Deep Learning-Based Astronomical Data Fusion and Analysis Method

Abstract

The present invention relates to the field of data processing, and in particular, to a method and system for astronomical data fusion analysis based on deep learning. The method comprises: acquiring multi-source astronomical data; the multi-source astronomical data all target the same observation object or the same observation area; inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to each of the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods; and using the analysis mode, performing multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data. This method can dynamically fuse relevant information from different data sources to achieve deep fusion analysis of multi-source astronomical data, thereby providing more accurate and comprehensive astronomical fusion data for astronomical research.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for astronomical data fusion analysis based on deep learning. Background Art

[0002] There are many types of astronomical data. For example, images and spectral data in the visible light band acquired by optical telescopes are used to observe celestial bodies such as galaxies, stars, and planets. Data in the ultraviolet band, typically acquired by specialized ultraviolet telescopes, aid in the study of high-temperature objects and the interstellar medium. Data acquired by radio telescopes is used to study celestial bodies and phenomena in the radio wave band, such as pulsars, radio galaxies, and interstellar gas. By splitting the light emitted by celestial bodies, spectral information of celestial bodies is obtained. This data can be used to analyze the composition, motion, temperature, and other aspects of celestial bodies. In addition, data from space exploration missions, such as planetary probes and solar probes, provide detailed information about planets, the Sun, and more.

[0003] Fusion of multiple astronomical data faces numerous challenges in related technologies. However, the differences in the physical properties of these data sets are a major obstacle. Data from different wavelengths, such as visible light, infrared, and radio, reflect the radiation characteristics of celestial objects within their respective spectral ranges. For example, optical data reveals the visible light emission and morphology of celestial objects, infrared data can penetrate interstellar dust to detect hidden objects, and radio data is used to study low-energy celestial bodies. How to effectively combine the physical information from these different wavelengths is a key issue that needs to be addressed in the fusion process.

[0004] In summary, it is urgent to propose a new technical solution to solve at least one of the above technical problems. Summary of the Invention

[0005] In response to the technical problems existing in the prior art, the present invention provides an astronomical data fusion analysis method and system based on deep learning, which is used to realize the automated fusion processing of multi-source astronomical data and provide a data basis for subsequent multi-source astronomical data processing.

[0006] In a first aspect, embodiments of the present application provide a method and system for astronomical data fusion analysis based on deep learning, the method comprising:

[0007] Acquiring multi-source astronomical data; wherein the multi-source astronomical data are all directed to the same observation object or the same observation area;

[0008] Inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods;

[0009] The analysis mode is adopted to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0010] In a second aspect, an embodiment of the present application provides an astronomical data fusion analysis system based on deep learning, the system comprising the following units, wherein:

[0011] A collection unit is configured to acquire multi-source astronomical data; the multi-source astronomical data are all for the same observation object or the same observation area;

[0012] an analysis unit configured to input the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods;

[0013] The fusion unit is configured to adopt the analysis mode to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising:

[0015] at least one processor, memory, and input-output unit;

[0016] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the deep learning-based astronomical data fusion analysis method of the first aspect.

[0017] In a fourth aspect, a computer-readable storage medium is provided, comprising instructions, which, when executed on a computer, enable the computer to execute the deep learning-based astronomical data fusion analysis method of the first aspect.

[0018] The present invention provides a method and system for astronomical data fusion analysis based on deep learning. This technical solution involves acquiring multi-source astronomical data, all of which are targeted at the same observation object or observation area. The multi-source astronomical data are then input into an adaptive exploration space model to obtain analysis modes corresponding to each of the multi-source astronomical data. The adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods. Using these analysis modes, the multi-source astronomical data is subjected to multi-branch fusion processing to obtain astronomical fusion data corresponding to the multi-source astronomical data. This method effectively addresses the issue of differences in the physical properties of astronomical data from different bands through an adaptive exploration space model, a multi-branch processing network, and a real-time fusion mechanism. While maintaining the unique characteristics of each band of data, it can dynamically fuse relevant information from different data sources to achieve deep fusion analysis of multi-source astronomical data, thereby providing more accurate and comprehensive astronomical fusion data for astronomical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flowchart of a deep learning-based astronomical data fusion analysis method and system according to an embodiment of the present application;

[0020] Figure 2 This is a schematic diagram of the structure of an astronomical data fusion analysis system based on deep learning according to an embodiment of the present application;

[0021] Figure 3 This is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0022] Figure 4 It is a structural diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0024] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of this application, "plurality" means two or more, unless otherwise specifically specified.

[0025] In the description of this application, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0026] There are many types of astronomical data. For example, images and spectral data in the visible light band acquired by optical telescopes are used to observe celestial bodies such as galaxies, stars, and planets. Data in the ultraviolet band, typically acquired by specialized ultraviolet telescopes, aid in the study of high-temperature objects and the interstellar medium. Data acquired by radio telescopes is used to study celestial bodies and phenomena in the radio wave band, such as pulsars, radio galaxies, and interstellar gas. By splitting the light emitted by celestial bodies, spectral information of celestial bodies is obtained. This data can be used to analyze the composition, motion, temperature, and other aspects of celestial bodies. In addition, data from space exploration missions, such as planetary probes and solar probes, provide detailed information about planets, the Sun, and more.

[0027] Fusion of multiple astronomical data faces numerous challenges in related technologies. However, the differences in the physical properties of these data sets are a major obstacle. Data from different wavelengths, such as visible light, infrared, and radio, reflect the radiation characteristics of celestial objects within their respective spectral ranges. For example, optical data reveals the visible light emission and morphology of celestial objects, infrared data can penetrate interstellar dust to detect hidden objects, and radio data is used to study low-energy celestial bodies. How to effectively combine the physical information from these different wavelengths is a key issue that needs to be addressed in the fusion process.

[0028] It is urgent to propose a new technical solution to solve at least one of the above technical problems.

[0029] This embodiment of the present application provides a deep learning-based astronomical data fusion analysis method and system. This technical solution involves acquiring multi-source astronomical data, each of which targets the same observation object or observation area. The multi-source astronomical data is then input into an adaptive exploration space model to obtain analysis modes corresponding to each of the multi-source astronomical data. The adaptive exploration space model is configured with configurable analysis mode parameters and analysis methods. Using these analysis modes, the multi-branch fusion processing is performed on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0030] From a technical point of view, in an embodiment of the present application, the method adopts an adaptive exploration space model, in which configurable analysis mode parameters and analysis methods are set. This model can dynamically adjust the processing method of each data source, and apply special feature extraction and processing strategies to data in different bands (such as visible light, infrared, and radio). For example, for optical data, specific edge detection or morphological analysis methods can be applied to highlight the celestial structure in visible light. For infrared data, a feature extraction network that can penetrate dust is used to focus on the radiation distribution and hidden features of celestial bodies. For radio data, long wavelength characteristics are used to focus on analyzing the physical properties of low-energy objects. This adaptive exploration model can select the optimal analysis method and parameters according to the characteristics of the input data to ensure the correct understanding and processing of information in different bands.

