A method for inverting asteroid gravity field and internal structure based on machine learning

Abstract

The present invention provides a method for inverting the gravity field and internal structure of an asteroid based on machine learning. When training a planetary deep neural gravity field network model based on machine learning, the internal density distribution of the asteroid is actually inferred based on external observation information. This process is also called gravity inversion. Using a planetary deep neural gravity field model based on deep learning for gravity inversion can perform various forms of prior density constraints through loss functions, thereby reducing the search space for gravity inversion optimization and improving the stability and accuracy of gravity inversion. The planetary deep neural gravity field model can integrate multi-source gravity observation data processing, and can simultaneously encode the asteroid's gravity field model, internal structure model, and three-dimensional shape model. The present invention will enhance the scientific value and practical significance of planetary exploration, and provide beneficial theoretical support and practical guidance for deep space exploration.

Description

Technical Field

[0001] The present invention relates to the field of deep space exploration technology, and in particular to a method for inverting the gravity field and internal structure of an asteroid based on machine learning. Background Art

[0002] There are still many challenges in studying the gravity field and internal structure of asteroids. The most effective and reliable way to measure the gravity field of an asteroid is to conduct on-site detection by launching a spacecraft. Since the United States launched the first asteroid probe in December 1978, humans have successfully launched and completed the corresponding detection mission targets of more than 20 asteroid probes, and have detected less than 30 asteroids. For the vast majority of asteroids, ground-based optical observations are limited. It can be said that humans know very little about asteroids. In addition, due to the weak gravity of asteroids and the complex dynamic mechanisms of asteroids affected by the sun and other major celestial bodies, they have a diverse dynamic environment, which greatly increases the difficulty of planning and implementing asteroid exploration missions.

[0003] Currently, gravity observation data from asteroid probes primarily consists of ground-based two-way Doppler velocity measurements. Fusing multi-source observation data from other onboard payloads (such as lidar and imaging) is relatively unexplored. Processing this multi-source data to invert the internal distribution characteristics of asteroids remains a hot topic and a key challenge in related research. When modeling asteroid gravity fields, the use of spherical harmonic series expansions can lead to non-convergence issues due to the irregular shapes of asteroids. Using gravity data to invert internal structure also presents non-uniqueness, so inferring the internal structure of an asteroid using gravity field models alone cannot guarantee a unique conclusion. Summary of the Invention

[0004] The present invention provides a method for inverting the gravity field and internal structure of an asteroid based on machine learning, so as to address the defects in the prior art.

[0005] In a first aspect, the present invention provides a method for inverting the gravity field and internal structure of an asteroid based on machine learning, comprising:

[0006] Obtaining a measured gravity field dataset and a terrain dataset of a sample planet, and preprocessing the measured gravity field dataset and the terrain dataset to obtain a training set and a test set;

[0007] Constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics, and the planetary internal structure characteristics;

[0008] Using the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model;

[0009] Inverting the test set using the initially trained planetary deep neural gravity field model to obtain a trained planetary deep neural gravity field model;

[0010] The measured gravity field data and topographic data of the planet to be measured are input into the trained planetary deep neural gravity field model, and the inversion results of the planetary gravity field and internal structure are output.

[0011] According to a method for inverting an asteroid's gravity field and internal structure based on machine learning provided by the present invention, the measured gravity field dataset and the terrain dataset are preprocessed to obtain a training set and a test set, including:

[0012] Formatting the measured gravity field dataset and the terrain dataset into PyTorch tensors and performing dimensionless processing;

[0013] The processed data is divided into the training set and the test set according to a preset division ratio.

[0014] According to the present invention, a method for inverting the gravity field and internal structure of an asteroid based on machine learning is provided to construct a planetary deep neural gravity field model, including:

[0015] A deep neural network is used to obtain a function that relates gravitational acceleration to position. This function has solutions outside the planet, on the planet's surface, and inside the planet and is differentiable for any order.

[0016] Determining the external gravity field characteristics of the planet, the surface shape characteristics of the planet, and the internal structure characteristics of the planet using the automatic differentiation characteristics of the deep neural network;

[0017] The loss function is constructed, which is jointly constrained by the planet's external gravity field characteristics, the planet's surface shape characteristics, and the planet's internal structure characteristics.

