A sensitive target-based space-ground radar cooperative observation method and system

Abstract

Embodiments of the present disclosure provide a method and system for satellite-ground radar cooperative observation based on sensitive targets, which are applied to the technical field of weather radar. The method comprises the following steps: acquiring satellite, radar and underlying surface data; identifying and processing the radar data to obtain the number, position, area of potential targets and the early warning level corresponding to each potential target, and comprehensively obtaining the satellite-ground joint early warning level; using the underlying surface data, potential targets and the satellite-ground joint early warning level to construct a sensitive target evaluation function and calculate the sensitivity score; and arranging and combining the sensitive targets and radar scanning modes, and performing optimization processing to select the optimal scanning mode. In this way, real-time tracking and dynamic monitoring of strong convective weather can be achieved, guiding multiple weather radars to efficiently carry out cooperative operation and improving the observation timeliness and early warning reliability of high-disaster strong convective weather.

Description

Technical Field

[0001] This disclosure relates to the field of weather radar technology, and in particular to a method and system for collaborative observation of sensitive targets using satellite-ground radar. Background Technology

[0002] Against the backdrop of rapid urbanization and high population density, severe convective weather, as a typical example of extreme weather, is characterized by its suddenness, small spatial scale, short lifespan, and high destructiveness, posing a demand for minute-level response and kilometer-level refined monitoring for disaster prevention, mitigation, and meteorological operations. When severe convective weather, especially short-duration heavy rainfall, occurs under specific conditions, it triggers secondary disasters (such as flash floods and mudslides), causing significant impacts on human production and lives. Whether using spaceborne precipitation radar or ground-based weather radar, single remote sensing methods are insufficient to simultaneously provide large-scale early warning and localized refined observation. Therefore, constructing an intelligent collaborative observation system for severe convective weather based on multi-source data fusion and centered on dynamic risk assessment is of great significance for improving disaster prevention and mitigation capabilities.

[0003] Currently, the intelligent collaborative observation method for severe convection has the following shortcomings:

[0004] 1. Single source of information for potential target identification: Currently, the identification of potential targets relies mainly on real-time weather radar echoes, which lacks comprehensive analysis with satellite cloud images of initial convection signals, cloud structure characteristics, and trends of formation and dissipation. Especially in the early development stage of convection, the advantages of satellite's wide-area and continuous observation are not fully utilized, resulting in insufficient timeliness and accuracy of early identification.

[0005] 2. Insufficient risk assessment dimensions: Current methods mostly focus on meteorological characteristics such as convective structure and intensity in radar observations, lacking comprehensive risk analysis of potential target landing areas. They do not fully consider the differences in exposure between densely populated and sparsely populated areas, and also ignore the differences in the degree of impact of strong convective cells on areas with complex terrain (e.g., mountains and hills) and areas with secondary disaster risks (e.g., landslides and flash floods), making it difficult to comprehensively assess the disaster risk level of different targets.

[0006] 3. Uneven scheduling and resource allocation for multiple targets: Currently, weather radar observation methods rely more on fixed scanning strategies or manual marking of key monitoring areas. Multiple weather radars have the same observation mode and perform continuous scanning at fixed intervals. In situations where multiple potential targets coexist, the strategy for allocating observation tasks is relatively simple and fails to fully balance the importance of targets, observation priorities, and resource utilization. This can easily lead to resource waste or missing measurements of key targets, affecting the overall efficiency and effectiveness of collaborative observation. Summary of the Invention

[0007] This disclosure provides a method and system for collaborative observation of satellite and ground radar based on sensitive targets, which solves the technical problems of insufficient satellite-ground joint early warning capability for severe weather, single sensitive target discrimination elements, and uneven scheduling and resource allocation of multi-target tasks.

[0008] According to a first aspect of this disclosure, a method for coordinated observation of sensitive targets using satellite-ground radar is provided. The method includes:

[0009] Acquire satellite data, radar data, and underlying surface data;

[0010] The radar data is identified and processed to obtain the number, location, area, and early warning level of each potential target. The combined early warning level of each potential target is then obtained.

