Diagnostic prediction method and system for boundary layer height based on COSMIC data

Abstract

This invention discloses a boundary layer height diagnosis and prediction method and system based on COSMIC data. The method includes: performing boundary layer height diagnosis based on COSMIC data to obtain boundary layer height data at different locations; using the boundary layer height data from different locations as labels, collecting the latitude and longitude of the corresponding locations, as well as the temperature and humidity at times prior to a specified prediction step, to construct a training dataset; constructing a machine learning model, using the training dataset to train and establish a mapping relationship between the input latitude and longitude, temperature and humidity, and the predicted boundary layer height value, so as to predict the boundary layer height value at any target location based on the latitude and longitude, temperature and humidity. This invention aims to utilize COSMIC data to achieve boundary layer height prediction, enabling rapid, accurate, and wide-range acquisition and prediction of boundary layer height information.

Description

Technical Field

[0001] This invention relates to the field of weather and climate forecasting technology, specifically to a boundary layer height diagnostic prediction method and system based on COSMIC data. Background Technology

[0002] Accurate planetary boundary layer information plays a crucial role in weather and climate forecasting systems, especially boundary layer height, which is a determinant of the type and amount of covering clouds, affects the Earth's radiation balance, and is closely related to surface heat flux, pollutant diffusion, and waveguide properties. Currently, the main methods for obtaining boundary layer height information include radiosonde, radar, and spaceborne remote sensing. Radiosonde data and radar echoes provide real-time and effective atmospheric information, and boundary layer height can be determined by establishing appropriate mathematical mapping relationships. However, deploying radiosonde and radar detection equipment over the sea is difficult, making it challenging to obtain atmospheric boundary layer information and hindering the study of large-scale oceanic boundary layer heights. In contrast, spaceborne remote sensing technology has a wide detection range and is inexpensive to acquire data, and can calculate boundary layer height using cloud top temperature and sea surface temperature detected by satellite. However, this method is limited to cloud-covered areas, and many related methods proposed by scholars are limited to cloudy or clear-sky conditions, with less than ideal results.

[0003] The COSMIC occultation detection technology, developed in recent years, is unaffected by clouds or weather and can detect global boundary layer height information, producing data with high coverage and high resolution. In recent years, methods for calculating boundary layer height using the refractive index of COSMIC data can be broadly classified into two categories: the maximum gradient method and the refractive index discontinuity method. The maximum gradient method is relatively simple in calculation and yields accurate results, but it is not sensitive to small perturbations at the boundary layer top, making it difficult to detect boundary layer tops with subtle refractive index changes. The refractive index discontinuity method, on the other hand, calculates the boundary layer height by finding refractive index discontinuities. Although the process is complex, it is also sensitive to refractive index perturbations. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a boundary layer height diagnosis and prediction method and system based on COSMIC data, which addresses the above-mentioned problems in the prior art. The present invention aims to use COSMIC data to realize boundary layer height, and can quickly, accurately and over a wide range of boundary layer height information and predict boundary layer height.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A boundary layer height diagnostic prediction method based on COSMIC data includes the following steps:

[0007] S1, perform boundary layer height diagnosis based on COSMIC data to obtain boundary layer height data at different locations;

[0008] S2 uses boundary layer height data at different locations as labels, collects the latitude and longitude of the corresponding locations, as well as the temperature and humidity at times before the specified prediction step, to build a training dataset;

[0009] S3. Construct a machine learning model and use the training dataset to train and establish a mapping relationship between the input latitude, longitude, temperature, and humidity and the predicted boundary layer height value, so as to predict the boundary layer height value of the target location based on the latitude, longitude, temperature, and humidity of any target location.

[0010] Optionally, step S1 includes:

[0011] S1.1, Resample the refractive index data in the COSMIC data;

[0012] S1.2, Calculate the refractive index gradient segmented based on the refractive index data after data resampling;

[0013] S1.3, filter the boundary layer tops according to the preset boundary layer top filtering rules to obtain the boundary layer height data of different positions corresponding to each boundary layer top. The preset boundary layer top filtering rules include: Rule (1): The boundary layer top must satisfy: ,in The refractive index gradient corresponding to the top of the boundary layer. The height of the boundary layer top. The refractive index gradient is defined as min, which is the minimum value. Rule (2): The refractive index gradient value corresponding to the top of the boundary layer. Less than a preset threshold; Rule (3): Height of the top of the boundary layer Less than the preset threshold; Rule (4): The number of minimum points of a refractive index profile that satisfy Rules (1) to (3) is less than the preset threshold; Rule (5): There are no two minimum points on the refractive index profile whose difference is less than their respective preset proportions, where the preset proportion is less than 1.

