Seismic data reconstruction method, device, equipment, medium and product
By converting seismic data to the vector offset domain and performing transfer learning, the correlation between adjacent seismic traces is utilized to solve the problem of low seismic data reconstruction efficiency and achieve efficient data reconstruction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2026-03-13
AI Technical Summary
Existing deep learning-based seismic data reconstruction methods are inefficient, consume a lot of computing and storage resources, and have long reconstruction cycles.
Seismic data is converted to the vector offset domain, and transfer learning is performed using the correlation between adjacent seismic traces to reduce the number of times the weight coefficients are updated. The data reconstruction order is determined through dynamic correction and adjacency relationship, and initial and target data reconstruction models are constructed.
It improves the efficiency of seismic data reconstruction, reduces the amount of computation, and shortens the reconstruction cycle.
Smart Images
Figure CN121657104A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, storage medium, and program product for reconstructing seismic data. Background Technology
[0002] Seismic data is crucial for analyzing subsurface structures and lithology. The quality of seismic data directly impacts the accuracy of seismic data analysis and interpretation. Due to economic costs or physical limitations, initial seismic data is often undersampled or irregularly distributed spatially, significantly increasing the difficulty of subsequent analysis. Therefore, it is necessary to restore and reconstruct the initial seismic data before analysis.
[0003] Currently, the reconstruction methods for initial seismic data are mainly divided into signal processing methods and deep learning methods. With the rapid development of artificial intelligence technology in recent years, seismic data reconstruction methods based on deep learning have received increasing attention. Existing deep learning-based seismic data reconstruction methods require a complete learning process for each set of seismic data, which involves thousands of iterations. For massive amounts of seismic data, this results in long data processing cycles and low efficiency. Furthermore, the reconstruction process consumes significant computational and storage resources. Summary of the Invention
[0004] This invention provides a method, apparatus, electronic device, storage medium, and program product for reconstructing seismic data, in order to solve the problems of low reconstruction efficiency and long cycle of seismic data. By converting seismic data to the vector offset domain and performing transfer learning based on the correlation between adjacent seismic traces in the vector offset domain, the number of times the weight coefficients in the data reconstruction model are updated is greatly reduced, the amount of computation for data reconstruction is reduced, and the reconstruction efficiency of seismic data is improved.
[0005] According to one aspect of the present invention, a method for reconstructing seismic data is provided, the method comprising:
[0006] Dynamic correction processing is performed on the first seismic data to determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the raw seismic signal acquired in the target area;
[0007] The target seismic gather is determined based on the amount of missing data in each pre-acquired seismic gather;
[0008] Based on the adjacency relationships between seismic gathers, the data reconstruction order of other seismic gathers, excluding the target seismic gather, is determined.
[0009] Based on the initial data reconstruction model, the target seismic gather is reconstructed to obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather.
[0010] Following the data reconstruction order, and based on the target data reconstruction model, data reconstruction is performed on other seismic gathers besides the target seismic gather, resulting in the data reconstruction results for each seismic gather.
[0011] According to another aspect of the present invention, a seismic data reconstruction apparatus is provided, the apparatus comprising:
[0012] The seismic gather determination module is used to perform dynamic correction processing on the first seismic data and determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the original seismic signal acquired in the target area;
[0013] The target gather determination module is used to determine the target seismic gather based on the amount of missing data in each pre-acquired seismic gather.
[0014] The reconstruction order determination module is used to determine the data reconstruction order of seismic gathers other than the target seismic gather based on the adjacency relationship between them.
[0015] The target model determination module is used to reconstruct the target seismic gather based on the initial data reconstruction model, and obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather;
[0016] The reconstruction result determination module is used to reconstruct data for other seismic gathers besides the target seismic gather according to the data reconstruction order and based on the target data reconstruction model, so as to obtain the data reconstruction results of each seismic gather.
[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0018] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the seismic data reconstruction method according to any embodiment of the present invention.
[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the seismic data reconstruction method according to any embodiment of the present invention.
[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the seismic data reconstruction method according to any embodiment of the present invention.