[0011] Using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning levels for the potential targets, a sensitive target evaluation function is constructed, and the sensitivity score corresponding to each potential target is calculated using the sensitive target evaluation function.

[0012] The system arranges and combines sensitive targets and radar scanning methods, and performs optimization to select the optimal scanning method.

[0013] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the satellite data is a satellite cloud image including a target area, wherein the target area is an area monitored by radar;

[0014] The underlying surface data includes: GDP map, population density map, land use rate map, and secondary disaster risk map of the target area.

[0015] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the identification and processing of radar data to obtain the number, location, area, and early warning level corresponding to each potential target in the radar data, and the comprehensive determination of the joint satellite-ground early warning level for each potential target, includes:

[0016] Potential areas for acquiring satellite data, including their location, area, and warning level;

[0017] Potential targets in the radar image at time n are identified using a threshold method; where n represents the current time.

[0018] Potential targets in the radar image at time n+1 are predicted using a ConvLSTM convolutional long short-term memory network.

[0019] Potential targets in the radar image at time n+1 are identified using a threshold method;

[0020] Potential target tracking is performed based on optical flow to obtain the lifecycle state of each potential target. ;

[0021] Based on each potential target and the potential area of ​​satellite data, the joint satellite-ground early warning level of each potential target is calculated using the formula for calculating the joint satellite-ground early warning level of potential targets.

[0022] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the formula for calculating the potential target satellite-ground joint early warning level is:

[0023]

[0024] in, Indicates spatial accuracy weights, Indicates the lifecycle state. Indicates the weighting coefficient. Indicates the satellite data warning level. This represents the maximum reflectivity of the radar target after normalization. This indicates the degree of overlap between the potential satellite area and the potential radar target.

[0025] As described above and in any possible implementation, a further implementation is provided, wherein the construction of a sensitive target evaluation function using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning levels of the potential targets includes:

[0026] The underlying surface data is used to obtain the economic situation, population density, land use rate, and secondary disaster types of potential target areas.

[0027] A sensitive target evaluation function is constructed using the joint early warning level of potential target satellites and ground stations, the economic situation of potential target areas, the population density of potential target areas, the land use rate of potential target areas, the types of secondary disasters in potential target areas, and weighting coefficients.

[0028] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the step of permuting and combining sensitive targets and radar scanning methods, and performing optimization processing to select the optimal scanning method includes:

[0029] The sensitivity scores of multiple potential targets are sorted in descending order, and the top q potential targets are taken as sensitive targets.

[0030] Based on q sensitive targets and R radars, all permutations and combinations of radar scanning methods are obtained, and the optimal scanning method is selected by optimizing all permutations and combinations through an objective function; where q and R are positive integers.

[0031] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the step of selecting the optimal scanning method by optimizing all permutations and combinations through an objective function includes:

[0032] Calculate the function values ​​corresponding to all permutations and combinations of radar scanning methods using the objective function;

[0033] The function values ​​are sorted in ascending order, and the scanning method corresponding to the smallest function value is taken as the optimal scanning method, which is then used as the radar's scheduling method.

[0034] According to a second aspect of this disclosure, a satellite-ground radar cooperative observation system based on sensitive targets is provided. The system includes:

[0035] The acquisition module is used to acquire satellite data, radar data, and underlying surface data.

[0036] The processing module is used to identify and process radar data to obtain the number, location, area, and early warning level of each potential target in the radar data, and to obtain the combined satellite-ground early warning level of each potential target.

[0037] The calculation module is used to construct a sensitive target evaluation function using the underlying surface data, potential targets and the corresponding satellite-ground joint early warning level of the potential targets, and to calculate the sensitivity score corresponding to each potential target using the sensitive target evaluation function;

[0038] The evaluation module is used to arrange and combine sensitive targets and radar scanning methods, and to perform optimization processing to select the optimal scanning method.

[0039] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0040] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods according to the first and / or second aspects of this disclosure.

