CN117784225A - Synchronous detection method and device for river channel and fault - Google Patents
Synchronous detection method and device for river channel and fault Download PDFInfo
- Publication number
- CN117784225A CN117784225A CN202211169806.4A CN202211169806A CN117784225A CN 117784225 A CN117784225 A CN 117784225A CN 202211169806 A CN202211169806 A CN 202211169806A CN 117784225 A CN117784225 A CN 117784225A
- Authority
- CN
- China
- Prior art keywords
- amplitude
- seismic data
- stack seismic
- dimensional post
- data
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 84
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 7
- 230000008021 deposition Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 8
- 238000002372 labelling Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005137 deposition process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000016507 interphase Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- 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
- 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
- G01V1/30—Analysis
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the invention provides a method and a device for synchronously detecting a river channel and a fault, belonging to the technical field of seismic data interpretation, wherein the method comprises the following steps: acquiring three-dimensional post-stack seismic data; processing the three-dimensional post-stack seismic data based on an amplitude minimum value and an amplitude maximum value in the three-dimensional post-stack seismic data; and taking the processed three-dimensional post-stack seismic data as input of a river channel and fault detection model to obtain a river channel and fault detection result. The river channel and fault synchronous detection method and device have the advantages of short time consumption in the detection process, high efficiency, accurate detection result, strong generalization capability, suitability for detection of different lithology river channel positions formed in different deposition environments, capability of eliminating influence of faults on accurate detection of the river channel and realization of detection of complex river channels.
Description
Technical Field
The invention relates to the field of seismic data interpretation, in particular to a river channel and fault synchronous detection method, a river channel and fault synchronous detection device, electronic equipment and a machine-readable storage medium.
Background
The river channel is one of important geological targets in oil and gas exploration, and it is important to accurately detect the position of the river channel and reveal the development process of the river channel. In the aspect of basin and perspective scale analysis, mastering the characteristics of a river channel is beneficial to quantitative analysis of landforms and accurate knowledge of a deposition process, and is beneficial to knowing the deposition environment and the main direction of sediments along with time; in terms of reservoir scale analysis, the determination of the volume of river sandstone and the properties of the fluid filled therein is of paramount importance; in the development stage of the oil-gas field, the macroscopic distribution characteristics, the deposition and the change rules of the river channel plane are accurately depicted, and important basis can be provided for optimization of development target blocks, programming of an oil-gas development scheme, well position and well track design and the like.
In the prior art, three-dimensional post-stack seismic data is widely used for river interpretation. However, manually explaining the river channel is long in time consumption, inaccurate in explanation result and influenced by human subjectivity; the conventional convolutional neural network is adopted for river channel detection, the label and the label generation mode are highly dependent, so that generalization capability in other work areas is poor, only the influence of folds is considered, the influence of faults is ignored, and the detection precision is greatly reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a synchronous detection method and device for river channels and faults, which are used for solving the problems that the manual explanation of the river channels is long in time consumption, inaccurate in explanation result and influenced by human subjectivity; the conventional convolutional neural network is adopted for river channel detection, so that the problem that the generalization capability in other work areas is poor due to high dependence on labels and label generation modes, and the detection accuracy is low due to the fact that only the influence of folds is considered and the influence of faults is ignored.
In order to achieve the above object, an embodiment of the present invention provides a method for detecting synchronization between a river and a fault, including:
acquiring three-dimensional post-stack seismic data;
processing the three-dimensional post-stack seismic data based on an amplitude minimum value and an amplitude maximum value in the three-dimensional post-stack seismic data;
and taking the processed three-dimensional post-stack seismic data as input of a river channel and fault detection model to obtain a river channel and fault detection result.
Optionally, processing the three-dimensional post-stack seismic data based on the amplitude minimum and the amplitude maximum in the three-dimensional post-stack seismic data includes:
determining an amplitude minimum value and an amplitude maximum value of the three-dimensional post-stack seismic data;
determining a normalized amplitude value based on the amplitude minimum and the amplitude maximum;
transforming the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first transformed data;
and obtaining the processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformation data.
