A method for constructing transient electromagnetic inversion model based on target dataset drive

Abstract

The present invention relates to a method for constructing a transient electromagnetic inversion model driven by a target dataset, comprising: constructing an initial training set, using the initial training set to train a first convolutional neural network to obtain an initial transient electromagnetic inversion network model; inputting the electromagnetic response data to be measured into the initial transient electromagnetic inversion model for prediction to obtain resistivity values; performing forward simulation on the resistivity values ​​to obtain electromagnetic response data from the forward simulation, and constructing predicted data based on the forward simulation electromagnetic response data and the resistivity values; extracting data from the initial training set that is similar to the electromagnetic response data to be measured, and constructing a target dataset based on the similar data and the predicted data; and migrating parameters from the initial transient electromagnetic inversion model to a second convolutional neural network for iterative learning of the target dataset to obtain a transient electromagnetic inversion model. The present invention aims to improve the accuracy of the network's inversion of the measured data through an iterative training strategy when performing deep learning inversion on the measured data.

Description

Technical Field

[0001] The present invention relates to the field of transient electromagnetic inversion technology, and in particular to a method for constructing a transient electromagnetic inversion model driven by a target data set. Background Art

[0002] Currently, transient electromagnetic inversion is mainly divided into two types: linear inversion and nonlinear inversion. Linear inversion methods, such as Occam inversion and Marquardt inversion, are highly dependent on the initial model, and the quality of the inversion results largely depends on whether a suitable initial model can be found. Nonlinear inversion methods, such as simulated annealing algorithms, particle swarm optimization algorithms, and Bayesian inversion, usually require a huge amount of computation due to the complexity of geophysical models. With the improvement of hardware computing power, electromagnetic inversion based on deep learning has become a research hotspot. Vladimir Puzyrev (2019) first explored the potential of deep learning methods in electromagnetic inversion. Subsequently, in recent years, deep learning-based methods have also been widely studied in the fields of CSEM inversion, MT inversion, AEM inversion, etc.

[0003] However, the above-mentioned deep learning-based inversion method is completely data-driven, and its performance depends largely on the richness of the training sample set. When processing data with a distribution different from that of the training sample set, the effect is often unsatisfactory. In response to this, many scholars have made improvements by adding physical constraints to the loss function of the deep learning network to control the training process of the network. For example, Jin et al. (2019) introduced the Jacobi differential operator in the forward model of the electromagnetic response of logging while drilling (LWD) predicted by convolutional neural network to construct a composite loss function of the model and data mismatch function. Sun et al. (2020) constructed a forward operator Γ based on recurrent neural network (RNN) to simulate wave propagation, realizing unsupervised deep learning seismic inversion, and its training process is equivalent to the optimization of conventional deterministic inversion methods. W.Liu et al. (2022) proposed incorporating the physical laws of magnetotelluric wave propagation into a purely data-driven deep learning method (PlainDNN), adding physics-based unfitted data to the loss function to guide network training, and verified it in magnetotelluric one-dimensional inversion. In addition, some scholars have combined deep learning with traditional methods to leverage the advantages of both methods. For example, Asif et al. (2022) used a neural network to predict the Jacobian matrix in the least squares inversion, integrated the neural network into the traditional least squares inversion, and verified it in the transient electromagnetic one-dimensional inversion. On this basis, Asif et al. (2022) obtained a forward operator through neural network training, integrated it into the least squares inversion, and ultimately achieved excellent performance in the airborne transient electromagnetic one-dimensional inversion.

[0004] Due to the complexity and non-uniqueness of geophysical models, as well as the high time and computational resource requirements, constructing large and detailed geophysical datasets and training networks is quite challenging. Furthermore, purely data-driven deep learning methods primarily learn the inversion operator L hidden between the input and output within the training set, so when tested on data outside the training set, the results are often unsatisfactory. In other words, data-driven deep learning inversion methods struggle to handle the fine details between the data and the model when faced with unseen data, unless large-scale training is performed with the data to be tested having the same statistical distribution. This results in certain limitations in the practical application of data-driven machine learning methods in geophysical inversion.