[0041] This disclosure provides a satellite-ground radar collaborative observation method based on sensitive targets. It comprehensively identifies sensitive targets using multi-source satellite and ground data, guiding multiple weather radars to efficiently conduct collaborative operations. This improves the timeliness of observations and the reliability of early warnings for highly hazardous severe convective weather. Specific beneficial effects include:

[0042] 1. This disclosure calculates the warning level of each potential target and optimizes the scanning mode of each weather radar (i.e., each weather radar is matched with a working mode) based on the sensitivity of multiple potential targets. Compared with the existing method where all weather radars have the same working mode, this method can realize real-time tracking and dynamic monitoring of severe convective weather, guide multiple weather radars to carry out efficient collaborative operations, and improve the observation timeliness and warning reliability of highly hazardous severe convective weather.

[0043] 2. This disclosure obtains the optimal scanning method of weather radar by optimizing the objective function, which can not only reduce the overall average control time, but also ensure that the time difference of the radar load balancing evaluation model between different weather radars is as small as possible (i.e., it can achieve a more uniform distribution of weather radar resources).

[0044] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0045] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0046] Figure 1 A flowchart of a satellite-ground radar cooperative observation method based on sensitive targets according to an embodiment of the present disclosure is shown;

[0047] Figure 2 A block diagram of a satellite-ground radar cooperative observation system based on a sensitive target, according to an embodiment of the present disclosure, is shown.

[0048] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0050] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0051] This disclosure proposes a satellite-ground radar collaborative observation method based on sensitive targets. It achieves efficient observation through multi-source data fusion and intelligent scheduling. First, it integrates satellite cloud images, multi-time radar data, and underlying surface data to accurately identify potential radar targets and track their lifecycles. Then, it calculates the joint satellite-ground early warning level by combining satellite data. Next, it fuses the early warning level with multi-dimensional information from underlying surface data to construct a sensitive target evaluation function to quantify the sensitivity of potential targets. Finally, it filters key sensitive targets based on sensitivity ranking, enumerates the scanning combinations of multiple radars and sensitive targets, and uses an objective function to optimize the optimal scanning scheduling method that balances radar load and observation efficiency. This disclosure overcomes the limitations of single data sources. Satellite-ground data collaboration improves the timeliness and accuracy of potential target identification, especially strengthening the capture of early convective signals. Simultaneously, it provides comprehensive risk assessment dimensions, incorporating underlying surface information such as economy, population, and topography, which better reflects actual disaster risk differences. It dynamically optimizes radar resource allocation, avoiding resource waste from fixed scanning or missing key targets, significantly improving the observation timeliness and early warning reliability of highly hazardous severe convective weather, and providing more scientific technical support for disaster prevention and mitigation.

[0052] Figure 1 A flowchart of a satellite-ground radar cooperative observation method 100 based on a sensitive target, according to an embodiment of this disclosure, is shown. Figure 1 As shown, a satellite-ground radar cooperative observation method based on sensitive targets includes:

[0053] S101 acquires satellite data, radar data, and underlying surface data.

[0054] In some embodiments, the satellite data is a satellite cloud image containing the target area, wherein the target area is the area monitored by the radar; the radar data of the target area includes: radar images of the target area at time n-2, radar images at time n-1, and radar images at time n, wherein n represents the current time; the underlying surface data includes: GDP map, population density map, land use rate map, and secondary disaster risk map containing the target area.

[0055] S102 identifies and processes radar data to obtain the number, location, area, and early warning level of each potential target, and then synthesizes the joint satellite-ground early warning level for each potential target.

[0056] In some embodiments, radar data is processed to identify the number, location, area, and warning level of potential targets in the radar data, and the combined satellite-ground warning level for each potential target is obtained, including:

[0057] Potential areas for acquiring satellite data, including their location, area, and warning level;

[0058] Potential targets in the radar image at time n are identified using a threshold method; where n represents the current time.

[0059] Potential targets in the radar image at time n+1 are predicted using a ConvLSTM convolutional long short-term memory network.

[0060] Potential targets in the radar image at time n+1 are identified using a threshold method;

[0061] Potential target tracking is performed based on optical flow to obtain the lifecycle state of each potential target. ;

[0062] Based on each potential target and the potential area of ​​satellite data, the joint satellite-ground early warning level of each potential target is calculated using the formula for calculating the joint satellite-ground early warning level of potential targets.

