A civil aviation wind shear and visibility warning method

Abstract

The present invention discloses a civil aviation wind shear and visibility warning method, comprising the following steps: collecting echo signals by using a high-precision coherent lidar with high spatio-temporal resolution, and simultaneously obtaining civil aviation meteorological conventional observation data; calculating the wind field distribution through a wind field inversion algorithm, and calculating the visibility distribution through a visibility inversion algorithm; positioning the wind shear area by using a wind shear identification algorithm, analyzing the spatio-temporal evolution trend of visibility and generating a visibility profile in combination with a spatio-temporal deduction algorithm; inputting the wind shear identification data, visibility profile data and meteorological conventional observation data into a machine learning model for modeling and training; generating a wind shear and visibility warning scheme over the airport based on the trained prediction model; generating a wind shear warning signal and a visibility warning information based on the warning scheme, and outputting them to the civil aviation meteorological warning system. The present invention can achieve high-precision joint warning of wind shear and visibility, and improve the warning accuracy under complex weather conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of aviation meteorology, and particularly to a civil aviation wind shear and visibility warning method. Background Art

[0002] In civil aviation operations, wind shear and low visibility are important meteorological factors affecting flight safety. Especially during the takeoff and landing phases of an aircraft, wind shear may cause sudden changes in flight attitude, excessive vertical acceleration, and flight trajectory deviation, while low visibility reduces the pilot's situational awareness and increases the risk of approach and landing. Therefore, accurately warning of wind shear and visibility changes is crucial for ensuring aviation safety.

[0003] Currently, the detection of wind shear mainly relies on ground Doppler weather radars, wind profilers, and the aircraft's own meteorological sensors. However, these methods have problems such as limited spatio-temporal resolution, limited detection range, and lagging response speed, making it difficult to meet the rapid warning requirements under complex meteorological conditions. In addition, the measurement of visibility usually relies on ground visibility meters and meteorological station observation data. Although these methods can provide relatively accurate point measurement results, they lack the ability to predict the spatio-temporal evolution trend of visibility. Especially in environmental conditions greatly affected by humidity and aerosols, traditional methods often have difficulty accurately retrieving the large-scale visibility distribution and predicting its future change trend. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A civil aviation wind shear and visibility warning method, comprising the following steps:

[0006] Collect echo signals using a high-precision, high spatio-temporal resolution coherent lidar, extract the frequency and intensity information in the echo signals, and simultaneously obtain the civil aviation meteorological routine observation data;

[0007] For the extracted frequency information, calculate the wind field distribution through a wind field inversion algorithm, and for the extracted intensity information, calculate the visibility distribution through a visibility inversion algorithm;

[0008] Based on the wind field inversion result, use a wind shear identification algorithm to locate the wind shear area and output the wind shear identification data. At the same time, based on the visibility inversion result, analyze the spatio-temporal evolution trend of visibility by combining a spatio-temporal deduction algorithm to generate a visibility profile and output the visibility profile data;

[0009] Input the wind shear identification data, visibility profile data, and routine meteorological observation data into a machine learning model for modeling training;

[0010] Based on the trained prediction model, generate a wind shear and visibility warning plan over the airport;

[0011] Generate a wind shear warning signal and visibility warning information based on the warning plan, and output them to the civil aviation meteorological warning system.

[0012] As a preferred solution of the civil aviation wind shear and visibility warning method described in the present invention, wherein: for the extracted frequency information, calculate the wind field distribution through a wind field inversion algorithm, including the following steps:

[0013] Preprocess the echo signal collected by a high-precision high-temporal and spatial resolution coherent lidar;

[0014] Use signal processing techniques to perform frequency spectrum analysis on the preprocessed echo signal;

[0015] Calculate the wind speed distribution along the lidar beam direction;

[0016] Combine the data in multiple lidar measurement directions and use the optimal interpolation method to invert the three-dimensional wind field vector distribution;

[0017] Fuse the wind field inversion result with the routine civil aviation meteorological observation data to correct the wind field error.

[0018] As a preferred solution of the civil aviation wind shear and visibility warning method described in the present invention, wherein: for the extracted intensity information, calculate the visibility distribution through a visibility inversion algorithm, including the following steps:

[0019] Preprocess the echo intensity signal collected by the coherent lidar;

[0020] Based on Mie scattering theory, use the atmospheric extinction coefficient and visibility to calculate the visibility, and the formula is:

[0021] ,

[0022] wherein, the extinction coefficient is inversely obtained by solving the lidar equation, and specifically, the Klett method or the Fernald method is used;

[0023] Combine the routine meteorological observation data to perform humidity correction and aerosol compensation on the visibility.

