Geological body gravity data inversion method and system based on improved diffusion model

Abstract

The invention relates to the technical field of geophysics, and particularly provides a geologic body gravity data inversion method and system based on an improved diffusion model, and the method comprises the following steps: building a plurality of gravity anomaly geologic body models based on preset constraint conditions, and obtaining gravity data; introducing a ResU-Net + + network into the encoder U-shaped structure of the diffusion model to obtain a ResDM-net + + network; based on the ResDM-net + + network and the gravity data, a three-dimensional physical structure model of the geologic body is obtained, and inversion of the gravity data of the geologic body is completed. The network mainly utilizes the high efficiency and clear structural design of ResU-Net + + in image segmentation and feature extraction to make up for the deficiencies of the diffusion model in efficiency and interpretation; and meanwhile, the denoising process of the diffusion model is used as a regularization means to help to reduce the over-fitting risk of the ResU-Net + + network under limited data.

Description

Technical Field

[0001] The invention belongs to the field of geophysical technology, and in particular relates to a geological gravity data inversion method and system based on an improved diffusion model. Background Art

[0002] In geophysical research, gravity inversion is a key technology that is widely used to identify geological anomalies, map underground rock structures, and help explore and extract important resources such as oil and minerals. By measuring changes in the gravity field on the earth's surface, the underground density distribution can be inferred, thereby discovering possible oil and gas reservoirs, mineral veins, and other geological features. This technology not only provides an important scientific basis for resource exploration, but also plays an important role in geological disaster warning and environmental protection.

[0003] In recent years, machine learning technology has made significant progress in various fields, especially in image processing and computer vision. Supervised learning, as a major category, uses labeled gravity data to train the model so that it can make accurate predictions on new gravity data. U-Net is a classic convolutional neural network architecture, which belongs to the category of supervised learning. U-Net adopts a symmetrical encoder-decoder structure and performs well in semantic information extraction and spatial detail recovery in image segmentation tasks. However, it uniformly weights features of equivalent levels during encoding and decoding, which may mask key geological features under less important geological features. To solve this problem, Jha et al. (2019) proposed the ResU-Net++ network, which first retains more gravity detail information by introducing residual connections; secondly, it uses compression and excitation modules as a lightweight attention mechanism to significantly enhance the network's ability to identify local and global geophysical features. However, its complex structure and large number of parameters easily lead to high computing resource requirements, slow training and inference speeds, and easy overfitting when data is limited. To improve this situation, the diffusion model proposed by Jascha et al. (2015) can generate samples with rich details, perform well in processing complex data, and has good robustness. It effectively simplifies the complex modules of the ResU-Net++ network and reduces the computational complexity and resource requirements of the overall model. However, it is not as good as the ResU-Net++ network in feature extraction. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the present invention provides a geological gravity data inversion method and system based on an improved diffusion model, which makes use of the high efficiency and clear structural design of ResU-Net++ in feature extraction to make up for the shortcomings of the diffusion model in efficiency and interpretability.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] The inversion method of geological gravity data based on the improved diffusion model includes the following steps:

[0007] Based on the preset constraints, multiple gravity anomaly geological body models are established to obtain gravity data; wherein the sizes of the gravity anomaly geological body models include 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5;

[0008] Introducing a ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain a ResDM-net++ network; wherein the diffusion model includes a forward diffusion process and a reverse diffusion process;

[0009] Based on the ResDM-net++ network and the gravity data, a three-dimensional physical structure model of the geological body is obtained, and the inversion of the geological gravity data is completed.

[0010] Preferably, the gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as :

[0011] ,

[0012] Where γ represents the gravitational constant, represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of Represents the volume element at the source point.

[0013] Preferably, in the diffusion model,

[0014] The forward diffusion process is to add noise to the original gravity data input into the diffusion model, and the formula is as follows:

[0015] ,

[0016] in, is at the time step data, is at the time step The noise factor is defined as , is a predefined noise table; is at the time step data, is random noise of the same shape as the input data;

[0017] The reverse diffusion process is to recover the original gravity data from the noisy data. The formula is as follows:

[0018]

[0019] is the output of the diffusion model encoder.