Optionally, determining a normalized amplitude value based on the amplitude minimum value and the amplitude maximum value includes:
the normalized amplitude value is calculated using the following calculation formula:
ΔA=A max -A min ;
wherein ΔA is a normalized amplitude value; a is that max Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
Optionally, transforming the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first transformed data, including:
the first transformation data is obtained using the following calculation formula:
A′ i =A i -A min ;
wherein A 'is' i Is the first transformed data; a is that i Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
Optionally, based on the normalized amplitude value and the first transformed data, obtaining processed three-dimensional post-stack seismic data includes:
the processed three-dimensional post-stack seismic data is calculated by using the following calculation formula:
wherein A' i To the treated three-dimensional post-stackEarthquake data; a's' i Is the first transformed data; Δa is the normalized amplitude value.
Optionally, the method further comprises:
synthesizing a plurality of sample data based on geology and geophysical theory, and constructing a training sample set;
and taking the training sample set as input of a deep learning neural network, and training to obtain the river channel and fault detection model.
The invention also provides a synchronous detection device for river and fault, which comprises:
the data acquisition module is used for acquiring three-dimensional post-stack seismic data;
the data processing module is used for processing the three-dimensional post-stack seismic data based on the minimum amplitude value and the maximum amplitude value in the three-dimensional post-stack seismic data;
and the result output module is used for taking the processed three-dimensional post-stack seismic data as the input of a river channel and fault detection model to obtain a river channel and fault detection result.
The data processing module specifically comprises:
the data amplitude determining module is used for determining an amplitude minimum value and an amplitude maximum value of the three-dimensional post-stack seismic data;
the normalized amplitude value determining module is used for determining a normalized amplitude value based on the amplitude minimum value and the amplitude maximum value;
the amplitude value conversion module is used for converting the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first conversion data;
and the data output module is used for obtaining the processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformation data.
In another aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for detecting synchronization between a river and a fault when executing the computer program.
In another aspect, the present invention further provides a machine-readable storage medium, where instructions are stored on the machine-readable storage medium, where the instructions are configured to cause a machine to perform the above-described method for detecting synchronization between a river and a fault.
According to the technical scheme, the obtained minimum amplitude value and maximum amplitude value of the three-dimensional post-stack seismic data are used for carrying out data processing on the three-dimensional post-stack seismic data to obtain processed three-dimensional post-stack seismic data, the processed three-dimensional post-stack seismic data are input into a detection river channel and fault detection model which are trained in advance to obtain river channel and fault detection results, the detection method can be suitable for detecting positions of different lithology river channels formed in different deposition environments, in addition, influences of faults on accurate river channel detection can be eliminated, detection of complex river channels is achieved, the detection process is short in time consumption, high in efficiency, accurate in detection results and strong in generalization capability.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 is a flow chart of a method for synchronous detection of river and fault provided by the invention;
FIG. 2 is a flow chart of data processing in the river channel and fault synchronous detection method provided by the invention;
FIG. 3 is a schematic structural diagram of a synchronous detection device for river and fault provided by the invention;
FIG. 4 is a schematic structural diagram of a data processing module in the synchronous detection device for river and fault provided by the invention;
FIG. 5 is a schematic representation of a first synthetic three-dimensional post-stack seismic data provided by the present invention;
FIG. 6 is a schematic view of three-dimensional river data based on the synthetic three-dimensional post-stack seismic data of FIG. 5 provided by the present invention;
FIG. 7 is a schematic representation of three-dimensional fault data based on the synthetic three-dimensional post-stack seismic data of FIG. 5 provided by the present invention;
FIG. 8 is a schematic representation of a second synthetic three-dimensional post-stack seismic data provided by the present invention;
FIG. 9 is a schematic representation of three-dimensional river data based on the synthetic three-dimensional post-stack seismic data of FIG. 8 provided by the present invention;
FIG. 10 is a schematic representation of three-dimensional fault data based on the synthetic three-dimensional post-stack seismic data of FIG. 8 provided by the present invention;
FIG. 11 is a schematic representation of three-dimensional post-stack seismic data for a work area provided by the present invention;
FIG. 12 is a schematic diagram showing the superposition of the three-dimensional post-stack seismic data of FIG. 11 and the corresponding river channel detection results according to the present invention;
fig. 13 is a schematic diagram showing superposition of the three-dimensional post-stack seismic data and corresponding fault detection results according to the present invention.