[0024] As a preferred embodiment of the civil aviation wind shear and visibility warning method of the present invention, wherein: the humidity correction for visibility includes the following steps:

[0025] Obtain the relative humidity through the meteorological station observation data;

[0026] Perform correction using the humidity growth factor, and the calculation formula is as follows:

[0027] ,

[0028] where, is the current relative humidity, is the reference humidity, is the empirical coefficient;

[0029] When the humidity is greater than the set value, introduce a non-linear correction model, such as:

[0030] ,

[0031] where, is the correction factor related to the environment;

[0032] Then, correct the extinction coefficient through the humidity growth factor , and the correction formula is:

[0033] ,

[0034] where, is the original extinction coefficient measured by lidar; is the extinction coefficient after humidity correction;

[0035] Finally, calculate the corrected visibility, that is, substitute into the Koschmieder formula to calculate the visibility.

[0036] As a preferred embodiment of the civil aviation wind shear and visibility warning method of the present invention, wherein: the aerosol compensation for visibility includes the following steps:

[0037] Obtain the aerosol optical depth AOD through the meteorological station observation data, and estimate the aerosol scattering coefficient in combination with the PM2.5 / PM10 monitoring data:

[0038] ,

[0039] where, and are empirical coefficients based on the regional environmental experience values; is the particulate matter concentration;

[0040] Use the Ångström exponent to correct the aerosol scattering coefficient:

[0041] ,

[0042] Among them, is the working wavelength of the lidar, is the reference wavelength, is the Angström exponent;

[0043] Calculate the extinction coefficient after aerosol compensation. When calculating, first calculate the aerosol compensation factor, and then calculate the corrected extinction coefficient according to the aerosol compensation factor; among them, the calculation formulas for the aerosol compensation factor and the corrected extinction coefficient are as follows:

[0044] ,

[0045] ,

[0046] Among them, is the empirical adjustment coefficient;

[0047] Substitute into the Koschmieder formula to calculate the visibility after aerosol compensation. The formula is as follows:

[0048] ,

[0049] Among them, is the visibility after aerosol compensation. The visibility data after aerosol compensation can avoid misjudgment caused by aerosol interference.

[0050] As a preferred scheme of the civil aviation wind shear and visibility warning method described in the present invention, among them: Calculate the visibility by combining the humidity correction and aerosol compensation. The calculation formula is as follows:

[0051] ,

[0052] Among them, is the visibility after humidity correction and aerosol compensation. By calculating the visibility data after humidity correction and aerosol compensation, the reliability of the warning is improved.

[0053] As a preferred scheme of the civil aviation wind shear and visibility warning method described in the present invention, among them: For the wind field inversion result, use the wind shear identification algorithm to detect the wind shear area and output the wind shear identification data, including the following steps:

[0054] Perform spatial grid division on the three-dimensional wind field data, and set vertical section grids along the airport runway and takeoff and landing path;

[0055] Calculate the wind speed gradient and wind direction mutation angle of adjacent grid cells, and set the thresholds for the wind speed gradient and wind direction mutation angle;

[0056] If a certain area simultaneously meets the wind speed gradient and wind direction mutation angle thresholds, it is marked as a potential wind shear area;

[0057] Perform time persistence verification on the potential wind shear area to eliminate transient interference;

[0058] Combined with the historical wind shear event database, determine the final wind shear area and its danger level through spatial pattern matching;

[0059] Integrate the spatial position, wind speed gradient value, wind direction mutation angle, duration, and corresponding danger level of the final wind shear area to generate wind shear identification data, which is used as the input of the warning model.

[0060] As a preferred solution of the civil aviation wind shear and visibility warning method described in the present invention, wherein: the threshold of the wind speed gradient is set such that the wind speed change per 100 meters in the horizontal direction is not less than 15 knots, or the wind speed change per 50 meters in the vertical direction is not less than 10 knots; the wind direction mutation angle threshold is set to ≥30°.