[0020] Preferably, the U-shaped structure of the ResDM-net++ network includes an encoder, a spatial pyramid module and a decoder, wherein the encoder consists of three downsampling modules, each of which includes a residual unit paired with a SE module; the decoder consists of three decoding modules, each of which includes an attention mechanism module, an upsampling layer, a feature connection layer and a residual unit.

[0021] Preferably, the SE module uses global pooling to transform the input gravity data Compressed into a vector , the compression formula is as follows:

[0022]

[0023] in, Represents input gravity data , represents the real number domain, H and W represent the number of rows and columns of gravity data extracted by convolution operation in the channel number C, respectively. Represents the row index, Represents the column index.

[0024] Preferably, the spatial pyramid module performs multi-scale sampling on the gravity data features extracted by the downsampling module by establishing different expansion rates to obtain multi-scale context information of the gravity data features; wherein the expansion rate is equipped with an equivalent convolution kernel, and the size of the equivalent convolution kernel is expressed as follows:

[0025] ,

[0026] Among them, 𝑘 is the original convolution kernel size, is the expansion coefficient.

[0027] The present invention also provides a geological gravity data inversion system based on an improved diffusion model, which is used to implement the method, comprising:

[0028] A gravity data acquisition module is used to establish multiple gravity anomaly geological body models based on preset constraints to acquire gravity data; wherein the sizes of the gravity anomaly geological body models include 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5;

[0029] A model improvement module, used for introducing a ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain a ResDM-net++ network; wherein the diffusion model includes a forward diffusion process and a reverse diffusion process;

[0030] The structural inversion module is used to obtain a three-dimensional physical structure model of the geological body based on the ResDM-net++ network and the gravity data, and complete the inversion of the geological gravity data.

[0031] Preferably, the gravity data acquisition module includes:

[0032] A model set building unit, used for combining multiple individual gravity anomaly geological body models to obtain a model set;

[0033] A model forward modeling unit, used to perform model forward modeling based on the model set to generate the gravity data; the gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as :

[0034] ,

[0035] Where γ represents the gravitational constant, represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of Represents the volume element at the source point.

[0036] Compared with the prior art, the beneficial effect of the present invention is that the core module of ResU-Net++ is added to the encoder structure of the diffusion model to construct a new network (i.e., ResDM-net++ network). The network mainly utilizes the high efficiency and clear structural design of ResU-Net++ in feature extraction to make up for the shortcomings of the diffusion model in efficiency and interpretability; at the same time, the denoising process of the diffusion model is used as a regularization method to help reduce the overfitting risk of the ResU-Net++ network under limited data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 Four arbitrarily selected model sets in the embodiments of the present invention; wherein (a) is model set 1; (b) is model set 2; (c) is model set 3; (d) is model set 4;

[0039] Figure 2 Schematic diagram of the process of acquiring model forward modeling data and gradient data in an embodiment of the present invention; wherein (a) is the extracted density model; (b) is the gravity forward modeling data Obtaining schematic diagram; (c) is gravity component data Obtaining schematic diagram; (d) is gravity component data Obtaining schematic diagram; (e) is gravity component data Obtaining schematic diagram; (f) is gravity component data Obtaining schematic diagram; (g) is gravity component data Obtaining schematic diagram; (h) is gravity component data Get the schematic diagram;

[0040] Figure 3 This is a theoretical schematic diagram of a diffusion model according to an embodiment of the present invention;

[0041] Figure 4 Schematic diagram of the ResDM-net++ network structure of an embodiment of the present invention; wherein (a) is a schematic diagram of the overall structure of the ResDM-net++ network; (b) is a schematic diagram of the encoding block structure in the ResDM-net++ network; (c) is a schematic diagram of the decoding block structure in the ResDM-net++ network;