[0018] According to a method for inverting the gravity field and internal structure of an asteroid based on machine learning provided by the present invention, the loss function includes:

[0019] Determine that the planetary deep neural gravity field model is a fully connected network based on a sinusoidal activation function, and the loss function for:

[0020]

[0021]

[0022]

[0023]

[0024]

[0025] in, 、 、 、 is the weight of each constraint, is the external observation constraint, is the loss function constrained by physical laws, is the range density constraint loss function, is the spherical harmonic coefficient constraint loss function, is the expression of the fully connected network, is the number of spherical harmonic coefficients, 、 are the minimum and maximum values ​​of the internal density constraints, is the constrained interior density of the asteroid, is the straight-line distance from the asteroid surface to the observation point, is the measured spherical harmonic coefficient vector, Predict the spherical harmonic coefficient vector for the network.

[0026] According to a method for inverting the asteroid gravity field and internal structure based on machine learning provided by the present invention, the planetary deep neural gravity field model is trained using the training set to obtain an initially trained planetary deep neural gravity field model, including:

[0027] Ignoring the spherical harmonic coefficient constraints, constraining the interior density to the average density, we obtain a pre-trained model representing the gravity field of a homogeneous asteroid.

[0028] Spherical harmonic coefficient constraints and normal density change constraints are added to the pre-trained model, and the internal density range constraint is adjusted to ~ ;

[0029] When the loss function When the minimum is reached, the training ends and the initially trained planetary deep neural gravity field model is obtained.

[0030] In a second aspect, the present invention further provides a system for inverting the gravity field and internal structure of an asteroid based on machine learning, comprising:

[0031] an acquisition module, configured to acquire a measured gravity field dataset and a terrain dataset of a sample planet, and preprocess the measured gravity field dataset and the terrain dataset to obtain a training set and a test set;

[0032] A construction module for constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics, and the planetary internal structure characteristics;

[0033] A training module, configured to train the planetary deep neural gravity field model using the training set to obtain an initially trained planetary deep neural gravity field model;

[0034] an inversion module, configured to invert the test set using the initially trained planetary deep neural gravity field model to obtain a trained planetary deep neural gravity field model;

[0035] The output module is used to input the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and output the inversion results of the planetary gravity field and internal structure.

[0036] In a third aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the above-described methods for inverting the gravity field and internal structure of an asteroid based on machine learning.

[0037] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for inverting the gravity field and internal structure of an asteroid based on machine learning.

[0038] The method provided by the present invention for inverting the asteroid gravity field and internal structure based on machine learning performs gravity inversion by using a planetary deep neural gravity field model based on deep learning. Compared with traditional methods, it can perform various forms of prior density constraints through loss functions, thereby reducing the search space for gravity inversion optimization and improving the stability and accuracy of gravity inversion. The planetary deep neural gravity field model can integrate multi-source gravity observation data processing and can simultaneously encode the asteroid's gravity field model, internal structure model and three-dimensional shape model. The present invention will enhance the scientific value and practical significance of planetary exploration and provide useful theoretical support and practical guidance for deep space exploration. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0040] Figure 1 1. It is a flow chart of the method for inverting the gravity field and internal structure of an asteroid based on machine learning provided by the present invention;

[0041] Figure 2 This is a flowchart of the asteroid deep neural gravity field model training provided by the present invention;

[0042] Figure 3 This is the flow chart of the gravity field solution of the Bennu asteroid provided by the present invention;

[0043] Figure 4 Schematic diagram of the system for inverting the gravity field and internal structure of an asteroid based on machine learning provided by the present invention;

[0044] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] In response to the shortcomings of the existing technology, the present invention provides a method for inverting the gravity field and internal structure of an asteroid based on machine learning. It can perform various forms of prior density constraints through loss functions, thereby reducing the search space of gravity inversion optimization and improving the stability and accuracy of gravity inversion.

[0047] Figure 1 : is a flow chart of a method for inverting the gravity field and internal structure of an asteroid based on machine learning provided by an embodiment of the present invention, such as Figure 1 Shown, including:

[0048] Step 100: Obtain a measured gravity field dataset and a terrain dataset of a sample planet, and preprocess the measured gravity field dataset and the terrain dataset to obtain a training set and a test set;

[0049] Step 200: Constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics, and the planetary internal structure characteristics;

[0050] Step 300: Using the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model;

[0051] Step 400: Invert the test set using the initially trained planetary deep neural gravity field model to obtain a trained planetary deep neural gravity field model;

[0052] Step 500: Input the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and output the inversion results of the planetary gravity field and internal structure.