[0005] Although the improvements of the above two methods have reduced the dependence on large-scale data to a certain extent and improved the generalization ability of the network, they have also complicated the network training process to a certain extent and increased the consumption of computing resources in the training stage. Summary of the Invention

[0006] The purpose of the present invention is to provide a transient electromagnetic inversion model construction method driven by a target dataset. By repeatedly updating the model and adjusting parameters, the real inversion results are gradually approached, thereby overcoming the limitations of traditional data-driven methods and improving the inversion accuracy and reliability.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] The transient electromagnetic inversion model construction method based on the target dataset drive includes:

[0009] Constructing an initial training set, and using the initial training set to train a first convolutional neural network to obtain an initial transient electromagnetic inversion network model;

[0010] Inputting the electromagnetic response data to be measured into the initial transient electromagnetic inversion model for prediction to obtain a resistivity value;

[0011] Performing forward simulation on the resistivity value to obtain electromagnetic response data of the forward simulation, and constructing prediction data based on the electromagnetic response data of the forward simulation and the resistivity value;

[0012] extracting data from the initial training set that is similar to the electromagnetic response data to be measured, and constructing a target data set based on the similar data and the predicted data;

[0013] The parameters in the initial transient electromagnetic inversion model are transferred to a second convolutional neural network to perform iterative learning on the target data set to obtain a transient electromagnetic inversion model.

[0014] Optionally, obtaining the initial training set includes:

[0015] Preset the thickness of the top layer and the depth of the bottom boundary of the underground geological structure, and divide it into several layers according to the method of cumulative increasing thickness of each layer;

[0016] Determine a plurality of control points between the top layer and the bottom layer, interpolate the control points, and obtain resistivity-thickness sample data between the top layer and the bottom layer;

[0017] Performing a one-dimensional transient electromagnetic numerical simulation based on the resistivity-thickness sample data to obtain a corresponding electromagnetic response;

[0018] Based on the resistivity values ​​and the corresponding electromagnetic responses, a sample data set is acquired, and the initial training set is divided from the sample data set.

[0019] Optionally, interpolating the control points includes: interpolating using a B-spline interpolation method.

[0020] Optionally, the convolutional neural network includes: an input layer, an output layer, a convolution layer and a fully connected layer, wherein the input layer is used to input the electromagnetic response, the output layer is used to output the resistivity value, and the data features extracted by the convolution layer are input to the fully connected layer.

[0021] Optionally, extracting data similar to the electromagnetic response data to be measured from the initial training set includes:

[0022] Obtain a relative average error between the electromagnetic response data in the initial training set and the electromagnetic response data to be measured; obtain the electromagnetic response data in the initial training set corresponding to the relative average error in the preset range as similar electromagnetic response data, and extract the resistivity value corresponding to the similar electromagnetic response data in the initial training set to obtain the similar data.

[0023] The present invention also provides a transient electromagnetic inversion method driven by a target data set, which uses a transient electromagnetic inversion model construction method driven by a target data set to construct a transient electromagnetic inversion model, input the electromagnetic response data to be predicted into the transient electromagnetic inversion model, and obtain the predicted resistivity value.

[0024] The present invention aims to improve the accuracy of network inversion of test data through deep learning inversion using an iterative training strategy. This method gradually approaches the true inversion result by repeatedly updating the model and adjusting parameters, thereby overcoming the limitations of traditional data-driven methods and improving inversion accuracy and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 any creative work.

[0026] Figure 1 A framework diagram of a method for constructing a transient electromagnetic inversion model driven by a target data set according to an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of sample set data generation according to an embodiment of the present invention;

[0028] Figure 3 This is a diagram of an iterative inversion network framework driven by a target data set according to an embodiment of the present invention;

[0029] Figure 4 This is a network model training loss graph according to an embodiment of the present invention;

[0030] Figure 5 This is a performance evaluation diagram of the initial network model according to an embodiment of the present invention;

[0031] Figure 6 This is a comparison diagram of the response errors of the iterative inversion network driven by the target data set according to an embodiment of the present invention;

[0032] Figure 7 1 is a comparison diagram of a certain sample point to be tested in an embodiment of the present invention using different methods, wherein Figure (a) is a response data fitting diagram, and Figure (b) is a resistivity value fitting diagram. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0034] 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.

