Meteorological environment parameter prediction method and device in offshore low-altitude range
By acquiring and preprocessing low-meteorological information, combining multi-dimensional distance discrimination and prediction models, the problem of predicting meteorological environment parameters in offshore low-altitude range is solved, efficient and accurate meteorological environment prediction is achieved, and effective support for low-altitude flight is provided.
Patent Information
- Application Number
- CN202411467631.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2025-01-03
AI Technical Summary
It is difficult for the prior art to conduct comprehensive and accurate prediction analysis of meteorological environmental parameters in the low altitude range near the sea, especially when the diversification of low-altitude marine space and great regional impacts.
By obtaining the low-altitude range information and meteorological information collection, pre-processing and discrete sampling processing are performed, combining multi-dimensional distance discrimination processing and near-field and far-field prediction models, the meteorological environmental parameter prediction value is calculated, and meteorological environmental parameter prediction is provided in the offshore low-altitude range.
It realizes comprehensive and accurate prediction and analysis of meteorological and environmental parameters in the low-altitude range of offshore seas, improves prediction efficiency and accuracy, and expands the application range through dynamic adaptation of far-field prediction models, and provides effective support for low-altitude flight evaluation.
Smart Images
Figure CN119247519A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the fields of atmospheric environment and numerical analysis, and in particular to a method and device for predicting meteorological environmental parameters in a low-altitude offshore area. Background Art
[0002] At present, low-altitude airspace is gradually becoming a new transportation space, and the application of various low-altitude aircraft is showing a booming growth trend. Since the meteorological environment of low-altitude ocean space is affected by various factors in the air, ocean and ground, its meteorological environment parameters show characteristics of diversity and are greatly affected by regions.
[0003] In the past, the forecast of meteorological parameters in the low-altitude offshore area only used ground observation data or atmospheric standard radiometers at a single point, lacking comprehensive forecast and analysis of low-altitude wind and environmental data such as air pressure, density, and temperature.
[0004] How to conduct a comprehensive and accurate forecast and analysis of the meteorological environment parameters in the offshore low-altitude ring range is an urgent problem to be solved. Therefore, it is necessary to provide a forecast method for meteorological environment parameters in the offshore low-altitude range to provide support for various activities in the low-altitude marine environment. Summary of the invention
[0005] The present invention mainly solves the problem of how to comprehensively and accurately predict and analyze meteorological environmental parameters in a low-altitude offshore range. The present invention discloses a method and device for predicting meteorological environmental parameters in a low-altitude offshore range.
[0006] In a first aspect of an embodiment of the present invention, a method for predicting meteorological environment parameters in a low-altitude offshore area is disclosed, comprising:
[0007] S1, obtaining low-altitude range information and low-altitude meteorological information set; the low-altitude meteorological information set includes location information of several collection locations and corresponding meteorological parameter information; the meteorological parameter information includes a collection information sequence of wind field, air pressure, temperature, and air density; the low-altitude range information includes height information, length information, and width information;
[0008] S2, preprocessing the low-altitude meteorological information set to obtain a preprocessed information set;
[0009] S3, performing discrete sampling processing on the low-altitude range information to obtain a discrete grid point set;
[0010] S4, performing meteorological parameter prediction processing on the discrete grid point set and the pre-processing information set to obtain predicted values of meteorological environment parameters in the offshore low-altitude range.
[0011] The preprocessing of the low-altitude meteorological information set to obtain the preprocessed information set includes:
[0012] S21, performing category check processing on the low-altitude meteorological information set to obtain a first information set;
[0013] S22: performing data normalization processing on the first information set to obtain a preprocessed information set.
[0014] The discrete sampling process is performed on the low-altitude range information to obtain a discrete grid point set, including:
[0015] S31, uniformly sampling the height information to obtain a discrete height value set; the discrete height value set includes a plurality of discrete height values;
[0016] S32, performing two-dimensional uniform sampling processing on the horizontal range information composed of the length information and the width information to obtain a discrete plane coordinate set; the discrete plane coordinate set includes a plurality of discrete plane coordinate points;
[0017] S33, combining the discrete height value set and the discrete plane coordinate set to obtain a discrete grid point set; the discrete grid point set includes a plurality of discrete grid points.