[0053] Specifically, an embodiment of the present invention first prepares the planet's measured gravity field data and terrain data set for training and testing, and constructs a planetary deep neural gravity field model. The planetary deep neural gravity field model uses a deep neural network to express the gravity field acceleration as a function of position. Solutions exist outside the asteroid, on the asteroid surface, and inside the asteroid, and are differentiable for any order. The planetary deep neural gravity field network is trained using the training set data. During the network training process, the automatic differentiation characteristics of the neural network are utilized to construct a loss function through external gravity observations, asteroid shape models, physical equations, prior internal density assumptions, and other information to jointly constrain the planetary deep neural gravity field neural network. Finally, the trained network model is used to invert the planetary gravity field on the test set data.

[0054] It is understandable that when training a planetary deep neural gravity field network model based on machine learning, one is actually inferring the internal density distribution of an asteroid based on external observation information. This process is also called gravity inversion. Using a planetary deep neural gravity field model based on deep learning for gravity inversion can perform various forms of prior density constraints through loss functions, thereby reducing the search space for gravity inversion optimization and improving the stability and accuracy of gravity inversion. The planetary deep neural gravity field model can integrate multi-source gravity observation data processing, and can simultaneously encode the asteroid's gravity field model, internal structure model, and three-dimensional shape model. This invention will enhance the scientific value and practical significance of planetary exploration, and provide beneficial theoretical support and practical guidance for deep space exploration.

[0055] Based on the above embodiment, step 100 includes preparing measured gravity field data and terrain data sets of the planet for training and testing.

[0056] The planet's measured gravity field and topographic data are formatted as PyTorch tensors for training purposes. Dimensionless processing is also performed to eliminate the units of the original physical quantities, simplifying the problem and making it easier to compare and analyze.

[0057] Step 200 includes constructing a deep neural gravity field model of the planet.

[0058] The planetary deep neural gravity field model uses a deep neural network to express the gravity field acceleration as a function of position. Solutions exist outside the asteroid, on the asteroid surface, and inside the asteroid, and are differentiable for any order. During the network training process, the automatic differentiation characteristics of the neural network are used to construct a loss function based on external gravity observations, asteroid shape models, physical equations, prior internal density assumptions, and other information to jointly constrain the neural network of the planetary deep neural gravity field model. The training process is as follows: Figure 2 shown.

[0059] Step 300 includes training a planetary deep neural gravity field network using the training set data.

[0060] First, a homogeneous spherical asteroid was considered to evaluate the model performance; secondly, an irregularly shaped double-layer heterogeneous asteroid was constructed to further analyze the model's ability to deduce the internal structure; finally, the measured gravity data of the asteroid were processed.

[0061] To select the coefficient cutoff order, the signal-to-noise ratio of the measured spherical harmonic gravity field coefficients must first be analyzed. Specifically, the ratio of the measured gravity coefficients to the coefficient uncertainties must be calculated. Furthermore, the terrain model is expanded into spherical harmonic coefficients according to the homogeneous density hypothesis, and the difference between these coefficients and the measured coefficients is calculated. This difference is then multiplied by the measured coefficient uncertainties to obtain the signal-to-noise ratio of the coefficients carrying heterogeneous information. Finally, analysis of the differences in the spherical harmonic coefficients between the homogeneous terrain model and the measured gravity field reveals that, considering computational cost, a 4th-order measured gravity field was selected to train the planetary deep neural gravity field model and invert the internal structure of the asteroid. Furthermore, the constraint of zero spherical harmonic coefficients was also considered in the training of the planetary deep neural gravity field model, with their respective uncertainties set to the corresponding spherical harmonic coefficient values ​​after the homogeneous shape model expansion.

[0062] (1)

[0063] (2)

[0064] (3)

[0065] (4)

[0066] (5)

[0067] Where: 、 、 、 is the weight of each constraint item. During training, the importance of each constraint item can be adjusted by adjusting the weight. is the external observation constraint, Constrained by the laws of physics, is the loss function of range density constraint, is the spherical harmonic coefficient constraint, is the expression of the fully connected network, is the number of spherical harmonic coefficients, 、 are the minimum and maximum values ​​of the internal density constraints, is the constrained interior density of the asteroid, is the straight-line distance from the asteroid surface to the observation point, is the measured spherical harmonic coefficient vector, Predict the spherical harmonic coefficient vector for the network. The loss function is in the outer space of the asteroid 、 Interior space and global space U Sampling is calculated.

[0068] For the planetary deep neural gravity field model of the asteroid, the global physical law constraint of formula (2), the density range constraint of formula (3), the spherical harmonic coefficient constraint of formula (4), and the normal density change constraint of formula (5) are considered for model training. The coarse-to-fine method is adopted during training. First, the spherical harmonic coefficient constraint is not considered, and the internal density is constrained to the average density. Then, a pre-trained model representing the gravity field of the homogeneous asteroid is obtained. Then, the spherical harmonic coefficient constraint and the normal density change constraint are added to the pre-trained model, and the internal density range constraint is adjusted to ~ , allowing it to produce heterogeneous internal density distribution, and the final planetary deep neural gravity field model can be obtained after training is completed.

