Methods, apparatus, equipment and storage media for interpreting airborne transient electromagnetic measurement data

Abstract

This invention provides a method, apparatus, device, and storage medium for interpreting transient electromagnetic measurement data. The method includes: transmitting a transient current to a point to be measured via a transmitting coil and receiving an electromagnetic signal via a receiving coil; determining the coordinates of the point to be measured based on the coordinates of the transmitting and receiving coils; and inputting the electromagnetic signal and the coordinates of the point to be measured into a transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured. This invention overcomes the limitations of existing single-mode representations by capturing the long-range dependence of spatiotemporal electromagnetic responses and achieving adaptive feature fusion of transient electromagnetic data. Furthermore, by introducing prior knowledge such as the geometric spatial information of the measurement point, the transmitting and receiving coordinates, and terrain undulations, the interpretation capability of the transient electromagnetic measurement data interpretation model is enhanced. Constructing a transient electromagnetic measurement data interpretation model based on three-dimensional information improves the reliability of the transient electromagnetic measurement data interpretation.

Description

Technical Field

[0001] This invention relates to the field of transient electromagnetic measurement data interpretation technology, and in particular to a method, apparatus, equipment and storage medium for interpreting airborne transient electromagnetic measurement data. Background Technology

[0002] The Transient Electromagnetic Method (TEM) is a highly efficient geophysical exploration technique based on Faraday's law of electromagnetic induction. Its principle involves transmitting a transient current into the subsurface, exciting a time-varying induced magnetic field and generating secondary eddy currents. The resistivity distribution of the subsurface medium is then inverted by receiving the secondary electromagnetic signal. Existing TEM measurements employ various data acquisition modes, and TEM exploration missions often utilize one-dimensional inversion to handle massive amounts of data and improve the efficiency of TEM measurements. However, one-dimensional inversion does not consider factors such as topographic relief and three-dimensional variations in the subsurface medium, resulting in less reliable interpretation results. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and storage medium for interpreting transient electromagnetic measurement data, in order to solve the problem of low reliability of interpretation results in existing transient electromagnetic measurement data interpretation methods.

[0004] This invention provides a method for interpreting airborne transient electromagnetic measurement data, comprising the following steps:

[0005] A transient current is transmitted to the point to be measured via a transmitting coil, and an electromagnetic signal is received via a receiving coil; the electromagnetic signal is generated based on the transient current.

[0006] Based on the coordinates of the transmitting coil and the receiving coil, the coordinates of the point to be measured are determined;

[0007] The electromagnetic signal and the coordinates of the point to be measured are input into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured.

[0008] The transient electromagnetic measurement data interpretation model was obtained by training with transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0009] According to a method for interpreting airborne transient electromagnetic measurement data provided by the present invention, the method further includes:

[0010] Determine the range of surface undulations, medium properties, and resistivity parameters; the resistivity of each type of medium is within the range of the resistivity parameters.

[0011] The distribution range of each attribute medium and the coordinates of the transceiver coils are determined in the region of the geoelectric model; the geoelectric model is constructed based on the range of surface undulations.

[0012] Training data is generated that includes the coordinates of the transceiver coil, terrain undulation data, and electromagnetic response data; the terrain undulation data is determined based on the range of surface undulation changes; the electromagnetic response data is determined based on the resistivity of each property medium and its distribution range.

[0013] According to the present invention, a method for interpreting airborne transient electromagnetic measurement data includes generating training data containing the coordinates of the transceiver coils, terrain undulation data, and electromagnetic response data, followed by:

[0014] The relative coordinates are obtained by fusing the coordinates of the transceiver coils and the terrain undulation data.

[0015] The coordinates of the target point are determined based on the coordinates of the transceiver coils;

[0016] The vertical resistivity distribution at the target point is obtained by interpolating below the target point.

[0017] According to a method for interpreting airborne transient electromagnetic measurement data provided by the present invention, the method further includes:

[0018] Based on the geometric coordinate normalization parameters and the three-dimensional coordinate tensor, the coordinates of the transceiver coil are normalized to obtain normalized coordinate data.

[0019] Based on the initial electromagnetic response, total emission current, and electromagnetic response normalization parameters, the electromagnetic response data is normalized to obtain the normalized electromagnetic response.

[0020] The vertical resistivity distribution is normalized to obtain normalized resistivity data.