[0063] In some embodiments, the formula for calculating the joint satellite-ground early warning level of potential targets is:

[0064]

[0065] in, Indicates spatial accuracy weights, Indicates the lifecycle state. Indicates the weighting coefficient. Indicates the satellite data warning level. This represents the maximum reflectivity of the radar target after normalization. This indicates the degree of overlap between the potential satellite area and the potential radar target.

[0066] In some embodiments, based on the geographic coordinate calibration information of satellite cloud images, the latitude and longitude ranges of potential hazardous weather areas such as convective cloud systems and heavy precipitation cloud clusters are determined to form vector boundary data, ensuring consistency with the spatial reference of subsequent radar data. Referring to the physical parameter inversion results of the satellite cloud images and combining them with meteorological industry standards, a preliminary warning level classification is performed on the potential areas, denoted as the satellite warning level. .

[0067] In some embodiments, a threshold method is used to achieve automated identification of potential targets. Specifically, the following steps are taken: referencing the radar echo characteristics of different types of severe weather and combining them with the climate characteristics of the target area, a dynamic echo intensity threshold is set. After grayscale processing of the radar image at time n, all pixels are traversed, and pixels with echo intensity exceeding the set threshold are marked as "candidate target pixels". Isolated noise points are removed by morphological filtering (such as dilation and erosion operations). Connectivity analysis is performed on the selected candidate target pixels, and each connected region is regarded as an independent potential target. The total number of connected regions is calculated and counted, which is the number of radar potential targets at time n.

[0068] In some embodiments, to achieve dynamic tracking of the lifecycle of potential targets, a Convolutional Long Short-Term Memory (ConvLSTM) network is used to predict the radar image at time n+1. Specifically, the radar images at three consecutive times (n-2, n-1, and n) are used as the input sequence, and a 3-layer ConvLSTM architecture is adopted to output the predicted echo intensity of the radar image at time n+1.

[0069] In some embodiments, the radar image at time n+1 predicted by ConvLSTM is used to identify potential targets using the same threshold method as at time n, ensuring consistency and comparability between the two identification results. The echo intensity threshold set at time n is directly reused. If the overall intensity of the predicted echo is too high, the threshold can be appropriately increased to avoid misidentifying weak echo interference as potential targets. Similarly, the number, location, area and preliminary warning level of each potential target at time n+1 are calculated and a time series correlation is established with the results at time n.

[0070] In some embodiments, to quantify the dynamic evolution characteristics of potential targets, optical flow is used to perform ID matching on radar potential targets at time n and time n+1, enabling continuous target tracking and evaluating the lifecycle state of each target accordingly. .

[0071] Specifically, for each potential target at time n (denoted as target A), its theoretical position at time n+1 is predicted based on the optical flow vector of its internal pixels. Then, a spatial distance comparison is performed with the actual identified potential target at time n+1 (denoted as target B) (with a distance threshold of ≤5km). If the overlap between the theoretical position and the center position of target B is ≥80%, they are determined to be the same target and assigned the same ID, thereby achieving continuous tracking of the target.

[0072] In some embodiments, based on the acquired multi-dimensional satellite and radar data, a comprehensive quantification of the risk level of each potential target is achieved through a fusion formula, the specific formula being:

[0073]

[0074] in, Indicates spatial accuracy weights, Indicates the lifecycle state. Indicates the weighting coefficient. Indicates the satellite data warning level. This represents the maximum reflectivity of the radar target after normalization. This indicates the degree of overlap between the potential satellite area and the potential radar target.

[0075] It should be noted that, In this way, to ensure The degree of overlap between potential satellite regions and potential weather radar targets refers to: first determining the degree of overlap between the potential region location in satellite data and the potential target location in radar data; if they do not overlap, then... If they overlap, then determine the degree of overlap between the potential area of ​​the satellite data and the potential target area of ​​the radar data.