[0035] This embodiment provides a method for constructing a transient electromagnetic inversion model driven by a target dataset, including:

[0036] Constructing an initial training set, and using the initial training set to train the first convolutional neural network to obtain an initial transient electromagnetic inversion network model;

[0037] Input the electromagnetic response data to be measured into the initial transient electromagnetic inversion model for prediction to obtain the resistivity value;

[0038] Performing forward simulation on the resistivity value to obtain electromagnetic response data of the forward simulation, and constructing prediction data based on the electromagnetic response data of the forward simulation and the resistivity value;

[0039] Extract data similar to the electromagnetic response data to be tested in the initial training set, and construct a target data set based on the similar data and the predicted data;

[0040] Furthermore, extracting data similar to the electromagnetic response data to be tested from the initial training set includes:

[0041] Obtain the relative average error between the electromagnetic response data in the initial training set and the electromagnetic response data to be measured; obtain the electromagnetic response data in the initial training set corresponding to the relative average error in the preset range as similar electromagnetic response data, and extract the resistivity value corresponding to the similar electromagnetic response data in the initial training set to obtain similar data.

[0042] The parameters in the initial transient electromagnetic inversion model are transferred to the second convolutional neural network to iteratively learn the target dataset to obtain the transient electromagnetic inversion model.

[0043] Furthermore, obtaining the initial training set includes: presetting the top thickness and bottom boundary depth of the underground geological structure, and dividing it into several layers according to the cumulative increasing method of the thickness of each layer; determining several control points between the top and bottom layers, interpolating the control points, and obtaining resistivity-thickness sample data between the top and bottom layers; performing transient electromagnetic one-dimensional numerical simulation based on the resistivity-thickness sample data to obtain corresponding electromagnetic responses; obtaining a sample data set based on the resistivity value and the corresponding electromagnetic response, and dividing the initial training set from the sample data set.

[0044] Specifically, considering that the resistivity values ​​of actual underground strata are usually distributed continuously rather than segmented, and the continuous distribution characteristics can well reflect the complexity of the underground geological structure, in order to generate relatively smooth and longitudinally continuous underground resistivity values, this embodiment adopts the following method to generate sample set data: first, the thickness of the top layer is set to 1m, the boundary depth of the last layer is set to 750m, and the layers are divided into 15 layers according to the method of cumulative increasing thickness of each layer to ensure that the random characteristics of the underground resistivity distribution are fully reflected; 5 control points are determined between 1 and 750m, as shown in the attached figure. Figure 2As shown in the darker dots, the depths of two control points are fixed at 1m and 750m, and the remaining three control points are randomly determined, but the depth between the control points is required to be within 50-200m. The resistivity of the control points is randomly generated within 10-1000Ω·m. The B-spline interpolation method is used based on the five control points to make the resistivity curve smoother, and finally a continuously distributed resistivity value from 1m to 750m is obtained. Figure 2 As shown. Using a rectangular loop source device, the generated resistivity-thickness sample data is substituted into the transient electromagnetic one-dimensional numerical simulation method to calculate the corresponding electromagnetic response. The coil length and width are 500m, the number of receiving time channels is 61, and the sampling time is 1e -4 ~1e -1 s, the emission current is 10A.

[0045] Furthermore, the convolutional neural network includes: an input layer, an output layer, a convolution layer and a fully connected layer, wherein the input layer is used to input electromagnetic response, the output layer is used to output resistivity value, and the data features extracted by the convolution layer are input to the fully connected layer.

[0046] Specifically, the convolutional neural network model framework is used as Figure 3 , the input of the network is electromagnetic response data, and the output is resistivity value. The network structure mainly consists of input layer and output layer, 4 convolutional layers and 2 fully connected layers. The input layer has 61 neurons, representing 61 electromagnetic response values; the output layer has 15 neurons, corresponding to 15 layers of resistivity values. The convolution kernel sizes of the 4 convolutional layers are 2×1, 3×1, 3×1 and 3×1, respectively, and the number of convolution kernels are 64, 128, 256 and 512, respectively, with a step size of 1; the pooling layer uses Max-pooling with a size of 2×1 and a step size of 2. The data features extracted by the convolution layer are input into the fully connected layer through the flattening layer. The number of neurons in the two fully connected layers are 1024 and 512, respectively. The activation function uses tanh. In order to quantitatively evaluate the convergence of the network training process, the following loss function is defined:

[0047]

[0048] Where N represents the number of layers of resistivity value, represents the resistivity value of the jth layer of the network prediction model, y j Indicates the resistivity value corresponding to the real geoelectric model.