[0021] According to the present invention, an airborne transient electromagnetic measurement data interpretation method is provided, wherein the transient electromagnetic measurement modes include a zero-offset measurement mode and a non-zero-offset measurement mode; the airborne transient electromagnetic measurement data interpretation method further includes:

[0022] A zero-offset data body is constructed based on the zero-offset measurement mode; the zero-offset data body includes a transmitting coil relative coordinate data body and a zero-offset electromagnetic response data body;

[0023] A non-zero offset data volume is constructed based on the aforementioned non-zero offset measurement mode; the non-zero offset data volume includes a transmitting coil relative coordinate data volume, a receiving coil relative coordinate data volume, and a non-zero offset electromagnetic response data volume.

[0024] Based on the zero-offset data volume and the non-zero-offset data volume, a variety of input data volumes are constructed; the input data volumes are used to train the transient electromagnetic measurement data interpretation model.

[0025] According to the present invention, an airborne transient electromagnetic measurement data interpretation method is provided, wherein multiple input data volumes are constructed based on the zero-offset data volume and the non-zero-offset data volume, and then the method includes:

[0026] Generate the first training strategy and the second training strategy;

[0027] The first training strategy is to train on various input data volumes sequentially; the second training strategy is to train on a mixture of multiple input data volumes.

[0028] The present invention also provides an airborne transient electromagnetic measurement data interpretation device, comprising the following modules:

[0029] The transceiver module is used to transmit transient current to the point to be measured through a transmitting coil and receive electromagnetic signals through a receiving coil; the electromagnetic signals are generated based on the transient current.

[0030] The point coordinate determination module is used to determine the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil.

[0031] The resistivity distribution interpretation module is used to input the electromagnetic signal and the coordinates of the point to be measured into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured.

[0032] The transient electromagnetic measurement data interpretation model was obtained by training with transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0033] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the airborne transient electromagnetic measurement data interpretation method as described above.

[0034] The present invention also provides a non-transient computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the airborne transient electromagnetic measurement data interpretation method as described above.

[0035] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the airborne transient electromagnetic measurement data interpretation method as described above.

[0036] This invention provides a method, apparatus, equipment, and storage medium for interpreting airborne transient electromagnetic measurement data. It proposes a method for interpreting airborne transient electromagnetic measurement data based on a transient electromagnetic measurement data interpretation model. By capturing the long-range dependence of spatiotemporal electromagnetic responses, adaptive feature fusion of transient electromagnetic data is achieved, overcoming the limitations of existing single-mode representations. Furthermore, by introducing geometric spatial information of measurement points, prior knowledge such as transmit / receive coordinates and terrain undulations, the interpretation capability of the transient electromagnetic measurement data interpretation model is enhanced. A transient electromagnetic measurement data interpretation model based on three-dimensional information is constructed, improving the reliability of the interpreted transient electromagnetic measurement data. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the airborne transient electromagnetic measurement data interpretation method provided by the present invention.

[0039] Figure 2 This is a schematic diagram illustrating the usage process of the transient electromagnetic measurement data interpretation model provided by the present invention.

[0040] Figure 3 This is a schematic diagram of the geoelectric model provided by the present invention.

[0041] Figure 4 This is a schematic diagram of the model training process in the airborne transient electromagnetic measurement data interpretation method provided by the present invention.

[0042] Figure 5 This is a schematic diagram of the various input data bodies provided by the present invention.

[0043] Figure 6 This is a schematic diagram of the first training strategy provided by the present invention.

[0044] Figure 7 This is a schematic diagram of the second training strategy provided by the present invention.

[0045] Figure 8 This is a schematic diagram of the structure of the airborne transient electromagnetic measurement data interpretation device provided by the present invention.

[0046] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] The following is combined Figures 1-9 The present invention describes a method, apparatus, device, and storage medium for interpreting airborne transient electromagnetic measurement data.

[0049] Figure 1 This is one of the flowcharts illustrating the airborne transient electromagnetic measurement data interpretation method provided by the present invention, such as... Figure 1 As shown, the method includes the following:

[0050] Step 100: Transient current is transmitted to the point to be measured through the transmitting coil, and electromagnetic signal is received through the receiving coil; the electromagnetic signal is generated based on the transient current.

[0051] After training the transient electromagnetic measurement data interpretation model, a data volume, including electromagnetic response data, is input into the model. A transient current is transmitted to the point to be measured via a transmitting coil, and an electromagnetic signal generated based on the transient current is received via a receiving coil. The time derivative of the vertical component of the magnetic induction intensity is used as the electromagnetic response data.