[0018] The step of performing meteorological parameter prediction processing on the discrete grid point set and the preprocessing information set to obtain the predicted values of meteorological environment parameters in the offshore low-altitude range includes:
[0019] S41, constructing a known sampling point set using the location information of all sampling locations in the low-altitude meteorological information set; the known sampling point set includes the location coordinates of a number of sampling points;
[0020] S42, performing a joint multi-dimensional distance discrimination process on each discrete grid point in the discrete grid point set and a known sampling point set to obtain a first discrimination result;
[0021] S43, when the first judgment result is yes, using a near-field prediction model, calculating and processing the pre-processing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point;
[0022] When the first discrimination result is no, using a far-field prediction model, calculating and processing the preprocessing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point;
[0023] S44, executing S42 to S43 for all discrete grid points in the discrete grid point set to obtain the predicted values of the meteorological environment parameters of all discrete grid points; determining the predicted values of the meteorological environment parameters of all discrete grid points as the predicted values of the meteorological environment parameters in the near-shore low-altitude range.
[0024] The joint multi-dimensional distance discrimination process includes:
[0025] Get the number of sampling points in the known sampling point set that satisfy the distance inequality group;
[0026] Determine whether the number of sampling points satisfying the distance inequality group is greater than or equal to a set number threshold N0, if it is greater than or equal to the set number threshold N0, confirm that the first judgment result is yes; if it is less than the set number threshold N0, confirm that the first judgment result is no;
[0027] The expression of the distance inequality group is:
[0028]
[0029] |z0-z i |≤λ3,
[0030] Among them, κ1 and κ2 are preset weighting coefficients, λ1, λ2 and λ3 are preset discrimination thresholds, (x0, y0, z0) are the position coordinates of the discrete grid points, (x i ,y i ,z i ) is the position coordinate of the i-th sampling point in the known sampling point set.
[0031] The expression of the near-field prediction model is:
[0032]
[0033]
[0034] Wherein, F(x0, y0, z0) is the wind field prediction value of the discrete grid point with the position coordinates (x0, y0, z0), X1, X2, and X3 are the wind field collection values of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set, (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) are the position coordinates of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; P(x0, y0, z0) is the predicted value of the air pressure, temperature, or air density of the discrete grid point with the position coordinates (x0, y0, z0), and Y1 and Y2 are the air pressure, temperature, or air density of the two sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; the predicted values of the meteorological environment parameters of the discrete grid points include the predicted values of the wind field, air pressure, temperature, and air density of the discrete grid points; ω 11 ,ω 12 ,ω 13 are the weight value of the first wind farm, the weight value of the second wind farm, and the weight value of the third wind farm, respectively, 21,ω 22 are the first meteorological weight value and the second meteorological weight value respectively;
[0035] The calculation expression of the weight value is:
[0036] ω 11 =A1 / P1,ω 12 =A2 / P2,ω 13 =A3 / P3,
[0037] ω 21 =V1 / Q1,ω 22 =V2 / Q2,
[0038] Among them, A1 is the wind field average of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P1 is the wind field variance of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A2 is the wind field average of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P2 is the wind field variance of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A3 is the wind field average of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, and P3 is the wind field variance of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set. V1 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, Q1 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, V2 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, Q2 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set;
[0039] The first closest, second closest, and third closest to the discrete grid point of the position coordinate (x0, y0, z0) refer to the first smallest, second smallest, and third smallest distances to the discrete grid point of the position coordinate (x0, y0, z0);
[0040] The far-field prediction model comprises:
[0041] Taking the location information of the collection location of the low-altitude meteorological information set as a known independent variable, and taking the meteorological parameter information in the pre-processed information as a known dependent variable;
[0042] Performing model identification processing on the known independent variables and the known dependent variables to obtain a prediction model;
[0043] The prediction model is used to process the position coordinates of each discrete grid point in the discrete grid point set to obtain the predicted value of the meteorological environment parameter of the discrete grid point.