[0049] The network was trained using the Adam optimizer. The hyperparameters were set as follows: learning rate lr = 0.0001, batch size batch_size = 1024, epochs = 5000, and early stopping. A dataset of 40,000 samples was generated and partitioned into a training set: validation set: test set ratio of 6.3:2.7:1.0.

[0050] like Figure 4 The figure below shows the model network training loss function. The dotted line represents the validation set error, and the solid line represents the training set error. Using an early stopping mechanism, we can see that the model training process exhibits no overfitting. The training loss and validation loss decrease continuously during training and eventually converge. The decrease in the training loss indicates that the model is gradually learning the patterns and regularities in the training data and continuously optimizing the model parameters. This demonstrates that the model does not exhibit significant overfitting during training and exhibits strong fitting capabilities.

[0051] This embodiment selects three geoelectric model data corresponding to the minimum, average, and maximum relative average error from the test set. Figure 5 The resistivity-depth curve comparison diagram of the original model and the inversion model, as well as the electromagnetic response comparison diagram of the original model and the inversion model of the three models are shown. Figure 5 Three data sets with the minimum, average, and maximum relative average errors are selected to plot the resistivity-depth graph of the original geoelectric model and the inverted geoelectric model (first row) and the electromagnetic response signal graph of the original geoelectric model and the inverted geoelectric model (second row). It can be observed from the figure that the inverted model fits the original model well. Although there are certain gaps in some layers, it is still within an acceptable range overall. In particular, for the model with the largest relative average error, although there are large errors in the resistivity prediction of some layers, the overall trend of resistivity with depth is consistent with the original model, and its corresponding electromagnetic response error is only 9.4%. This further demonstrates the high accuracy of the inversion results. It meets the assumption that the deep learning inversion method is efficient and the accuracy can be guaranteed to a certain extent.

[0052] Specifically, such as Figure 1The upper left module is the initial network model training part, the upper right part is the data set required for iterative inversion, and the lower part is the iterative training part. First, the initial training set is generated through numerical simulation, that is, the Train data in the upper left module, and then the convolutional neural network model is trained to obtain the initial transient electromagnetic inversion network model. Finally, the electromagnetic response data to be measured, that is, the Objective data in the upper right module, is predicted for the first time to obtain the corresponding resistivity value DL Predict. Then, the electromagnetic response data in the Train data and the electromagnetic response data to be measured (Objective data) are extracted. The data with a relative average error (such as formula 2) within 5% is extracted, that is, Objective dataend, including the corresponding resistivity value. Afterwards, the Objective data end is merged with the DL Predict (resistivity value) and the electromagnetic response obtained by forward simulation of the DLPredict to form the data set New Data (in the lower module) required for iterative inversion. Finally, a transfer learning strategy is adopted for the initial network Model-1, that is, the initial transient electromagnetic inversion network model. That is, the network framework is kept unchanged, the model parameters in Model-1 are migrated to Model (the second convolutional neural network) to initialize the model parameters, and then the New Data is learned. This process is iterated multiple times to achieve iterative inversion driven by the target data set.

[0053]

[0054] Where M is the number of time channels, d j is the true electromagnetic response of the jth time channel, Predict the electromagnetic response of the network for the jth time channel.

[0055] Figure 6 The solid line in the middle is the model response error predicted by the initial network model for 50 test data, and the dotted line is the model response error predicted by the iterative inversion network driven by the target data set. Figure 6 It can be clearly observed that after the iterative inversion driven by the target data set, except for individual data, the response error of the test data is reduced to a low level as a whole, indicating that the iterative inversion strategy driven by the target data set has a certain effect. In addition, by comparing the results of a certain test point under different methods, Figure 7 , where the dotted line is the true value, the dashed line is the result obtained by the initial network inversion, and the dotted line is the result after 5 iterations of the iterative inversion network driven by the target dataset. Figure 7 It can be observed in the subgraph (a) that after 5 iterations, the response error of the data is close to the true response value, and the response accuracy is improved to a certain extent. Figure 7(b) It can be clearly observed that the result after 5 iterations (dashed line) is closer to the true resistivity value, which is more obvious in the shallow part with a depth of 100-200m. In summary, this embodiment improves the inversion accuracy of the network for the measured data through simple iterative inversion.