Description of the reference numerals
10-a data acquisition module; 20-a data processing module;
30-a result output module; 21-a data amplitude determination module;
22-a normalized amplitude value determining module; 23-an amplitude value conversion module;
24-data output module.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
The terms "first," "second," "third," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
Furthermore, the terms "substantially," "essentially," and the like, are intended to be limited to the precise form disclosed herein and are not necessarily intended to be limiting. For example: the term "substantially equal" does not merely mean absolute equal, but is difficult to achieve absolute equal during actual production and operation, and generally has a certain deviation. Thus, in addition to absolute equality, "approximately equal to" includes the above-described case where there is a certain deviation. In other cases, the terms "substantially", "essentially" and the like are used in a similar manner to those described above unless otherwise indicated.
FIG. 1 is a flow chart of a method for synchronous detection of river and fault provided by the invention; FIG. 3 is a schematic structural diagram of a synchronous detection device for river and fault provided by the invention; FIG. 4 is a schematic structural diagram of a data processing module in the synchronous detection device for river and fault provided by the invention; FIG. 5 is a schematic representation of a first synthetic three-dimensional post-stack seismic data provided by the present invention; FIG. 6 is a schematic view of three-dimensional river data based on the synthetic three-dimensional post-stack seismic data of FIG. 5 provided by the present invention; FIG. 7 is a schematic representation of three-dimensional fault data based on the synthetic three-dimensional post-stack seismic data of FIG. 5 provided by the present invention; FIG. 8 is a schematic representation of a second synthetic three-dimensional post-stack seismic data provided by the present invention; FIG. 9 is a schematic representation of three-dimensional river data based on the synthetic three-dimensional post-stack seismic data of FIG. 8 provided by the present invention; FIG. 10 is a schematic representation of three-dimensional fault data based on the synthetic three-dimensional post-stack seismic data of FIG. 8 provided by the present invention; FIG. 11 is a schematic representation of three-dimensional post-stack seismic data for a work area provided by the present invention; FIG. 12 is a schematic diagram showing the superposition of the three-dimensional post-stack seismic data of FIG. 11 and the corresponding river channel detection results according to the present invention; fig. 13 is a schematic diagram showing superposition of the three-dimensional post-stack seismic data and corresponding fault detection results according to the present invention.
Example 1
As shown in fig. 1, an embodiment of the present invention provides a method for detecting synchronization between a river and a fault, including:
step one, acquiring three-dimensional post-stack seismic data;
specifically, the relevant steps for obtaining three-dimensional post-stack seismic data based on existing seismic data are well known to those skilled in the art and will not be described in detail herein.
Step two, processing the three-dimensional post-stack seismic data based on the minimum amplitude value and the maximum amplitude value in the three-dimensional post-stack seismic data;
specifically, as shown in fig. 2, the specific steps of the second step include:
step 201, determining an amplitude minimum value and an amplitude maximum value of the three-dimensional post-stack seismic data;
step 202, determining a normalized amplitude value based on the amplitude minimum value and the amplitude maximum value;
step 203, transforming the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first transformed data, wherein the first transformed data is the three-dimensional post-stack seismic data with the amplitude minimum value of 0;
step 204, obtaining the processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformation data, wherein the amplitude range of the processed three-dimensional post-stack seismic data is between 0 and 1.
Further, determining a normalized amplitude value based on the amplitude minimum and the amplitude maximum, comprising:
the normalized amplitude value is calculated using the following calculation formula:
ΔA=A max -A min ;
wherein ΔA is a normalized amplitude value; a is that max Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
Further, transforming the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first transformed data, including:
the first transformation data is obtained using the following calculation formula:
A′ i =A i -A min ;
wherein A 'is' i Is the first transformed data; a is that i Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
Further, based on the normalized amplitude values and the first transformed data, processed three-dimensional post-stack seismic data is obtained, comprising:
the processed three-dimensional post-stack seismic data is calculated by using the following calculation formula:
wherein A' i The processed three-dimensional post-stack seismic data; a's' i Is the first transformed data; Δa is the normalized amplitude value.