[0042] Figure 5 This is a schematic diagram of an SE module according to an embodiment of the present invention;

[0043] Figure 6 This is a schematic diagram of a spatial pyramid module according to an embodiment of the present invention;

[0044] Figure 7 This is a schematic diagram of an attention mechanism module according to an embodiment of the present invention;

[0045] Figure 8 The three-dimensional views and sections of the embodiment of the present invention are shown in FIG. 1 , wherein (a) is a schematic diagram at Y=1000m; (b) is a schematic diagram at X=2200m;

[0046] Fig. 9 The diffusion model under 10% noise in the embodiment of the present invention, the slice diagram of the geological structure model obtained by inverting the ResU-Net++ and ResDM-net++ networks in Y=1000m; where (a) is Quantity; (b) and Quantity; (c) , , and Component; (d) , , , , , and Quantity;

[0047] Fig.10 The diffusion model under 10% noise in the embodiment of the present invention, the slice diagram of the geological structure model obtained by inverting the ResU-Net++ and ResDM-net++ networks in combination with different components at X=2200m; where (a) is Quantity; (b) and Quantity; (c) , , and Component; (d) , , , , , and Quantity;

[0048] Fig.11The ResDM-net++ network of the embodiment of the present invention combines 7 gravity components under 10% noise conditions, and the observed gravity field, predicted gravity field and fitting difference diagram of different components; (a) Quantity; (b) Quantity; (c) Component; (d) Quantity;

[0049] Fig.12 The loss curves of network training and verification of the embodiment of the present invention; (a) is the loss curve of the custom diffusion model; (b) is the loss curve of ResU-Net++; (c) is the loss curve of ResDM-net++;

[0050] Fig.13 The present invention is a flowchart of a method for inverting geological gravity data based on an improved diffusion model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Embodiment 1

[0054] like Fig.13 As shown, the geological gravity data inversion method based on the improved diffusion model includes the following steps:

[0055] S1: Based on the preset constraints, multiple gravity anomaly geological body models are established to obtain gravity data; specifically, to achieve the accuracy of density, depth and geological target size attributes, it is necessary to develop a detailed training sample set containing various geological body shapes. Therefore, in order to simulate various geological bodies showing gravity anomalies, we combined multiple separate gravity anomaly geological body models under specific constraints, and randomly placed 1 to 5 small models in space to form a model set, and the positions were random. The selected small model sizes were 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5. Figure 1 Four randomly selected model sets are shown. Figure 1 (a) is model set 1; Figure 1 (b) is model set 2; Figure 1(c) is model set 3; Figure 1 (d) is model set 4; this embodiment generates a total of 10,000 model sets, 8,000 of which are allocated for neural network training and 2,000 for verification purposes.

[0056] A further embodiment is that Figure 2 As shown, in order to add geophysical constraints to deep learning and obtain more realistic prediction data, this embodiment combines the components of gravity gradient data (gravity data), where gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as : ,

[0057] Where γ represents the gravitational constant , represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of represents the volume element at the source point. This formula is essential for calculating the gravitational effect of a specific density distribution on surrounding points in space and is often used in gravity inversion tasks to simulate underground structures. Figure 2 As shown, Figure 2 (a) is the density model, Figure 2 (b) is the gravity forward modeling data Get the schematic diagram; Figure 2 (c) is the gravity component data Get the schematic diagram; Figure 2 (d) is the gravity component data Get the schematic diagram; Figure 2 (e) is the gravity component data Get the schematic diagram; Figure 2 (f) is the gravity component data Get the schematic diagram; Figure 2 (g) is the gravity component data Get the schematic diagram; Figure 2 (h) is the gravity component data Get the schematic.

