A method and system for timely early warning and control of bird flocks at airports based on radar monitoring

Abstract

This invention relates to the field of bird strike prevention and control technology, specifically to a method and system for timely early warning and prevention of bird flocks at airports based on radar monitoring. It utilizes radar to scan a monitoring area in real time, obtaining real-time dynamic data on bird activity, integrating this data into a monitoring dataset, generating spatial mapping data reflecting the spatial density distribution and gathering hotspots of bird flocks within the monitoring area, and defining risk zones. If, based on the real-time dynamic data, it is determined that a bird flock has entered a risk zone, dynamic adjustment parameters are generated to optimize the scanning strategy of the radar monitoring system. A real-time updated monitoring report is generated based on the real-time dynamic data, further generating a prevention and control command dataset and a final response plan. The technical solution presented in this invention, based on radar monitoring of the target area, provides accurate data with a wide coverage area. Furthermore, by adjusting the radar scanning strategy after a bird flock enters a risk zone, it improves data monitoring accuracy, resulting in highly accurate and timely monitoring reports.

Description

Technical Field

[0001] This invention relates to the field of bird strike prevention and control technology, specifically to a method and system for timely early warning and prevention of bird flocks at airports based on radar monitoring. Background Technology

[0002] Current methods for monitoring and controlling bird activity around airports have significant shortcomings. Many solutions rely too heavily on manual observation or single data sources, making it difficult to comprehensively capture the dynamic changes in bird activity, especially in integrating multi-dimensional information in complex environments. Furthermore, existing methods lack the accuracy and timeliness of early warnings when predicting peak bird activity periods and key areas, failing to meet the rapid response needs of airports. Simultaneously, in terms of real-time dynamic monitoring of bird activity using technological means, traditional monitoring methods struggle to cover large areas, and data update speeds are slow, easily missing critical activity windows. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method and system for timely early warning and prevention of bird flocks at airports based on radar monitoring, so as to solve the problems of slow data updates, insufficient data accuracy and timeliness, and difficulty in covering a large area in the existing schemes for monitoring bird flock activities.

[0004] According to a first aspect of the present invention, a method for timely early warning and control of bird flocks at airports based on radar monitoring is provided, comprising:

[0005] The monitoring area is scanned in real time using a pre-deployed radar monitoring system to obtain real-time dynamic data on bird activity; the location, number, and movement trajectory of the birds are obtained from the scanned data and integrated into a monitoring dataset;

[0006] Based on the monitoring dataset, spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area is generated, and risk areas are defined based on the spatial mapping data; if it is determined from real-time dynamic data that a bird flock has entered a risk area, dynamic adjustment parameters are generated.

[0007] The scanning strategy of the radar monitoring system is optimized and adjusted according to the dynamic adjustment parameters; a real-time updated monitoring report is generated based on real-time dynamic data.

[0008] Based on real-time updated monitoring reports, a prevention and control instruction dataset containing structured information to guide airport operational adjustments is generated, and a final response plan is generated based on the prevention and control instruction dataset.

[0009] Preferably, when generating spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, the method further includes:

[0010] The data in the monitoring dataset is segmented into time series to generate fragments of bird activity data containing different time periods;

[0011] Based on fragmented bird activity data, features are extracted from preset key indicators for each time period to obtain the activity characteristics of the bird flock in each time period.

[0012] When generating spatial mapping data, hotspot areas of different levels are generated for different time periods based on the activity characteristics.

[0013] Preferably, the method further includes:

[0014] Cluster analysis was performed on fragmented data of bird flock activities;

[0015] Obtain environmental data for the monitoring area;

[0016] By combining cluster analysis results with environmental data, environmental factor analysis was conducted to obtain the activity characteristics of bird flocks and the distribution of activity patterns of environmental factors.

[0017] Based on the aforementioned activity patterns, a bird flock activity prediction model under specific environmental conditions is established;

[0018] The bird flock activity prediction model and the real-time dynamic data are used to determine whether the bird flock has entered a risk area.

[0019] Preferably, the method further includes:

[0020] Obtain bird flock behavior records within a preset historical time span, and extract time elements, spatial elements, and activity characteristic elements from each bird flock behavior record;

[0021] All extracted elements are fused with the current bird flock's activity patterns to construct a three-dimensional feature matrix of time, space, and behavior.