[0069] It should be noted that there is no gravitational observational information within the asteroid's interior, so it is impossible to directly constrain the acceleration output by the network. However, based on the fact that the asteroid's gravitational potential satisfies the Poisson equation, an expression for the corresponding acceleration field can be derived. This leads to the conclusion that the divergence of the asteroid's internal acceleration field is directly related to the internal density. Therefore, some a priori assumptions can be made about the network's inferred internal density. Based on the expression for the gravitational potential in the polyhedron model and the orthogonal relationship between the spherical harmonic coefficients, predicted values ​​of the gravity field coefficients can be obtained by volume integration of the network's output density. Finally, by comparing the predicted spherical harmonic coefficients with the measured coefficients and considering the covariance matrix of the measured coefficients, a loss function for constraining the spherical harmonic coefficients is derived. In addition to the measured spherical harmonic coefficients, constraints can be set based on prior knowledge of the asteroid and the physical meaning of each coefficient, along with their uncertainties. Other constraints can also be set based on the different characteristics of the target to better train the network.

[0070] During the training process of the planetary deep neural gravity field network, the appropriate spherical harmonic coefficient truncation order is selected to generate the gravity field model. The training adopts a coarse-to-fine approach. When the overall loss function L reaches the minimum, the training ends and the final planetary deep neural gravity field network model is obtained.

[0071] Finally, the trained network model is used to invert the planetary gravity field on the test set data.

[0072] by Figure 3 The solution of the gravity field of the Bennu asteroid shown in the figure is used as an example to illustrate. First, dynamic modeling is performed. The prior parameters are input to obtain the motion equation and variational equation. The motion equation and variational equation are numerically integrated and converted into state vector, state transfer matrix and sensitivity matrix. Further metrology modeling is performed, and the measured observation values ​​are input to obtain the observation residuals and observation partial derivatives. Then the error equation is established and the least squares method is used to solve the parameter correction value. If the value meets the convergence condition, the least squares method is used to obtain the corrected parameters and parameter covariance. Otherwise, the iterative solution is performed again and the dynamic modeling is performed again.

[0073] The following describes the system for inverting the asteroid gravity field and internal structure based on machine learning provided by the present invention. The system for inverting the asteroid gravity field and internal structure based on machine learning described below and the method for inverting the asteroid gravity field and internal structure based on machine learning described above can be referenced to each other.

[0074] Figure 4 is a schematic diagram of the structure of a system for inverting the gravity field and internal structure of an asteroid based on machine learning provided by an embodiment of the present invention, such as Figure 4 As shown, it includes: an acquisition module 41, a construction module 42, a training module 43, an inversion module 44 and an output module 45, wherein:

[0075] The acquisition module 41 is used to obtain the measured gravity field dataset and terrain dataset of the sample planet, pre-process the measured gravity field dataset and the terrain dataset to obtain a training set and a test set; the construction module 42 is used to construct a planetary deep neural gravity field model, and the planetary deep neural gravity field model includes a loss function jointly constrained by the planet's external gravity field characteristics, the planet's surface shape characteristics and the planet's internal structure characteristics; the training module 43 is used to use the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model; the inversion module 44 is used to use the initially trained planetary deep neural gravity field model to invert the test set to obtain a trained planetary deep neural gravity field model; the output module 45 is used to input the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and output the inversion results of the planetary gravity field and internal structure.

[0076] Figure 5 An example of a physical structure diagram of an electronic device is shown below. Figure 5 As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute a method for inverting the asteroid gravity field and internal structure based on machine learning, which includes: obtaining a measured gravity field dataset and a terrain dataset of a sample planet, preprocessing the measured gravity field dataset and the terrain dataset to obtain a training set and a test set; constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics and the planetary internal structure characteristics; using the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model; using the initially trained planetary deep neural gravity field model to invert the test set to obtain a trained planetary deep neural gravity field model; inputting the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and outputting the inversion result of the planetary gravity field and internal structure.