[0076] S103, using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning level of the potential targets, a sensitive target evaluation function is constructed, and the sensitivity score corresponding to each potential target is calculated using the sensitive target evaluation function.

[0077] In some embodiments, constructing a sensitive target evaluation function using the underlying surface data, the potential target, and the corresponding satellite-ground joint early warning level of the potential target includes:

[0078] The underlying surface data is used to obtain the economic situation, population density, land use rate, and secondary disaster types of potential target areas.

[0079] A sensitive target evaluation function is constructed using the joint early warning level of potential target satellites and ground stations, the economic situation of potential target areas, the population density of potential target areas, the land use rate of potential target areas, the types of secondary disasters in potential target areas, and weighting coefficients.

[0080] In some embodiments, the expression for the sensitive target evaluation function X is:

[0081]

[0082] in, , , , , This represents the weighting parameter.

[0083] In some embodiments, the weight parameters are calculated using the Analytic Hierarchy Process (AHP) and the Entropy Weight Method (EWM). , , , , .

[0084] In some embodiments, subjective weight construction includes calculating using AHP. , , , , .

[0085] Specifically, first, construct the judgment matrix. ;in, Indicators Relative indicators Importance score, satisfying , , ;

[0086] Calculate the judgment matrix The product of elements in each row ;

[0087] Calculate the judgment matrix Geometric mean of each row element ;

[0088] Calculate the subjective weight vector ;

[0089] in, , , , , .

[0090] In some embodiments, the objective weights are constructed using EWM calculations. , , , , .

[0091] Specifically, construct the original matrix ;in, Indicates the number of evaluation units. Indicates the number of evaluation indicators;

[0092] Data standardization processing, including indicators The calculation formula is:

[0093]

[0094] in, The elements of the original matrix B .

[0095] Calculate the entropy value and entropy weight; where, the entropy value... The calculation formula is:

[0096] ;in, ;

[0097] Entropy weight The calculation formula is:

[0098]

[0099] in, , , , , .

[0100] In some embodiments, weight coupling is utilized The calculation formula is obtained through coupled calculation. , , , , .

[0101] Specifically, weight coupling The calculation formula is:

[0102]

[0103] in, , , , , Therefore, the weight parameters are calculated by combining the subjective AHP method with the objective EWM method. , , , , This allows the subjective AHP method and the objective EWM method to complement each other, thereby improving the weighting parameters. , , , , The accuracy of the calculation improves the evaluation function for sensitive targets. The accuracy of the calculation.

[0104] S104 arranges and combines sensitive targets and radar scanning methods, and performs optimization processing to select the optimal scanning method.

[0105] In some embodiments, arranging and combining sensitive targets and radar scanning methods, and performing optimization processing to select the optimal scanning method includes:

[0106] The sensitivity scores of multiple potential targets are sorted in descending order, and the top q potential targets are taken as sensitive targets.

[0107] Based on q sensitive targets and R radars, all permutations and combinations of radar scanning methods are obtained, and the optimal scanning method is selected by optimizing all permutations and combinations through an objective function; where q and R are positive integers.

[0108] Specifically, sensitivity scoring for multiple potential targets in the radar image at time n. Sort the potential targets from largest to smallest, select the top q potential targets, and designate these q potential targets as sensitive targets. Sensitive targets Taiwan radar formation The scanning method of a weather radar, and the formation The scanning methods of each weather radar are optimized to obtain the optimal scanning method for each weather radar. This optimal scanning method is the scheduling method for the weather radar.

[0109] In some embodiments, selecting the optimal scanning method by optimizing all permutations and combinations using an objective function includes:

[0110] Calculate the function values ​​corresponding to all permutations and combinations of radar scanning methods using the objective function;

[0111] The function values ​​are sorted in ascending order, and the scanning method corresponding to the smallest function value is taken as the optimal scanning method, which is then used as the radar's scheduling method.