[0022] Generate a feature dataset reflecting the activity trends of bird flocks based on the three-dimensional feature matrix;

[0023] The peak activity periods of bird flocks are determined based on the aforementioned feature dataset;

[0024] The radar monitoring system generates time-period adjustment parameters based on the peak activity periods of the bird flocks.

[0025] Preferably, the method further includes:

[0026] Thresholds for several key indicators of bird flock activity trends can be set according to user instructions;

[0027] If any key indicator of bird flock activity trend in the feature dataset exceeds the set threshold, the current feature dataset and the historical feature dataset are jointly input into the machine learning model for secondary peak prediction, generating a peak prediction result with a time window and corresponding probability value.

[0028] High-risk periods are marked based on the peak prediction results;

[0029] Based on the marked high-risk time periods, generate adjustment parameters for the high-risk time periods of the radar monitoring system.

[0030] Preferably, the method further includes:

[0031] Time windows are determined based on peak bird activity periods or high-risk periods.

[0032] Data corresponding to the time window is selected from real-time dynamic data and historical monitoring datasets, and spatial features are extracted. The extracted spatial features include the distribution of bird activity center points, density gradient changes, and trajectory concentration.

[0033] Based on the spatial characteristics, a spatial density distribution map and a clustering hotspot database of bird activity are established within the monitoring area using a spatial aggregation algorithm. Risk areas are then defined based on the spatial density map and the clustering hotspot database.

[0034] Obtain the airport infrastructure layer and locate the risk area on the airport infrastructure layer.

[0035] Preferably, the method further includes: acquiring peak flight times at the airport, and generating peak flight adjustment parameters for the radar monitoring system based on the peak flight times at the airport.

[0036] Preferably, the method further includes:

[0037] The generated prevention and control instruction dataset includes information on bird flock type, expected path, risk level, recommended response timing, and intervention priority.

[0038] The aforementioned prevention and control instruction dataset is sent to the airport flight scheduling system and ground operation system.

[0039] Preferably, when generating the spatial density distribution map and cluster hotspot database corresponding to the monitoring area, the method further includes:

[0040] Based on a uniform spatial resolution, the monitoring area is divided into regular grid units to obtain a geographic grid model;

[0041] The data in the monitoring dataset is mapped to the corresponding grid of the geographic grid model. The number and density changes of bird flocks in each grid are counted at unit time intervals. A spatiotemporal dynamic dataset is established based on the statistical data.

[0042] Based on the spatiotemporal dynamic dataset, the data on the raster is smoothed to generate a risk heatmap.

[0043] According to a second aspect of the present invention, a radar-based airport bird flock timely early warning and control system is provided, comprising:

[0044] The radar monitoring module is used to scan the monitoring area in real time using a pre-deployed radar monitoring system to obtain real-time dynamic data on bird activity; it also obtains data on the location, number, and movement trajectory of the birds from the scanned data and integrates them into a monitoring dataset.

[0045] The spatial mapping and comparison module is used to generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, and to define risk areas based on the spatial mapping data; if it is determined from real-time dynamic data that a bird flock has entered a risk area, dynamic adjustment parameters are generated.

[0046] The scanning strategy optimization module is used to optimize and adjust the scanning strategy of the radar monitoring system according to the dynamic adjustment parameters; and to generate a real-time updated monitoring report based on real-time dynamic data.

[0047] The prevention and control instruction generation module is used to generate a prevention and control instruction dataset containing structured information to guide airport operation adjustments based on real-time updated monitoring reports, and to generate the final response plan based on the prevention and control instruction dataset.

[0048] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0049] It is understood that the technical solution presented in this invention can utilize radar to scan the monitoring area in real time, obtain real-time dynamic data on bird activity, integrate it into a monitoring dataset, and then generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area, and define risk areas. If it is determined from the real-time dynamic data that a bird flock has entered a risk area, dynamic adjustment parameters are generated to optimize and adjust the scanning strategy of the radar monitoring system. A real-time updated monitoring report is generated based on the real-time dynamic data, and then a prevention and control command dataset is generated to generate the final response plan. The technical solution presented in this invention is based on radar monitoring of the target area, with accurate data and a large coverage area. At the same time, it adjusts the radar scanning strategy after the bird flock enters the risk area to improve the accuracy of data monitoring, so that the generated monitoring report has high accuracy and timeliness. Through the generated prevention and control command dataset, accurate early warning and prevention and control of bird activity can be achieved, effectively reducing the risk of bird strikes and ensuring aviation safety.

