Calculation method and device for effective elastic thickness of lithosphere

Abstract

The invention discloses a lithosphere effective elastic thickness calculation method and device, and relates to the technical field of geophysical geological resource exploration. According to the method, actually measured topographic data and actually measured gravity abnormal data in a research area are processed by using a trained lithosphere effective elastic thickness prediction model; after the deep learning model based on data driving is trained, proper parameters do not need to be selected during calculation, the problem that calculation results of the effective elastic thickness of the lithosphere are inconsistent due to improper parameter selection in the inversion process of a spectrum analysis method can be solved, and the calculation accuracy of the lithosphere is improved. And the accuracy and reliability of a calculation result are improved.

Description

Technical Field

[0001] The present application relates to the technical field of geophysical geological resource exploration, and in particular to a method and device for calculating the effective elastic thickness of the lithosphere based on a deep learning network. Background Art

[0002] The strength of the lithosphere and how it responds to loading and unloading are fundamental issues with wide-ranging implications in geodynamic research. e ) is a parameter that describes the strength of the lithosphere and is the response of the lithosphere to bending deformation. The amplitude and spatial scale of the lithosphere bending are controlled by its T e So, T e It is a comprehensive reflection of the rheological, strength structure and stress effects of the lithosphere. e It can explain information such as the temperature structure of the lithosphere, stress distribution, crust-mantle coupling state, earthquake generation mechanism, craton stability, anisotropy and inheritance of the lithosphere fabric, and has key guiding significance for in-depth research on continental evolution and dynamic processes.

[0003] The current mainstream method for calculating the effective elastic thickness of the lithosphere is the spectral analysis method. Previous researchers have conducted a lot of research on this method and applied it to different research areas, obtaining corresponding interpretation results, which has played an important role in the study of continental evolution and dynamic processes. However, due to different parameter selection, different researchers may obtain different results even in the same research area, resulting in inconsistent calculation results. Summary of the invention

[0004] The purpose of this application is to provide a method and device for calculating the effective elastic thickness of the lithosphere, which can overcome the problem of inconsistent calculation results of the effective elastic thickness of the lithosphere caused by improper parameter selection during the inversion process of the spectral analysis method, thereby improving the accuracy and reliability of the calculation results.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for calculating the effective elastic thickness of the lithosphere, comprising:

[0007] Obtain measured topographic data and measured gravity anomaly data in the study area;

[0008] The measured topographic data and the measured gravity anomaly data are used as input, and the lithosphere effective elastic thickness value is output using a trained lithosphere effective elastic thickness prediction model.

[0009] Optionally, the lithosphere effective elastic thickness prediction model is a neural network model.

[0010] Optionally, the training process of the lithosphere effective elastic thickness prediction model specifically includes:

[0011] Simulating topographic data and gravity anomaly data of a lithosphere with effective elastic thickness under the action of external forces according to a forward modeling method and a flexural equation, wherein the flexural equation is used to describe the bending degree of an elastic thin plate of the lithosphere under the action of external forces;

[0012] The topographic data and gravity anomaly data are used as feature data, and the effective elastic thickness is used as label data to train the lithosphere effective elastic thickness prediction model.

[0013] Optionally, the number of input channels in the lithosphere effective elastic thickness prediction model is 2, and the number of output channels is 1.

[0014] Optionally, the activation function in the lithosphere effective elastic thickness prediction model uses a ReLU function in the middle layer and a Sigmoid function in the last layer.

[0015] Optionally, the upsampling process in the lithosphere effective elastic thickness prediction model is subjected to batch normalization.

[0016] Optionally, the optimizer in the lithosphere effective elastic thickness prediction model uses the AdamW algorithm.

[0017] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-mentioned methods for calculating the effective elastic thickness of the lithosphere.

[0018] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for calculating the effective elastic thickness of the lithosphere.

[0019] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for calculating the effective elastic thickness of the lithosphere.

[0020] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0021] The present application provides a method and device for calculating the effective elastic thickness of the lithosphere. The method processes the measured topographic data and the measured gravity anomaly data in the study area by using a trained prediction model for the effective elastic thickness of the lithosphere to obtain the effective elastic thickness value of the lithosphere. After the data-driven deep learning model is trained, there is no need to select appropriate parameters during calculation. The method can overcome the problem of inconsistent calculation results of the effective elastic thickness of the lithosphere caused by improper parameter selection during the inversion process of the spectral analysis method, thereby improving the accuracy and reliability of the calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is an application environment diagram of a method for calculating effective elastic thickness of the lithosphere in Example 1 of the present application;

[0024] Figure 2 A schematic flow chart of a method for calculating the effective elastic thickness of the lithosphere provided in Example 1 of the present application;