[0031] In an embodiment of the present application, through the design of a multi-branch network, an independent processing branch is established for each band of data (such as visible light, infrared, and radio). Each branch is equipped with a corresponding neural network structure, which is specifically used for the extraction and representation of the modal features. In this way, the data of each band can maximize its specific information. For example, the optical branch focuses on morphology, brightness, and surface structure features. The infrared branch extracts deeply embedded thermal radiation information, which can penetrate dust and detect obscured celestial bodies. The radio branch focuses on studying weak signals from low-energy celestial bodies and celestial bodies at greater distances. The multi-branch structure ensures that astronomical data with different physical properties can be effectively processed and represented separately, while also avoiding the problem of losing key information in the direct fusion process.

[0032] In an embodiment of the present application, the method adopts a real-time fusion module of the data stream to fuse data from different bands in real time by dynamically adjusting the weight and contribution of each branch. In particular, through an adaptive weight mechanism, the fusion method can be flexibly adjusted according to the needs of different scenarios (such as the need to highlight infrared information to detect hidden celestial bodies or emphasize radio data to analyze low-energy celestial bodies). This real-time fusion mechanism can balance the contribution of information from different bands according to the characteristics of the actual observation target (such as galaxies, nebulae, etc.), ensuring that the final fusion result not only retains the key information of each band, but also effectively combines the correlations between different bands.

[0033] Furthermore, during the fusion process, this method uses a neural network's joint feature learning mechanism to construct a unified high-dimensional feature space, aligning and aggregating information from different modalities. Combined with deep learning's self-attention mechanism (such as the Transformer architecture), it can exploit the complex correlations between multi-source data and uncover potential interactions and interdependencies. For example, in analyzing galactic cores, optical and infrared data may reveal complementary information. Joint processing can more accurately interpret the physical state and evolution of celestial bodies. Adaptive weighting and data processing mechanisms dynamically adjust the influence of data from different bands in the fusion process. For example, when data quality in a particular band is poor (such as noise interference in radio data), the fusion mechanism reduces its weight and relies more on information from other bands. This mechanism effectively improves the robustness of data fusion and ensures the stability of the fusion results.

[0034] In summary, the embodiments of this application effectively address the issue of differences in the physical properties of astronomical data from different bands through an adaptive exploration space model, a multi-branch processing network, and a real-time fusion mechanism. While maintaining the unique characteristics of each band's data, they can dynamically fuse relevant information from different data sources, enabling deep fusion analysis of multi-source astronomical data, thereby providing more accurate and comprehensive astronomical fusion data for astronomical research.

[0035] The astronomical data fusion analysis solution based on deep learning provided in the embodiments of the present application can also be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a dedicated device (such as a dedicated terminal device with an astronomical data fusion analysis system based on deep learning). These electronic devices can also be equipped with the chips introduced in the above embodiments. Alternatively, these electronic devices can also be installed with a service program for executing the astronomical data fusion analysis solution based on deep learning.

[0036] Figure 1 A flowchart of a deep learning-based astronomical data fusion analysis method and system is provided in the embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0037] 101, obtain multi-source astronomical data;

[0038] 102. Input the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data.

[0039] 103 , using the analysis mode to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0040] In the embodiments of this application, the multi-source astronomical data are all for the same observation object or the same observation area. In the embodiments of this application, the multi-source astronomical data are all for the same observation object or the same observation area. Specifically, in astronomical observation, different observation equipment and different bands (such as visible light, infrared, radio, etc.) are used to observe the same celestial body or the same sky area. This approach ensures that multimodal data obtained from different angles reflects the multiple physical properties of the same celestial body or area.

[0041] Consistency of the observed object means that data acquired through different observational methods all target the same celestial body. This consistency can improve the accuracy of data fusion, because all data sources target the same celestial body. Although they may come from different wavelengths, they all reflect the different physical properties of that celestial body. For example, in stellar observations, visible light data can reveal the brightness and surface activity of stars, while infrared data can detect the cooling process of the star's outer layers, and radio data may reveal changes in the magnetic field near the star. For galaxy observations, visible light observations can reveal the morphological structure of the galaxy, infrared data can penetrate dust clouds and display the star-forming regions within the galaxy, and radio data can provide information on the activity of the galaxy's core. By processing multi-source data on the same observed object, more complete celestial information can be obtained, avoiding the misalignment and errors that may occur when fusion of data from different observed objects.

[0042] Consistency of the observation area means that all data come from the same observation area (i.e., the sky region), and observation data in different bands cover the same astronomical area. This is very important for studying large-scale structures or extended celestial bodies (such as nebulae, star clusters, galaxy clusters, etc.). For nebula observations, visible light data shows the emission spectrum of the nebula, infrared data can penetrate interstellar dust and detect more obscured areas, and radio data can reveal the distribution of low-temperature gas in the nebula. For galaxy cluster observations, galaxy clusters are composed of multiple galaxies, and observations in different bands can respectively reveal the characteristics of different galaxies in the cluster and the distribution of gas and dark matter within the cluster. In this case, data from all bands reflect different physical processes and properties in the same region, ensuring that comprehensive and three-dimensional information about the region can be obtained when the data is fused.

[0043] When multi-source data acquired for the same observational object or region are fused, data from each wavelength provides different levels of information about that object or region, enabling a more comprehensive understanding of astronomical phenomena. Data from different wavelengths can complement each other, helping to address potential blind spots in a single wavelength. For example, infrared data can reveal objects obscured by dust, whereas visible light cannot. By fusing multimodal data from the same object or region, a multi-dimensional, integrated analysis of the object's diverse physical properties can be achieved, yielding a richer physical description. For example, when studying galaxies, optical data can provide information about their morphology, while radio data can provide insights into their activity. Because observational data from different wavelengths often exhibit varying levels of noise and error, fusing these data can improve overall observational accuracy. For example, certain wavelengths may be more stable at high or low energies, and fusing data from different wavelengths can reduce observational errors.

[0044] In astronomical evolution research, different wavelengths of data reflect the activity of celestial bodies at different stages. For example, the formation of early stars may be revealed through infrared and radio data, while the maturation of stars may be primarily recorded through visible light observations.

[0045] In the large-scale structure of the universe, when observing galaxy clusters or the large-scale structure of the universe, multimodal observations can reveal the distribution of matter at different scales, such as the distribution of galaxies, gas, and dark matter, forming a comprehensive understanding of the structure of the universe.