[0050] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0052] Figure 1 This is a schematic diagram illustrating the steps of a radar-based method for timely early warning and control of bird flocks at airports, according to an exemplary embodiment.

[0053] Figure 2 This is a schematic block diagram illustrating a radar-based early warning and control system for airport bird flocks, according to an exemplary embodiment. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0055] In one embodiment, Figure 1 This is a schematic diagram illustrating the steps of a radar-based early warning and control method for airport bird flocks, according to an exemplary embodiment. See also... Figure 1 This paper provides a method for timely early warning and control of bird flocks at airports based on radar monitoring, including:

[0056] Step S11: Use a pre-deployed radar monitoring system to scan the monitoring area in real time to obtain real-time dynamic data of bird activity; obtain data related to the location, number and movement trajectory of the bird flock from the scanned data, and integrate them into a monitoring dataset.

[0057] The deployed radar monitoring system has a large coverage area and can scan the area around the airport around the clock to obtain real-time dynamic data on bird activity. This data is then used to generate a monitoring dataset containing location, number, and movement trajectory information, providing preliminary information on bird distribution.

[0058] In practical applications, X-band or C-band high-frequency phased array radars are deployed, configured with multiple antenna arrays to achieve 360-degree scanning of a radius of approximately 10 kilometers around the airport. The radar units calculate the flight speed of the bird flock using the Doppler effect and combine this with echo intensity to determine target size and density, thereby establishing a preliminary three-dimensional bird flock activity model. The data acquisition frequency is set to twice per second to ensure sufficient temporal resolution and coverage accuracy. The acquired echo data is filtered, target extracted, and tracked using a digital signal processor (DSP) to form a standardized monitoring dataset, including individual bird coordinates, flight direction, velocity vector, and flock density parameters.

[0059] Step S12: Based on the monitoring dataset, generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area, and define risk areas based on the spatial mapping data; if it is determined from real-time dynamic data that a bird flock has entered a risk area, then generate dynamic adjustment parameters.

[0060] In practice, a rasterization algorithm is used to divide the monitoring area into fixed grid units (grids, such as 50×50 meters). Density-weighted interpolation is then performed based on the monitoring data to generate a spatial density distribution map in the form of a heatmap. Simultaneously, clustering based on an improved K-means algorithm is used to identify high-frequency areas of historical bird flock activity, forming a clustering hotspot database. The spatial density distribution map and the clustering hotspot database serve as spatial mapping data. Real-time data is compared with this spatial mapping data. If a bird flock enters a defined risk area, the system triggers a dynamic adjustment process. Adjustment parameters include the radar scan angle subdivision level, pulse repetition frequency (PRF), and the resolution gate width of the radar signal processing.

[0061] Step S13: Optimize and adjust the scanning strategy of the radar monitoring system according to the dynamic adjustment parameters; generate a real-time updated monitoring report based on real-time dynamic data.

[0062] In practical applications, by utilizing the above dynamically adjusted parameters and employing an embedded fuzzy control algorithm, the system comprehensively assesses factors such as target activity frequency, density, and movement trends to determine radar power allocation, scanning azimuth priority, and data transmission bandwidth configuration. Based on this, the system generates real-time monitoring reports that include not only routine bird flock information but also behavioral change trend analysis and risk level assessment indicators, providing a technical basis for downstream dynamic decision-making.

[0063] Step S14: Based on the real-time updated monitoring report, generate a prevention and control instruction dataset containing structured information to guide airport operation adjustments, and generate the final response plan based on the prevention and control instruction dataset.

[0064] In practice, step S14 integrates a rule-based reasoning mechanism to fuse and analyze real-time updated monitoring reports with airport operation plans (including takeoff and landing times and route distribution), generating a prevention and control instruction dataset based on priority. This dataset is output in structured JSON format and includes specific operational instructions such as suggested adjustments to flight times, activation areas for prevention and control equipment, and power recommendations for interfering equipment. It can be automatically connected to the airport operation control system via API to achieve a closed-loop response.