[0044] In a second aspect of an embodiment of the present invention, a device for predicting meteorological environment parameters in a low-altitude offshore area is disclosed, the device comprising:
[0045] A memory storing executable program code;
[0046] a processor coupled to the memory;
[0047] The processor calls the executable program code stored in the memory to execute the method for predicting meteorological environment parameters in the near-shore low-altitude range.
[0048] According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the method for predicting meteorological environment parameters in a low-altitude offshore area.
[0049] According to a fourth aspect of an embodiment of the present invention, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the method for predicting meteorological environment parameters in a low-altitude offshore area.
[0050] The beneficial effects of the present invention are:
[0051] The present invention realizes comprehensive and accurate forecast and analysis of meteorological environmental parameters in the near-shore low-altitude range, provides forecast data of meteorological environmental parameters in the near-shore low-altitude range, and provides effective support for conducting low-altitude flight assessment and guarantee.
[0052] The present invention performs a joint multi-dimensional distance discrimination process on each discrete grid point in the discrete grid point set with a known sampling point set, establishes different prediction models based on the discrimination results, realizes classification prediction of different categories of data, and effectively improves the prediction efficiency and accuracy.
[0053] The far-field prediction model established by the present invention introduces the idea of model identification, realizes dynamic adaptation and matching of various types of data, and improves the application scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION
[0055] In order to better understand the content of the present invention, an embodiment is given here.
[0056] Figure 1 It is a flow chart for implementing the method of the present invention.
[0057] In a first aspect of the embodiment of the present application, a method for predicting meteorological environment parameters in a low-altitude offshore area is disclosed, comprising:
[0058] S1, obtaining low-altitude range information and low-altitude meteorological information set; the low-altitude meteorological information set includes location information of several collection locations and corresponding meteorological parameter information; the meteorological parameter information includes a collection information sequence of wind field, air pressure, temperature, and air density; the low-altitude range information includes height information, length information, and width information;
[0059] S2, preprocessing the low-altitude meteorological information set to obtain a preprocessed information set;
[0060] S3, performing discrete sampling processing on the low-altitude range information to obtain a discrete grid point set;
[0061] S4, performing meteorological parameter prediction processing on the discrete grid point set and the pre-processing information set to obtain predicted values of meteorological environment parameters in the offshore low-altitude range.
[0062] The preprocessing of the low-altitude meteorological information set to obtain the preprocessed information set includes:
[0063] S21, performing category check processing on the low-altitude meteorological information set to obtain a first information set;
[0064] S22: performing data normalization processing on the first information set to obtain a preprocessed information set.
[0065] The discrete sampling process is performed on the low-altitude range information to obtain a discrete grid point set, including:
[0066] S31, uniformly sampling the height information to obtain a discrete height value set; the discrete height value set includes a plurality of discrete height values;
[0067] S32, performing two-dimensional uniform sampling processing on the horizontal range information composed of the length information and the width information to obtain a discrete plane coordinate set; the discrete plane coordinate set includes a plurality of discrete plane coordinate points;
[0068] S33, combining the discrete height value set and the discrete plane coordinate set to obtain a discrete grid point set; the discrete grid point set includes a plurality of discrete grid points;
[0069] The step of performing meteorological parameter prediction processing on the discrete grid point set and the preprocessing information set to obtain the predicted values of meteorological environment parameters in the offshore low-altitude range includes:
[0070] S41, constructing a known sampling point set using the location information of all sampling locations in the low-altitude meteorological information set; the known sampling point set includes the location coordinates of a number of sampling points;
[0071] S42, performing a joint multi-dimensional distance discrimination process on each discrete grid point in the discrete grid point set and a known sampling point set to obtain a first discrimination result;
[0072] S43, when the first judgment result is yes, using a near-field prediction model, calculating and processing the pre-processing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point;
[0073] When the first discrimination result is no, using a far-field prediction model, calculating and processing the preprocessing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point;
[0074] S44, executing S42 to S43 for all discrete grid points in the discrete grid point set to obtain the predicted values of the meteorological environment parameters of all discrete grid points; determining the predicted values of the meteorological environment parameters of all discrete grid points as the predicted values of the meteorological environment parameters in the near-shore low-altitude range.
