundaries; and setting the data above the top layer and below the bottom layer in each data of the whole block of data to zero to obtain the interlayer data between the target layers. Or obtaining the minimum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; and performing adaptive pooling on each data between the top layer data and the bottom layer data by taking the minimum interlayer spacing as an adaptive pooling output value to obtain interlayer data between target layers. Or obtaining the maximum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data; carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data; and comparing the output data with the maximum interlayer spacing, and when the comparison result shows that the output data is consistent in size, acquiring interlayer data between target interlayers according to the output data.
The invention has the beneficial technical effects that: based on an unsupervised deep neural network, the seismic data are compressed and feature extracted by using a self-encoder network, the data dimension is reduced, the data redundancy is removed, the horizon feature is extracted, and particularly, the seismic data with different thicknesses among layers can be compressed and feature extracted; and performing cluster analysis on the extracted characteristic data to provide reliable support for subsequent seismic facies analysis and the like.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method.
As shown in fig. 12, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 12; furthermore, the electronic device 600 may also comprise components not shown in fig. 12, which may be referred to in the prior art.
As shown in fig. 12, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. A method for extracting and clustering seismic data features based on a depth self-encoder, the method comprising:
acquiring seismic data, and extracting interlayer data between target layers according to the seismic data and target level information;
bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model;
extracting the seismic data through the feature model to obtain feature data;
and carrying out clustering analysis on the characteristic data to obtain characteristic points, and reducing the characteristic points into an original two-dimensional plane to obtain a waveform clustering result.
2. The method of claim 1, wherein extracting inter-layer data between target layers from the seismic data and target level information comprises:
extracting top layer data and bottom layer data according to the seismic data and the target level;
acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data;
and acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data.
3. The method of claim 2, wherein computing inter-layer data between target layers from the top-layer data, the bottom-layer data, and corresponding coordinate data comprises:
obtaining whole data in the seismic data by taking the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data as boundaries;
and setting the data above the top layer and below the bottom layer in each data of the whole block of data to zero to obtain the interlayer data between the target layers.
4. The method of claim 2, wherein computing inter-layer data between target layers from the top-layer data, the bottom-layer data, and corresponding coordinate data comprises:
obtaining the minimum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data;
and performing adaptive pooling on each data between the top layer data and the bottom layer data by taking the minimum interlayer spacing as an adaptive pooling output value to obtain interlayer data between target layers.
5. The method of claim 2, wherein computing inter-layer data between target layers from the top-layer data, the bottom-layer data, and corresponding coordinate data comprises:
obtaining the maximum interlayer spacing between the top layer data and the bottom layer data according to the coordinate data corresponding to the top layer data and the coordinate data corresponding to the bottom layer data;
carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data;
and comparing the output data with the maximum interlayer spacing, and when the comparison result shows that the output data is consistent in size, acquiring interlayer data between target interlayers according to the output data.
6. The method of claim 1, wherein the step of bringing the inter-layer data into a depth self-encoder network for unsupervised training to obtain a feature model comprises: and carrying out unsupervised training by bringing the interlayer data into a convolution self-encoder or a full-connection self-encoder to obtain a feature model.
7. A seismic data feature extraction and clustering device based on a depth self-encoder is characterized by comprising a data extraction module, a model training module, a feature extraction module and a clustering module;
the data extraction module is used for acquiring seismic data and extracting interlayer data between target layers according to the seismic data and target level information;
the model training module is used for bringing the interlayer data into a depth self-encoder network for unsupervised training to obtain a feature model;
the characteristic extraction module is used for extracting characteristic data from the seismic data through the characteristic model;
the clustering module is used for carrying out clustering analysis on the characteristic data to obtain characteristic points, and restoring the characteristic points to an original two-dimensional plane to obtain a waveform clustering result.
8. The depth self-encoder based seismic data feature extraction and clustering apparatus of claim 7, wherein the data extraction module comprises an inter-layer data extraction unit for extracting top-layer data and bottom-layer data from the seismic data and a target level; acquiring coordinate data of the top layer data and the bottom layer data in the seismic data according to the top layer data and the bottom layer data in the seismic data; and acquiring interlayer data between target layers according to the top layer data, the bottom layer data and the corresponding coordinate data in the seismic data.