[0058] In order to reconstruct the three-dimensional physical structure model of the geological body from gravity data, the present invention uses the ResDM-net++ network, which adds important modules of the ResU-Net++ network to the U-shaped structure of the encoder of the diffusion model, including residual blocks, SE modules, spatial pyramid modules, and attention mechanism modules. It effectively combines the advantages of the diffusion model and the ResU-Net++ network. This innovation can greatly improve the structural perception ability and segmentation accuracy in the image generation process, while enhancing the robustness and accuracy of the generated results.

[0059] S2: Introduce the ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain the ResDM-net++ network;

[0060] Among them, Figure 3 As shown, the diffusion model includes a forward diffusion process (i.e., forward propagation) and a reverse diffusion process (i.e., reverse propagation); a further implementation method is that, in the diffusion model,

[0061] The forward diffusion process is to add noise to the original gravity data input into the diffusion model, and the formula is as follows:

[0062]

[0063] in, is at the time step data, is at the time step The noise factor is defined as , is a predefined noise table; is at the time step data, is random noise with the same shape as the input data.

[0064] The reverse diffusion process is to recover the original gravity data from the noisy data. The formula is as follows:

[0065]

[0066] is the output of the diffusion model encoder. The encoder ( ) Change the current is encoded and converted to The inverse diffusion formula recovers the original data from the noisy data and tries to reconstruct the clean signal.

[0067] A further embodiment is that Figure 4 As shown in the figure, the U-shaped structure of the ResDM-net++ network includes an encoder, a spatial pyramid module and a decoder, wherein the encoder consists of three downsampling modules (encoding blocks), each of which includes a residual unit paired with a SE module (Squeeze & Excite). In this embodiment, the residual unit is a residual unit, which includes a Batch Norm & ReLU layer and a Conv2D layer; the decoder consists of three decoding modules (decoding blocks), each of which includes an attention mechanism module, an upsampling layer (UpBlock), a feature connection layer and a residual unit. Figure 4 In (c), the feature connection layer is represented by the connection line between the upsampling layer and the residual unit. These components include residual blocks and attention blocks to enhance detail capture and noise reduction. Figure 4 As shown in (b), each downsampling module includes a residual unit paired with a SE module; Figure 4 As shown in (a), in the ResDM-net++ network, first, the "In Conv" operation applies a 2D convolution with a kernel size of 3x3, padding of 1, and one input channel to the input gravity data of length 21x21. This operation increases the dimension from 7 channels to 32 channels. The "Out Conv" operation converts the decoding block into a single-channel representation. This layer links the underground geology with the observed gravity changes based on the training of the network on supervised learning labels as the final three-dimensional physical structure model output. The ASPP module and the ASPP output block are both spatial pyramid modules, in which the ASPP module acts as a bridge connection and the ASPP output block acts as an output. The circle with a "+" sign in front of the decoding block indicates that the channel connection is used as a downsampling operation, doubling the number of channels and reducing the input length by half. The circle with a "+" sign in the blocks of the encoding block and the decoding block represents the residual connection. Among them, the attention mechanism module is as follows Figure 7 shown.

[0068] like Figure 4 As shown in (a), the ResDM-net++ network includes an "In Conv", three encoding blocks, an ASPP module, an ASPP output block, three decoding blocks and an "Out Conv". These components include residual blocks and attention blocks to enhance detail capture and noise reduction. The multi-channel information is converted into the dimension required for network input through "In Conv" and connected to the encoding block. Figure 4 As shown in (b), each encoding block contains a residual unit paired with a SE module. This module enhances key gravity map features by increasing the weight of information channels while reducing irrelevant data, thereby optimizing feature representation. In the decoding block (see Figure 4 (c)) combines the attention mechanism with the upsampling and connection process to retain key information through residual connections and enhance the network's predictive performance. The purpose of the "upsampling" operation is to reduce the number of channels in the input vector by half while doubling its length. In order to address challenges such as increasing training errors and "gradient dispersion or explosion" associated with deep networks, improved recurrent residual units are used in both the encoder and decoder. These units consist of two consecutive convolutional blocks, including a Batch Norm layer and a ReLU layer, which simplifies the training process and ensures consistent information flow in the network. This structure not only simplifies training, but also improves the network's ability to accurately predict and simulate complex geophysical structures. Finally, the corresponding dimension is output through "Out Conv", thereby connecting the gravity field with the model density information.