[0052] Step 200: Determine the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil;

[0053] The input data also includes transceiver coil coordinate data (i.e., the coordinates of the transmitting and receiving coils) and terrain undulation data. The coordinates of the measurement point are determined based on the transceiver coil coordinate data, which in turn are related to the measurement mode. For the zero-offset measurement mode, since the transmitting and receiving coils coincide, the horizontal coordinate of the measurement point must coincide with the horizontal coordinate of either the transmitting or receiving coil, and its horizontal coordinate can be denoted as Col. For the non-zero-offset measurement mode, the measurement point is located at the midpoint of the line connecting the transmitting and receiving coils, and its horizontal coordinate can be denoted as Cnol. When both zero-offset and non-zero-offset data are used simultaneously to infer the vertical resistivity distribution of the medium below the measurement point, the horizontal coordinate of the measurement point is (Col + Cnol) / 2.

[0054] Step 300: Input the electromagnetic signal and the coordinates of the point to be measured into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured;

[0055] The transient electromagnetic measurement data interpretation model was obtained by training with transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0056] The process of using the transient electromagnetic measurement data interpretation model mainly includes constructing the data volume, data normalization, convolution and position encoding, inputting to the Transformer layer, and linear transformation, etc., as detailed in the following steps. Figure 2 As shown. Specifically, the steps are as follows: 1. Construct a data volume and determine the coordinates of the points to be measured; 2. Normalize the data volume; 3. Input the normalized data volume into a convolutional layer and a position encoding layer for processing; 4. Combine the outputs of the convolutional layer and the position encoding layer and input them into a Transformer layer; 5. Input the output of the Transformer layer into a convolutional layer; 6. Input the output of the convolutional layer into a linear layer to obtain the resistivity distribution interpretation result of the points to be measured.

[0057] This embodiment achieves adaptive feature fusion of transient electromagnetic data by capturing the long-range dependence of spatiotemporal electromagnetic response, thus overcoming the limitations of existing single-mode representations. Furthermore, by introducing prior knowledge such as the geometric spatial information of measurement points, transmit and receive coordinates, and terrain undulations, the interpretation capability of the transient electromagnetic measurement data interpretation model is enhanced. A transient electromagnetic measurement data interpretation model based on three-dimensional information is constructed, thereby improving the reliability of transient electromagnetic measurement data interpretation.

[0058] In one embodiment, the airborne transient electromagnetic measurement data interpretation method provided by this invention may further include:

[0059] Step 10: Determine the range of surface undulations, medium properties, and resistivity parameters; the resistivity of each type of medium is within the range of the resistivity parameters.

[0060] Step 20: Determine the distribution range of each attribute medium and the coordinates of the transceiver coils within the region of the geoelectric model; the geoelectric model is constructed based on the range of surface undulations.

[0061] Step 30: Generate training data containing the coordinates of the transceiver coil, terrain undulation data, and electromagnetic response data; the terrain undulation data is determined based on the range of surface undulation changes; the electromagnetic response data is determined based on the resistivity of each property medium and its distribution range.

[0062] During the model training phase, the process of generating training data includes geoelectric model design (such as...). Figure 3(As shown). The airborne transient electromagnetic measurement data interpretation method provided by this invention is geared towards airborne transient electromagnetic detection missions, where the detection target is typically a subsurface high-conductivity anomaly. To construct a geoelectric model of an undulating surface, it is necessary to set the surface undulation range parameter [-D, D], where -D represents the distance below the horizontal plane and D represents the distance above the horizontal plane. This invention randomly sets initial undulation points and corresponding heights within the model region and uses linear interpolation to interpolate the undulation conditions of the initial undulation points to the horizontal coordinates of each surface grid node in the geoelectric model, thus obtaining the surface undulation results for each surface grid node in the geoelectric model.

[0063] In addition to considering surface undulation factors to enhance the generalization ability of training data, the characteristics of random media, a key factor affecting the generalization ability of physical exploration data, can also be introduced. Before introducing the setting method of random media, it is necessary to clarify the characteristics and distribution range of naturally formed media properties. Taking the resistivity property (or conductivity property) of the medium as an example, the resistivity of most naturally formed rocks is roughly between 10 and 10,000. Therefore, the resistivity parameter of the random model designed in this invention varies within the range of [10, 10,000].