Thus, the specific steps of step two may also be described as:
the method comprises the steps of obtaining an amplitude minimum value and an amplitude maximum value of three-dimensional post-stack seismic data, and obtaining three-dimensional post-stack seismic data (namely first transformation data) with an amplitude minimum value of 0 by carrying out difference on the amplitude of the three-dimensional post-stack seismic data and the amplitude minimum value; the maximum value of the amplitude is differenced with the minimum value of the amplitude to obtain a normalized amplitude value; the three-dimensional post-stack seismic data (namely first transformation data) with the amplitude minimum value of 0 and the normalized amplitude value are taken as a quotient to obtain the processed three-dimensional post-stack seismic data, wherein the amplitude range of the data is between 0 and 1, and the data is specifically expressed by adopting the following calculation formula:
wherein A' i The processed three-dimensional post-stack seismic data; a is that i Is the maximum amplitude; a is that max Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
And step three, taking the processed three-dimensional post-stack seismic data as input of a river channel and fault detection model to obtain a river channel and fault detection result.
Specifically, as shown in fig. 11, 12 and 13, the data size is 700×1600×400, the spatial sampling interval is 12.5m, the temporal sampling interval is 2ms, the vertical coordinate is the vertical measurement line number, the horizontal coordinate is the connection measurement line number, and the vertical coordinate is the time. By adopting the method for detection, the detection result is obtained, and as shown in fig. 12 and 13, all river channel positions (dark color positions) and fault positions (dark color positions) in the three-dimensional post-stack seismic data with the complex structural background are accurately detected.
Further, the method further comprises:
synthesizing a plurality of sample data based on geology and geophysical theory, and constructing a training sample set;
and taking the training sample set as input of a deep learning neural network, and training to obtain the river channel and fault detection model.
Specifically, in order to ensure generalization capability of the river channel and the fault detection model, a training sample set for training the river channel and the fault detection model is processed (normalized), so that each sample consists of synthesized three-dimensional post-stack seismic data with a numerical range between 0 and 1, and corresponding accurate labeling three-dimensional river channel data and accurate labeling three-dimensional fault data. Therefore, in order to ensure the consistency of the input of the pre-trained river channel and fault detection model, the input three-dimensional post-stack seismic data is normalized. In order to overcome the problem, 9600 pairs of synthesized three-dimensional post-stack seismic data with various and complex structural modes, corresponding accurate labeling three-dimensional river channel data and accurate labeling three-dimensional fault data with the size of 96 x 96 are automatically generated based on geological and geophysical theory, and a training sample set is formed.
In the embodiment of the invention, the river channel and the fault detection model have two task outputs, namely, the processed three-dimensional post-stack seismic data are input into the river channel and the fault detection model which are trained in advance for prediction, one branch of the river channel and the fault detection model can output a river channel detection result, and the other branch of the network model can output a fault detection result. In the embodiment of the invention, the elements such as the number of convolution layers, the size of convolution kernel, the step length, the activation function and the like of the river channel and fault detection model are designed according to the requirements of the invention. According to the river channel and fault detection model, an encoder part, a decoder part and an output part are sequentially built according to a deep learning principle:
the encoder section consists of five stages for extracting features of different scales from the input three-dimensional post-stack seismic data. Each stage contains one or two convolutional layers and a residual function is learned, i.e. the input of each stage is added to the output of the last convolutional layer of that stage. The introduction of the residual error learning mechanism is helpful to overcome the problem of performance degradation and improve the accuracy. In each stage, the convolution kernel size of the convolution layer is 3 x 3, pooling is achieved by a convolution operation with a convolution kernel size of 2 x 2 and a step size of 2. It can be noted that the number of features per stage doubles and the resolution halves. After each convolution layer, batch normalization (Batch Nom1 adaptation) and ReLU (Rectified Linear Unit) activation functions are applied to improve the stability and nonlinear approximation capabilities of the network.