[0061] As a preferred solution of the civil aviation wind shear and visibility warning method described in the present invention, wherein: based on the visibility inversion result, analyze the spatio-temporal evolution trend of visibility by combining spatio-temporal deduction algorithms to generate a visibility profile, and output visibility profile data, including the following steps:

[0062] Input the visibility data inverted by lidar and the meteorological station observation data into the spatio-temporal Kriging model to generate a visibility spatio-temporal cube for the airport area;

[0063] Based on the visibility spatio-temporal cube, extract the visibility spatio-temporal profile along the flight takeoff and landing path, and predict the future visibility change trend by the optical flow method;

[0064] Perform morphological dilation processing on the low visibility area to identify continuous dangerous areas;

[0065] Combine the spatio-temporal changes of humidity and aerosol data to correct the prediction result of the optical flow method and generate a visibility evolution probability map;

[0066] Based on the visibility evolution probability map, extract the visibility profile on the flight path and mark the mutation points and continuous low visibility sections;

[0067] Integrate the spatial position, prediction time, visibility numerical distribution, mutation point position, and low value section information of the visibility profile to generate visibility profile data, which is used as one of the input data sources of the warning model.

[0068] As a preferred solution of the civil aviation wind shear and visibility warning method described in the present invention, wherein: the extraction of the visibility spatio-temporal profile includes the following steps:

[0069] Set spatial sampling lines according to airport runways and standard arrival and departure procedures to ensure coverage of critical flight phases;

[0070] Based on the generated visibility spatio-temporal cube, perform three-dimensional linear interpolation along the path to obtain a continuous visibility spatio-temporal distribution;

[0071] Taking the horizontal distance as the abscissa, the height as the ordinate, and the time series as the third dimension, construct a visibility spatio-temporal profile to characterize the vertical distribution and time evolution characteristics of visibility along the airway.

[0072] Advantages of the present invention:

[0073] 1. The present invention accurately locates the wind shear area through the wind field inversion algorithm and the wind shear identification algorithm. At the same time, by combining the visibility inversion algorithm and the visibility spatio-temporal deduction algorithm with humidity correction and aerosol compensation, it dynamically predicts the visibility evolution trend of the key airway of the airport, so as to achieve high-precision joint warning of wind shear and visibility and improve the warning accuracy under complex weather conditions;

[0074] 2. The present invention uses the optical flow method to predict the future visibility change trend and combines the humidity and aerosol influence factors for dynamic correction to achieve short-term visibility warning. By morphological dilation processing of the low-value area, it accurately marks the low visibility mutation points and the continuously low visibility segments, so as to provide a more accurate visibility evolution prediction for aircraft approach and landing. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0076] Figure 1 is a flow chart of a civil aviation wind shear and visibility warning method of the present invention;

[0077] Figure 2 is a flow chart of calculating the wind field distribution through the wind field inversion algorithm of a civil aviation wind shear and visibility warning method of the present invention;

[0078] Figure 3 is a flow chart of calculating the visibility distribution through the visibility inversion algorithm of a civil aviation wind shear and visibility warning method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0079] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification.

[0080] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0081] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or alternative embodiment that mutually excludes other embodiments.

[0082] Furthermore, the present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure are enlarged locally not in accordance with the general scale, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0083] Embodiment 1

[0084] Referring to Figures 1-3 , for an embodiment of the present invention, a civil aviation wind shear and visibility warning method is provided, including the following steps:

[0085] S1: Use a high-precision and high spatio-temporal resolution coherent lidar to collect echo signals, extract the frequency and intensity information in the echo signals, and simultaneously obtain civil aviation meteorological routine observation data to provide more comprehensive and accurate information for subsequent meteorological analysis and warning.

[0086] Specifically, the civil aviation meteorological routine observation data includes information such as surface wind, visibility, precipitation, temperature, humidity, and pressure, and is subjected to zonal noise filtering to improve the data quality.

[0087] It should be noted that the high-precision and high spatio-temporal resolution coherent lidar is an advanced remote sensing detection device. High precision means that the error of its measurement results is small and it can provide accurate meteorological parameter information; high spatio-temporal resolution means that the lidar has high resolution capabilities in both the time and space dimensions, and can perform multiple observations on a small area in a short time, thereby capturing the rapid changes and subtle differences of meteorological elements. The coherent lidar emits a laser beam and receives the echo signal reflected by the target, and uses coherent detection technology to extract the frequency and intensity information in the echo signal, which belongs to the prior art and will not be elaborated in detail herein.

[0088] S2: For the extracted frequency information, calculate the wind field distribution through a wind field inversion algorithm, and for the extracted intensity information, calculate the visibility distribution through a visibility inversion algorithm.

[0089] S21: For the extracted frequency information, calculate the wind field distribution through a wind field inversion algorithm, including the following steps:

[0090] S211: Denoise, filter, and normalize the echo signals collected by a high-precision high spatio-temporal resolution coherent lidar to improve the signal quality and provide a reliable data basis for subsequent analysis.