[0046] The multi-source astronomical data described in the embodiments of this application all target the same observation object or region. By utilizing multimodal data acquired from different wavelengths, fusing this data can overcome the limitations of single-wavelength observations and provide more comprehensive astronomical information. This fusion method can effectively improve the accuracy, depth, and breadth of astronomical data analysis, enabling astronomers to better understand the physical properties and evolution of celestial objects or regions.

[0047] 101. Acquire multi-source astronomical data. In an embodiment of the present application, step 101 is intended to acquire multiple types of astronomical data from different observation devices, bands, or platforms, where these data originate from the same observation object or region. Multi-source astronomical data includes data from different bands, such as visible light, infrared, radio, ultraviolet, and X-rays. Each type of data reflects the different physical properties of celestial bodies, such as brightness, morphology, and energy state. This data is collected using different ground-based or space-based telescopes, processed, calibrated, and stored in a database. Acquiring multi-source data facilitates a comprehensive understanding of celestial body properties, improves observation accuracy, and supports the study of complex astronomical phenomena.

[0048] Each type of astronomical data reflects the physical properties of celestial objects in different wavelengths. For example, infrared data can reveal stars hidden within dust clouds, while visible light data can reveal the surface brightness of stars. Data from different wavelengths also differ in spatial and temporal resolution. For example, ground-based telescopes have lower spatial resolution due to atmospheric influences, while space telescopes have higher resolution. Observations in different wavelengths are affected by different noise levels. For example, radio data is susceptible to ground-based radio interference, while infrared data is susceptible to thermal noise. Therefore, the acquisition of multi-source data also requires consideration of noise processing and data quality optimization.

[0049] By acquiring data in different wavelengths, the physical state of celestial bodies can be revealed from multiple dimensions. For example, visible light and infrared data can simultaneously reveal the surface and internal state of a star. The complementarity of multi-source data helps improve the accuracy of observational results. For example, observations of the same star in the infrared and radio bands can verify each other, thereby improving the reliability of the data. Many astronomical phenomena (such as supernova explosions and galaxy formation) involve multiple physical processes. Acquiring multi-source data helps to study these complex astronomical phenomena more comprehensively.

[0050] In the embodiments of the present application, the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods. This setting is intended to provide flexible and efficient analysis capabilities based on different exploration needs and data backgrounds. This configuration mechanism can adjust and optimize the model's behavior according to different application scenarios and observation targets, ensuring high-precision and efficient analysis under complex data sets.

[0051] Analysis mode parameters refer to the core parameters used by the adaptive exploration space model under different operating conditions. These parameters determine how the model processes input data and performs exploration and analysis. These parameters can be configured according to different needs and mainly include:

[0052] Spatial resolution determines the spatial accuracy used by the model during exploration. Different astronomical phenomena have different requirements for resolution. Larger resolutions are suitable for large-scale astronomical structures (such as galaxy clusters), while smaller resolutions are suitable for high-precision observations (such as observations of individual stars).

[0053] Time resolution: When performing time series analysis on dynamically changing astronomical phenomena (such as supernova explosions or stellar activities), different time interval parameters need to be configured in order to capture the changing process of celestial bodies.

[0054] Band selection: Depending on the specific astronomical research object, different electromagnetic bands (such as infrared, radio, X-ray, etc.) are selected for analysis. This parameter can be configured to use only a single band or to fuse multiple bands.

[0055] Noise filtering parameters are used to configure the degree of noise treatment during data preprocessing. Different observation devices or bands may encounter different noise sources, which requires flexible setting of noise filtering intensity to improve data quality.

[0056] Analysis methods refer to the specific methods used by the adaptive exploration space model to process and analyze multi-source astronomical data. Different analysis methods can be optimized for specific research objectives or data types. Exemplary methods include:

[0057] Statistical analysis: Quantitative analysis of the overall characteristics of the observational data, such as calculating statistical quantities like mean, variance, and standard deviation. This method is suitable for preliminary analysis of large-scale survey data or for studying the properties of celestial populations.

[0058] Frequency domain analysis: By performing Fourier transform or wavelet transform on astronomical signals, the periodic variation characteristics in the signals are extracted. It is suitable for studying periodic celestial bodies such as pulsars.

[0059] Time domain analysis: Analyzes the temporal variations of celestial bodies’ brightness, position, and other characteristics. It is mainly used for astronomical phenomena with obvious temporal variations, such as variable stars and supernova explosions.

[0060] Multimodal data fusion analysis: This combines astronomical data from different wavelengths for comprehensive analysis of complex celestial systems. For example, combining infrared, visible, and radio data to analyze the multi-layered structure of galaxies.

[0061] Machine learning analysis: Introducing machine learning algorithms (such as classification, regression, or clustering algorithms) to perform pattern recognition or predictive analysis on astronomical data. This approach is suitable for discovering potential astronomical patterns or performing automated data classification in large datasets.

[0062] The Adaptive Exploration Space Model dynamically adjusts these parameters and analysis methods based on data input and analysis requirements. By continuously optimizing its configuration, the model adapts to different data sources and analysis tasks, ensuring improved computational efficiency while maintaining accuracy. For example, when input data is noisy, the model automatically increases noise filtering intensity; when observing rapidly changing celestial bodies, the model automatically switches to time-domain analysis mode to capture transient changes.

[0063] When studying the evolution of stars or galaxies, multimodal data fusion and time-domain analysis can be used to compare data from different periods, yielding detailed trajectories of celestial evolution. Multi-band data (such as visible light, infrared, and radio) from the same observational object can be fused to obtain the multidimensional physical properties of the object or region. Machine learning models can be used to automatically classify celestial objects such as galaxies, quasars, and pulsars from large amounts of sky survey data.

[0064] In the embodiments of this application, the adaptive exploration space model can be flexibly adjusted to different observation requirements and data types by setting configurable analysis mode parameters and analysis methods. Through this adaptive mechanism, the model can dynamically optimize the analysis process, improve the efficiency and accuracy of data processing, and thus better meet the needs of astronomy for analyzing multi-source data.

[0065] As an optional embodiment, in step 102, inputting the multi-source astronomical data into the adaptive exploration space model to obtain the analysis modes corresponding to the multi-source astronomical data can be implemented as follows:

[0066] A multimodal feature extraction layer is used to extract multimodal astronomical features from the multi-source astronomical data; the multimodal astronomical features include at least one of the following: an observed space feature, an observed calorific value change feature, and a radio time series feature;

[0067] Using a projection layer, the multi-source astronomical data are projected into an adaptive exploration space respectively; the adaptive exploration space is constructed by a pre-configured astronomical space model;

[0068] Using a routing module, the multimodal astronomical features are transmitted to corresponding analysis units;

[0069] Using an analysis layer, learning from the multimodal astronomical features corresponding to each analysis unit to obtain modal attribute features corresponding to each of the multimodal astronomical features;

[0070] A configuration layer is used to match the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute characteristics; and configurable analysis mode parameters and analysis methods are set in the analysis unit.