[0065] It is understood that the technical solution presented in this invention can utilize radar to scan the monitoring area in real time, obtain real-time dynamic data on bird activity, integrate it into a monitoring dataset, and then generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area, and define risk areas. If it is determined from the real-time dynamic data that a bird flock has entered a risk area, dynamic adjustment parameters are generated to optimize and adjust the scanning strategy of the radar monitoring system. A real-time updated monitoring report is generated based on the real-time dynamic data, and then a prevention and control command dataset is generated to generate the final response plan. The technical solution presented in this invention is based on radar monitoring of the target area, with accurate data and a large coverage area. At the same time, it adjusts the radar scanning strategy after the bird flock enters the risk area to improve the accuracy of data monitoring, so that the generated monitoring report has high accuracy and timeliness. Through the generated prevention and control command dataset, accurate early warning and prevention and control of bird activity can be achieved, effectively reducing the risk of bird strikes and ensuring aviation safety.

[0066] Preferably, when generating the monitoring dataset, the process further includes: using data cleaning techniques to remove noise and outliers from the monitoring dataset. This means that mean filtering, median filtering, and Z-score-based statistical methods are used to clean outlier data points and environmental noise in the initial monitoring dataset, thereby improving the accuracy of subsequent data processing.

[0067] In a preferred embodiment, step S12, when generating spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, further includes:

[0068] The data in the monitoring dataset is segmented into time series to generate bird activity fragments containing different time periods; based on the bird activity fragments, features of preset key indicators within each time period are extracted to obtain the activity characteristics of the bird flocks in each time period; when generating spatial mapping data, hotspot areas of different levels in different time periods are generated based on the activity characteristics.

[0069] In this embodiment, the cleaned data is divided according to time labels, and a sliding window mechanism is used to segment the bird flock activity data into time series segments. For example, every 10 minutes is considered an analysis segment, thus forming a continuous set of bird flock activity time segments. Subsequently, the system extracts features from key indicators such as changes in bird numbers, movement speed, and spatial density within each time period, calculates the corresponding activity feature parameters, and identifies bird flock behavior patterns in different time periods through cluster analysis. These activity features are marked as hotspot areas of different levels in the spatially mapped data image, serving as an important basis for risk identification.

[0070] In this preferred embodiment, the method further includes:

[0071] Cluster analysis is performed on fragmented bird activity data; environmental data of the monitoring area is obtained; environmental factor analysis is performed on the cluster analysis results and environmental data to obtain the activity characteristics of the bird flock and the activity pattern distribution of environmental factors; a bird flock activity prediction model under specific environmental conditions is established based on the activity pattern distribution; and the bird flock activity prediction model and the real-time dynamic data are used to determine whether the bird flock has entered the risk area.

[0072] This embodiment, building upon time series segmentation and feature extraction, further introduces a clustering algorithm and environmental factor fusion analysis mechanism. First, the cleaned bird activity fragment data are subjected to K-means or DBSCAN clustering analysis according to time periods. This analysis forms cluster centers based on bird numbers, speeds, densities, and activity areas, identifying typical activity patterns. Then, the system accesses real-time and historical meteorological databases around the airport to extract environmental data matching the corresponding time periods, including temperature, wind speed, wind direction, and humidity. Through correlation analysis (such as Pearson correlation coefficient, Spearman rank correlation, etc.) or multiple regression modeling, the mapping relationship between bird activity characteristics and environmental factor variables is identified, yielding the distribution of bird activity characteristics and environmental factor activity patterns, and establishing a predictive model for bird aggregation or migration under specific environmental conditions.

[0073] This embodiment combines cluster analysis results with environmental factor analysis to generate a set of multidimensional activity pattern distribution maps, showing the common activity locations, intensities, and behavioral patterns of bird flocks within specific temperature ranges or wind speed intervals. These multidimensional activity pattern distribution maps are further incorporated into the prediction of high-risk periods and areas, assisting the system in making early warning decisions under new meteorological conditions.

[0074] In this preferred embodiment, the method further includes:

[0075] The system acquires bird flock behavior records within a preset historical time span, extracts time elements, spatial elements, and activity characteristic elements from each record, fuses all extracted elements with the current bird flock activity pattern distribution, and constructs a three-dimensional feature matrix of time-space-behavior. Based on the three-dimensional feature matrix, it generates a feature dataset reflecting the bird flock activity trend; based on the feature dataset, it determines the peak activity period of the bird flock; and based on the peak activity period of the bird flock, it generates time period adjustment parameters for the radar monitoring system.