[0064] This embodiment constructs a model training dataset with generalization characteristics by designing a stochastic geoelectric model and performing simulation calculations.

[0065] In one embodiment, the airborne transient electromagnetic measurement data interpretation method provided by this invention may further include:

[0066] Step 40: Fuse the coordinates of the transceiver coil and the terrain undulation data to obtain relative coordinates;

[0067] Step 50: Determine the coordinates of the target point based on the coordinates of the transceiver coil;

[0068] Step 60: By interpolating below the target point, the vertical resistivity distribution below the target point is obtained.

[0069] After obtaining the training data, it is preprocessed, including coordinate data fusion. Both the transceiver coil coordinates and terrain undulation data are coordinate data. In three-dimensional space, the volume recording the transceiver coil coordinates or receiver coil coordinates is controlled by only three variables (i.e., three-dimensional coordinates); while the volume recording terrain undulations is controlled by N×3 variables (N being the number of scattered points recording terrain undulations). Therefore, compared to the volume recording terrain undulations, the number of variables in the transceiver coil coordinate data volume or receiver coil coordinate data volume is smaller, limiting its impact on parameter tuning during model training. Furthermore, the key to inverting airborne transient electromagnetic detection data is recording various relative coordinate data, not absolute coordinates (such as geodetic coordinates and latitude and longitude). Therefore, this invention calculates the relative coordinates of the transceiver coils to the terrain undulation data points, thereby simultaneously describing the transceiver coil coordinate information and the undulating terrain, and also fusing the originally less informative transceiver coil coordinates with the undulating terrain coordinate data.

[0070] The measurement points in the training data of this invention are the points where the vertical resistivity distribution of the medium needs to be determined, and the vertical resistivity distribution of the medium at any point can be obtained by interpolation using a geoelectric model.

[0071] This embodiment reduces data storage by fusing transceiver coil coordinates with undulating terrain coordinates, thus preserving data information.

[0072] In one embodiment, the airborne transient electromagnetic measurement data interpretation method provided by this invention may further include:

[0073] Step 70: Based on the geometric coordinate normalization parameters and the three-dimensional coordinate tensor, normalize the coordinates of the transceiver coil to obtain normalized coordinate data;

[0074] Step 80: Based on the initial electromagnetic response, total emission current, and electromagnetic response normalization parameters, normalize the electromagnetic response data to obtain the normalized electromagnetic response.

[0075] Step 90: Normalize the vertical resistivity distribution to obtain normalized resistivity data.

[0076] The model training process provided by this invention involves three types of data: coordinate data, electromagnetic response data, and point resistivity data. To improve the convergence of the model training process, it is necessary to normalize each type of data.

[0077] For the coordinate data of the transceiver coil Propose geometric coordinate normalization parameters Then any relative coordinate value needs to be divided by This allows us to obtain normalized coordinate data. As shown in Formula 1.

[0078] (1)

[0079] in, It is a three-dimensional coordinate tensor that describes the undulations of the Earth's surface.

[0080] There are two key characteristics to electromagnetic response data: the data is correlated with the amplitude of the transmitted signal; and the secondary field decays rapidly. Assume the initial electromagnetic response is... Then the normalized electromagnetic response can be calculated using formula 2.

[0081] (2)

[0082] in, This represents the electromagnetic response data after normalization. This represents the total current in the transmitting coil; This represents the normalized parameter of the electromagnetic response.

[0083] For resistivity data RES, normalization can be performed using the following formula 3.

[0084] (3)

[0085] in, This represents the normalized resistivity value; This represents the resistivity normalization parameter.

[0086] This embodiment improves the convergence of the model training process by normalizing the training data.

[0087] Figure 4 This is a schematic diagram of the model training process in the airborne transient electromagnetic measurement data interpretation method provided by the present invention, as shown below. Figure 4 As shown, the method may further include:

[0088] Step 400: Construct a zero-offset data volume based on the zero-offset measurement mode; the zero-offset data volume includes a transmitting coil relative coordinate data volume and a zero-offset electromagnetic response data volume;

[0089] Step 500: Construct a non-zero offset data body based on the non-zero offset measurement mode; the non-zero offset data body includes a transmitting coil relative coordinate data body, a receiving coil relative coordinate data body, and a non-zero offset electromagnetic response data body;

[0090] Step 600: Based on the zero offset data volume and the non-zero offset data volume, construct multiple input data volumes; the input data volumes are used to train the transient electromagnetic measurement data interpretation model.