[0075] The joint multi-dimensional distance discrimination process comprises:
[0076] Get the number of sampling points in the known sampling point set that satisfy the distance inequality group;
[0077] Determine whether the number of sampling points satisfying the distance inequality group is greater than or equal to a set number threshold N0, if it is greater than or equal to the set number threshold N0, confirm that the first judgment result is yes; if it is less than the set number threshold N0, confirm that the first judgment result is no;
[0078] The expression of the distance inequality group is:
[0079]
[0080] |z0-z i |≤λ3,
[0081] Among them, κ1 and κ2 are preset weighting coefficients, λ1, λ2 and λ3 are preset discrimination thresholds, (x0, y0, z0) are the position coordinates of the discrete grid points, (x i ,y i ,z i ) is the position coordinate of the i-th sampling point in the known sampling point set.
[0082] The expression of the near-field prediction model is:
[0083]
[0084] Among them, X(x0, y0, z0) is the wind field prediction value of the discrete grid point with position coordinates (x0, y0, z0), X1, X2, and X3 are the wind field collection values of the three sampling points closest to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) are the position coordinates of the three sampling points closest to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set; Y(x0, y0, z0) is the predicted value of the air pressure, temperature or air density of the discrete grid point with position coordinates (x0, y0, z0), and Y1 and Y2 are the air pressure, temperature or air density of the two sampling points closest to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set; the predicted values of the meteorological environment parameters of the discrete grid points include the predicted values of the wind field, air pressure, temperature and air density of the discrete grid points.
[0085] The expression of the near-field prediction model is:
[0086]
[0087] Wherein, F(x0, y0, z0) is the wind field prediction value of the discrete grid point with the position coordinates (x0, y0, z0), X1, X2, and X3 are the wind field collection values of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set, (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) are the position coordinates of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; P(x0, y0, z0) is the predicted value of the air pressure, temperature, or air density of the discrete grid point with the position coordinates (x0, y0, z0), and Y1 and Y2 are the air pressure, temperature, or air density of the two sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; the predicted values of the meteorological environment parameters of the discrete grid points include the predicted values of the wind field, air pressure, temperature, and air density of the discrete grid points; ω 11 ,ω 12 ,ω 13 are the weight value of the first wind farm, the weight value of the second wind farm, and the weight value of the third wind farm, respectively, 21 ,ω 22 are the first meteorological weight value and the second meteorological weight value respectively;
[0088] The calculation expression of the weight value is:
[0089] ω 11 =A1 / P1,ω 12 =A2 / P2,ω 13 =A3 / P3,
[0090] ω 21 =V1 / Q1,ω 22 =V2 / Q2,
[0091] Among them, A1 is the wind field average of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P1 is the wind field variance of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A2 is the wind field average of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P2 is the wind field variance of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A3 is the wind field average of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, and P3 is the wind field variance of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set. V1 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, Q1 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, V2 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, Q2 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set;
[0092] The first closest, second closest, and third closest to the discrete grid point of the position coordinate (x0, y0, z0) refer to the first smallest, second smallest, and third smallest distances to the discrete grid point of the position coordinate (x0, y0, z0);
[0093] The far-field prediction model comprises:
[0094] Taking the location information of the collection location of the low-altitude meteorological information set as a known independent variable, and taking the meteorological parameter information in the pre-processed information as a known dependent variable;
[0095] Performing model identification processing on the known independent variables and the known dependent variables to obtain a prediction model;
[0096] The prediction model is used to process the position coordinates of each discrete grid point in the discrete grid point set to obtain the predicted value of the meteorological environment parameter of the discrete grid point.