[0091] S212: Use signal processing techniques, such as fast Fourier transform or wavelet transform and other signal processing techniques, to perform frequency spectrum analysis on the preprocessed echo signals, and accurately extract the Doppler frequency shift information in the signals. These frequency shift information reflect the motion state of particles in the atmosphere and are the key basis for subsequent wind speed calculation.

[0092] S213: Based on the Doppler frequency shift formula calculate the wind speed distribution along the lidar beam direction, where is the laser wavelength, is the Doppler frequency shift. Through this formula, the frequency shift information can be converted into actual wind speed values to obtain the wind speed distribution along the beam direction.

[0093] S214: Combine the data measured in multiple lidar directions and use the optimal interpolation method to invert the three-dimensional wind field vector distribution.

[0094] It should be noted that the optimal interpolation method is an objective analysis method based on the least squares principle and is an existing technology that has been widely used in the assimilation and inversion of meteorological data. Through this method, the three-dimensional wind field vector distribution can be accurately inverted. The three-dimensional wind field vector distribution contains spatially gridded data of wind speed magnitude and direction and is used for subsequent wind shear identification.

[0095] S215: Integrate the wind field inversion results with the civil aviation meteorological routine observation data to perform wind field error correction and improve the accuracy of the wind field distribution. The wind field error correction can be implemented using existing technologies and will not be elaborated in detail here.

[0096] S22: For the extracted intensity information, calculate the visibility distribution through a visibility inversion algorithm, including the following steps:

[0097] S221: Preprocess the echo intensity signals collected by the coherent lidar.

[0098] During preprocessing, first, a noise filtering algorithm is used to accurately remove the background noise in the signal, effectively reducing the interference of noise on subsequent calculations. Then, a normalization method is adopted to adjust the echo intensity signal to a unified dimension and range, ensuring the comparability of signals at different times and positions, and laying a foundation for accurate subsequent calculations.

[0099] S222: Based on Mie scattering theory, calculate the visibility using the correlation between the atmospheric extinction coefficient and the visibility . The formula is:

[0100] ,

[0101] where the extinction coefficient is obtained by inverting the lidar equation, specifically using the Klett method or the Fernald method.

[0102] S223: Combine conventional meteorological observation data (such as humidity, aerosol concentration) to perform humidity correction and aerosol compensation on the visibility, so as to improve the accuracy of visibility measurement, help predict weather changes more accurately, and can help pilots and air traffic controllers better understand the weather conditions around the airport and make safer flight decisions.

[0103] Specifically, the humidity correction and aerosol compensation for the visibility include the following steps:

[0104] When performing humidity correction:

[0105] Obtain the relative humidity (RH) through meteorological station observation data;

[0106] Use the humidity growth factor for correction. The calculation formula is as follows:

[0107] ,

[0108] where is the current relative humidity (%), is the reference humidity, usually taken as 50%, is the empirical coefficient, generally taken as 0.6 - 1.2, depending on the type of environmental aerosol.

[0109] When the humidity is greater than the set value, the set value is set to 80%, that is, when > 80%, introduce a non-linear correction model, such as:

[0110] ,

[0111] where is the correction factor related to the environment, usually taken as 0.1 - 0.3.

[0112] Then, correct the extinction coefficient through the humidity growth factor :

[0113] ,

[0114] where is the original extinction coefficient measured by lidar; is the extinction coefficient after humidity correction.

[0115] Finally, calculate the corrected visibility by substituting into the Koschmieder formula to calculate the visibility:

[0116] ,

[0117] When performing aerosol compensation:

[0118] Obtain the aerosol optical depth (AOD) from the meteorological station observation data, and estimate the aerosol scattering coefficient in combination with the PM2.5 / PM10 monitoring data:

[0119] ,

[0120] where: and are empirical coefficients based on the regional environmental empirical values; is the particulate matter concentration ( ).

[0121] Use the Ångström exponent to correct the aerosol scattering coefficient:

[0122] ,

[0123] where is the lidar operating wavelength (such as 355 nm, 532 nm); is the reference wavelength, usually taken as 550 nm; is the Ångström exponent, generally taken as 1.0 - 1.5.