[0091] For input data in multiple measurement modes, the measurement modes are divided into zero-offset, common-offset, and multi-offset measurements. In zero-offset mode, the coordinates of the receiving coil coincide with those of the transmitting coil, so only the position of the transmitting coil needs to be obtained. In contrast, common-offset and multi-offset modes record the spatial position of the receiving coil simultaneously. Model training for common-offset data can also default to and solidify the offset information in the input data; however, the model trained on this model is not applicable to other offset scenarios. Therefore, whether the offset is zero is a crucial factor. To improve generalization, if the offset is not zero, the position information of both the transmitting and receiving coils is recorded simultaneously; if the offset is zero, only the position information of either the transmitting or receiving coil is recorded.

[0092] This invention proposes an input data volume consisting of two main parts: a zero-offset data volume and a non-zero-offset data volume. The zero-offset data volume can be further subdivided into a transmitting coil relative coordinate data volume and a zero-offset electromagnetic response data volume; the non-zero-offset data volume can be subdivided into a transmitting coil relative coordinate data volume, a receiving coil relative coordinate data volume, and a non-zero-offset electromagnetic response data volume. To achieve the capability to interpret measurement data from multiple modes, this invention also combines the above zero-offset and non-zero-offset data volumes into a unified input data volume.

[0093] To enable data interpretation capabilities across multiple measurement modes, this invention proposes three training data volumes, such as... Figure 5 As shown. The first type, namely input data body (a), contains both zero-offset data body and non-zero-offset data body; the second type, namely input data body (b), contains only zero-offset data body; the third type, namely input data body (c), contains only non-zero-offset data body.

[0094] This embodiment improves the model's ability to interpret measurement data in multiple modes by constructing an input data volume.

[0095] In one embodiment, the airborne transient electromagnetic measurement data interpretation method provided by this invention may further include:

[0096] Step 700: Generate the first training strategy and the second training strategy;

[0097] The first training strategy is to train on various input data volumes sequentially; the second training strategy is to train on a mixture of multiple input data volumes.

[0098] The training process of the transient electromagnetic measurement data interpretation model includes training strategy selection, training dataset generation, data normalization, convolution and position encoding, Transformer processing, linear layers, loss function determination and model parameter update, so that the trained model can acquire the ability to interpret multi-mode measurement data of airborne transient electromagnetic detection.

[0099] The model training process is as follows:

[0100] I. Constructing the Training Dataset. The original dataset can be divided into three data subsets. Therefore, the above data training process can follow the following two training strategies.

[0101] The first training strategy involves training sequentially on different data subsets. This means that training is not performed using data from other subsets until training on a specific subset is complete. However, this first strategy suffers from the issue of training sequence. Figure 6 As shown.

[0102] The second training strategy involves mixing data from different subsets and then having the data from each subset participate in training simultaneously. This strategy eliminates the issue of training order. Figure 7 As shown.

[0103] Second, normalize the constructed training data.

[0104] Third, the normalized data is fed into the Transformer network after passing through convolutional layers and positional encoding.

[0105] Fourth, the output data of the Transformer network is passed through convolutional layers and linear layers in sequence, and the output data is compared with the resistivity distribution data of the target point to calculate the loss function.

[0106] 5. Adjust the parameters in the Transformer network iteratively based on the results of the loss function.

[0107] 6. Repeat steps 3 to 5 above until the maximum number of iterations is reached or the termination condition is met by the loss function.

[0108] This embodiment enables the transient electromagnetic measurement data interpretation model to interpret measurement data in multiple modes through the constructed model training framework and training process.

[0109] The following describes the airborne transient electromagnetic measurement data interpretation device provided by the present invention. The airborne transient electromagnetic measurement data interpretation device described below can be referred to in correspondence with the airborne transient electromagnetic measurement data interpretation method described above.

[0110] Please refer to Figure 8 The present invention also provides an airborne transient electromagnetic measurement data interpretation device, comprising:

[0111] The transceiver module 701 is used to transmit a transient current to the point to be measured through a transmitting coil and receive an electromagnetic signal through a receiving coil; the electromagnetic signal is generated based on the transient current.

[0112] The point coordinate determination module 702 is used to determine the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil.

[0113] The resistivity distribution interpretation module 703 is used to input the electromagnetic signal and the coordinates of the point to be measured into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured.