[0021] The technical solution of this invention involves performing dynamic correction processing on first seismic data to determine at least two seismic gathers in the vector offset domain. The first seismic data consists of raw seismic signals acquired in the target area. A target seismic gather is determined based on the amount of missing data in each pre-acquired seismic gather. The data reconstruction order of other seismic gathers (excluding the target seismic gather) is determined based on the adjacency relationships between the seismic gathers. Data reconstruction is performed on the target seismic gather based on the initial data reconstruction model, yielding the data reconstruction result of the target seismic gather and the target data reconstruction model. The target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather. Following the data reconstruction order, and based on the target data reconstruction model, data reconstruction is performed on other seismic gathers (excluding the target seismic gather), yielding the data reconstruction results for each seismic gather. This technical solution solves the problems of low reconstruction efficiency and long cycle time for seismic data. By converting seismic data to the vector offset domain and performing transfer learning based on the correlation between adjacent seismic traces within the vector offset domain, the number of updates to the weight coefficients in the data reconstruction model is greatly reduced, lowering the computational load of data reconstruction and improving the reconstruction efficiency of seismic data.
[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a flowchart of a seismic data reconstruction method provided in Embodiment 1 of the present invention;
[0025] Figure 2This is a flowchart of a seismic data reconstruction method provided in Embodiment 2 of the present invention;
[0026] Figure 3 This is a schematic diagram of a seismic data reconstruction device according to Embodiment 3 of the present invention;
[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the seismic data reconstruction method of this invention. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.
[0030] Example 1
[0031] Figure 1 This is a flowchart illustrating a seismic data reconstruction method according to Embodiment 1 of the present invention. This embodiment is applicable to seismic data analysis scenarios. The method can be executed by a seismic data reconstruction device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:
[0032] S110. Perform dynamic correction processing on the first seismic data to determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the original seismic signal acquired in the target area.
[0033] This scheme can be executed by electronic devices such as computers and servers. The electronic devices can acquire the first seismic data of the target area and perform dynamic correction processing on the first seismic data based on a stacking velocity model. The first seismic data can be the raw seismic signal acquired in the target area. After dynamic correction processing, the electronic devices can perform gather sorting on the first seismic data to obtain multiple seismic gathers in the offset vector tile domain. Understandably, adjacent seismic gathers in the offset vector tile domain have similarities, which is beneficial for transfer learning during data reconstruction.
[0034] S120. Determine the target seismic gather based on the amount of missing data in each pre-acquired seismic gather.
[0035] Electronic devices can pre-detect missing data in each seismic trace set to determine the amount of missing data in each set. The electronic devices can then sort the seismic trace sets by the amount of missing data and select the one with the smallest amount of missing data as the target seismic trace set. This allows the data reconstruction model to learn more comprehensive seismic features during its initial learning, reducing the difficulty of learning seismic features in subsequent seismic trace sets.
[0036] S130. Based on the adjacency relationship between each seismic gather, determine the data reconstruction order of other seismic gathers besides the target seismic gather.
[0037] It is understandable that seismic gathers are geographically adjacent. The seismic characteristics of adjacent geographical locations are correlated. Electronic devices can determine the data reconstruction order based on the adjacency relationships between seismic gathers. This data reconstruction order can be the sequence in which the seismic gathers are reconstructed. In this order, the target seismic gather can be the first to undergo data reconstruction. Adjacent seismic gathers to the target gather can be reconstructed after the target gather's data reconstruction is complete, and so on. The timing of the start of data reconstruction for each seismic gather depends on whether its adjacent seismic gather has completed its reconstruction. For example, the target seismic gather is gather A, and it has two adjacent seismic gathers: gather B and gather C. Gathering B has two adjacent seismic gathers: gather D and gather E. The data reconstruction sequence can include: seismic gather A -> seismic gather B (seismic gather C) -> seismic gather D (seismic gather E). That is, after the data reconstruction of seismic gather A is completed, the data reconstruction of seismic gather B and seismic gather C is performed. After the data reconstruction of seismic gather B is completed, the data reconstruction of seismic gather D and seismic gather E is performed.
[0038] S140. Based on the initial data reconstruction model, the target seismic gather is reconstructed to obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather.