[0097] The value of the quantity threshold N0 is greater than or equal to 9.
[0098] The wind field acquisition value can be obtained by averaging the acquisition information sequence, or by using an average weighted model;
[0099] The model identification process is to process each type of meteorological environment parameter separately to obtain a corresponding prediction model, and use the prediction model to process the position coordinates of each discrete grid point in the discrete grid point set to obtain each corresponding type of meteorological environment parameter.
[0100] The model identification process may adopt a least squares processing method.
[0101] The model to be identified used in the model identification process may be a state space model or an ARMA model, and the pattern recognition process is to determine the parameters of the model to be identified.
[0102] The category checking process is to determine whether the category of each data in the information set belongs to a preset category set, and delete the data that does not belong to the preset category set from the information set.
[0103] The data normalization process is to obtain the maximum value of each type of data in the set, and divide each data in the type of data by the maximum value to obtain normalized data.
[0104] The discrete height value set and the discrete plane coordinate set are combined to obtain a discrete grid point set. Specifically, for example, when the discrete height value set is [1,2] and the discrete plane coordinate set is [(2,3), (2,2), (3,2), (3,3)], the discrete grid point set is [(2,3,1), (2,2,1), (3,2,1), (3,3,1), (2,3,2), (2,2,2), (3,2,2), (3,3,2)].
[0105] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for predicting meteorological environmental parameters in a low-altitude offshore area, characterized in that: include: S1, obtaining low-altitude range information and low-altitude meteorological information set; the low-altitude meteorological information set includes location information of several collection locations and corresponding meteorological parameter information; the meteorological parameter information includes a collection information sequence of wind field, air pressure, temperature, and air density; the low-altitude range information includes height information, length information, and width information; S2, preprocessing the low-altitude meteorological information set to obtain a preprocessed information set; S3, performing discrete sampling processing on the low-altitude range information to obtain a discrete grid point set; S4, performing meteorological parameter prediction processing on the discrete grid point set and the pre-processing information set to obtain predicted values of meteorological environment parameters in the offshore low-altitude range.
2. The method for predicting meteorological environment parameters in the offshore low-altitude range as claimed in claim 1, characterized in that: The preprocessing of the low-altitude meteorological information set to obtain the preprocessed information set includes: S21, performing category check processing on the low-altitude meteorological information set to obtain a first information set; S22: performing data normalization processing on the first information set to obtain a preprocessed information set.
3. The method for predicting meteorological environmental parameters in the offshore low-altitude range as claimed in claim 1, characterized in that: The discrete sampling process is performed on the low-altitude range information to obtain a discrete grid point set, including: S31, uniformly sampling the height information to obtain a discrete height value set; the discrete height value set includes a plurality of discrete height values; S32, performing two-dimensional uniform sampling processing on the horizontal range information composed of the length information and the width information to obtain a discrete plane coordinate set; the discrete plane coordinate set includes a plurality of discrete plane coordinate points; S33, combining the discrete height value set and the discrete plane coordinate set to obtain a discrete grid point set; the discrete grid point set includes a plurality of discrete grid points.
4. The method for predicting meteorological environmental parameters in the offshore low-altitude range as claimed in claim 1, characterized in that: The step of performing meteorological parameter prediction processing on the discrete grid point set and the preprocessing information set to obtain the predicted values of meteorological environment parameters in the offshore low-altitude range includes: S41, constructing a known sampling point set using the location information of all sampling locations in the low-altitude meteorological information set; the known sampling point set includes the location coordinates of a number of sampling points; S42, performing a joint multi-dimensional distance discrimination process on each discrete grid point in the discrete grid point set and a known sampling point set to obtain a first discrimination result; S43, when the first judgment result is yes, using a near-field prediction model, calculating and processing the pre-processing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point; When the first discrimination result is no, using a far-field prediction model, calculating and processing the preprocessing information set to obtain a predicted value of the meteorological environment parameter of the discrete grid point; S44, executing S42 to S43 for all discrete grid points in the discrete grid point set to obtain the predicted values of the meteorological environment parameters of all discrete grid points; determining the predicted values of the meteorological environment parameters of all discrete grid points as the predicted values of the meteorological environment parameters in the near-shore low-altitude range.