[0069] In a further embodiment, the SE module optimizes feature representation by increasing the weights of information channels to enhance key gravity data features while reducing irrelevant data.

[0070] like Figure 5 As shown in Figure 1, the SE module plays a central role in the precise recalibration of channel feature weights when processing gravity data. The module amplifies important features by adding weights to informative channels, while shrinking noisy and insignificant features by reducing the corresponding weights. This increase and decrease in weights improves the network's operational efficiency and its ability to identify complex patterns in gravity data - a key aspect of geophysical analysis. The SE module pools the input gravity data into a single global pool. Compressed into a vector , the compression formula is as follows:

[0071]

[0072] in, Represents input gravity data , represents the real number domain, H and W represent the number of rows and columns of gravity data extracted by convolution operation in the channel number C, respectively. Represents the row index, Represents the column index.

[0073] In order to identify channel-level correlations, an excitation operation is used during feature extraction to give amplified weights to key feature maps within feature channels to emphasize key information while reducing unimportant information. This operation produces a weight value for each feature channel through two fully connected layers. The resulting output is obtained by multiplying each channel by its associated channel weight. The output of this mapping operation is shown below:

[0074] ,

[0075] in, Represents a mapping operation, a two-dimensional tensor Represented as input information of an element of represents the field of real numbers, and Represents the sigmoid function. Weight The matrix is ​​represented as and The SE block is able to identify channel correlations, thereby increasing sensitivity to critical channels, while suppressing redundant or irrelevant information. Such irrelevant information may appear as noise, thus affecting the prediction performance of the network.

[0076] Classic pooling mechanisms used in CNNs, including max pooling and average pooling, are widely used to reduce the spatial dimensions of feature maps, allowing the model to understand more abstract and high-level features. However, these operations can lead to a reduction in spatial resolution and loss of complex details, while computational resources limit the number and dimensionality of convolution kernels. This can cause significant difficulties in identifying elongated, ribbon-like formations (such as narrow geological formations, faults, and fractures), which are common in geophysical data.

[0077] A further implementation method is that, in order to solve the above problem, the present invention uses a spatial pyramid module to read contextual information of different scales in the data, so that the original input resolution is maintained without losing information during the geophysical inversion process. Figure 6 As shown in the figure, the spatial pyramid module establishes different expansion rates and combines the gravity data features extracted by the downsampling module in different proportions for multi-scale sampling, which effectively increases the size of the convolution kernel and obtains the multi-scale context information of the gravity data features. Among them, the expansion rate is equipped with an equivalent convolution kernel (receptive field), and the size of the equivalent convolution kernel is expressed as follows:

[0078] ,

[0079] Among them, 𝑘 is the original convolution kernel size, is the expansion coefficient. The output size after convolution is defined as:

[0080] ,

[0081] in Indicates the output size, Indicates the input size. Indicates the length of the stride. Padding( ) operation solves the problem of information loss near the image boundaries after each convolution operation. This is achieved by replacing the missing boundary parts with zeros.

[0082] In the decoder, the attention mechanism is combined with the upsampling and connection process to retain key information through residual connections and enhance the network's predictive performance. The purpose of the "upsampling" operation is to reduce the number of channels in the input vector by half while doubling its length. In order to address challenges such as increasing training errors and "gradient dispersion or explosion" associated with deep networks, improved recurrent residual units are used in both the encoder and decoder. These units consist of two consecutive convolutional blocks, including a BatchNorm layer and a ReLU layer, which simplifies the training process and ensures consistent information flow in the network. This structure not only simplifies training, but also improves the network's ability to accurately predict and simulate complex geophysical structures.