[0039] Electronic devices can construct initial data reconstruction models based on deep learning theory. For example, the initial data reconstruction model can be a semantic segmentation model based on network structures such as U-Net and MultiResUNet. The data reconstruction model can include encoding units and decoding units. The encoding unit is used to extract seismic features from the seismic trace set, and the decoding unit is used to reconstruct the missing data in the seismic trace set based on the seismic features, thereby obtaining fully sampled seismic data.
[0040] Electronic devices can input the target seismic gather into the initial data reconstruction model. The initial data reconstruction model can reconstruct the target seismic gather multiple times until the output data of the initial data reconstruction model meets the preset data evaluation index. The output data is then used as the data reconstruction result of the target seismic gather.
[0041] Electronic devices can also preset the number of iterations, input the target seismic gather into the initial data reconstruction model, and the initial data reconstruction model can perform data reconstruction of the target seismic gather for a preset number of iterations. The output data of the initial data reconstruction model at the last data reconstruction is used as the data reconstruction result of the target seismic gather.
[0042] It's easy to understand that whether the data evaluation metric or the number of iterations is used as the stopping condition for data reconstruction, the weight coefficients in the initial data reconstruction model are continuously adjusted during the iterative process based on each output data. Electronic devices can use the initial data reconstruction model where the stopping condition is met as the target data reconstruction model.
[0043] S150. Following the data reconstruction order, based on the target data reconstruction model, reconstruct the data of other seismic gathers besides the target seismic gather to obtain the data reconstruction results of each seismic gather.
[0044] The electronic device can, according to the data reconstruction order, use the seismic gathers that require data reconstruction after the target seismic gather as the new target seismic gathers. Based on the target data reconstruction model, the target seismic gathers are reconstructed to obtain the data reconstruction results. The data reconstruction model outputting the target seismic gather's data reconstruction results is then used as the new target data reconstruction model to reconstruct the seismic gathers that follow the target seismic gather, until all seismic gathers have been reconstructed, thus obtaining the data reconstruction results for each seismic gather.
[0045] The technical solution of this invention involves performing dynamic correction processing on first seismic data to determine at least two seismic gathers in the vector offset domain. The first seismic data consists of raw seismic signals acquired in the target area. A target seismic gather is determined based on the amount of missing data in each pre-acquired seismic gather. The data reconstruction order of other seismic gathers (excluding the target seismic gather) is determined based on the adjacency relationships between the seismic gathers. Data reconstruction is performed on the target seismic gather based on the initial data reconstruction model, yielding the data reconstruction result of the target seismic gather and the target data reconstruction model. The target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather. Following the data reconstruction order, and based on the target data reconstruction model, data reconstruction is performed on other seismic gathers (excluding the target seismic gather), yielding the data reconstruction results for each seismic gather. This technical solution solves the problems of low reconstruction efficiency and long cycle time for seismic data. By converting seismic data to the vector offset domain and performing transfer learning based on the correlation between adjacent seismic traces within the vector offset domain, the number of updates to the weight coefficients in the data reconstruction model is greatly reduced, lowering the computational load of data reconstruction and improving the reconstruction efficiency of seismic data.
[0046] Example 2
[0047] Figure 2 This is a flowchart of a seismic data reconstruction method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2 As shown, the method includes:
[0048] S201. Perform dynamic correction processing on the first seismic data to determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the original seismic signal acquired in the target area.
[0049] In this scheme, the data reconstruction model can be built based on MultiResUNet. Compared with U-Net, MultiResUNet has the following characteristics: (1) all filter operators in the network structure are three-dimensional; (2) the convolutional layers are all replaced with multi-resolution (MultiRes) units, which can extract multi-scale features but have fewer parameters; (3) the skip connections in the U-Net network are replaced with residual path units; (4) the downsampling layer in the encoder uses a 3×3×3 convolutional kernel with a stride of 2×2×2, and the upsampling in the decoder uses nearest neighbor interpolation. The multi-resolution (MultiRes) convolutional layers in MultiResUNet can extract information of different shapes and scales and have fewer parameters, making them more suitable for solving complex seismic data reconstruction problems. In order to obtain similarity information of different dimensions of seismic data, each multi-resolution convolutional layer in the data reconstruction model can use a three-dimensional convolutional kernel.