[0071] In this optional embodiment 102, the analysis process for multi-source astronomical data is implemented through an adaptive exploration space model, and the specific steps include multimodal feature extraction, projection, routing, analysis and configuration. The following example illustrates this process:

[0072] Suppose we analyze a galaxy. We have acquired multi-source astronomical data, including visible light, infrared, and radio data, using various astronomical instruments and wavelengths. This data is fed into the adaptive exploration space model, which then performs the following steps:

[0073] The multimodal feature extraction layer extracts multimodal features from multi-source astronomical data:

[0074] Observational spatial characteristics: Visible light data provides spatial information such as the morphology and brightness distribution of galaxies, such as the size and structure of galaxies (such as spiral arms and core regions).

[0075] Observation of calorific value variation characteristics: Infrared data reveals temperature variations in dust clouds and star-forming regions in galaxies, reflecting the thermal state of the galaxies.

[0076] Radio timing characteristics: Radio data provide characteristics of physical activity in galaxies by observing activities in the center of galaxies, such as changes in radio jets or pulsars.

[0077] The projection layer then projects these multi-source data into an adaptive exploration space constructed using a preconfigured astronomical space model. This model presents the data in a higher-dimensional representation, fusing data from different wavelengths to provide a deeper understanding of the overall properties of galaxies. For example, visible light data is projected into the morphological space of galaxies; infrared data is projected into the thermodynamic space of temperature variations; and radio data is projected into the temporal dynamics of radio activity.

[0078] The routing module then transmits these different modal features (such as galaxy morphology, thermal distribution, and radio activity characteristics) to different analysis units. For example, morphological features are transmitted to a unit dedicated to analyzing galaxy structure, thermal variation features are transmitted to a unit analyzing the interstellar medium and star formation, and radio features are transmitted to a unit analyzing high-energy astrophysical phenomena.

[0079] Each analysis unit then performs corresponding analysis based on the received features. The Galaxy Morphology Unit learns structural features from visible light data, analyzing the galaxy's spiral arms, the brightness distribution of the core, and other aspects. The Star Formation and Thermal State Analysis Unit learns the temperature characteristics of star-forming regions from infrared data and analyzes the activity levels of these regions. The Radio Analysis Unit learns temporal variations in radio data and analyzes whether the radio activity at the galaxy's center is related to a black hole.

[0080] The configuration layer matches the most appropriate analysis mode based on the various modal properties learned from the analysis unit (such as galaxy morphology, star formation activity, and frequency of radio activity). For example, if the galaxy morphology shows a tight spiral structure and the infrared data show significant star formation activity, the analysis mode will focus more on the study of star formation and evolution. If strong radio jet features are detected in the radio data and they change rapidly, the configured analysis mode may focus on the analysis of black hole activity and jets.

[0081] Each analysis unit will further use different analysis methods (such as time series analysis, thermodynamic analysis, etc.) based on these matching patterns to generate the final analysis results. For example, if the galaxy is an active galactic nucleus (AGN), multimodal feature extraction can reveal the presence of radio jet activity in its center, and infrared data indicate that the dust cloud near the center of the galaxy is heating. The configuration layer will match these features to the AGN activity analysis pattern. The model will further use high-energy radio time series analysis, focusing on the intensity changes of radio jets, and thermodynamic analysis to study the relationship between temperature changes in the central region of the galaxy and black hole activity.

[0082] Through the above process, the adaptive exploration space model can flexibly and accurately process multi-source astronomical data and generate in-depth analysis results for specific astronomical phenomena.

[0083] Further optionally, in the above steps, a multimodal feature extraction layer is used to extract multimodal astronomical features from the multi-source astronomical data, which can be implemented as follows:

[0084] Identifying data modality types contained in the multi-source astronomical data;

[0085] Generate corresponding feature extraction branches based on the identified data modality type to obtain a feature extraction network; wherein the feature extraction branches include at least independent extraction branches and mixed extraction branches;

[0086] inputting the multi-source astronomical data into the feature extraction network;

[0087] In the feature extraction network, each independent extraction branch is used to extract a set of independent astronomical data features of the corresponding modality, and the mixed extraction branch is used to extract a set of mixed astronomical data features of at least two modalities;

[0088] The extracted independent astronomical data features and mixed astronomical data features are input into a cross-modal interaction layer, and interactive astronomical data features are extracted from the independent astronomical data features and the mixed astronomical data features; the cross-modal interaction layer is dynamically adjusted based on the structural branches in the feature extraction network.

[0089] In a further optional embodiment, the multimodal feature extraction layer can be implemented by constructing a network architecture based on feature extraction branches to extract features for different types of astronomical data. The following is an example of how to extract independent and mixed astronomical data features through the feature extraction network and dynamically adjust and interactively analyze them in the cross-modal interaction layer.

[0090] Suppose a star is being studied using visible light, infrared, and radio data, each of which reflects different physical properties of the star. First, identify the various modalities of the input multi-source astronomical data. For example, visible light data is used to reveal the star's brightness, color, and surface characteristics. Infrared data is used to reveal the temperature distribution within or around the star, particularly interstellar dust and star-forming regions. Radio data is used to reveal low-energy electromagnetic radiation from or around the star, particularly its magnetic field and electromagnetic activity.

[0091] Based on the identified data modality type, the system generates corresponding feature extraction branches and constructs a feature extraction network. Within this network, independent extraction branches generate independent feature extraction branches for each modality, processing the data of each modality independently to extract its unique physical characteristics. A hybrid extraction branch generates hybrid extraction branches for data from at least two modalities, extracting comprehensive cross-modal features and capturing the complementarity between the modalities.

[0092] Next, each modal data is input into its corresponding independent extraction branch. The visible light independent extraction branch extracts stellar surface brightness, color, and morphological features, such as stellar spots and luminosity variations. The infrared independent extraction branch extracts thermodynamic characteristics surrounding the star, particularly the temperature distribution of dust clouds or thermal variations in star-forming regions. The radio independent extraction branch extracts radio activity characteristics, such as temporal variations in stellar magnetic fields and pulsed radio signals. Simultaneously, the hybrid extraction branch combines multimodal data. The visible-infrared hybrid extraction branch combines the optical characteristics of the stellar surface with the thermal state of the surrounding dust clouds to extract correlations between stellar luminosity and thermal variations. The infrared-radio hybrid extraction branch combines thermal characteristics with radio signals to extract interactive features between stellar thermal and magnetic activity. The independent and hybrid astronomical data features extracted by the cross-modal interaction layer are input into the cross-modal interaction layer. This interaction layer combines information from different modalities and further extracts interactive features from these features.