The decoder section consists of four stages for systematically aggregating the multi-scale information. Similar to the encoder section, each stage also contains one or two convolutional layers, again employing a residual learning mechanism. The size of the convolution kernel of each stage is also 3 x 3, up-sampling is achieved by a deconvolution operation with a convolution kernel size of 2 x 2 and a step size of 2. Features extracted from the encoder section are connected to corresponding stages of the decoder section by a skip layer connection for spatial resolution compensation.
The output section consists of two branches sharing the same decoding characteristics, each branch consisting of two convolution layers of convolution kernel size 3 x 3 and one convolution layer of convolution kernel size l x l, followed by Batch normalization (Batch Nom1 adaptation) and sigmoid activation functions. The first branch is used for river channel detection tasks, and the second branch is used for fault detection tasks.
And during training, inputting the synthesized three-dimensional post-stack seismic data subjected to normalization processing into a river channel and fault detection model in batches, wherein the batch size is set to be 4. An adaptive moment estimation optimization algorithm is used to optimize the network, the learning rate is set to 0.0001, the total training period is set to 100, and all samples in the training sample set are traversed one period.
More specifically, the vertical coordinate in fig. 5, 6 and 7 is the vertical measurement line number, the horizontal coordinate is the connection measurement line number, and the vertical coordinate is the time. As shown in fig. 5, 6 and 7, in the first three-dimensional post-stack seismic data of the sample subjected to complex structural deformation (including a series of alternating fold deformation and fracture deformation), the river channel position and the fault position are accurately marked; in fig. 6, the river position is marked with 1, and the other positions are marked with 0; where the interrupt level in fig. 7 is labeled 1 and the other levels are labeled 0.
More specifically, the vertical coordinates of fig. 8, 9 and 10 are the vertical measurement numbers, the horizontal coordinates are the link measurement numbers, and the vertical coordinates are the time. As shown in fig. 8, 9 and 10, the second synthesized three-dimensional post-stack seismic data generated by the invention has rich and various fold and fault structure information, can be highly similar to actual data, and has accurately marked river channel positions and fault positions, wherein the river channel positions in fig. 9 are marked as 1, and other positions are marked as 0; where the interrupt level in fig. 10 is labeled 1 and the other levels are labeled 0.
Taking the first synthesized three-dimensional post-stack seismic data and the second synthesized three-dimensional post-stack seismic data as examples, accurate labeling samples are provided for training of river channel and fault detection models. The existence of a sufficient number of tag data in the training sample set lays a solid big data foundation for the rapid and accurate implementation of the river channel and fault synchronous detection method based on deep learning.
Example 2
As shown in fig. 3, an embodiment of the present invention further provides a device for detecting synchronization between a river and a fault, including:
a data acquisition module 10 for acquiring three-dimensional post-stack seismic data;
a data processing module 20, configured to process the three-dimensional post-stack seismic data based on an amplitude minimum value and an amplitude maximum value in the three-dimensional post-stack seismic data;
and the result output module 30 is used for taking the processed three-dimensional post-stack seismic data as input of a river channel and fault detection model to obtain river channel and fault detection results.
Further, as shown in fig. 4, the data processing module 20 specifically includes:
a data amplitude determining module 21 for determining an amplitude minimum and an amplitude maximum of the three-dimensional post-stack seismic data;
a normalized amplitude value determining module 22 for determining a normalized amplitude value based on the amplitude minimum value and the amplitude maximum value;
an amplitude value transformation module 23, configured to transform an amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value, to obtain first transformed data;
the data output module 24 is configured to obtain processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformed data.
Example 3
The embodiment of the invention provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the river channel and fault synchronous detection method when executing the computer program.
Example 4
The embodiment of the invention provides a machine-readable storage medium, which stores instructions for causing a machine to execute the river channel and fault synchronization detection method.
Through the technical scheme, detection accuracy and detection efficiency of river channels and faults are remarkably improved:
1. in the process of constructing the dual-task accurate labeling data set, the river channels with different forms are added into the model in the form of relative impedance, so that the river channel and fault detection model can adapt to detection of different lithology river channel positions formed in different deposition environments.