[0077] Furthermore, the logic instructions in the aforementioned memory 530 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 portion that contributes to the prior art, or a portion 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 for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0078] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for inverting the asteroid gravity field and internal structure based on machine learning provided by the above-mentioned methods, the method comprising: obtaining a measured gravity field dataset and a terrain dataset of a sample planet, preprocessing the measured gravity field dataset and the terrain dataset to obtain a training set and a test set; constructing a planetary deep neural gravity field model, the planetary deep neural gravity field model comprising a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics and the planetary internal structure characteristics; using the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model; using the initially trained planetary deep neural gravity field model to invert the test set to obtain a trained planetary deep neural gravity field model; inputting the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and outputting the inversion result of the planetary gravity field and internal structure. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0079] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for inverting the gravity field and internal structure of an asteroid based on machine learning, characterized in that: include: Obtaining a measured gravity field dataset and a terrain dataset of a sample planet, and preprocessing the measured gravity field dataset and the terrain dataset to obtain a training set and a test set; Constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics, and the planetary internal structure characteristics; Using the training set to train the planetary deep neural gravity field model to obtain an initially trained planetary deep neural gravity field model; Inverting the test set using the initially trained planetary deep neural gravity field model to obtain a trained planetary deep neural gravity field model; The measured gravity field data and topographic data of the planet to be measured are input into the trained planetary deep neural gravity field model, and the inversion results of the planetary gravity field and internal structure are output.

2. The method for inverting the asteroid gravity field and internal structure based on machine learning according to claim 1, characterized in that: Preprocessing the measured gravity field dataset and the terrain dataset to obtain a training set and a test set includes: Formatting the measured gravity field dataset and the terrain dataset into PyTorch tensors and performing dimensionless processing; The processed data is divided into the training set and the test set according to a preset division ratio.

3. The method for inverting the asteroid gravity field and internal structure based on machine learning according to claim 1, characterized in that: Construct a deep neural gravity field model of the planet, including: A deep neural network is used to obtain a function that relates gravitational acceleration to position. This function has solutions outside the planet, on the planet's surface, and inside the planet and is differentiable for any order. Determining the external gravity field characteristics of the planet, the surface shape characteristics of the planet, and the internal structure characteristics of the planet using the automatic differentiation characteristics of the deep neural network; The loss function is constructed, which is jointly constrained by the planet's external gravity field characteristics, the planet's surface shape characteristics, and the planet's internal structure characteristics.

4. The method for inverting the asteroid gravity field and internal structure based on machine learning according to claim 1, characterized in that: The loss function includes: Determine that the planetary deep neural gravity field model is a fully connected network based on a sinusoidal activation function, and the loss function for: in, 、 、 、 is the weight of each constraint, is the external observation constraint, is the loss function constrained by physical laws, is the range density constraint loss function, is the spherical harmonic coefficient constraint loss function, is the expression of the fully connected network, is the number of spherical harmonic coefficients, 、 are the minimum and maximum values ​​of the internal density constraints, is the constrained interior density of the asteroid, is the straight-line distance from the asteroid surface to the observation point, is the measured spherical harmonic coefficient vector, Predict the spherical harmonic coefficient vector for the network.

5. The method for inverting the asteroid gravity field and internal structure based on machine learning according to claim 4, characterized in that: The planetary deep neural gravity field model is trained using the training set to obtain an initially trained planetary deep neural gravity field model, including: Ignoring the spherical harmonic coefficient constraints, the interior density is constrained to the average density, resulting in a pre-trained model representing the gravity field of a homogeneous asteroid. Spherical harmonic coefficient constraints and normal density change constraints are added to the pre-trained model, and the internal density range constraint is adjusted to ~ ; When the loss function When the minimum is reached, the training ends and the initially trained planetary deep neural gravity field model is obtained.

6. A system for inverting the gravity field and internal structure of an asteroid based on machine learning, characterized in that: include: an acquisition module, configured to acquire a measured gravity field dataset and a terrain dataset of a sample planet, and preprocess the measured gravity field dataset and the terrain dataset to obtain a training set and a test set; A construction module for constructing a planetary deep neural gravity field model, wherein the planetary deep neural gravity field model includes a loss function jointly constrained by the planetary external gravity field characteristics, the planetary surface shape characteristics, and the planetary internal structure characteristics; A training module, configured to train the planetary deep neural gravity field model using the training set to obtain an initially trained planetary deep neural gravity field model; an inversion module, configured to invert the test set using the initially trained planetary deep neural gravity field model to obtain a trained planetary deep neural gravity field model; The output module is used to input the measured gravity field data and terrain data of the planet to be measured into the trained planetary deep neural gravity field model, and output the inversion results of the planetary gravity field and internal structure.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for inverting the gravity field and internal structure of an asteroid based on machine learning as described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for inverting the gravity field and internal structure of an asteroid based on machine learning as described in any one of claims 1 to 5 is implemented.

Images