[0124] Calculate the extinction coefficient after aerosol compensation. When calculating, first calculate the aerosol compensation factor, and then calculate the corrected extinction coefficient according to the aerosol compensation factor. Among them, the aerosol compensation factor and the corrected extinction coefficient calculation formulas are as follows:

[0125] ,

[0126] ,

[0127] where is the empirical adjustment coefficient, usually taken as 0.1 - 0.3.

[0128] Substitute into the Koschmieder formula to calculate the visibility after aerosol compensation:

[0129] ,

[0130] where, is the visibility after aerosol compensation. The visibility data after aerosol compensation can avoid misjudgment caused by aerosol interference.

[0131] Finally, combine humidity correction and aerosol compensation to calculate the visibility. The calculation formula is as follows:

[0132] ,

[0133] where, is the visibility after humidity correction and aerosol compensation. By calculating the visibility data after humidity correction and aerosol compensation, the reliability of early warning can be improved.

[0134] The above method of humidity correction + aerosol compensation improves the accuracy of visibility inversion under extreme weather conditions, thus ensuring the reliability of low visibility warning at the airport.

[0135] S3: Based on the wind field inversion result, use the wind shear identification algorithm to locate the wind shear area and output the wind shear identification data. At the same time, based on the visibility inversion result, combine the spatio-temporal deduction algorithm to analyze the spatio-temporal evolution trend of visibility to generate a visibility profile and output the visibility profile data.

[0136] Specifically, based on the wind field inversion result, using the wind shear identification algorithm to detect the wind shear area includes the following steps:

[0137] S311: Conduct spatial grid division on the three-dimensional wind field data, and set vertical profile grids along the airport runway and takeoff and landing paths (horizontal resolution ≤ 100 m, vertical resolution ≤ 50 m).

[0138] S312: Calculate the wind speed gradient and wind direction mutation angle of adjacent grid cells.

[0139] Specifically, the wind speed gradient threshold is set to ≥ 15 knots / 100 m (horizontal) or ≥ 10 knots / 50 m (vertical);

[0140] The wind direction mutation angle threshold is set to ≥ 30°.

[0141] When the wind speed gradient and wind direction mutation in a certain area reach the preset threshold at the same time, that is, the horizontal wind speed change within 100 meters is not less than 15 knots, or the vertical wind speed change within 50 meters is not less than 10 knots, and the wind direction change angle between adjacent grid cells is not less than 30°, the area will be marked as a potential wind shear area.

[0142] For the marked potential wind shear areas, further time continuity verification is required. Specifically, it is necessary to confirm whether the wind shear phenomenon in the area persists for at least 2 minutes, so as to eliminate misjudgments caused by transient interference and ensure the accuracy of the identification results.

[0143] After confirming the time persistence of the potential wind shear area, it is necessary to combine the historical wind shear event database and use spatial pattern matching technology to conduct a detailed analysis of the potential area. By comparing historical data with current observation data, the specific scope of the wind shear area is finally determined, and the danger level is scientifically divided into low, medium and high levels according to its impact and potential risks, providing a strong basis for subsequent risk prevention and response measures.

[0144] The spatial position of the final wind shear area, wind speed gradient value, wind direction mutation angle, duration and corresponding danger level are integrated to generate wind shear identification data. The wind shear identification data is used to describe the spatial distribution characteristics and intensity change characteristics of wind shear over the airport, and serves as the input of the early warning model.

[0145] Furthermore, based on the visibility inversion results, the spatiotemporal evolution trend of visibility is analyzed and the visibility profile is generated by combining the spatiotemporal deduction algorithm, including the following steps:

[0146] S321: Input the visibility data of discrete points (visibility data inverted by lidar and observation data of meteorological stations) into the space-time Kriging model to generate the visibility space-time cube of the airport area (time resolution ≤ 5 minutes, spatial resolution ≤ 200m).

[0147] It should be noted that the space-time Kriging model is an extension of the traditional Kriging method in the space-time dimension. Its core is to model the coupling of spatial correlation and temporal correlation through the space-time covariance function. This method can simultaneously consider the data correlation in time and space, and perform linear unbiased optimal estimation of unsampled points. Generating the visibility space-time cube of the airport area through the space-time Kriging model can help improve the operating efficiency and safety of the airport and reduce the risk of flight delays and accidents caused by low visibility weather. It belongs to the existing technology and will not be described in detail here.

[0148] S322: Based on the visibility space-time cube, the visibility space-time profile is extracted along the flight take-off and landing path, and the visibility change trend in the next 15-30 minutes is predicted by the optical flow method.