2. Because the number of the simulated riverways in different forms in the model is randomly set in the process of constructing the dual-task accurate labeling data set, and the direction, width, length, thickness and relative impedance value of the riverways change along with the space position, the riverway and fault detection model can adapt to the detection of the position of the complex riverway such as close inter-phase or mutual interweaving.
3. Because various folds and fracture deformation are carried out in the process of constructing the dual-task accurate labeling data set, and in addition, data augmentation and knowledge sharing among tasks are carried out, the river channel and the fault detection model can synchronously detect the river channel and the fault under the complex structural background, and further, the influence of the fault on the accurate detection of the river channel is effectively eliminated;
4. because the invention is based on a deep learning algorithm and performs operation on the GPU, the invention has higher calculation efficiency, and for a three-dimensional seismic data volume of 4.56GB, the detection of all river channels and faults in the whole three-dimensional seismic data volume can be completed only by 4.4 minutes by using the NVIDIA V100 GPU, and the manual interpretation needs days and the precision can not be ensured.
The foregoing details of the optional implementation of the embodiment of the present invention have been described in detail with reference to the accompanying drawings, but the embodiment of the present invention is not limited to the specific details of the foregoing implementation, and various simple modifications may be made to the technical solution of the embodiment of the present invention within the scope of the technical concept of the embodiment of the present invention, and these simple modifications all fall within the protection scope of the embodiment of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, various possible combinations of embodiments of the present invention are not described in detail.
Those skilled in the art will appreciate that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, including instructions for causing a single-chip microcomputer, chip or processor (processor) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In addition, any combination of various embodiments of the present invention may be performed, so long as the concept of the embodiments of the present invention is not violated, and the disclosure of the embodiments of the present invention should also be considered.
Claims (10)
1. A synchronous detection method for river channels and faults is characterized by comprising the following steps:
acquiring three-dimensional post-stack seismic data;
processing the three-dimensional post-stack seismic data based on an amplitude minimum value and an amplitude maximum value in the three-dimensional post-stack seismic data;
and taking the processed three-dimensional post-stack seismic data as input of a river channel and fault detection model to obtain a river channel and fault detection result.
2. The method of claim 1, wherein processing the three-dimensional post-stack seismic data based on an amplitude minimum and an amplitude maximum in the three-dimensional post-stack seismic data comprises:
determining an amplitude minimum value and an amplitude maximum value of the three-dimensional post-stack seismic data;
determining a normalized amplitude value based on the amplitude minimum and the amplitude maximum;
transforming the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first transformed data;
and obtaining the processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformation data.
3. The method of claim 2, wherein determining a normalized amplitude value based on the amplitude minimum and the amplitude maximum comprises:
the normalized amplitude value is calculated using the following calculation formula:
ΔA=A max -A min ;
wherein ΔA is a normalized amplitude value; a is that max Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
4. The method of claim 2, wherein transforming the amplitude value of each of the three-dimensional post-stack seismic data based on the amplitude minima to obtain first transformed data comprises:
the first transformation data is obtained using the following calculation formula:
A′ i =A i -A min ;
wherein A 'is' i Is the first transformed data; a is that i Is the maximum amplitude; a is that min Is the minimum value of the amplitude.
5. The method of claim 2, wherein deriving processed three-dimensional post-stack seismic data based on the normalized amplitude values and the first transformed data comprises:
the processed three-dimensional post-stack seismic data is calculated by using the following calculation formula:
wherein A' i The processed three-dimensional post-stack seismic data; a's' i Is the first transformed data; Δa is the normalized amplitude value.
6. The method according to claim 1, wherein the method further comprises:
synthesizing a plurality of sample data based on geology and geophysical theory, and constructing a training sample set;
and taking the training sample set as input of a deep learning neural network, and training to obtain the river channel and fault detection model.
7. Synchronous detection device of river course and fault, characterized by, include:
the data acquisition module is used for acquiring three-dimensional post-stack seismic data;
the data processing module is used for processing the three-dimensional post-stack seismic data based on the minimum amplitude value and the maximum amplitude value in the three-dimensional post-stack seismic data;
and the result output module is used for taking the processed three-dimensional post-stack seismic data as the input of a river channel and fault detection model to obtain a river channel and fault detection result.