5. The method for predicting meteorological environmental parameters in the offshore low-altitude range as claimed in claim 4, characterized in that: The joint multi-dimensional distance discrimination process comprises: Get the number of sampling points in the known sampling point set that satisfy the distance inequality group; Determine whether the number of sampling points satisfying the distance inequality group is greater than or equal to a set number threshold N0, if it is greater than or equal to the set number threshold N0, confirm that the first judgment result is yes; if it is less than the set number threshold N0, confirm that the first judgment result is no; The expression of the distance inequality group is: |z0-z i |≤λ3, Among them, κ1 and κ2 are preset weighting coefficients, λ1, λ2 and λ3 are preset discrimination thresholds, (x0, y0, z0) are the position coordinates of the discrete grid points, (x i ,y i ,z i ) is the position coordinate of the i-th sampling point in the known sampling point set.
6. The method for predicting meteorological environmental parameters in the offshore low-altitude range as claimed in claim 5, characterized in that: The expression of the near-field prediction model is: Wherein, F(x0, y0, z0) is the wind field prediction value of the discrete grid point with the position coordinates (x0, y0, z0), X1, X2, and X3 are the wind field collection values of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set, (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) are the position coordinates of the three sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; P(x0, y0, z0) is the predicted value of the air pressure, temperature, or air density of the discrete grid point with the position coordinates (x0, y0, z0), and Y1 and Y2 are the air pressure, temperature, or air density of the two sampling points closest to the discrete grid point with the position coordinates (x0, y0, z0) in the known sampling point set; the predicted values of the meteorological environment parameters of the discrete grid points include the predicted values of the wind field, air pressure, temperature, and air density of the discrete grid points; ω 11 ,ω 12 ,ω 13 are the weight value of the first wind farm, the weight value of the second wind farm, and the weight value of the third wind farm, respectively, 21 ,ω 22 are the first meteorological weight value and the second meteorological weight value respectively; The calculation expression of the weight value is: oh 11 =A1 / P1,ω 12 =A2 / P2,ω 13 =A3 / P3, oh 21 =V1 / Q1,ω 22 =V2 / Q2, Among them, A1 is the wind field average of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P1 is the wind field variance of several sampling points within a preset distance around the first closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A2 is the wind field average of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, P2 is the wind field variance of several sampling points within a preset distance around the second closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, A3 is the wind field average of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set, and P3 is the wind field variance of several sampling points within a preset distance around the third closest sampling point of the discrete grid point to the position coordinate (x0, y0, z0) in the known sampling point set. V1 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, Q1 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the first closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, V2 is the sum of the mean air pressure, mean temperature and mean air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set, and Q2 is the sum of the median air pressure, median temperature and median air density of several sampling points within the preset distance around the second closest sampling point to the discrete grid point with position coordinates (x0, y0, z0) in the known sampling point set.
7. The method for predicting meteorological environmental parameters in the offshore low-altitude range as claimed in claim 5, characterized in that: The far-field prediction model comprises: Taking the location information of the collection location of the low-altitude meteorological information set as a known independent variable, and taking the meteorological parameter information in the pre-processed information as a known dependent variable; Performing model identification processing on the known independent variables and the known dependent variables to obtain a prediction model; The prediction model is used to process the position coordinates of each discrete grid point in the discrete grid point set to obtain the predicted value of the meteorological environment parameter of the discrete grid point.
8. A device for predicting meteorological environmental parameters in the low-altitude offshore area, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for predicting meteorological environment parameters in the near-shore low-altitude range as described in any one of claims 1 to 7.
9. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, which, when called by a computer, are used to execute the method for predicting meteorological environment parameters in the near-shore low-altitude range as described in any one of claims 1 to 7.
10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the method for predicting meteorological environment parameters in the near-shore low-altitude range as described in any one of claims 1 to 7.