[0149] Specifically, the extraction of the visibility spatio-temporal profile includes the following steps:

[0150] Set spatial sampling lines according to the airport runway and standard arrival and departure procedures (such as the ILS approach path) to ensure coverage of key flight phases, such as takeoff, approach, and landing;

[0151] Based on the generated visibility spatio-temporal cube, perform three-dimensional linear interpolation along the path to obtain a continuous visibility spatio-temporal distribution;

[0152] Taking the horizontal distance (along the runway axis) as the abscissa, the altitude (AGL) as the ordinate, and the time series as the third dimension, construct a visibility spatio-temporal profile to characterize the vertical distribution and time evolution characteristics of visibility along the route.

[0153] S323: Perform morphological dilation on the low visibility area (≤1000m) to identify continuous dangerous areas. This morphological dilation method uses well-known techniques in the field and can refer to Section 4.3 (Identification of Hazardous Weather Areas) of ICAO Doc 9837 "Aeronautical Meteorological Information Manual" and Chapter 16 (Spatial Analysis of Meteorological Data) of WMO-No.1200 "Meteorological Instruments and Methods of Observation".

[0154] S324: Combine the spatio-temporal variations of humidity and aerosol data to correct the prediction results of the optical flow method and generate a visibility evolution probability map. The generation of the visibility evolution probability map uses ensemble forecasting techniques. References: Zhou et al. "Atmospheric Environment" 2021 (Aerosol-Visibility Relationship Model).

[0155] S325: Based on the visibility evolution probability map, extract the visibility profile on the flight path and mark the mutation points (areas with a probability space gradient ≥ 0.2% / m) and continuously low visibility segments (continuous segments with a probability > 70% and a duration ≥ 10 minutes). The profile extraction and marking methods use the standard processing procedures in aeronautical meteorological services (see Annex C of ICAO Annex 3).

[0156] S326: Integrate the spatial position, prediction time, visibility value distribution, mutation point position, and low value section information of the visibility profile to generate visibility profile data, which is used to depict the visibility change trend along the route and serve as one of the input data sources for the early warning model.

[0157] S4: Input the wind shear identification data, visibility profile data, and meteorological routine observation data into a machine learning model for modeling and training.

[0158] Specifically, inputting wind shear recognition data, visibility profile data, and conventional meteorological observation data into a machine learning model for modeling and training includes the following steps:

[0159] S41: Clean, denoise, normalize, and align the wind shear recognition data, visibility profile data, and conventional meteorological observation data to ensure consistent data quality and eliminate outliers, providing reliable input for subsequent feature extraction and training.

[0160] S42: Extract key features (core variables affecting wind shear and visibility changes) from the preprocessed data, such as wind shear gradient, spatio-temporal visibility change rate, meteorological element correlation parameters, etc., and perform dimensionality reduction and feature selection. Among them, the dimensionality reduction process uses the principal component analysis method to reduce the data dimension and retain the main information. Feature selection adopts recursive feature elimination or feature importance evaluation based on the tree model to screen the most predictive features and improve the model training efficiency.

[0161] S43: Divide the data into a training set, a validation set, and a test set according to the ratio of 7:1.5:1.5, and label the categories or severity levels of wind shear and low visibility events based on the historical meteorological event library, providing reliable labels for supervised learning.

[0162] S44: Select the Generalized Regression Neural Network (GRNN) as the basic model to construct a prediction model, and define the loss function, optimization method, and hyperparameters.

[0163] Define the loss function, that is, according to the task requirements, select the mean square error or cross-entropy loss function to measure the difference between the predicted value and the true value of the crossbeam. The optimization method uses the Adam optimizer, combined with the learning rate decay strategy, to accelerate the model convergence. The hyperparameter settings can be determined by network search or random search to determine key hyperparameters such as the smoothing factor of GRNN.

[0164] S45: Use the training set for multiple rounds of iterative training, adjust the model parameters through the gradient descent algorithm, and combine K-fold cross-validation to evaluate the performance of the model on different data subsets to prevent overfitting. Set the performance monitoring on the validation set, and stop training in advance when the performance no longer improves to avoid overfitting.

[0165] S46: Calculate metrics such as prediction error, confusion matrix, and AUC-ROC on the test set to comprehensively evaluate the model performance. According to the evaluation results, adjust the model structure (such as adding hidden layers, changing activation functions) or hyperparameters (such as learning rate, regularization coefficient) to optimize the model effect.

[0166] S47: Integrate multiple GRNN models for ensemble learning, and adopt weighted average or voting mechanism to improve the prediction stability and accuracy, so as to obtain the final GRNN neural network prediction model. Then deploy the final prediction model to the warning system interface.