8. The apparatus of claim 7, wherein the data processing module specifically comprises:
the data amplitude determining module is used for determining an amplitude minimum value and an amplitude maximum value of the three-dimensional post-stack seismic data;
the normalized amplitude value determining module is used for determining a normalized amplitude value based on the amplitude minimum value and the amplitude maximum value;
the amplitude value conversion module is used for converting the amplitude value of each data in the three-dimensional post-stack seismic data based on the amplitude minimum value to obtain first conversion data;
and the data output module is used for obtaining the processed three-dimensional post-stack seismic data based on the normalized amplitude value and the first transformation data.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of channel and fault synchronization detection of any one of claims 1-6 when the computer program is executed.
10. A machine-readable storage medium having instructions stored thereon for causing a machine to perform the method of channel and fault synchronization detection of any of claims 1-6.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211169806.4A CN117784225A (en) | 2022-09-22 | 2022-09-22 | Synchronous detection method and device for river channel and fault |
PCT/CN2022/138860 WO2024060427A1 (en) | 2022-09-22 | 2022-12-14 | River channel and fault synchronous test method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211169806.4A CN117784225A (en) | 2022-09-22 | 2022-09-22 | Synchronous detection method and device for river channel and fault |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117784225A true CN117784225A (en) | 2024-03-29 |
Family
ID=90382434
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211169806.4A Pending CN117784225A (en) | 2022-09-22 | 2022-09-22 | Synchronous detection method and device for river channel and fault |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN117784225A (en) |
WO (1) | WO2024060427A1 (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103792576A (en) * | 2014-01-28 | 2014-05-14 | 中国石油天然气股份有限公司 | Reservoir heterogeneous detection method and device based on gradient structure tensor |
CN103869358A (en) * | 2014-02-18 | 2014-06-18 | 中国石油天然气股份有限公司 | Fault identification method and equipment based on histogram equalization |
CN107632320A (en) * | 2017-08-21 | 2018-01-26 | 西安交通大学 | Seismic data Time-Frequency Analysis Method based on synchronous extraction S-transformation |
CN109655894A (en) * | 2017-10-12 | 2019-04-19 | 中国石油化工股份有限公司 | Carbonate rock ancient stream channel seismic inversion low frequency model construction method and system |
CN113296152A (en) * | 2020-02-21 | 2021-08-24 | 中国石油天然气集团有限公司 | Fault detection method and device |
CN113805235A (en) * | 2020-06-11 | 2021-12-17 | 中国石油天然气股份有限公司 | Three-dimensional seismic facies identification method and device based on convolutional neural network |
CN113902769A (en) * | 2021-08-18 | 2022-01-07 | 南方海洋科学与工程广东省实验室(广州) | Seismic fault identification method based on deep learning semantic segmentation |
US20220027126A1 (en) * | 2020-07-22 | 2022-01-27 | Shanghai Cambricon Information Technology Co., Ltd. | Data normalization processing method, storage medium and computer equipment |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9523781B2 (en) * | 2012-12-27 | 2016-12-20 | Schlumberger Technology Corporation | Normalization seismic attribute |
CN113703044B (en) * | 2020-05-20 | 2024-04-09 | 中国石油化工股份有限公司 | Correction method and device for ancient river channel width, electronic equipment and storage medium |
CN113900141B (en) * | 2020-07-06 | 2024-05-28 | 中国石油天然气股份有限公司 | Oil-gas distribution prediction method and device |
CN114462113A (en) * | 2020-10-21 | 2022-05-10 | 中国石油化工股份有限公司 | Concealed river depicting method and device based on amplitude ratio, electronic equipment and medium |
CN114755721A (en) * | 2021-01-12 | 2022-07-15 | 中国石油化工股份有限公司 | Unet-based river channel sand body top surface prediction method |
-
2022
- 2022-09-22 CN CN202211169806.4A patent/CN117784225A/en active Pending
- 2022-12-14 WO PCT/CN2022/138860 patent/WO2024060427A1/en unknown