[0114] The transient electromagnetic measurement data interpretation model was obtained by training with transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0115] Optionally, the airborne transient electromagnetic measurement data interpretation device further includes:

[0116] A variation range determination model is used to determine the variation range of surface undulations, medium properties, and resistivity parameters; the resistivity of each property medium is within the variation range of the resistivity parameters.

[0117] A transceiver coil coordinate determination model is used to determine the distribution range of various attribute media and the transceiver coil coordinates within the region of the geoelectric model; the geoelectric model is constructed based on the range of surface undulations.

[0118] A training data generation model is used to generate training data containing the coordinates of the transceiver coil, terrain undulation data, and electromagnetic response data; the terrain undulation data is determined based on the range of surface undulation changes; the electromagnetic response data is determined based on the resistivity of each property medium and its distribution range.

[0119] Optionally, the airborne transient electromagnetic measurement data interpretation device further includes:

[0120] A data fusion model is used to fuse the coordinates of the transceiver coil and the terrain undulation data to obtain relative coordinates;

[0121] A target point coordinate determination model is used to determine the coordinates of a target point based on the coordinates of the transceiver coil.

[0122] The resistivity distribution of the target point in the training data is obtained, and the vertical resistivity distribution under the target point is obtained by interpolation below the target point.

[0123] Optionally, the airborne transient electromagnetic measurement data interpretation device further includes:

[0124] A normalized processing model for transceiver coil coordinates is used to normalize the coordinates of the transceiver coil based on geometric coordinate normalization parameters and a three-dimensional coordinate tensor to obtain normalized coordinate data.

[0125] An electromagnetic response data normalization processing model is used to normalize the electromagnetic response data based on the initial electromagnetic response, the total emission current, and the electromagnetic response normalization parameters to obtain a normalized electromagnetic response.

[0126] A normalization model for vertical resistivity distribution is used to normalize the vertical resistivity distribution to obtain normalized resistivity data.

[0127] Optionally, the transient electromagnetic measurement mode includes a zero-offset measurement mode and a non-zero-offset measurement mode; the airborne transient electromagnetic measurement data interpretation device further includes:

[0128] A zero-offset data volume construction model is used to construct a zero-offset data volume based on the zero-offset measurement mode; the zero-offset data volume includes a transmitting coil relative coordinate data volume and a zero-offset electromagnetic response data volume;

[0129] A non-zero offset data volume construction model is used to construct a non-zero offset data volume based on the non-zero offset measurement mode; the non-zero offset data volume includes a transmitting coil relative coordinate data volume, a receiving coil relative coordinate data volume, and a non-zero offset electromagnetic response data volume.

[0130] An input data volume construction model is used to construct multiple input data volumes based on the zero-offset data volume and the non-zero-offset data volume; the input data volume is used to train the transient electromagnetic measurement data interpretation model.

[0131] Optionally, the airborne transient electromagnetic measurement data interpretation device further includes:

[0132] A training policy generation model is used to generate a first training policy and a second training policy.

[0133] The first training strategy is to train on various input data volumes sequentially; the second training strategy is to train on a mixture of multiple input data volumes.

[0134] Figure 9 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 9As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logic instructions in the memory 830 to execute an airborne transient electromagnetic measurement data interpretation method. This method includes: transmitting a transient current to a point to be measured via a transmitting coil, and receiving an electromagnetic signal via a receiving coil; the electromagnetic signal is generated based on the transient current; determining the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil; inputting the electromagnetic signal and the coordinates of the point to be measured into a transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured; the transient electromagnetic measurement data interpretation model is trained using transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0135] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the airborne transient electromagnetic measurement data interpretation method provided by the above methods. The method includes: transmitting a transient current to a point to be measured through a transmitting coil and receiving an electromagnetic signal through a receiving coil; the electromagnetic signal is generated based on the transient current; determining the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil; inputting the electromagnetic signal and the coordinates of the point to be measured into a transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured; the transient electromagnetic measurement data interpretation model is trained by transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0137] In another aspect, the present invention also provides a non-transient computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the airborne transient electromagnetic measurement data interpretation method provided by the methods described above. This method includes: transmitting a transient current to a point to be measured via a transmitting coil, and receiving an electromagnetic signal via a receiving coil; the electromagnetic signal is generated based on the transient current; determining the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil; inputting the electromagnetic signal and the coordinates of the point to be measured into a transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured; the transient electromagnetic measurement data interpretation model is trained using transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