[0083] The decoder consists of three decoding modules, each of which consists of an attention mechanism, an upsampling process, a feature connection layer, and a residual unit. The attention mechanism (i.e., Convolutional Block Attention Module, CBAM) is integrated into the gravity network model because the model contains a large number of parameters. By introducing CBAM, the model can focus on key features in the channel dimension and spatial dimension respectively, improve the expression ability of important information, and suppress redundant features. This mechanism enhances the effectiveness of the model, optimizes information retention, and thus improves training efficiency and prediction accuracy. The input of CBAM is the encoder feature map And decoder feature map , both come from the same layer in the U-Net structure and have the same dimensions. The difference is that represents low-resolution data, while represents high-resolution data. The output of CBAM is defined as , which achieves efficient information extraction by enhancing the features relevant to the current task and highlighting the key areas of gravity anomalies. Specifically, Figure 7 As shown, the output is the input feature With attention weight The element-by-element multiplication of is as follows:

[0084] ,

[0085] in, It can be expressed as:

[0086] ,

[0087] in, After batch normalization, ReLU activation function, a 2D convolution and max pooling (MaxPool), the first single channel attention weight is generated. ; After batch normalization (BatchNorm), ReLU activation function and a two-dimensional convolution, the second single-channel attention weight is generated . compared to The only difference in the calculation process is the maximum pooling process. (...) Representatives will After batch normalization, ReLU activation function and a two-dimensional convolution, we get .

[0088] The CBAM module selectively highlights the gravity anomaly features related to the task, while suppressing redundant or irrelevant information by combining the attention mechanism of the channel and spatial dimensions. It captures the global correlation between features in the channel dimension and accurately locates the distribution area of ​​anomalies in the spatial dimension, effectively dealing with the problems of complex features and information redundancy of gravity anomaly data, thereby improving the effectiveness of feature expression and significantly improving the accuracy and efficiency of gravity inversion tasks.

[0089] In order to verify the robustness of the network, the present invention uses the fitting error E to describe the gravity observation loss. The specific calculation formula of this loss is as follows:

[0090]

[0091] Where N is the total number of observation points; represents theoretical observational gravity data; Represents predicted gravity data.

[0092] S3: Based on the ResDM-net++ network and gravity data, the three-dimensional physical structure model of the geological body is obtained, and the inversion of the geological gravity data is completed.

[0093] Embodiment 2

[0094] The present invention also provides a geological gravity data inversion system based on an improved diffusion model, which is used to implement a method, including:

[0095] A gravity data acquisition module is used to establish multiple gravity anomaly geological body models based on preset constraints to acquire gravity data; wherein the sizes of the gravity anomaly geological body models include 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5;

[0096] A model improvement module is used to introduce the ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain the ResDM-net++ network; wherein the diffusion model includes a forward diffusion process and a reverse diffusion process;

[0097] The structural inversion module is used to obtain the three-dimensional physical structure model of the geological body based on the ResDM-net++ network and gravity data, and complete the inversion of the geological gravity data.

[0098] A further implementation is that the gravity data acquisition module comprises:

[0099] A model set building unit, used for combining multiple individual gravity anomaly geological body models to obtain a model set;

[0100] Model forward modeling unit, used to perform model forward modeling based on the model set and generate gravity data; gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as : ,

[0101] Where γ represents the gravitational constant , represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of Represents the volume element at the source point.

[0102] Embodiment 3

[0103] In order to evaluate the effectiveness of the network in feature detection, the present invention extracts a set of models from the test set. Figure 8 (a) and Figure 8(b) shows a visual description of the model and views at different slices for predictive analysis. The model has a uniform density of 1.0 g / cm³. The observation field spans from 0 m to 4000 m along the x-axis and from 0 m to 4000 m along the y-axis. The data point spacing is 200 m, with a total of 441 data points, and the vertical component of gravity is calculated. The space is divided into 8000 cubic units (20m × 20m × 20m), each with a side length of 200 meters. To improve readability, the density of all 3D perspective parts exceeds 0.5 g / cm 3 .