[0076] In practice, this implementation method, based on the identification of environmental factors and bird activity patterns, can further construct a comprehensive trend prediction model. First, the system collects bird behavior records spanning at least 12 months, with data sources including radar monitoring systems, manual observation reports, and third-party databases. For each record, elements such as time tags (hours, days of the week, months), spatial location (latitude and longitude, distance from the runway, etc.), and activity characteristics (number, flight altitude, speed) are extracted and fused with the current distribution of bird activity patterns. The system utilizes a multidimensional tensor structure to construct a three-dimensional feature matrix of time-space-behavior, and performs dimensionality reduction using principal component analysis (PCA) or t-SNE methods to extract representative feature factors.

[0077] The data in the three-dimensional feature matrix is ​​used to train a prediction model (such as an LSTM long short-term memory network or a random forest regression model) to model trends and identify high-frequency activity patterns under specific time periods (such as early morning or evening), seasonality (such as the spring migration season), and spatial location (such as the humid area east of the airport). Based on this, the system generates a feature dataset reflecting bird activity trends. This feature dataset is used to determine potential peak bird activity periods and to generate time-period adjustment parameters for the radar monitoring system based on these peak activity periods, so as to trigger corresponding monitoring frequencies and control response strategies.

[0078] In this preferred embodiment, the method further includes:

[0079] According to user instructions, thresholds for multiple key indicators of bird flock activity trends are set; if any key indicator of bird flock activity trends in the feature dataset exceeds the set threshold, the current feature dataset and historical feature datasets are jointly input into the machine learning model for secondary peak prediction, generating peak prediction results with time windows and corresponding probability values; high-risk periods are marked according to the peak prediction results; and high-risk period adjustment parameters for the radar monitoring system are generated according to the marked high-risk periods.

[0080] In practice, this embodiment, based on the construction of a feature dataset, further introduces a machine learning prediction mechanism to achieve accurate identification of peak activity periods of bird flocks.

[0081] The system first sets thresholds for several key indicators of activity trends, such as a daily average growth rate of bird populations exceeding 15%, an expansion of activity range exceeding a radius of 300 meters, or a risk index exceeding 70% for the corresponding historical time period. When any one or more of these key indicator thresholds are triggered, the system automatically invokes a trained machine learning model for further peak prediction. This model can employ algorithms such as Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), or Long Short-Term Memory (LSTM) networks to learn the temporal distribution characteristics based on the patterns of concentrated bird activity in historical data.

[0082] The prediction model takes current and historical feature datasets as input, including time, location, activity intensity, and weather parameters. The output is a set of predictions with a time window (e.g., 06:30–08:00) and corresponding probability values ​​(e.g., 87.3%). These results are used to label high-risk time periods, and the system dynamically adjusts radar scanning priority, pre-start time of control equipment, and monitoring frequency configuration accordingly to ensure optimal allocation of control resources during critical periods.

[0083] In this way, the system implements a data-driven proactive risk identification strategy, which makes the early warning mechanism more time-sensitive and predictive in terms of accuracy, thereby improving the airport's operational safety management capabilities during peak bird seasons.

[0084] In this preferred embodiment, the method further includes:

[0085] Time windows are determined based on peak bird activity periods or high-risk periods; data corresponding to the time windows are selected from real-time dynamic data and historical monitoring datasets, and spatial features are extracted, including the distribution of bird activity center points, density gradient changes, and trajectory concentration; based on the spatial features, a spatial density distribution map and a clustering hotspot database of bird activity are established within the monitoring area using a spatial aggregation algorithm, and risk areas are defined based on the spatial density distribution map and clustering hotspot database; an airport infrastructure layer is obtained, and the risk areas are located on the airport infrastructure layer.

[0086] In practice, this embodiment, after predicting peak periods, further introduces a spatial feature analysis mechanism to achieve precise location of bird gathering areas. The system first filters real-time monitoring data and historical comparative data within the corresponding time window based on peak bird activity periods or high-risk periods, extracting representative spatial features, including the distribution of bird activity center points, density gradient changes, and trajectory concentration. Using spatial aggregation algorithms (such as kernel density estimation, Voronoi diagram analysis, or hotspot identification algorithms), a bird activity heatmap is established in the area surrounding the airport, and the areas are marked. The spatial mapping results are refined into multiple risk level areas, each with specific geographic coordinate boundaries, historical bird density statistics, and behavioral trend curves. The system combines airport infrastructure layers (such as runways, taxiways, and terminal locations) to accurately locate high-risk areas on the airport operations map. This location information can be used to guide radar beam scheduling, optimize the deployment strategy of air defense equipment, and dynamically adjust flight takeoff and landing paths.