[0138] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0139] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for interpreting airborne transient electromagnetic measurement data, characterized in that, include: Transient current is transmitted to the point to be measured through a transmitting coil, and electromagnetic signals are received through a receiving coil. The electromagnetic signal is generated based on the transient current; Based on the coordinates of the transmitting coil and the receiving coil, the coordinates of the point to be measured are determined; The electromagnetic signal and the coordinates of the point to be measured are input into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured. The transient electromagnetic measurement data interpretation model was obtained by training transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data. The method for interpreting airborne transient electromagnetic measurement data also includes: Determine the range of surface undulations, medium properties, and resistivity parameters; the resistivity of each type of medium is within the range of the resistivity parameters. The distribution range of each attribute medium and the coordinates of the transceiver coils are determined in the region of the geoelectric model; the geoelectric model is constructed based on the range of surface undulations. Training data is generated that includes the coordinates of the transceiver coil, terrain undulation data, and electromagnetic response data; the terrain undulation data is determined based on the range of surface undulation changes; the electromagnetic response data is determined based on the resistivity of each property medium and its distribution range. The generation of training data, which includes the coordinates of the transceiver coil, terrain undulation data, and electromagnetic response data, then includes: The relative coordinates are obtained by fusing the coordinates of the transceiver coils and the terrain undulation data. The coordinates of the target point are determined based on the coordinates of the transceiver coils; The vertical resistivity distribution at the target point is obtained by interpolating below the target point.

2. The method for interpreting airborne transient electromagnetic measurement data according to claim 1, characterized in that, The method for interpreting airborne transient electromagnetic measurement data also includes: Based on the geometric coordinate normalization parameters and the three-dimensional coordinate tensor, the coordinates of the transceiver coil are normalized to obtain normalized coordinate data. Based on the initial electromagnetic response, total emission current, and electromagnetic response normalization parameters, the electromagnetic response data is normalized to obtain the normalized electromagnetic response. The vertical resistivity distribution is normalized to obtain normalized resistivity data.

3. The method for interpreting airborne transient electromagnetic measurement data according to claim 1, characterized in that, Transient electromagnetic measurement modes include zero-offset measurement mode and non-zero-offset measurement mode; The method for interpreting airborne transient electromagnetic measurement data also includes: A zero-offset data body is constructed based on the zero-offset measurement mode; the zero-offset data body includes a transmitting coil relative coordinate data body and a zero-offset electromagnetic response data body; A non-zero offset data volume is constructed based on the aforementioned non-zero offset measurement mode; the non-zero offset data volume includes a transmitting coil relative coordinate data volume, a receiving coil relative coordinate data volume, and a non-zero offset electromagnetic response data volume. Based on the zero-offset data volume and the non-zero-offset data volume, a variety of input data volumes are constructed; the input data volumes are used to train the transient electromagnetic measurement data interpretation model.

4. The method for interpreting airborne transient electromagnetic measurement data according to claim 3, characterized in that, Based on the zero-offset data volume and the non-zero-offset data volume, multiple input data volumes are constructed, which then includes: Generate the first training strategy and the second training strategy; The first training strategy is to train on various input data volumes sequentially; the second training strategy is to train on a mixture of multiple input data volumes.

5. An airborne transient electromagnetic measurement data interpretation device applying the airborne transient electromagnetic measurement data interpretation method as described in any one of claims 1 to 4, characterized in that, include: The transceiver module is used to transmit transient current to the point to be measured through the transmitting coil and receive electromagnetic signals through the receiving coil. The electromagnetic signal is generated based on the transient current; The point coordinate determination module is used to determine the coordinates of the point to be measured based on the coordinates of the transmitting coil and the receiving coil. The resistivity distribution interpretation module is used to input the electromagnetic signal and the coordinates of the point to be measured into the transient electromagnetic measurement data interpretation model to obtain the resistivity distribution interpretation result of the point to be measured. The transient electromagnetic measurement data interpretation model was obtained by training with transceiver coil sample coordinates, terrain undulation simulation data, and electromagnetic response sample data.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the airborne transient electromagnetic measurement data interpretation method as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the airborne transient electromagnetic measurement data interpretation method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the airborne transient electromagnetic measurement data interpretation method as described in any one of claims 1 to 4.

Images