[0112] Specifically, input Sensitive targets Taiwan radar and The moving time matrix corresponding to the radar Scan time matrix Coverage matrix The enumeration method is used to list the results. The scanning method of a weather radar utilizes an objective function. calculate The function values ​​corresponding to each weather radar scanning method. The function values ​​corresponding to each weather radar scanning mode are sorted from smallest to largest. The scanning mode corresponding to the smallest function value is selected as the optimal scanning mode, and this optimal scanning mode is used as the scheduling mode for the weather radar.

[0113] In some embodiments, the radar load balancing evaluation model time The calculation formula is:

[0114]

[0115] in, This represents the total number of sensitive targets;

[0116] Average operating time of the radar The calculation formula is:

[0117]

[0118] Standard deviation of radar operation time in Taiwan The calculation formula is:

[0119]

[0120] objective function The calculation formula is:

[0121]

[0122] in: Represents an exponential function, when the sensitive target Assigned to radar The value is 1 if the condition is met, and 0 otherwise. Indicates sensitive targets Assigned to radar , express Weather radars participating in scanning operations in Taiwan's weather radar system. , Represents the adjustment coefficient, shift time matrix Represent each element Indicates radar Move to sensitive target Time, scan time matrix Represent each element Indicates radar For sensitive targets Scanning time, coverage matrix Represent each element Indicates radar Capable of scanning sensitive targets .

[0123] According to the embodiments of this disclosure, the following technical effects are achieved:

[0124] 1. This invention calculates the warning level of each potential target and optimizes the scanning mode of each weather radar (i.e., each weather radar is matched with a working mode) based on the sensitivity of multiple potential targets. Compared with the existing method where all weather radars have the same working mode, this method can realize real-time tracking and dynamic monitoring of severe convective weather, guide multiple weather radars to carry out efficient collaborative operations, and improve the observation timeliness and warning reliability of highly hazardous severe convective weather.

[0125] 2. This invention combines subjective AHP (Analytic Hierarchical Method) with objective EWM (Empirical Weighing Method) to calculate weight parameters a, b, c, d, and e, so that the subjective AHP and objective EWM methods complement each other, thereby improving the accuracy of the calculation of weight parameters a, b, c, d, and e, and thus improving the accuracy of the calculation of the sensitive target evaluation function X.

[0126] 3. This invention obtains the optimal scanning mode of weather radar by calculating the objective function F(a), which can not only reduce the overall average control time, but also ensure that the time difference of the radar load balancing evaluation model between different weather radars is as small as possible (i.e., it can achieve a more uniform distribution of weather radar resources).

[0127] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0128] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0129] Figure 2 A block diagram of a satellite-ground radar cooperative observation system 200 based on a sensitive target, according to an embodiment of the present disclosure, is shown. Figure 2 As shown, system 200 includes:

[0130] Acquisition module 201 is used to acquire satellite data, radar data, and underlying surface data;

[0131] Processing module 202 is used to identify and process radar data to obtain the number, location, area, and early warning level of each potential target in the radar data, and to obtain the combined satellite-ground early warning level of each potential target.

[0132] The calculation module 203 is used to construct a sensitive target evaluation function using the underlying surface data, potential targets and the satellite-ground joint early warning level corresponding to the potential targets, and to calculate the sensitivity score corresponding to each potential target using the sensitive target evaluation function.

[0133] The evaluation module 204 is used to arrange and combine sensitive targets and radar scanning methods, and to perform optimization processing to select the optimal scanning method.

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0135] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0136] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0137] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0138] Electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in ROM 302 or a computer program loaded into RAM 303 from storage unit 308. RAM 303 can also store various programs and data required for the operation of electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via bus 304. I / O interface 305 is also connected to bus 304.