[0087] In a preferred embodiment, the method further includes: acquiring peak flight times at the airport and generating peak flight adjustment parameters for the radar monitoring system based on the peak flight times at the airport.

[0088] This embodiment adopts a time-priority weighting mechanism, which adjusts the radar scanning frequency according to the peak flight hours at the airport and limits the centralized allocation of scanning resources during high-risk periods.

[0089] In this implementation, the scanning strategy optimization module introduces a time-segment priority weighting mechanism to achieve dynamic allocation of radar resources and scanning task scheduling. The system first obtains the airport's daily flight operation plan, dividing the day into multiple time segments, such as the early morning segment (06:00–08:00), the midday segment (11:00–13:00), and the evening segment (17:00–19:00), and assigns weight values ​​to each time segment based on flight density, takeoff and landing frequency, and historical bird strike risk data. For example, a high-density flight segment can be assigned a weight value of 0.9, while a low-density segment is assigned only a value of 0.3.

[0090] The system associates radar scanning frequency, resolution, and scanning angle range with this weighting factor in its scanning strategy, forming dynamic parameter scheduling rules. Specifically, during high-weight periods, the system automatically increases the radar scanning frequency (e.g., from once per minute to once every 20 seconds), narrows the scanning angle range to improve spatial accuracy, and enhances the update frequency of the target tracking algorithm. Simultaneously, during off-peak periods, the system appropriately reduces radar resource utilization to maintain overall system energy consumption and load balance.

[0091] In addition, to achieve centralized resource allocation, a scanning resource scheduling table is set up in the system to control the spatio-temporal distribution of the radar scanning beam, and the tasks of multiple radars are preferentially scheduled to the overlapping area of high-risk areas and high-priority periods. This strategy enables the system to still cover key areas and key time points under limited resources, ensuring monitoring effectiveness and emergency response capabilities.

[0092] It should be noted that the method further includes:

[0093] The generated prevention and control instruction dataset includes information such as bird flock type, predicted path, risk level, recommended response timing, and intervention priority;

[0094] Send the prevention and control instruction dataset to the airport flight scheduling system and the ground operation system.

[0095] In this embodiment, the system not only outputs structured prevention and control instruction data, but also realizes connection with the airport operation control system through a preset communication interface to achieve automatic information transmission and system-level linkage response. This interface follows a unified data communication protocol (such as RESTful API or Socket communication standard), and supports data encapsulation in JSON or XML format, ensuring seamless parsing and reception of instruction content between different systems.

[0096] In the specific operation process, the prevention and control instruction generation module encapsulates the prevention and control instructions containing high-risk periods, regional coordinates, and recommended response measures (such as adjusting the takeoff order, postponing flight plans, activating bird repellent devices) into structured data packets, and sends them to the airport flight scheduling system and the ground operation system through the interface. The receiving-end system triggers corresponding logical judgments and operation processes according to the instruction information, such as automatically adjusting the shift plan, notifying the tower to change the flight path, and issuing early warning notices to ground personnel.

[0097] The prevention and control instruction dataset includes information such as bird flock type, predicted path, risk level, recommended response timing, and intervention priority to support the formulation of multi-level response strategies.

[0098] In this implementation manner, when generating the prevention and control instruction dataset, multi-dimensional information is integrated to construct structured response instructions to support the hierarchical response mechanism and strategy optimization. First, the system identifies and labels the bird flock type through radar echo features (such as target size, flight speed, reflection intensity) combined with the historical database, such as distinguishing migratory birds, water birds, or predatory bird species.

[0099] Based on the identification of bird species, the system predicts their future paths using their trajectory information and meteorological data, and determines whether there is any overlap with the airport's operating area. The system assigns a risk level to each individual or group of birds, comprehensively considering factors such as the number and species of birds, their trajectory, and flight density. It assesses the potential impact on operational safety using a risk scoring model (such as fuzzy logic or Bayesian networks) and expresses it as a numerical classification (such as high, medium, and low).

[0100] Simultaneously, the system dynamically provides suggested response times (such as "activate within 5 minutes" or "pre-process 30 minutes before takeoff") based on radar update cycles, bird flock speed, and response device activation times. It also assigns intervention priorities to various intervention methods (such as acoustic bird deterrence, laser intervention, and flight adjustments), comprehensively evaluating intervention costs, timeliness, and applicability. Ultimately, the generated prevention and control instruction dataset contains complete response strategy recommendations, supporting airport operations centers in implementing tiered handling strategies based on different risk levels.