[0104] Fig. 9 and Fig.10 The inversion slice results of the model at Y=1000m and X=2200m are shown respectively. The three columns in the figure show the comparison of the results of the custom diffusion model, ResU-Net++ and ResDM-net++ networks. Fig. 9 (a) and Fig.10 (a) shows three network usages Component prediction; Fig. 9 (b) and Fig.10 (b) Describes three network combinations and Component prediction; Fig. 9 (c) and Fig.10 (c) Describes three network combinations , , and Component prediction; Fig. 9 (d) and Fig.10 (d) Describes three network combinations , , , , , and Component prediction.

[0105] from Fig. 9 It can be seen that under the condition of 10% noise, the models predicted by different components of the three networks basically restore the shape and density of the test model from the slice. Fig. 9 As can be seen from the three columns, with the increase of the types of training gravity components, the slices of the same network prediction model show better results in terms of boundaries and density, and the addition of other components helps to identify the x, y, and z directions; Fig. 9 (a)- Fig. 9(d) It can be seen that the slices of the ResDM-net++ network prediction model are better than the custom diffusion model and the ResU-Net++ network in both boundary and density dimensions. Therefore, the present invention concludes that the ResDM-net++ network has clear slice boundary predictions in the joint 7 gravity component prediction model, and the density restoration range and size are close to the test model, which also verifies the robustness of the network to noise in the model.

[0106] Similarly, Fig.10 It can be seen that under the condition of 10% noise, the models predicted by different components of the three networks basically restore the shape and density of the test model from the slice. Fig.10 As can be seen from each column, as the types of training gravity components increase, the slices of the same network prediction model show better results in terms of boundaries and density, and the addition of other components helps the recognition of the x, y, and z directions; Fig.10 (a)- Fig.10 (d) It can be seen that the slices of the ResDM-net++ network prediction model are better than the custom diffusion model and ResU-Net++ network in both boundary and density dimensions. Therefore, we conclude that the ResDM-net++ network has clear slice boundary predictions in the joint 7 gravity component prediction model, and the density restoration range and size are close to the test model, which also verifies the network's robustness to noise in the model.

[0107] Based on the previous analysis of the slicing effect of different networks combined with different components to predict the model and the length of the article, Fig.11 Only the ResDM-net++ network combined with the four gravity components under 10% noise conditions is shown, and the observed gravity field, predicted gravity field and fitting difference diagram of different components are shown. Fig.11 (a)- Fig.11 (d) Display separately , , and As can be seen from the figure, the shape and field value of the predicted field are basically consistent with the observed field, the fitting error is less than 5%, which is in line with the error range. The inversion result is credible. In combination with the situation not shown, the ResDM-net++ network combines the four gravity components to predict the smallest fitting error and the best effect.

[0108] Fig.12 (a)- Fig.12(c) depicts the (MSE) loss curves of the custom diffusion model, ResU-Net++, and ResDM-net++ networks. As the training progresses, the loss function converges significantly. It is worth noting that the loss functions of the three networks all show convergence. This convergence indicates that the difference between the predicted value and the actual value is minimized, indicating that the network model has reached a stable state during the training process.

[0109] Table 1 shows the memory usage, GPU utilization, training time, and number of training grids for the custom diffusion model, ResU-Net++, and ResDM-net++ networks. By comparison, we can see that the GPU utilization of ResDM-net++ reaches 99%. From the perspective of training time, the custom diffusion model takes less time due to its simple structure and fewer parameters. ResU-Net++ takes the most time, and the ResDM-net++ network is between the two. The number of grids trained for the three networks is 8000. In order to fully understand the configuration of the network, Table 2 details the hyperparameters used during network training.