9. The apparatus of claim 8, wherein the inter-layer data extraction unit is configured to obtain a whole block of data from the seismic data with the coordinate data corresponding to the top-layer data and the coordinate data corresponding to the bottom-layer data as a boundary; and setting the data above the top layer and below the bottom layer in each data of the whole block of data to zero to obtain the interlayer data between the target layers.
10. The depth self-encoder based seismic data feature extraction and clustering device of claim 8, wherein the inter-layer data extraction unit is configured to obtain a minimum interlayer distance between the top-layer data and the bottom-layer data according to the coordinate data corresponding to the top-layer data and the coordinate data corresponding to the bottom-layer data; and performing adaptive pooling on each data between the top layer data and the bottom layer data by taking the minimum interlayer spacing as an adaptive pooling output value to obtain interlayer data between target layers.
11. The depth self-encoder based seismic data feature extraction and clustering device of claim 8, wherein the inter-layer data extraction unit is configured to obtain a maximum inter-layer distance between the top-layer data and the bottom-layer data according to the coordinate data corresponding to the top-layer data and the coordinate data corresponding to the bottom-layer data; carrying out interpolation/resampling processing on each channel of data between the top layer data and the bottom layer data to obtain a plurality of output data; and comparing the output data with the maximum interlayer spacing, and when the comparison result shows that the output data is consistent in size, acquiring interlayer data between target interlayers according to the output data.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 6 when executing the computer program.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205663.9A CN112463776A (en) | 2020-11-02 | 2020-11-02 | Seismic data feature extraction and clustering method and device based on depth self-encoder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205663.9A CN112463776A (en) | 2020-11-02 | 2020-11-02 | Seismic data feature extraction and clustering method and device based on depth self-encoder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112463776A true CN112463776A (en) | 2021-03-09 |
Family
ID=74834911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011205663.9A Pending CN112463776A (en) | 2020-11-02 | 2020-11-02 | Seismic data feature extraction and clustering method and device based on depth self-encoder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112463776A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634714A (en) * | 2009-08-26 | 2010-01-27 | 中国石油大学(华东) | Q structure establishment technology based on prestack seismic channel set earth layer |
| CN101852863A (en) * | 2009-04-03 | 2010-10-06 | 中国石油集团东方地球物理勘探有限责任公司 | Method for processing seismic data by using high-precision single-channel spectrum analysis technology |
| CN107153217A (en) * | 2017-07-10 | 2017-09-12 | 中国石油集团川庆钻探工程有限公司地球物理勘探公司 | A kind of low signal-to-noise ratio regional model road construction method |
| WO2018071632A1 (en) * | 2016-10-14 | 2018-04-19 | Chevron U.S.A. Inc. | System and method for seismic facies identification using machine learning |
| CA2985433A1 (en) * | 2016-11-14 | 2018-05-14 | Symroc Business And Project Management Ltd. | Vibration-analysis system and method therefor |
| CN110231652A (en) * | 2019-06-03 | 2019-09-13 | 中国海洋石油集团有限公司 | A kind of seismic facies extracting method of the Noise application space cluster based on density |
| CN111580156A (en) * | 2019-02-18 | 2020-08-25 | 中国石油天然气股份有限公司 | Automatic picking method and system for seismic zero-value slices |
| CN111767942A (en) * | 2020-05-19 | 2020-10-13 | 中国石油天然气集团有限公司 | Seismic fault data processing method and device |
-
2020
- 2020-11-02 CN CN202011205663.9A patent/CN112463776A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101852863A (en) * | 2009-04-03 | 2010-10-06 | 中国石油集团东方地球物理勘探有限责任公司 | Method for processing seismic data by using high-precision single-channel spectrum analysis technology |