[0025] Figure 3 is the T distributed in the form of a linear frequency modulation signal in Example 1 of the present application e Schematic diagram of the results;

[0026] Figure 4 This is a schematic diagram of the U-net calculation results obtained when testing the U-net method in Example 1 of the present application;

[0027] Figure 5 This is a schematic diagram of the calculation results obtained when the U-net method is tested in Example 1 of the present application using the traditional wavelet method and the center wave number |k0|=2.668;

[0028] Figure 6 This is a schematic diagram of the calculation results obtained when the U-net method is tested in Example 1 of the present application using the traditional wavelet method and the central wave number |k0|=3.081;

[0029] Figure 7 This is a schematic diagram of the calculation results obtained when the U-net method is tested in Example 1 of the present application using the traditional wavelet method and the central wave number |k0|=3.773;

[0030] Figure 8This is a schematic diagram of the calculation results obtained when the U-net method is tested in Example 1 of the present application using the traditional wavelet method and the central wave number |k0|=5.336;

[0031] Fig. 9 This is a schematic diagram of the calculation results obtained when the U-net method is tested in Example 1 of the present application using the traditional wavelet method and the center wave number |k0|=7.547;

[0032] Fig.10 This is a schematic diagram of the comparison results of the profile y=1500 km calculated using the U-net method and the traditional wavelet method when testing the U-net method in Example 1 of the present application;

[0033] Fig.11 A spatial variation diagram of the effective elastic thickness of the lithosphere in the Qinghai-Tibet Plateau and its surrounding areas calculated using the method of the present invention in Example 1 of the present application;

[0034] Fig.12 The spatial variation diagram of the effective elastic thickness of the lithosphere in the Qinghai-Tibet Plateau and its surrounding areas calculated using the traditional wavelet method in Example 1 of the present application when the central wave number |k0|=3.773;

[0035] Fig.13 A schematic diagram of the structure of a computer device provided in Example 2 of the present application. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] Example 1

[0039] The method for calculating the effective elastic thickness of the lithosphere provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, or it can be integrated on the server 104, or it can be placed on the cloud or other servers. The terminal 102 can send the measured topographic data and the measured gravity anomaly data in the research area to be processed to the server 104. After the server 104 receives the measured topographic data and the measured gravity anomaly data to be processed, it uses the measured topographic data and the measured gravity anomaly data as input, and uses the trained lithosphere effective elastic thickness prediction model to output the lithosphere effective elastic thickness value. The server 104 can feed back the obtained lithosphere effective elastic thickness value to the terminal 102. In addition, in some embodiments, a method for calculating the effective elastic thickness of the lithosphere can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly use the method for calculating the effective elastic thickness of the lithosphere to process the measured topographic data and the measured gravity anomaly data to be processed, or the server 104 can obtain the measured topographic data and the measured gravity anomaly data to be processed from the data storage system and process them using the method for calculating the effective elastic thickness of the lithosphere.

[0040] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0041] The correlation spectrum analysis method is limited by the selection of parameters such as window size and central wave number: the smaller the central wave number, the higher the spatial resolution, but the smaller the conversion wavelength that can be reflected, and the higher T cannot be restored well. e value; the larger the central wave number, the better the high T can be restored e The window size is similar to the central wave number, and a larger window can recover higher T e value, but the spatial resolution is poor; smaller windows restore T e The spatial resolution of the value is higher, but it cannot recover higher T e Different parameter selections lead to large differences in the results obtained by different researchers in the same study area, which often causes disputes in research and differences in geological interpretation. Therefore, a new inversion T e The method solves the problem of inconsistent calculation results caused by the need to select appropriate parameters in the inversion process, thereby improving the accuracy and reliability of the research.

[0042] This embodiment takes into account that intelligent methods such as deep learning can directly extract information from data. To this end, a calculation method for effective elastic thickness based on deep learning is established to provide a breakthrough and new ideas for solving this problem.

[0043] Based on this, in an exemplary embodiment, Figure 2 As shown, a method for calculating the effective elastic thickness of the lithosphere is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 201 to 202. Among them:

[0044] Step 201, obtaining measured topographic data and measured gravity anomaly data in the study area.

[0045] Step 202: Taking the measured topographic data and the measured gravity anomaly data as input, the trained lithosphere effective elastic thickness prediction model is used to output the lithosphere effective elastic thickness value.

[0046] The lithosphere effective elastic thickness prediction model in this embodiment is a neural network model, preferably a U-net network model.

[0047] In order to make those skilled in the art more aware of the specific implementation process of the above steps 201 to 202 of the present application, a specific explanation is given below.

[0048] (1) Training of U-net network model.