[0056] The deep learning-based transient electromagnetic inversion network, without any intervention, achieved model and response relative average errors of 0.0504 and 0.0310, respectively, for 50 samples different from the training set (the number of samples from the measured data of a single survey line was close). This high accuracy meets the assumption that deep learning inversion methods are efficient and can guarantee accuracy to a certain extent.

[0057] The target dataset proposed in this embodiment consists of two parts:

[0058] The proposed method uses a dataset consisting of (1) data similar to the target data, i.e., data with a response error less than a specified threshold (default 5%), and (2) a dataset consisting of the resistivity values ​​and corresponding responses predicted by the network. The initial training model is then transferred to the target dataset using a transfer learning strategy. After five iterations of inversion, the proposed method achieves a model relative average error of 0.0379 and a response relative average error of 0.0105, respectively. Compared to the initial predictions, both the model error and the response error are reduced by 3 to 5 times.

[0059] In summary, this embodiment improves the inversion accuracy of the network for the data to be measured through simple iterative inversion.

[0060] This embodiment also provides a transient electromagnetic inversion method driven by a target dataset. A transient electromagnetic inversion model is constructed using a transient electromagnetic inversion model construction method driven by a target dataset. The electromagnetic response data to be predicted is input into the transient electromagnetic inversion model to obtain a predicted resistivity value.

[0061] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A method for constructing a transient electromagnetic inversion model driven by a target dataset, characterized in that: include: Constructing an initial training set, and using the initial training set to train a first convolutional neural network to obtain an initial transient electromagnetic inversion network model; Obtaining the initial training set includes: Preset the thickness of the top layer and the depth of the bottom boundary of the underground geological structure, and divide it into several layers according to the method of cumulative increasing thickness of each layer; Determine a plurality of control points between the top layer and the bottom layer, interpolate the control points, and obtain resistivity-thickness sample data between the top layer and the bottom layer; Performing a one-dimensional transient electromagnetic numerical simulation based on the resistivity-thickness sample data to obtain a corresponding electromagnetic response; Based on the resistivity value and the corresponding electromagnetic response, a sample data set is obtained, and the initial training set is divided from the sample data set; The convolutional neural network includes: an input layer, an output layer, a convolution layer, and a fully connected layer, wherein the input layer is used to input the electromagnetic response, the output layer is used to output the resistivity value, and the data features extracted by the convolution layer are input to the fully connected layer; Inputting the electromagnetic response data to be measured into the initial transient electromagnetic inversion network model for prediction to obtain the resistivity value; Performing forward simulation on the resistivity value to obtain electromagnetic response data of the forward simulation, and constructing prediction data based on the electromagnetic response data of the forward simulation and the resistivity value; extracting data from the initial training set that is similar to the electromagnetic response data to be measured, and constructing a target data set based on the similar data and the predicted data; Extracting data from the initial training set that is similar to the electromagnetic response data to be measured includes: Obtaining a relative average error between the electromagnetic response data in the initial training set and the electromagnetic response data to be measured; obtaining electromagnetic response data in the initial training set corresponding to the relative average error within a preset range as similar electromagnetic response data, and extracting the resistivity value corresponding to the similar electromagnetic response data in the initial training set to obtain the similar data; Calculating the relative average error of the response includes: ； Where M is the number of time channels, is the true electromagnetic response of the jth time channel, Predict the electromagnetic response of the network for the jth time channel; The parameters in the initial transient electromagnetic inversion network model are transferred to a second convolutional neural network to perform iterative learning on the target data set to obtain a transient electromagnetic inversion model.

2. The method for constructing a transient electromagnetic inversion model based on target dataset drive according to claim 1, characterized in that: Interpolating the control points includes: interpolating using a B-spline interpolation method.

3. A transient electromagnetic inversion method driven by a target dataset, characterized in that: A transient electromagnetic inversion model is constructed using the target data set driven transient electromagnetic inversion model construction method according to any one of claims 1-2, and the electromagnetic response data to be predicted is input into the transient electromagnetic inversion model to obtain the predicted resistivity value.

Images