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103792576A (en) * | 2014-01-28 | 2014-05-14 | 中国石油天然气股份有限公司 | Reservoir heterogeneous detection method and device based on gradient structure tensor |
CN103869358A (en) * | 2014-02-18 | 2014-06-18 | 中国石油天然气股份有限公司 | Fault identification method and equipment based on histogram equalization |
CN107632320A (en) * | 2017-08-21 | 2018-01-26 | 西安交通大学 | Seismic data Time-Frequency Analysis Method based on synchronous extraction S-transformation |
CN109655894A (en) * | 2017-10-12 | 2019-04-19 | 中国石油化工股份有限公司 | Carbonate rock ancient stream channel seismic inversion low frequency model construction method and system |
CN113296152A (en) * | 2020-02-21 | 2021-08-24 | 中国石油天然气集团有限公司 | Fault detection method and device |
CN113805235A (en) * | 2020-06-11 | 2021-12-17 | 中国石油天然气股份有限公司 | Three-dimensional seismic facies identification method and device based on convolutional neural network |
US20220027126A1 (en) * | 2020-07-22 | 2022-01-27 | Shanghai Cambricon Information Technology Co., Ltd. | Data normalization processing method, storage medium and computer equipment |
CN113902769A (en) * | 2021-08-18 | 2022-01-07 | 南方海洋科学与工程广东省实验室(广州) | Seismic fault identification method based on deep learning semantic segmentation |
Also Published As
Publication number | Publication date |
---|---|
WO2024060427A1 (en) | 2024-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110657984B (en) | Planetary gearbox fault diagnosis method based on reinforced capsule network | |
CN113095413B (en) | Variable working condition fault diagnosis method, system, storage medium and equipment | |
CN111695473B (en) | Tropical cyclone strength objective monitoring method based on long-short-term memory network model | |
CN112132102B (en) | Intelligent fault diagnosis method combining deep neural network with artificial bee colony optimization | |
CN113486574A (en) | Sound velocity profile completion method and device based on historical data and machine learning | |
CN103268607A (en) | Common object detection method on weak supervision condition | |
CN115451803B (en) | Water gate real-time monitoring and early warning method based on fusion of GNSS and measuring robot | |
CN115935139A (en) | Space field interpolation method for ocean observation data | |
CN113822201A (en) | Deep learning method for underwater object shape recognition based on flow field velocity component time course | |
CN114565594A (en) | Image anomaly detection method based on soft mask contrast loss | |
CN115688864A (en) | Shield tunneling machine cutter head health assessment method, system, medium, equipment and terminal | |
CN116628959A (en) | Method and device for detecting migration of pollutants in sand-carrying river and electronic equipment | |
CN112766301A (en) | Similarity judgment method for indicator diagram of oil extraction machine | |
CN112668606A (en) | Step type landslide displacement prediction method based on gradient elevator and quadratic programming | |
Tobely et al. | Position detection of unexploded ordnance from airborne magnetic anomaly data using 3-D self organized feature map | |
CN115880505B (en) | Low-order fault intelligent identification method for target edge detection neural network | |
CN117784225A (en) | Synchronous detection method and device for river channel and fault | |
CN114385619B (en) | Multi-channel ocean observation time sequence scalar data missing value prediction method and system | |
CN116224265A (en) | Ground penetrating radar data inversion method and device, computer equipment and storage medium | |
CN115577612A (en) | Tunnel resistivity polarizability joint inversion gradient optimization method based on deep learning | |
CN113496070B (en) | Method, device, equipment and medium for processing stratum capture section curve | |
CN110503142B (en) | Multi-source remote sensing product hierarchy Bayesian fusion method based on space-time random effect addition process model | |
CN113050191B (en) | Shale oil TOC prediction method and device based on double parameters | |
CN113392705A (en) | Method for identifying pipeline leakage target in desert area based on convolutional neural network | |
CN118501951B (en) | Offshore drilling well Zhou Shengsu imaging method, device, apparatus and storage medium |
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 |