[0049] (1-1) Obtain the training dataset.

[0050] Generate random values ​​of lithosphere effective elastic thickness, surface load, and underground load, and load them on the elastic thin plate simulating the lithosphere. Specifically, the fractal Brownian motion (FBM) model is used to simulate T e Random distribution of known T e Two grids with fractal spectra are randomly generated using the RAN2 random number generator and the spectral synthesis method to represent the surface and subsurface loads.

[0051] Based on the flexure equation of anisotropic elastic thin plate and Parker (1972)'s interface gravity anomaly forward algorithm, the topographic data and gravity anomaly data when the effective elastic thickness of the lithosphere is known are synthesized. The flexure equation is used to describe the bending degree of the elastic thin plate of the lithosphere when subjected to external forces. Specifically,

[0052] Under the condition that the surface and underground loads and the effective elastic thickness of the lithosphere are known, the deflection of the lithosphere after equilibrium is calculated using the deflection equation, thereby obtaining the surface topography and Moho surface undulation after equilibrium. The gravity anomaly is obtained using the Moho forward formula of Parker (1972). At this point, a set of topographic data and gravity anomaly data are obtained when the effective elastic thickness of the lithosphere is known.

[0053] The terrain data and gravity anomaly data obtained above are 256*256 matrices. To avoid the network learning to generate random T e function, and then it needs to be cut into small blocks of 64*64.

[0054] (1-2) Train the U-net network.

[0055] Improvements were made to the U-net network: the number of input channels was set to 2, and the number of output channels was set to 1; batch normalization was performed in each upsampling process; the ReLU function was used in the middle layer of the activation function, and the Sigmoid function was used in the last layer; Dropout regularization was added; and the AdamW algorithm was used as the optimizer.

[0056] Adjust the relevant parameters in the U-net network, such as learning rate, number of multi-threads (num workers), batch size, weight decay, regularization weight (dropout prob), etc., so that the train loss and test loss curves show a downward trend and eventually stabilize.

[0057] The effective elastic thickness of the lithosphere is set as label data, and the corresponding gravity anomaly value and terrain value are set as feature data, which are input into the U-net network model for training.

[0058] (2) Use the trained U-net network model.

[0059] The measured topographic data and Bouguer gravity anomaly data are input into the trained U-net network model to calculate the effective elastic thickness of the lithosphere.

[0060] (3) Results presentation.

[0061] The effective elastic thickness of the lithosphere is plotted based on the results to intuitively display the effective elastic thickness data of the lithosphere.

[0062] The U-net network model of this embodiment has been trained, and you only need to run the script in a suitable python environment. The writing language is python 3.9.18, and the neural network framework used is Pytorch.

[0063] The dependent packages and their versions are as follows:

[0064]

[0065] This embodiment is based on the characteristics that the deep learning network can directly obtain information from the data and the U-net network is sensitive to the location information of the data. A method for calculating the effective elastic thickness of the lithosphere based on the U-net network is established, and the calculation of the effective elastic thickness of the lithosphere is realized based on this; compared with the traditional wavelet method for calculating the effective elastic thickness of the lithosphere, this method has higher accuracy and spatial resolution, and does not require the selection of relevant parameters for calculation. The present invention can be used to perform high-precision calculation of the effective elastic thickness of the lithosphere, which is conducive to further geological interpretation and scientific research.

[0066] like Figure 3 Setting T e The distribution is a linear frequency modulation signal, generating 100 sets of test data. Using the surface topography after equalization and the Bouguer gravity anomaly obtained by forward calculation, T is inverted by wavelet analysis and U-net method. e value, and with the model setting T e Comparison between the real values ​​to test the wavelet analysis method and deep learning method to invert T e The advantages and disadvantages.

[0067] Test results such as Figure 4-10 As shown, the smaller the central wave number, the better the T can be restored. e Changing boundaries have higher spatial resolution, but cannot restore T well e The larger the central wave number, the higher the T can be restored. e The U-net method recovers high T e The ability to recover low T values ​​is significantly better than the wavelet analysis method. e The ability of the U-net method to recover T is better than that of the wavelet analysis method when |k0| is 7.547. e The ability to change the boundary is higher than that of the wavelet analysis method, and has a higher spatial resolution. When the central wave number |k0| is 2.668, 3.081, 3.773, 5.336 and 7.547, the inversion results and T e The root mean square errors between the model and the true value are 15.25, 14.49, 13.63, 13.99 and 15.51 respectively. The values ​​inverted by the deep learning method are similar to Te The root mean square error between the model and the true value is 10.89, which is much lower than the traditional wavelet inversion method, indicating that the U-net inversion T e The method has higher accuracy (see Table 1 for details).