[0139] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including voice input, speech input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0146] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0147] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0148] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for joint observation of sensitive targets using satellite-ground radar, characterized in that, include: Acquire satellite data, radar data, and underlying surface data; Radar data is processed to identify the number, location, area, and warning level of potential targets. A combined satellite-ground warning level is then determined for each potential target, including: Potential areas for acquiring satellite data, including their location, area, and warning level; Potential targets in the radar image at time n are identified using a threshold method; where n represents the current time. Potential targets in the radar image at time n+1 are predicted using a ConvLSTM convolutional long short-term memory network. Potential targets in the radar image at time n+1 are identified using a threshold method; Potential target tracking is performed based on optical flow to obtain the lifecycle state of each potential target. ; Based on each potential target and the potential area of ​​satellite data, the joint satellite-ground early warning level for each potential target is calculated using the formula for calculating the joint satellite-ground early warning level for potential targets; wherein, the formula for calculating the joint satellite-ground early warning level for potential targets is: in, Indicates spatial accuracy weights, Indicates the lifecycle state. Indicates the weighting coefficient. Indicates the satellite data warning level. This represents the maximum reflectivity of the radar target after normalization. This indicates the degree of overlap between the potential satellite area and the potential radar target; Using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning levels for the potential targets, a sensitive target evaluation function is constructed, and the sensitivity score corresponding to each potential target is calculated using the sensitive target evaluation function. The system arranges and combines sensitive targets and radar scanning methods, and performs optimization to select the optimal scanning method.

2. The method according to claim 1, characterized in that, The satellite data is a satellite cloud image including the target area, where the target area is the area monitored by the radar; The underlying surface data includes: GDP map, population density map, land use rate map, and secondary disaster risk map of the target area.

3. The method according to claim 1, characterized in that, The process of constructing a sensitive target evaluation function using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning levels for the potential targets includes: The underlying surface data is used to obtain the economic situation, population density, land use rate, and secondary disaster types of potential target areas. A sensitive target evaluation function is constructed using the joint early warning level of potential target satellites and ground stations, the economic situation of potential target areas, the population density of potential target areas, the land use rate of potential target areas, the types of secondary disasters in potential target areas, and weighting coefficients.

4. The method according to claim 1, characterized in that, The process of arranging and combining sensitive targets and radar scanning methods, and then performing optimization to select the optimal scanning method includes: The sensitivity scores of multiple potential targets are sorted in descending order, and the top q potential targets are taken as sensitive targets. Based on q sensitive targets and R radars, all permutations and combinations of radar scanning methods are obtained, and the optimal scanning method is selected by optimizing all permutations and combinations through an objective function; where q and R are positive integers.

5. The method according to claim 4, characterized in that, The process of selecting the optimal scanning method by optimizing all permutations and combinations using an objective function includes: Calculate the function values ​​corresponding to all permutations and combinations of radar scanning methods using the objective function; The function values ​​are sorted in ascending order, and the scanning method corresponding to the smallest function value is taken as the optimal scanning method, which is then used as the radar's scheduling method.

6. A satellite-ground radar cooperative observation system based on sensitive targets, characterized in that, include: The acquisition module is used to acquire satellite data, radar data, and underlying surface data. The processing module is used to identify and process radar data to obtain the number, location, area, and early warning level of each potential target in the radar data, and to obtain the combined satellite-ground early warning level of each potential target. The calculation module is used to construct a sensitive target evaluation function using the underlying surface data, potential targets, and the corresponding satellite-ground joint early warning levels for the potential targets, and to calculate the sensitivity score for each potential target using the sensitive target evaluation function, including: Potential areas for acquiring satellite data, including their location, area, and warning level; Potential targets in the radar image at time n are identified using a threshold method; where n represents the current time. Potential targets in the radar image at time n+1 are predicted using a ConvLSTM convolutional long short-term memory network. Potential targets in the radar image at time n+1 are identified using a threshold method; Potential target tracking is performed based on optical flow to obtain the lifecycle state of each potential target. ; Based on each potential target and the potential area of ​​satellite data, the joint satellite-ground early warning level for each potential target is calculated using the formula for calculating the joint satellite-ground early warning level for potential targets; wherein, the formula for calculating the joint satellite-ground early warning level for potential targets is: in, Indicates spatial accuracy weights, Indicates the lifecycle state. Indicates the weighting coefficient. Indicates the satellite data warning level. This represents the maximum reflectivity of the radar target after normalization. This indicates the degree of overlap between the potential satellite area and the potential radar target; The evaluation module is used to arrange and combine sensitive targets and radar scanning methods, and to perform optimization processing to select the optimal scanning method.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

Images