[0167] Through the above steps, a more accurate and efficient joint warning model for wind shear and visibility can be constructed.

[0168] S5: Generate a warning plan for wind shear and visibility over the airport based on the trained prediction model.

[0169] S6: Generate a wind shear warning signal and a visibility warning message based on the warning plan, and output them to the civil aviation meteorological warning system.

[0170] In summary, the present invention is based on the fusion of multi-source data such as coherent lidar and civil aviation meteorological observation data, and combines machine learning models. Through the wind field inversion algorithm and the wind shear identification algorithm, the wind shear area is accurately located. At the same time, the visibility inversion algorithm and the visibility spatio-temporal deduction algorithm are used to combine humidity correction and aerosol compensation to dynamically predict the evolution trend of visibility on the key routes of the airport, so as to realize the joint warning of high-precision wind shear and visibility and improve the warning accuracy under complex weather conditions. The present invention generates a visibility spatio-temporal cube of the airport area through the spatio-temporal Kriging model to realize the continuous change modeling of visibility over time and space, uses the optical flow method to predict the future visibility change trend and combines humidity and aerosol influence factors for dynamic correction to realize minute-level short-term visibility warning, and accurately marks low visibility mutation points and continuous low visibility segments through morphological dilation processing of the low value area, so as to provide a more accurate visibility evolution prediction for aircraft approach and landing. The present invention constructs a humidity correction method based on the humidity growth factor and the non-linear correction model to solve the problem of low visibility calculation under high humidity conditions. At the same time, an aerosol compensation method combining Angström exponent correction and aerosol optical depth (AOD) parameterization model is adopted to reduce the visibility error caused by polluted weather, and a unified visibility correction formula is constructed by integrating the dynamic compensation factors of humidity and aerosol, so as to achieve adaptive correction under different environmental conditions and improve the visibility inversion accuracy under extreme weather conditions, ensuring the reliability of low visibility warning at the airport.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A civil aviation wind shear and visibility early warning method, characterized in that: The following steps are involved: Use high-precision, high-temporal and high-resolution coherent laser radar to collect echo signals, extract frequency and intensity information from echo signals, and simultaneously obtain routine civil aviation meteorological observation data; Based on the extracted frequency information, the wind field distribution is calculated by the wind field inversion algorithm, and based on the extracted intensity information, the visibility distribution is calculated by the visibility inversion algorithm; Based on the wind field inversion results, the wind shear identification algorithm is used to locate the wind shear area and output the wind shear identification data. At the same time, based on the visibility inversion results, the spatiotemporal evolution trend of visibility is analyzed in combination with the spatiotemporal deduction algorithm to generate the visibility profile and output the visibility profile data; Inputting the wind shear identification data, visibility profile data and conventional meteorological observation data into a machine learning model for modeling training; Generate wind shear and visibility warning plans over the airport based on the trained prediction model; Generate wind shear warning signals and visibility warning information based on the warning scheme, and output them to the civil aviation meteorological warning system; Among them, based on the visibility inversion result, combining the spatiotemporal deduction algorithm to analyze the spatiotemporal evolution trend of visibility to generate a visibility profile, and outputting the visibility profile data, the following steps are included: The visibility data inverted by LiDAR and the observation data of the weather station are input into the space-time Kriging model to generate the visibility space-time cube of the airport area; Based on the visibility space-time cube, the visibility space-time profile is extracted along the flight take-off and landing path, and the future visibility change trend is predicted by the optical flow method; Perform morphological expansion processing on low visibility areas to identify continuous dangerous areas; Combining the spatiotemporal changes of humidity and aerosol data, the prediction results of the optical flow method are corrected to generate a visibility evolution probability map; Based on the visibility evolution probability map, the visibility profile on the flight path is extracted, and the mutation points and continuous low visibility sections are marked; The spatial position, forecast time, visibility value distribution, mutation point position and low-value section information of the visibility profile are integrated to generate visibility profile data as one of the input data sources of the early warning model.

2. The civil aviation wind shear and visibility early warning method according to claim 1, characterized in that: The method of calculating the wind field distribution by using a wind field inversion algorithm for the extracted frequency information comprises the following steps: Preprocess the echo signals collected by high-precision and high-temporal and high-spatial resolution coherent lidar; Using signal processing technology, frequency spectrum analysis is performed on the pre-processed echo signal; Calculate the wind speed distribution along the LiDAR beam direction; Combining data from multiple LiDAR measurement directions, the three-dimensional wind field vector distribution is inverted using the optimal interpolation method; The wind field inversion results are integrated with the conventional civil aviation meteorological observation data to correct the wind field errors.