[0093] Interactive astronomical data features can capture the correlation between different modal data of stars, such as whether changes in surface brightness are related to changes in the thermal value of its surroundings, or whether magnetic field activity affects the optical characteristics of the star's surface.

[0094] The cross-modal interaction layer dynamically adjusts the structure of the feature extraction network's branches. For example, the system can dynamically adjust the type of features extracted and the structure of the branches based on the quality of the input data or the research objectives. If radio data indicates strong magnetic field activity in a star, the system might increase the weight of the radio and infrared mixed branches to further analyze the impact of magnetic activity on the stellar environment. If infrared data indicates large temperature fluctuations around a star, the system will prioritize analyzing the interaction between infrared and visible light to explore the relationship between the star's brightness and its thermal state.

[0095] For example, when studying a pulsar with a strong magnetic field, the temporal characteristics of the pulse signal are extracted using a separate radio branch, while the relationship between magnetic field activity and heating of the surrounding material is analyzed using a mixed infrared and radio branch. The cross-modal interaction layer dynamically adjusts the analysis, prioritizing the correlation between the temporal variations of the pulse signal and fluctuations in the infrared heating value.

[0096] Through this flexible feature extraction and interactive analysis mechanism, the system can more comprehensively analyze multi-source astronomical data, reveal the complex relationship between different modal data of celestial objects, and provide astronomers with valuable scientific insights.

[0097] Further optionally, in the above steps, a projection layer is used to project the multi-source astronomical data into the adaptive exploration space respectively, which can be implemented as follows:

[0098] Independent astronomical data features, mixed astronomical data features, and interactive astronomical data features are projected into the adaptive exploration space according to the multimodal dimension to obtain multiple astronomical data feature points; and multiple corresponding astronomical data exploration paths are constructed by fitting the multiple astronomical data feature points.

[0099] The intersections between multiple astronomical data exploration paths correspond to interactive or mixed astronomical data features, and the independent feature points within multiple astronomical data exploration paths correspond to independent astronomical data features. In the adaptive exploration space, independent feature points of multi-source astronomical data are projected onto their respective exploration paths, such as brightness feature points on the visible light data path and temperature feature points on the infrared data path. When data from different modalities are correlated or interactive, these exploration paths will intersect in space. For example, the intersection of infrared and radio data represents the mutual influence of high-energy activity and temperature changes in galaxies. These intersections correspond to mixed or interactive astronomical data features, reflecting the complex physical connections between different modalities.

[0100] To illustrate this using the example of studying galaxy evolution, the aforementioned steps first require inputting visible light, infrared, and radio data into the adaptive exploration space. The brightness distribution characteristics of the visible light data, the temperature distribution characteristics of the infrared data, and the temporal signal characteristics of the radio data are projected into independent astronomical data feature points, forming three corresponding exploration paths. Each independent feature point on these paths reflects the individual physical properties of the galaxy in that mode, such as its brightness variation and temperature structure.

[0101] Next, the interaction features of the mixed infrared and radio data are projected onto the same exploration space, forming path intersections that represent the relationship between high-energy activity within the galaxy and ambient temperature variations. These intersections represent the interactions between these modes, revealing, for example, the connection between black hole activity and star-forming regions. Using these intersections, astronomers can gain insight into the complex physical relationships between these modes.

[0102] Further optionally, in the above steps, a routing module is used to transmit the multimodal astronomical features to the corresponding analysis unit, which can be implemented as follows: astronomical data feature points in multiple astronomical data exploration paths are input into the routing module; and each astronomical data feature point is allocated to the corresponding analysis unit through the adaptive weight and routing allocation matrix in the routing module.

[0103] Specifically, during this process, the system first inputs the characteristic points in the multimodal astronomical data exploration path into the routing module. Then, using the adaptive weights and routing assignment matrix within this module, each characteristic point is assigned to the corresponding analysis unit. The adaptive weights are used to dynamically adjust the assignment based on the importance of the data features, ensuring that key features are prioritized, while the routing assignment matrix is responsible for rationally distributing characteristic points from different modalities to specific analysis units, enabling in-depth modal analysis or cross-modal correlation research.

[0104] For example, the routing module is expressed as the following formula: In the above formula, F i is the i-th astronomical data feature point, W i is the modal feature weight corresponding to the i-th astronomical data feature point, T ij is the degree of fit between the i-th astronomical data feature point and the j-th analysis unit, α is a specific parameter used to adjust the sensitivity of the activation function. The lower the specific parameter value of α, the more balanced the adaptive distribution of the astronomical data feature points. A represents the probability that the i-th astronomical data feature point in the routing assignment matrix is assigned to the j-th analysis unit, j is the function used by the jth analysis unit to process the received i-th astronomical data feature point, β j is the importance weight of the j-th analysis unit in the output value, and O is the comprehensive output value corresponding to the j-th analysis unit.

[0105] The above formula describes how the routing module dynamically assigns multiple astronomical data feature points to different analysis units based on their modal feature weights and fitness. Using adaptive weights, specific parameters for the activation function sensitivity, and a routing assignment matrix, the formula calculates the probability of each astronomical data feature point being assigned to each analysis unit. Each analysis unit then performs specific processing on the received feature points and outputs a composite result based on their importance weights. This approach ensures that different feature points are efficiently and appropriately assigned to the most appropriate analysis units, improving the accuracy and efficiency of the overall analysis.

[0106] Further optionally, in the above steps, an analysis layer is used to learn the modal attribute features corresponding to each of the multimodal astronomical features from the multimodal astronomical features corresponding to each analysis unit. This can be achieved by: each analysis unit learns the corresponding modal attribute features from the different modal astronomical features received by each analysis unit.

[0107] Here, the modal attribute features are used to reflect the characteristics of the corresponding astronomical data sources. Exemplarily, the astronomical data source characteristics include at least one of the following: spatial distribution characteristics, time series characteristics, spectral characteristics, frequency spectrum characteristics, and cross-modal interaction characteristics.

[0108] In this scenario, modal attribute features are used to reflect the characteristics of each astronomical data source. The following are several examples illustrating the characteristics of different astronomical data sources and their modal attribute features:

[0109] Spatial distribution characteristics: By analyzing optical images of galaxy clusters, we can determine their distribution patterns in the universe. Modal properties can include the position coordinates and density distribution of galaxies. For example, by analyzing the distribution of galaxies in three-dimensional space using optical modal data, we can derive their spatial distribution characteristics.