[0050] S202. Sort the seismic gathers by the amount of missing data and select the seismic gather with the smallest amount of missing data as the target seismic gather.
[0051] Understandably, electronic devices can sort the missing data of each seismic trace set and select the seismic trace set with the smallest missing data as the target seismic trace set. This allows the data reconstruction model to learn more comprehensive seismic features during its initial learning, reducing the difficulty of learning seismic features in subsequent seismic trace sets.
[0052] S203. Based on the adjacency relationship between each seismic gather, determine the data reconstruction order of other seismic gathers besides the target seismic gather.
[0053] S204. Based on the initial data reconstruction model, the target seismic gather is reconstructed to obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather.
[0054] In one feasible approach, the data reconstruction model includes a data reconstruction network and weight coefficients;
[0055] The process of reconstructing the target seismic gather based on the initial data reconstruction model to obtain the data reconstruction results of the target seismic gather and the target data reconstruction model includes:
[0056] The initial data reconstruction model is determined based on the data reconstruction network and the randomly generated weight coefficients;
[0057] Based on the initial data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficients of the last data reconstruction matching are output.
[0058] The target data reconstruction model is determined based on the weight coefficients matched in the last data reconstruction.
[0059] As is easily understood, a data reconstruction model includes a data reconstruction network and weight coefficients. The data reconstruction network represents the network structure of the data reconstruction model, and the weight coefficients represent the connection strength between neurons in the data reconstruction network. In the initial stage of the data reconstruction model, the electronic device can randomly generate a set of weight coefficients that match the data reconstruction network, thus forming the initial data reconstruction model.
[0060] The electronic device can pre-set the number of iterations, input the target seismic gather into the initial data reconstruction model, perform at least one data reconstruction, and use the output data of the initial data reconstruction model in the last data reconstruction as the data reconstruction result of the target seismic gather. Simultaneously, the electronic device can extract the weight coefficients from the initial data reconstruction model in the last data reconstruction, and combine the weight coefficients matched in the last data reconstruction with the data reconstruction network to obtain the target data reconstruction model.
[0061] S205. Update the target seismic gather using neighboring seismic gathers.
[0062] S206. Based on the target data reconstruction model, reconstruct the target seismic gather, determine the data reconstruction results of the target seismic gather, and update the target data reconstruction model.
[0063] In this scheme, the step of reconstructing the target seismic gather based on the target data reconstruction model, determining the data reconstruction result of the target seismic gather, and updating the target data reconstruction model includes:
[0064] Based on the target data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficient of the last data reconstruction matching is output.
[0065] Update the target data reconstruction model based on the weight coefficients matched in the last data reconstruction.
[0066] In this scheme, the electronic device can be pre-set with the number of iterations, input the target seismic gather into the target data reconstruction model, perform at least one data reconstruction, and use the output data of the target data reconstruction model from the last data reconstruction as the data reconstruction result of the target seismic gather. Simultaneously, the electronic device can extract the weight coefficients from the target data reconstruction model from the last data reconstruction, and combine the weight coefficients matched from the last data reconstruction with the data reconstruction network to obtain a new target data reconstruction model.
[0067] S207. Determine whether all seismic gathers have completed data reconstruction.
[0068] After each target seismic gather data reconstruction is completed, the electronic device can determine whether all seismic gathers have completed data reconstruction. If all seismic gathers have completed data reconstruction, then execute S208-S209; if any seismic gathers have not completed data reconstruction, then return to execute S205.
[0069] S208. Output the data reconstruction results of each seismic gather.
[0070] S209. Perform reaction correction processing on the data reconstruction results of each seismic gather to obtain the second seismic data.
[0071] Understandably, the data reconstruction process of each seismic gather is implemented in the vector offset domain. For the convenience of subsequent seismic data imaging, inversion and other operations, electronic equipment can perform reaction correction processing on the data reconstruction results of each seismic gather to obtain the second seismic data, that is, the reconstructed seismic data.