[0101] It should be noted that the generation of the spatial density distribution map and hotspot database corresponding to the monitoring area also includes:

[0102] Based on a unified spatial resolution, the monitoring area is divided into regular grid units to obtain a geographic grid model. Data from the monitoring dataset is mapped to the corresponding grids in the geographic grid model. The number and density changes of bird flocks in each grid are statistically analyzed at unit time intervals. A spatiotemporal dynamic dataset is established based on the statistical data. Based on the spatiotemporal dynamic dataset, the data on the grid is smoothed to generate a risk heat map.

[0103] In this embodiment, the system first divides the monitoring area around the airport into regular grid units according to a uniform spatial resolution (e.g., 50m × 50m) to form a geographic grid model. The system maps the initial monitoring data collected by radar to the corresponding grids and counts the changes in the number and density of bird flocks in each grid at unit time intervals (e.g., every 10 minutes) to establish a spatiotemporal dynamic dataset.

[0104] Based on this, the system uses a kernel density estimation algorithm or a Gaussian spatial weighting method to smooth the raster data and generate a risk heatmap. The heatmap uses a color gradient visualization scheme to express the intensity and trend of bird activity, typically using blue to red to represent a gradual change from low to high density. It also incorporates a timeline to dynamically demonstrate changes in bird distribution over different time periods, forming a visualized time-series layer. This heatmap can be overlaid on an airport geographic information system (GIS) map to help operations personnel intuitively identify high-risk areas and their evolution paths.

[0105] In another embodiment, see Figure 2 This paper provides a radar-based airport bird flock timely early warning and control system, including:

[0106] The radar monitoring module is used to scan the monitoring area in real time using a pre-deployed radar monitoring system to obtain real-time dynamic data on bird activity; it also obtains data on the location, number, and movement trajectory of the birds from the scanned data and integrates them into a monitoring dataset.

[0107] The spatial mapping and comparison module is used to generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, and to define risk areas based on the spatial mapping data; if it is determined from real-time dynamic data that a bird flock has entered a risk area, dynamic adjustment parameters are generated.

[0108] The scanning strategy optimization module is used to optimize and adjust the scanning strategy of the radar monitoring system according to the dynamic adjustment parameters; and to generate a real-time updated monitoring report based on real-time dynamic data.

[0109] The prevention and control instruction generation module is used to generate a prevention and control instruction dataset containing structured information to guide airport operation adjustments based on real-time updated monitoring reports, and to generate the final response plan based on the prevention and control instruction dataset.

[0110] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0111] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0112] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0113] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0114] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0116] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0117] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0118] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for timely early warning and control of bird flocks at airports based on radar monitoring, characterized in that, include: The monitoring area is scanned in real time using a pre-deployed radar monitoring system to obtain real-time dynamic data on bird activity; The location, number, and movement trajectory of bird flocks were obtained from the scanned data and integrated into a monitoring dataset; Based on the monitoring dataset, spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area is generated, and risk areas are defined based on the spatial mapping data. If real-time dynamic data indicates that a flock of birds has entered a risk area, then dynamic adjustment parameters are generated. The scanning strategy of the radar monitoring system is optimized and adjusted according to the dynamic adjustment parameters. Generate real-time updated monitoring reports based on real-time dynamic data; Based on real-time updated monitoring reports, a prevention and control instruction dataset containing structured information to guide airport operation adjustments is generated, and a final response plan is generated based on the prevention and control instruction dataset. When generating spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, the method further includes: performing time series segmentation on the data in the monitoring dataset to generate bird activity fragment data containing different time periods; extracting features from preset key indicators within each time period based on the bird activity fragment data to obtain the activity characteristics of bird flocks within each time period; and generating hotspot areas of different levels in different time periods based on the activity characteristics when generating spatial mapping data. It also includes: dividing the monitoring area into regular grid units according to a uniform spatial resolution to obtain a geographic grid model; mapping the data in the monitoring dataset to the grids corresponding to the geographic grid model; statistically analyzing the changes in the number and density of bird flocks in each grid at unit time intervals; establishing a spatiotemporal dynamic dataset based on the statistical data; and smoothing the data on the grids based on the spatiotemporal dynamic dataset to generate a risk heat map.