[0110] Timing characteristics: By analyzing the radio pulse signals emitted by pulsars, we can obtain the characteristics of their periodic variations. Modal attribute characteristics can include pulse period, time delay, etc. For example, by observing pulsar radio signals using a radio telescope, we can obtain their timing characteristics, such as periodic variations and intensity fluctuations.

[0111] Spectral properties: By analyzing a star's spectral data, we can determine its elemental composition, temperature, velocity, and other characteristics. Modal properties can include the position, intensity, and width of spectral lines. For example, analyzing a star's spectral lines reveals strong hydrogen line signatures, indicating that it is primarily composed of hydrogen, which is a characteristic of its spectrum.

[0112] Spectral properties: Analyzing the spectral distribution in radio astronomy data allows identification of different radio sources in the universe. Modal properties can include frequency range, signal strength, and other characteristics. For example, when studying the cosmic microwave background radiation, radio spectrum data can be used to analyze its spectral properties, including frequency distribution and intensity fluctuations.

[0113] Cross-modal interaction characteristics: By combining data from different modalities, such as optical, infrared, and X-rays, we can identify multi-band characteristics of celestial objects and reflect their cross-modal behavior. Modal attribute characteristics can include common features observed in different modalities. For example, analyzing the optical, X-ray, and radio signals of a black hole revealed that the data from each modality showed rapid accretion of matter, demonstrating its cross-modal interaction characteristics.

[0114] These modal property characteristics help to gain a deeper understanding of the physical and chemical properties of astronomical data sources and enhance the study and interpretation of cosmic phenomena.

[0115] In the above steps, an analysis layer is set up to perform in-depth processing on the multimodal astronomical features received by each analysis unit. Specifically, the analysis layer extracts and learns the attributes of different modalities from each analysis unit, such as brightness in the optical mode, temperature in the infrared mode, and electromagnetic wave characteristics in the radio mode. Each analysis unit learns the unique properties of the specific modal data it receives through pattern recognition and feature extraction algorithms. Finally, the analysis layer summarizes the attributes of each modality, providing a foundation for subsequent comprehensive analysis or cross-modal fusion.

[0116] Further optionally, in the above steps, using a configuration layer, matching the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute features can be implemented as follows:

[0117] Aggregate the tag information from modal attribute features corresponding to different data sources into multiple sets of comprehensive attribute features; each set of comprehensive attribute features is used to represent the characteristic analysis characteristics corresponding to at least one set of the multimodal astronomical features; and construct a corresponding analysis model based on each set of comprehensive attribute features. In this embodiment of the present application, the analysis model includes at least: an analysis model prototype, analysis model parameters, and an analysis model parameter adjustment strategy.

[0118] Modal attribute features from different astronomical data sources are often tagged with information such as observation type, data source (optical, infrared, radio, etc.), and physical phenomenon (pulsars, galaxies, black holes, etc.). The configuration layer aggregates attribute features into comprehensive attribute features based on this tagging information.

[0119] Consider multimodal observational data from a pulsar, including radio data (timing characteristics), X-ray data (energy characteristics), and optical data (spectral characteristics). The modal attribute features of these data sources carry different labeling information (such as "pulse period," "high-energy radiation," and "spectral line position"). These features are aggregated through the configuration layer to produce a set of comprehensive attribute features reflecting the multimodal behavior of the pulsar. Each set of comprehensive attribute features represents a specific analytical characteristic of the multimodal astronomical signature. These characteristics are used to determine which features are relevant to the target analysis task (such as object classification and feature detection). In the case of a pulsar, comprehensive attribute features might include "pulse period consistency," "high-energy X-ray burst intensity," and "spectral line redshift characteristics." These features are used to represent analytical characteristics of the object, such as its timing behavior and high-energy radiation properties, helping scientists further analyze its physical properties. Based on each set of comprehensive attribute features, the configuration layer constructs an appropriate analysis model for each data set. The main components of an analysis model include an analysis model prototype, analysis model parameters, and a parameter adjustment strategy. For example, for pulsars, the analysis model prototype can use a timing analysis model (such as the Fourier transform) to analyze the periodicity of the pulse signal. Analysis model parameters may include pulse period range and noise level, which are used to optimize analysis accuracy. A strategy for adjusting analysis model parameters could be to adaptively adjust parameters if the observed data is noisy, such as increasing the filter strength to reduce interference and improve signal analysis accuracy.

[0120] As you can understand, the analytical model prototype provides an analytical framework or algorithm for processing specific types of astronomical data. Examples include time series analysis, spectrum analysis, and spectral line fitting. The analytical model parameters are used to adjust the model to different data conditions. For example, different astronomical objects have different pulse periods, and the model can be configured with different parameters to account for these differences. The analytical model parameter adjustment strategy dynamically adjusts model parameters based on real-time data feedback. For example, when the noise level in optical data increases, the filter parameters can be adjusted to ensure accurate extraction of target features.

[0121] Suppose we are analyzing an active galactic nucleus (AGN). During the process of modal attribute feature aggregation, the optical, infrared, and radio data of the AGN each contain distinct signature information, such as radiation intensity in the optical mode, temperature distribution in the infrared mode, and jet activity characteristics in the radio mode. These features are aggregated by configuring layers to form a set of comprehensive attribute signatures. These comprehensive attribute signatures may represent the energy release, jet activity, and accretion characteristics of the AGN, which are crucial for studying the physical mechanisms of AGNs. Based on these comprehensive attribute signatures, a model suitable for AGN analysis is systematically constructed. The prototype analysis model may be a jet analysis model based on radio data, with parameters such as jet intensity and jet velocity. The parameter adjustment strategy may be to dynamically adapt to the background noise in the radio data to more clearly distinguish the jet characteristics.

[0122] In this way, the configuration layer constructs corresponding analysis models based on the modal attribute characteristics of different astronomical data sources, thereby improving the processing and analysis capabilities of multimodal astronomical data.

[0123] As an optional embodiment, in step 103, the analysis mode is adopted to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data, which can be implemented as follows:

[0124] Constructing a multi-branch processing network based on the analysis pattern; the multi-branch processing network includes at least a processing branch corresponding to each of the analysis patterns, the branch structure and processing flow of the processing branch being determined by the analysis pattern;

[0125] Inputting the multi-source astronomical data into the multi-branch processing network to obtain corresponding multiple groups of multi-source astronomical data analysis result data streams;

[0126] A data stream real-time fusion module is used to perform real-time fusion processing on multiple sets of multi-source astronomical data analysis result data streams according to their respective dynamic weights to obtain the astronomical fusion data; the dynamic weights are determined by the feedback scores of the corresponding processing branches.