[0072] The technical solution of this invention involves performing dynamic correction processing on first seismic data to determine at least two seismic gathers in the vector offset domain. The first seismic data consists of raw seismic signals acquired in the target area. A target seismic gather is determined based on the amount of missing data in each pre-acquired seismic gather. The data reconstruction order of other seismic gathers (excluding the target seismic gather) is determined based on the adjacency relationships between the seismic gathers. Data reconstruction is performed on the target seismic gather based on the initial data reconstruction model, yielding the data reconstruction result of the target seismic gather and the target data reconstruction model. The target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather. Following the data reconstruction order, and based on the target data reconstruction model, data reconstruction is performed on other seismic gathers (excluding the target seismic gather), yielding the data reconstruction results for each seismic gather. This technical solution solves the problems of low reconstruction efficiency and long cycle time for seismic data. By converting seismic data to the vector offset domain and performing transfer learning based on the correlation between adjacent seismic traces within the vector offset domain, the number of updates to the weight coefficients in the data reconstruction model is greatly reduced, lowering the computational load of data reconstruction and improving the reconstruction efficiency of seismic data.
[0073] Example 3
[0074] Figure 3 This is a schematic diagram of a seismic data reconstruction device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:
[0075] The seismic gather determination module 310 is used to perform dynamic correction processing on the first seismic data and determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the original seismic signal acquired in the target area;
[0076] The target gather determination module 320 is used to determine the target seismic gather based on the amount of missing data in each pre-acquired seismic gather;
[0077] The reconstruction order determination module 330 is used to determine the data reconstruction order of seismic gathers other than the target seismic gather based on the adjacency relationship between each seismic gather;
[0078] The target model determination module 340 is used to reconstruct the target seismic gather based on the initial data reconstruction model, and obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather;
[0079] The reconstruction result determination module 350 is used to reconstruct the data of other seismic gathers besides the target seismic gather according to the data reconstruction order and based on the target data reconstruction model, so as to obtain the data reconstruction results of each seismic gather.
[0080] In this solution, the target gather determination module 320 is specifically used for:
[0081] The seismic gathers are sorted by the amount of missing data, and the seismic gather with the smallest amount of missing data is selected as the target seismic gather.
[0082] In one feasible approach, the data reconstruction model includes a data reconstruction network and weight coefficients;
[0083] The target model determination module 340 is specifically used for:
[0084] The initial data reconstruction model is determined based on the data reconstruction network and the randomly generated weight coefficients;
[0085] Based on the initial data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficients of the last data reconstruction matching are output.
[0086] The target data reconstruction model is determined based on the weight coefficients matched in the last data reconstruction.
[0087] In a preferred embodiment, the reconstruction result determination module 350 is specifically used for:
[0088] Update the target seismic gather using neighboring seismic gathers;
[0089] Based on the target data reconstruction model, the target seismic gathers are reconstructed, the data reconstruction results of the target seismic gathers are determined, and the target data reconstruction model is updated.
[0090] Return to the process of updating the target seismic gather using neighboring seismic gathers, reconstructing the target seismic gather based on the target data reconstruction model, until all seismic gathers have been reconstructed, and outputting the data reconstruction results of each seismic gather.
[0091] Based on the above scheme, optionally, the step of reconstructing the target seismic gather based on the target data reconstruction model, determining the data reconstruction result of the target seismic gather, and updating the target data reconstruction model includes:
[0092] Based on the target data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficient of the last data reconstruction matching is output.
[0093] Update the target data reconstruction model based on the weight coefficients matched in the last data reconstruction.
[0094] Based on the above scheme, the device also includes a reaction correction module, which is used to perform reaction correction processing on the data reconstruction results of each seismic gather after obtaining the data reconstruction results of each seismic gather, so as to obtain the second seismic data.
[0095] The seismic data reconstruction apparatus provided in this embodiment of the invention can execute the seismic data reconstruction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.
[0096] Example 4
[0097] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0098] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.
[0099] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0100] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as methods for reconstructing seismic data.