3. The civil aviation wind shear and visibility early warning method according to claim 1, characterized in that: The method of calculating the visibility distribution by using a visibility inversion algorithm for the extracted intensity information comprises the following steps: Preprocessing the echo intensity signal collected by the coherent laser radar; Based on Mie scattering theory, using the atmospheric extinction coefficient and visibility The visibility is calculated by the correlation relationship, and the formula is: Among them, 3.912 is a fixed constant, which reflects the human eye's ability to perceive contrast. is the extinction coefficient, which is obtained by solving the lidar equation inversion, specifically using the Klett method or the Fernald method; The visibility is corrected for humidity and compensated for aerosols in combination with routine meteorological observation data.

4. The civil aviation wind shear and visibility early warning method according to claim 3, characterized in that: The humidity correction for visibility comprises the following steps: Relative humidity is obtained through weather station observation data; The humidity growth factor is used for correction, and the calculation formula is as follows: in, is the current relative humidity, is the base humidity, is the empirical coefficient; When the humidity is greater than the set value, a nonlinear correction model is introduced; in, is the correction factor related to the environment; Then, the humidity growth factor Correct the extinction coefficient, the correction formula is: in, is the original extinction coefficient, measured by lidar; is the extinction coefficient after humidity correction; Finally, calculate the corrected visibility, which is Substitute into Koschmieder formula to calculate visibility.

5. The civil aviation wind shear and visibility early warning method according to claim 4, characterized in that: The aerosol compensation for visibility comprises the following steps: The aerosol optical depth AOD is obtained through the meteorological station observation data; Calculate the extinction coefficient after aerosol compensation. When calculating, first calculate the aerosol compensation factor, and then calculate the corrected extinction coefficient based on the aerosol compensation factor; the calculation formulas for the aerosol compensation factor and the corrected extinction coefficient are as follows: in, is the experience adjustment coefficient; Substitute into the Koschmieder formula to calculate the visibility after aerosol compensation. The formula is as follows: in, The visibility is compensated by aerosol. The visibility data after aerosol compensation can avoid misjudgment caused by aerosol interference.

6. The civil aviation wind shear and visibility early warning method according to claim 5, characterized in that: The visibility is calculated by combining the humidity correction and aerosol compensation, and the calculation formula is as follows: in, In order to improve the reliability of early warning, the visibility data after humidity correction and aerosol compensation are calculated.

7. The civil aviation wind shear and visibility early warning method according to claim 1, characterized in that: Based on the wind field inversion result, a wind shear area is detected using a wind shear identification algorithm, and wind shear identification data is output, including the following steps: The three-dimensional wind field data is spatially gridded, and vertical profile grids are set along the airport runway and take-off and landing path; Calculate the wind speed gradient and wind direction mutation angle of adjacent grid cells, and set the wind speed gradient and wind direction mutation angle thresholds; If an area meets both the wind speed gradient and wind direction sudden change angle thresholds, it is marked as a potential wind shear area; Verify the time continuity of potential wind shear areas and eliminate transient interference; Combined with the historical wind shear event database, the final wind shear area and its hazard level are determined through spatial pattern matching; The spatial position, wind speed gradient value, wind direction sudden change angle, duration and corresponding danger level of the final wind shear area are integrated to generate wind shear identification data as input of the early warning model.

8. The civil aviation wind shear and visibility early warning method according to claim 7, characterized in that: The threshold of the wind speed gradient is set to a wind speed change of not less than 15 knots per 100 meters in the horizontal direction, or a wind speed change of not less than 10 knots per 50 meters in the vertical direction; the threshold of the wind direction mutation angle is set to ≥30°.

9. The civil aviation wind shear and visibility early warning method according to claim 1, characterized in that: The extraction of visibility spatiotemporal profile comprises the following steps: Set spatial sampling lines according to airport runways and standard approach and departure procedures to ensure coverage of critical flight phases; Based on the generated visibility space-time cube, three-dimensional linear interpolation is performed along the path to obtain the continuous visibility space-time distribution; With horizontal distance as the abscissa, height as the ordinate and time series as the third dimension, a spatiotemporal profile of visibility is constructed to characterize the vertical distribution and temporal evolution characteristics of visibility along the route.

Images