[0127] In step 103, the system first constructs a multi-branch processing network based on different analysis modes. Each processing branch represents an analysis mode, and its branch structure and processing flow are determined by the characteristics of the analysis mode. This allows the system to employ different analysis methods for different astronomical data sources (such as optical, radio, and infrared). For example, time series analysis is used for pulsar signal analysis, while spectrum analysis is used for spectral data processing. Each branch independently processes its own data source, ensuring highly targeted and accurate processing. Secondly, after the multi-source astronomical data is input into the multi-branch processing network, it undergoes independent analysis by each processing branch, generating multiple sets of analysis result data streams. These data streams correspond to the analysis results for each data source. For example, when analyzing an active galactic nucleus (AGN), optical data passes through the spectral analysis branch, radio data passes through the radio jet analysis branch, and infrared data passes through the energy distribution analysis branch, ultimately obtaining analysis results for different modes. This allows for the determination of various aspects of the AGN, such as its spectral characteristics, radio jet intensity, and infrared radiation distribution.

[0128] The real-time data stream fusion module then fuses these multiple analysis result streams. The core fusion mechanism is based on the dynamic weighting of each data stream, which is determined by the feedback score of each processing branch. The feedback score reflects the branch's analysis accuracy, data credibility, and other factors. For example, during the AGN analysis, if the radio data signal is very clear and has a high feedback score, the radio analysis branch's data stream will be given a higher weight. Meanwhile, due to poor observation conditions and high noise levels, the infrared data has a lower feedback score and a relatively lower weight. This dynamic adjustment allows the system to highlight more representative data sources in real time, preventing noise from influencing the overall analysis results.

[0129] Finally, by fusing the various data streams, the system ultimately generates comprehensive astronomical fusion data. This data incorporates the best of multiple sources, providing a more comprehensive and accurate result. For example, in an AGN analysis, the final astronomical fusion data might include comprehensive information on the AGN's radio jet activity, infrared radiation characteristics, and optical spectral signatures. This fused data not only provides a clearer picture of the AGN's physical mechanisms but also offers a more complete analysis of astronomical phenomena than would be possible from a single data source.

[0130] When studying an active galactic nucleus (AGN), it is often necessary to combine data from different wavelengths for comprehensive analysis. For example, optical data provides the radiation intensity and spectral characteristics of the AGN; radio data provides the strength and structure of the AGN's jet activity; and infrared data reveals the heating and energy distribution of the dust surrounding the AGN. Optical data enter the spectral analysis model branch, radio data enter the radio jet analysis model branch, and infrared data enter the energy distribution analysis model branch. Each processing branch performs independent analysis to generate its corresponding data stream. The radio jet branch has a higher feedback score, indicating a strong jet signal and a more reliable analysis result. However, due to its high noise content, the infrared data has a lower score. Based on the feedback score, the radio jet data stream is assigned a higher weight, and its analysis results serve as the primary reference. By combining the characteristics of different wavelengths, a complete picture of the AGN can be obtained, describing its radio jet activity, optical radiation characteristics, and infrared radiation distribution. This multi-branch fusion analysis approach can extract more valuable information from complex astronomical data, reduce the limitations of single-modal data, and enhance understanding of multimodal astronomical phenomena.

[0131] In an embodiment of the present application, multi-source astronomical data is acquired; the multi-source astronomical data all target the same observation object or the same observation area; the multi-source astronomical data is input into an adaptive exploration space model to obtain analysis modes corresponding to each of the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods; using the analysis mode, the multi-branch fusion processing is performed on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data. In this solution, the problem of physical property differences between astronomical data in different bands is effectively solved through the adaptive exploration space model, multi-branch processing network, and real-time fusion mechanism. While maintaining the unique characteristics of each band of data, it can dynamically fuse relevant information from different data sources to achieve deep fusion analysis of multi-source astronomical data, thereby providing more accurate and comprehensive astronomical fusion data for astronomical research.

[0132] In another embodiment of the present application, an astronomical data fusion analysis system based on deep learning is also provided. Figure 2 The astronomical data fusion analysis system based on deep learning includes the following units:

[0133] A collection unit is configured to acquire multi-source astronomical data; the multi-source astronomical data are all for the same observation object or the same observation area;

[0134] an analysis unit configured to input the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods;

[0135] The fusion unit is configured to adopt the analysis mode to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0136] Further optionally, the analysis unit inputs the multi-source astronomical data into the adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data, and is configured to:

[0137] A multimodal feature extraction layer is used to extract multimodal astronomical features from the multi-source astronomical data; the multimodal astronomical features include at least one of the following: an observed space feature, an observed calorific value change feature, and a radio time series feature;

[0138] Using a projection layer, the multi-source astronomical data are projected into an adaptive exploration space respectively; the adaptive exploration space is constructed by a pre-configured astronomical space model;

[0139] Using a routing module, the multimodal astronomical features are transmitted to corresponding analysis units;

[0140] Using an analysis layer, learning from the multimodal astronomical features corresponding to each analysis unit to obtain modal attribute features corresponding to each of the multimodal astronomical features;

[0141] A configuration layer is used to match the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute characteristics; and configurable analysis mode parameters and analysis methods are set in the analysis unit.

[0142] Further optionally, the analysis unit uses a multimodal feature extraction layer to extract multimodal astronomical features from the multi-source astronomical data, and is configured to:

[0143] Identifying data modality types contained in the multi-source astronomical data;

[0144] Generate corresponding feature extraction branches based on the identified data modality type to obtain a feature extraction network; wherein the feature extraction branches include at least independent extraction branches and mixed extraction branches;

[0145] inputting the multi-source astronomical data into the feature extraction network;

[0146] In the feature extraction network, each independent extraction branch is used to extract a set of independent astronomical data features of the corresponding modality, and the mixed extraction branch is used to extract a set of mixed astronomical data features of at least two modalities;

[0147] The extracted independent astronomical data features and mixed astronomical data features are input into a cross-modal interaction layer, and interactive astronomical data features are extracted from the independent astronomical data features and the mixed astronomical data features; the cross-modal interaction layer is dynamically adjusted based on the structural branches in the feature extraction network.

[0148] Further optionally, the analysis unit uses a projection layer to project the multi-source astronomical data into the adaptive exploration space respectively, and is configured to:

[0149] Projecting independent astronomical data features, mixed astronomical data features, and interactive astronomical data features into an adaptive exploration space according to a multimodal dimension to obtain multiple astronomical data feature points;

[0150] Multiple astronomical data exploration paths are constructed by fitting multiple astronomical data feature points;

[0151] The intersections of the multiple astronomical data exploration paths correspond to interactive astronomical data features or mixed astronomical data features, and the independent feature points in the multiple astronomical data exploration paths correspond to independent astronomical data features.