2. The method according to claim 1, characterized in that, Also includes: Cluster analysis was performed on fragmented data of bird flock activities; Acquire environmental data for the monitoring area; By combining cluster analysis results with environmental data, environmental factor analysis was conducted to obtain the activity characteristics of bird flocks and the distribution of activity patterns of environmental factors. Based on the aforementioned activity patterns, a bird flock activity prediction model under specific environmental conditions is established; The bird flock activity prediction model and the real-time dynamic data are used to determine whether the bird flock has entered a risk area.

3. The method according to claim 2, characterized in that, Also includes: Obtain bird flock behavior records within a preset historical time span, and extract time elements, spatial elements, and activity characteristic elements from each bird flock behavior record; All extracted elements are fused with the current bird flock's activity patterns to construct a three-dimensional feature matrix of time, space, and behavior. Generate a feature dataset reflecting the activity trends of bird flocks based on the three-dimensional feature matrix; The peak activity periods of bird flocks are determined based on the aforementioned feature dataset; The radar monitoring system generates time-period adjustment parameters based on the peak activity periods of the bird flocks.

4. The method according to claim 3, characterized in that, Also includes: Thresholds for several key indicators of bird flock activity trends can be set according to user instructions; If any key indicator of bird flock activity trend in the feature dataset exceeds the set threshold, the current feature dataset and the historical feature dataset are jointly input into the machine learning model for secondary peak prediction, generating a peak prediction result with a time window and corresponding probability value. High-risk periods are marked based on the peak prediction results; Based on the marked high-risk time periods, generate adjustment parameters for the high-risk time periods of the radar monitoring system.

5. The method according to claim 4, characterized in that, Also includes: Time windows are determined based on peak bird activity periods or high-risk periods. Data corresponding to the time window is selected from real-time dynamic data and historical monitoring datasets, and spatial features are extracted. The extracted spatial features include the distribution of bird activity center points, density gradient changes, and trajectory concentration. Based on the spatial characteristics, a spatial density distribution map and a clustering hotspot database of bird activity are established within the monitoring area using a spatial aggregation algorithm. Risk areas are then defined based on the spatial density map and the clustering hotspot database. Obtain the airport infrastructure layer and locate the risk area on the airport infrastructure layer.

6. The method according to claim 1, characterized in that, Also includes: Obtain peak flight times at the airport and generate peak flight adjustment parameters for the radar monitoring system based on these times.

7. The method according to claim 1, characterized in that, Also includes: The generated prevention and control instruction dataset includes information on bird flock type, expected path, risk level, recommended response timing, and intervention priority. The aforementioned prevention and control instruction dataset is sent to the airport flight scheduling system and ground operation system.

8. A timely early warning and control system for airport bird flocks based on radar monitoring, characterized in that, include: The radar monitoring module is used to scan the monitoring area in real time using a pre-deployed radar monitoring system to obtain real-time dynamic data on bird activity. The location, number, and movement trajectory of bird flocks were obtained from the scanned data and integrated into a monitoring dataset; The spatial mapping and comparison module is used to generate spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, and to define risk areas based on the spatial mapping data. If real-time dynamic data indicates that a flock of birds has entered a risk area, then dynamic adjustment parameters are generated. When generating spatial mapping data that reflects the spatial density distribution and gathering hotspots of bird flocks in the monitoring area based on the monitoring dataset, the method further includes: performing time series segmentation on the data in the monitoring dataset to generate bird activity fragment data containing different time periods; extracting features from preset key indicators within each time period based on the bird activity fragment data to obtain the activity characteristics of bird flocks within each time period; and generating hotspot areas of different levels in different time periods based on the activity characteristics when generating spatial mapping data. It also includes: dividing the monitoring area into regular grid units according to a uniform spatial resolution to obtain a geographic grid model; mapping the data in the monitoring dataset to the grids corresponding to the geographic grid model; statistically analyzing the changes in the number and density of bird flocks in each grid at unit time intervals; establishing a spatiotemporal dynamic dataset based on the statistical data; and smoothing the data on the grids based on the spatiotemporal dynamic dataset to generate a risk heat map. The scanning strategy optimization module is used to optimize and adjust the scanning strategy of the radar monitoring system according to the dynamic adjustment parameters; and to generate a real-time updated monitoring report based on real-time dynamic data. The prevention and control instruction generation module is used to generate a prevention and control instruction dataset containing structured information to guide airport operation adjustments based on real-time updated monitoring reports, and to generate the final response plan based on the prevention and control instruction dataset.

Images