[0068] Table 1 Root mean square difference between deep learning method and traditional wavelet method in calculating lithosphere effective elastic thickness

[0069] method Root mean square error (RMSE) Deep Learning 10.89 <![CDATA[|k0|=2.668]]> 15.25 <![CDATA[|k0|=3.081]]> 14.49 <![CDATA[|k0|=3.773]]> 13.63 <![CDATA[|k0|=5.336]]> 13.99 <![CDATA[|k0|=7.547]]> 15.51

[0070] In order to further verify the effect of this method in practical cases, the WGM2012 gravity anomaly data and ETOPO1 topographic data in the range of 70-105°E; 25-42°N were selected to calculate the effective elastic thickness of the lithosphere. Fig.11 ) and the results of wavelet method in traditional spectrum analysis method ( Fig.12 ) for comparison. It can be seen that the effective elastic thickness of the lithosphere obtained by the present invention is in the Tarim Basin and the Qaidam Basin, etc. e The value area is higher. And at the edge of the basin, T e The change gradient of the value is higher, and a significant mutation occurs at the plate boundary. Compared with the results obtained by traditional methods, it is more consistent with geological facts. The results calculated by traditional methods do not have a significant T mutation at the edge of the basin. e The value changes suddenly, and even low values ​​appear in some locations in the middle of the basin, which is inconsistent with geological reality. Therefore, the results obtained by this method have higher accuracy and spatial resolution, highlighting the advantages of the present invention.

[0071] The present application also provides an application scenario, which applies the above-mentioned method for calculating the effective elastic thickness of the lithosphere. Specifically: The method for calculating the effective elastic thickness of the lithosphere provided in this embodiment can be applied to the scenarios of geological exploration and structural analysis. The scenarios of geological exploration and structural analysis include crustal structure research, seismic activity monitoring, and mineral resource assessment. The method for calculating the effective elastic thickness of the lithosphere provided in this embodiment belongs to the data analysis link in crustal structure research. The method for calculating the effective elastic thickness of the lithosphere provided in this embodiment improves the efficiency and accuracy of geological exploration by accurately calculating the elastic thickness of the lithosphere, providing an important scientific basis for geological research and resource development.

[0072] Example 2

[0073] This embodiment provides a computer device, which may be a server or a terminal. Its internal structure diagram may be as follows: Fig.13As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store any data in a method for calculating the effective elastic thickness of the lithosphere. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for calculating the effective elastic thickness of the lithosphere in Example 1 is implemented.

[0074] Those skilled in the art will understand that Fig.13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] Example 3

[0076] This embodiment provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, a method for calculating the effective elastic thickness of the lithosphere in the above-mentioned embodiment 1 is implemented.

[0077] Example 4

[0078] This embodiment provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for calculating the effective elastic thickness of the lithosphere in the above-mentioned embodiment 1.

[0079] Example 5

[0080] This embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements a method for calculating the effective elastic thickness of the lithosphere in the above-mentioned embodiment 1.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0082] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0083] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0084] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for calculating the effective elastic thickness of the lithosphere, characterized in that: The method for calculating the effective elastic thickness of the lithosphere comprises: Obtain measured topographic data and measured gravity anomaly data in the study area; The measured topographic data and the measured gravity anomaly data are used as input, and the lithosphere effective elastic thickness value is output using a trained lithosphere effective elastic thickness prediction model.

2. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The prediction model of lithosphere effective elastic thickness is a neural network model.

3. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The training process of the lithosphere effective elastic thickness prediction model includes: Simulating topographic data and gravity anomaly data of a lithosphere with effective elastic thickness under the action of external forces according to a forward modeling method and a flexural equation, wherein the flexural equation is used to describe the bending degree of an elastic thin plate of the lithosphere under the action of external forces; The topographic data and gravity anomaly data are used as feature data, and the effective elastic thickness is used as label data to train the lithosphere effective elastic thickness prediction model.

4. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The number of input channels in the lithosphere effective elastic thickness prediction model is 2, and the number of output channels is 1.

5. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The activation function in the lithosphere effective elastic thickness prediction model uses the ReLU function in the middle layer and the Sigmoid function in the last layer.

6. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The upsampling process in the lithosphere effective elastic thickness prediction model is batch normalized.

7. The method for calculating the effective elastic thickness of the lithosphere according to claim 1, characterized in that: The optimizer in the lithosphere effective elastic thickness prediction model uses the AdamW algorithm.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for calculating the effective elastic thickness of the lithosphere as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a method for calculating the effective elastic thickness of the lithosphere according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, a method for calculating the effective elastic thickness of the lithosphere according to any one of claims 1 to 7 is implemented.

Images