[0152] Further optionally, the analysis unit adopts a routing module to transmit the multimodal astronomical features to a corresponding analysis unit, and is configured to:

[0153] Inputting astronomical data feature points in a plurality of astronomical data exploration paths into a routing module;

[0154] Allocate each astronomical data feature point to the corresponding analysis unit through the adaptive weight and routing allocation matrix in the routing module;

[0155] Among them, the routing module is expressed as the following formula: Among them, F i is the i-th astronomical data feature point, W i is the modal feature weight corresponding to the i-th astronomical data feature point, T ij is the degree of fit between the i-th astronomical data feature point and the j-th analysis unit, α is a specific parameter used to adjust the sensitivity of the activation function. The lower the specific parameter value of α, the more balanced the adaptive distribution of the astronomical data feature points. A represents the probability that the i-th astronomical data feature point in the routing assignment matrix is assigned to the j-th analysis unit, j is the function used by the jth analysis unit to process the i-th astronomical data feature point received, β j is the importance weight of the j-th analysis unit in the output value, and O is the comprehensive output value corresponding to the j-th analysis unit.

[0156] Further optionally, the analysis unit, using the analysis layer, learns from the multimodal astronomical features corresponding to each analysis unit to obtain the modal attribute features corresponding to each of the multimodal astronomical features, and is configured as follows:

[0157] By means of each analysis unit, corresponding modal attribute features are learned from the astronomical features of different modalities received; the modal attribute features are used to reflect the characteristics of the corresponding astronomical data source; the astronomical data source characteristics include at least one of the following: spatial distribution characteristics, temporal characteristics, spectral characteristics, frequency spectrum characteristics, and cross-modal interaction characteristics;

[0158] The analysis unit, using a configuration layer, matches the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute features and is configured as follows:

[0159] Aggregating tag information in modal attribute features corresponding to different data sources into multiple groups of comprehensive attribute features; each group of comprehensive attribute features is used to represent feature analysis characteristics corresponding to at least one group of the multimodal astronomical features;

[0160] A corresponding analysis model is constructed based on each set of comprehensive attribute features; the analysis model at least includes: an analysis model prototype, analysis model parameters, and an analysis model parameter adjustment strategy.

[0161] Further optionally, the fusion unit adopts the analysis mode to perform multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data, and is configured to:

[0162] Constructing a multi-branch processing network based on the analysis pattern; the multi-branch processing network includes at least a processing branch corresponding to each of the analysis patterns, the branch structure and processing flow of the processing branch being determined by the analysis pattern;

[0163] Inputting the multi-source astronomical data into the multi-branch processing network to obtain corresponding multiple groups of multi-source astronomical data analysis result data streams;

[0164] A data stream real-time fusion module is used to perform real-time fusion processing on multiple sets of multi-source astronomical data analysis result data streams according to their respective dynamic weights to obtain the astronomical fusion data; the dynamic weights are determined by the feedback scores of the corresponding processing branches.

[0165] The system can implement various steps in the above method embodiments, which will not be expanded here.

[0166] In the embodiments of the present application, automatic fusion processing of multi-source astronomical data is achieved, providing a data basis for subsequent processing of multi-source astronomical data.

[0167] See also Figure 3 , Figure 3Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented: acquiring multi-source astronomical data; the multi-source astronomical data are all for the same observation object or the same observation area; inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods; and using the analysis mode, multi-branch fusion processing is performed on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0168] See also Figure 4 , Figure 4 Schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, it implements the following steps: obtaining multi-source astronomical data; the multi-source astronomical data are all for the same observation object or the same observation area; inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis patterns corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis pattern parameters and analysis methods; using the analysis pattern, multi-branch fusion processing is performed on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data.

[0169] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0171] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0172] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0173] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0174] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0175] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for astronomical data fusion analysis based on deep learning, characterized in that: The method comprises: Acquiring multi-source astronomical data; wherein the multi-source astronomical data are all directed to the same observation object or the same observation area; Inputting the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods; Using the analysis mode, performing multi-branch fusion processing on the multi-source astronomical data to obtain astronomical fusion data corresponding to the multi-source astronomical data; Inputting the multi-source astronomical data into the adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data includes: A multimodal feature extraction layer is used to extract multimodal astronomical features from the multi-source astronomical data; the multimodal astronomical features include at least one of the following: an observed space feature, an observed calorific value change feature, and a radio time series feature; Using a projection layer, independent astronomical data features, mixed astronomical data features, and interactive astronomical data features are projected into an adaptive exploration space; the adaptive exploration space is constructed by a pre-configured astronomical space model; Using a routing module, the astronomical data feature points in multiple astronomical data exploration paths are input into the routing module, and each astronomical data feature point is assigned to a corresponding analysis unit through the adaptive weight and routing assignment matrix in the routing module; Using an analysis layer, learning from the multimodal astronomical features corresponding to each analysis unit to obtain modal attribute features corresponding to each of the multimodal astronomical features; A configuration layer is used to match the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute characteristics; and configurable analysis mode parameters and analysis methods are set in the analysis unit.

2. An astronomical data fusion analysis system based on deep learning, characterized in that: The system includes the following units, wherein: A collection unit is configured to acquire multi-source astronomical data; the multi-source astronomical data are all for the same observation object or the same observation area; an analysis unit configured to input the multi-source astronomical data into an adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data; the adaptive exploration space model is provided with configurable analysis mode parameters and analysis methods; a fusion unit configured to perform multi-branch fusion processing on the multi-source astronomical data using the analysis mode to obtain astronomical fusion data corresponding to the multi-source astronomical data; Inputting the multi-source astronomical data into the adaptive exploration space model to obtain analysis modes corresponding to the multi-source astronomical data includes: A multimodal feature extraction layer is used to extract multimodal astronomical features from the multi-source astronomical data; the multimodal astronomical features include at least one of the following: an observed space feature, an observed calorific value change feature, and a radio time series feature; Using a projection layer, independent astronomical data features, mixed astronomical data features, and interactive astronomical data features are projected into an adaptive exploration space; the adaptive exploration space is constructed by a pre-configured astronomical space model; Using a routing module, the astronomical data feature points in multiple astronomical data exploration paths are input into the routing module, and each astronomical data feature point is assigned to a corresponding analysis unit through the adaptive weight and routing assignment matrix in the routing module; Using an analysis layer, learning from the multimodal astronomical features corresponding to each analysis unit to obtain modal attribute features corresponding to each of the multimodal astronomical features; A configuration layer is used to match the analysis modes corresponding to the multi-modal astronomical features based on the modal attribute characteristics; and configurable analysis mode parameters and analysis methods are set in the analysis unit.

3. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the astronomical data fusion analysis method based on deep learning as described in claim 1.

4. A non-transitory computer-readable storage medium, characterized in that The storage medium stores a computer software program, which, when executed by a processor, implements the astronomical data fusion analysis method based on deep learning as claimed in claim 1.

Images