[0110] Table 1

[0111]

[0112] Table 2

[0113]

[0114] In order to make a more quantitative evaluation of the inversion results of the three networks, the present invention calculates the field map fitting error of each network, and only the fitting error of the combined 7 components is shown here, as shown in Table 3. As can be seen from the table, ResDM-net++ has the smallest fitting error and the best result.

[0115] Table 3

[0116]

[0117] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for inversion of geological gravity data based on an improved diffusion model, characterized in that: The following steps are involved: Based on the preset constraints, multiple gravity anomaly geological body models are established to obtain gravity data; wherein the sizes of the gravity anomaly geological body models include 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5; Introducing a ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain a ResDM-net++ network; wherein the diffusion model includes a forward diffusion process and a reverse diffusion process; Based on the ResDM-net++ network and the gravity data, a three-dimensional physical structure model of the geological body is obtained, and the inversion of the geological gravity data is completed.

2. The method according to claim 1, characterized in that The gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as : ， Where γ represents the gravitational constant, represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of Represents the volume element at the source point.

3. The method according to claim 1, characterized in that In the diffusion model, The forward diffusion process is to add noise to the original gravity data input into the diffusion model, and the formula is as follows: in, is at the time step data, is at the time step The noise figure is defined as , is a predefined noise table; is at the time step data, is random noise of the same shape as the input data; The reverse diffusion process is to recover the original gravity data from the noisy data. The formula is as follows: ， is the output of the diffusion model encoder.

4. The method according to claim 1, characterized in that: The U-shaped structure of the ResDM-net++ network includes an encoder, a spatial pyramid module and a decoder, wherein the encoder consists of three downsampling modules, each of which includes a residual unit paired with a SE module; the decoder consists of three decoding modules, each of which includes an attention mechanism module, an upsampling layer, a feature connection layer and a residual unit.

5. The method according to claim 4, characterized in that The SE module uses global pooling to transform the input gravity data Compressed into a vector , the compression formula is as follows: ， in, Represents input gravity data , represents the real number domain, H and W represent the number of rows and columns of gravity data extracted by convolution operation in the channel number C, respectively. Represents the row index, Represents the column index.

6. The method according to claim 4, characterized in that The spatial pyramid module performs multi-scale sampling on the gravity data features extracted by the downsampling module by establishing different expansion rates to obtain multi-scale context information of the gravity data features; wherein the expansion rate is equipped with an equivalent convolution kernel, and the size of the equivalent convolution kernel is expressed as follows: ， Among them, 𝑘 is the original convolution kernel size, is the expansion coefficient.

7. A geological gravity data inversion system based on an improved diffusion model, used to implement the method according to any one of claims 1 to 6, characterized in that: include: A gravity data acquisition module is used to establish multiple gravity anomaly geological body models based on preset constraints to acquire gravity data; wherein the sizes of the gravity anomaly geological body models include 3x3x3, 4x4x4, 5x5x5, 4x4x2 and 3x3x5; A model improvement module, used for introducing a ResU-Net++ network into the encoder U-shaped structure of the diffusion model to obtain a ResDM-net++ network; wherein the diffusion model includes a forward diffusion process and a reverse diffusion process; The structural inversion module is used to obtain a three-dimensional physical structure model of the geological body based on the ResDM-net++ network and the gravity data, and complete the inversion of the geological gravity data.

8. The system according to claim 7, characterized in that The gravity data acquisition module comprises: A model set building unit, used for combining multiple individual gravity anomaly geological body models to obtain a model set; A model forward modeling unit, used to perform model forward modeling based on the model set to generate the gravity data; the gravity data includes gravity component data , , , , , and ;in, is the gravity response simulated by using multiple gravity anomaly geological body models, denoted as , the vertical component of the gravity field is recorded as : ， Where γ represents the gravitational constant, represents the density distribution in a certain abnormal domain D underground, is the corresponding forward linear operator, kernel function , , represents the field point position vector, represents the source position vector, is the field point position vector The vertical coordinate of is the source position vector The vertical coordinate of Represents the volume element at the source point.

Images