[0101] In some embodiments, the seismic data reconstruction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the seismic data reconstruction method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the seismic data reconstruction method by any other suitable means (e.g., by means of firmware).
[0102] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.
[0103] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable seismic data reconstruction apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0104] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0105] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0106] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0107] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0108] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0109] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for reconstructing seismic data, characterized in that, The method includes: Dynamic correction processing is performed on the first seismic data to determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the raw seismic signal acquired in the target area; The target seismic gather is determined based on the amount of missing data in each pre-acquired seismic gather; Based on the adjacency relationships between seismic gathers, the data reconstruction order of other seismic gathers, excluding the target seismic gather, is determined. Based on the initial data reconstruction model, the target seismic gather is reconstructed to obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather. Following the data reconstruction order, and based on the target data reconstruction model, data reconstruction is performed on other seismic gathers besides the target seismic gather, resulting in the data reconstruction results for each seismic gather.
2. The method according to claim 1, characterized in that, The step of determining the target seismic gather based on the amount of missing data in each pre-acquired seismic gather includes: The seismic gathers are sorted by the amount of missing data, and the seismic gather with the smallest amount of missing data is selected as the target seismic gather.
3. The method according to claim 1, characterized in that, The data reconstruction model includes a data reconstruction network and weight coefficients; The process of reconstructing the target seismic gather based on the initial data reconstruction model to obtain the data reconstruction results of the target seismic gather and the target data reconstruction model includes: The initial data reconstruction model is determined based on the data reconstruction network and the randomly generated weight coefficients; Based on the initial data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficients of the last data reconstruction matching are output. The target data reconstruction model is determined based on the weight coefficients matched in the last data reconstruction.
4. The method according to claim 1, characterized in that, The process involves reconstructing data for all seismic gathers except the target seismic gather, based on the target data reconstruction model and following the data reconstruction order, to obtain the data reconstruction results for each seismic gather, including: Update the target seismic gather using neighboring seismic gathers; Based on the target data reconstruction model, the target seismic gathers are reconstructed, the data reconstruction results of the target seismic gathers are determined, and the target data reconstruction model is updated. Return to the process of updating the target seismic gather using neighboring seismic gathers, reconstructing the target seismic gather based on the target data reconstruction model, until all seismic gathers have been reconstructed, and outputting the data reconstruction results of each seismic gather.
5. The method according to claim 4, characterized in that, The process of reconstructing the target seismic gather based on the target data reconstruction model, determining the data reconstruction result of the target seismic gather, and updating the target data reconstruction model includes: Based on the target data reconstruction model, the target seismic gather is reconstructed at least once to obtain the data reconstruction result of the target seismic gather, and the weight coefficient of the last data reconstruction matching is output. Update the target data reconstruction model based on the weight coefficients matched in the last data reconstruction.
6. The method according to claim 1, characterized in that, After obtaining the data reconstruction results of each seismic gather, the method further includes: The data reconstruction results of each seismic gather are subjected to reaction correction processing to obtain the second seismic data.
7. A seismic data reconstruction device, characterized in that, The device includes: The seismic gather determination module is used to perform dynamic correction processing on the first seismic data and determine at least two seismic gathers in the vector offset domain; wherein, the first seismic data is the original seismic signal acquired in the target area; The target gather determination module is used to determine the target seismic gather based on the amount of missing data in each pre-acquired seismic gather. The reconstruction order determination module is used to determine the data reconstruction order of seismic gathers other than the target seismic gather based on the adjacency relationship between them. The target model determination module is used to reconstruct the target seismic gather based on the initial data reconstruction model, and obtain the data reconstruction result of the target seismic gather and the target data reconstruction model; wherein, the target data reconstruction model is the data reconstruction model that outputs the data reconstruction result of the target seismic gather; The reconstruction result determination module is used to reconstruct data for other seismic gathers besides the target seismic gather according to the data reconstruction order and based on the target data reconstruction model, so as to obtain the data reconstruction results of each seismic gather.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the seismic data reconstruction method according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for reconstructing seismic data according to any one of claims 1-6.
10. A computer program product comprising a computer program that, when executed by a processor, implements a method for reconstructing seismic data according to any one of claims 1-6.