| CN101634714A (en) * | 2009-08-26 | 2010-01-27 | 中国石油大学(华东) | Q structure establishment technology based on prestack seismic channel set earth layer |
| WO2018071632A1 (en) * | 2016-10-14 | 2018-04-19 | Chevron U.S.A. Inc. | System and method for seismic facies identification using machine learning |
| CA2985433A1 (en) * | 2016-11-14 | 2018-05-14 | Symroc Business And Project Management Ltd. | Vibration-analysis system and method therefor |
| CN107153217A (en) * | 2017-07-10 | 2017-09-12 | 中国石油集团川庆钻探工程有限公司地球物理勘探公司 | A kind of low signal-to-noise ratio regional model road construction method |
| CN111580156A (en) * | 2019-02-18 | 2020-08-25 | 中国石油天然气股份有限公司 | Automatic picking method and system for seismic zero-value slices |
| CN110231652A (en) * | 2019-06-03 | 2019-09-13 | 中国海洋石油集团有限公司 | A kind of seismic facies extracting method of the Noise application space cluster based on density |
| CN111767942A (en) * | 2020-05-19 | 2020-10-13 | 中国石油天然气集团有限公司 | Seismic fault data processing method and device |
Non-Patent Citations (3)
| Title |
|---|
| S. MOSTAFA MOUSAVI , WEIQIANG ZHU , WILLIAM ELLSWORTH , GREGORY BEROZA: "Unsupervised Clustering of Seismic Signals Using Deep Convolutional Autoencoders", IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, vol. 16, no. 11, 1 May 2019 (2019-05-01), pages 1693 - 1697, XP011756167, DOI: 10.1109/LGRS.2019.2909218 * |
| 李磊 詹仕凡 冉贤华 刘书艳 万忠宏 陶春峰: "高斯混合模型在储层特征分析中的应用", 中国地球科学联合学术年会 2020, 18 October 2020 (2020-10-18), pages 2057 - 2058 * |
| 林煜;廖军;王飞;李磊;郁智: "基于深度学习的波形聚类方法在储层预测中的应用", 中国石油学会2019 年物探技术研讨会, 9 September 2019 (2019-09-09), pages 648 - 651 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10360899B2 (en) | Method and device for processing speech based on artificial intelligence | |
| US11657823B2 (en) | Channel-compensated low-level features for speaker recognition | |
| CN110600017B (en) | Training method of voice processing model, voice recognition method, system and device | |
| US10380996B2 (en) | Method and apparatus for correcting speech recognition result, device and computer-readable storage medium | |
| US11620983B2 (en) | Speech recognition method, device, and computer-readable storage medium | |
| CN108351984B (en) | Hardware-efficient deep convolutional neural network | |
| CN108205803B (en) | Image processing method, and training method and device of neural network model | |
| CN107240396B (en) | Speaker self-adaptation method, device, equipment and storage medium | |
| CN110102051B (en) | Method and device for detecting game plug-in | |
| CN109766476B (en) | Video content emotion analysis method and device, computer equipment and storage medium | |
| CN112584062A (en) | Background audio construction method and device | |
| US11983866B2 (en) | Image defect detection method, electronic device using the same | |
| CN113780326A (en) | Image processing method and device, storage medium and electronic equipment | |
| CN111353493B (en) | Text image direction correction method and device | |
| CN117556394A (en) | APP digital watermark generation method, decoding method, system, equipment and storage medium | |
| CN112463776A (en) | Seismic data feature extraction and clustering method and device based on depth self-encoder | |
| CN114167500A (en) | Method and device for separating adjacent shot interference based on convolutional neural network | |
| CN113960654B (en) | Seismic data processing method and system | |
| CN114283817A (en) | Speaker verification method and system | |
| CN114220177A (en) | Lip syllable recognition method, device, equipment and medium | |
| CN116917930A (en) | Method and apparatus for correcting image based on image compression quality in electronic device | |
| CN115811590A (en) | Mobile audio/video device and audio/video playing control method | |
| CN112639832A (en) | Identifying salient features of a generating network | |
| CN113808606B (en) | Voice signal processing method and device | |
| CN113687420A (en) | Method and device for removing surface wave noise of seismic data |
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 |