[0014] Optionally, data resampling in step S1.1 refers to using cubic spline interpolation to interpolate the refractive index data in the COSMIC data from the original vertical resolution to obtain a higher precision vertical resolution.

[0015] Optionally, step S1.2, which calculates the refractive index gradient segmentally based on the refractive index data after data resampling, includes: using a sliding window of a specified size for the refractive index data after data resampling, fitting a fitting curve to the refractive index points within the sliding window, and calculating the refractive index gradient of each segment of the fitting curve according to the following formula:

[0016] ,

[0017] In the above formula, For the fitted curve, Let z be the refractive index gradient, z represent the vertical height, and B be a constant coefficient.

[0018] Optionally, the refractive index gradient value corresponding to the top of the boundary layer in rule (2) of step S1.3. Less than a preset threshold means the refractive index gradient value corresponding to the top of the boundary layer. satisfy: The height of the boundary layer top in rule (3) Less than the preset threshold means In rule (4), the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than the preset threshold means that the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than 7. In rule (5), the absence of two minimum points with a difference less than their respective preset proportions on the refractive index profile means that there are no two minimum points with a difference less than 30% of their respective minimums on the refractive index profile.

[0019] Optionally, step S1.3, when filtering boundary layer tops according to the preset boundary layer top filtering rules, also includes calculating the sharpness coefficient S of the filtered boundary layer tops according to the following formula, and deleting boundary layer tops whose sharpness coefficient S is less than a preset threshold:

[0020]

[0021] In the above formula, The refractive index gradient at the top of the selected boundary layer, The root mean square of the minimum refractive index gradient within a specified height of the refractive index profile.

[0022] Optionally, the machine learning model constructed in step S3 is a Long Short-Term Memory (LSTM) network.

[0023] Furthermore, the present invention also provides a boundary layer height diagnostic prediction system based on COSMIC data, including a microprocessor and a memory interconnected thereto, wherein the microprocessor is programmed or configured to execute the boundary layer height diagnostic prediction method based on COSMIC data.

[0024] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute the boundary layer height diagnostic prediction method based on COSMIC data by a processor.

[0025] Furthermore, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the COSMIC-based boundary layer height diagnostic prediction method via a processor.

[0026] Compared with existing technologies, the present invention has the following advantages: Although existing technologies can diagnose boundary height based on COSMIC, they cannot predict the boundary layer height at any subsequent target location. The present invention, based on boundary layer height diagnosis using COSMIC data to obtain boundary layer height data at different locations, uses the boundary layer height data at different locations as labels, collects the latitude and longitude of the corresponding locations, as well as the temperature and humidity at times before a specified prediction step, to construct a training dataset. The training dataset is used to train and establish a mapping relationship between the input latitude and longitude, temperature and humidity, and the predicted boundary layer height value, so as to predict the boundary layer height of any target location based on the latitude and longitude, temperature and humidity. This enables the prediction of the boundary layer height at any subsequent target location, and allows for the rapid, accurate, and wide-range acquisition and prediction of boundary layer height information. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the basic process of the method in an embodiment of the present invention.

[0028] Figure 2 This is a flowchart illustrating the method of an embodiment of the present invention, which includes a boundary layer height diagnosis step.

[0029] Figure 3 This is a schematic diagram of the results obtained in an embodiment of the present invention. Detailed Implementation

[0030] like Figure 1 As shown, the boundary layer height diagnostic prediction method based on COSMIC data in this embodiment includes the following steps:

[0031] S1, perform boundary layer height diagnosis based on COSMIC data to obtain boundary layer height data at different locations;

[0032] S2 uses boundary layer height data at different locations as labels, collects the latitude and longitude of the corresponding locations, as well as the temperature and humidity at times before the specified prediction step, to build a training dataset;

[0033] S3. Construct a machine learning model and use the training dataset to train and establish a mapping relationship between the input latitude, longitude, temperature, and humidity and the predicted boundary layer height value, so as to predict the boundary layer height value of the target location based on the latitude, longitude, temperature, and humidity of any target location.

[0034] Obtaining boundary layer height using radiosonde and radar equipment is difficult due to the demanding setup requirements, making it challenging to acquire boundary layer height data over large areas of the ocean. While spaceborne remote sensing technology offers a wide detection range, it is limited by weather conditions and requires high cloud cover. However, COSMIC occultation detection technology is unaffected by weather and can detect global boundary layer information. Its data boasts high coverage and high resolution; therefore, boundary layer height diagnosis based on COSMIC data can yield accurate and comprehensive data for different locations, thereby improving the accuracy of boundary layer height prediction.

[0035] Traditional methods for obtaining boundary layer height data based on COSMIC data utilize the refractive index breakpoint method. Because this method is sensitive to refractive index disturbances, the calculated boundary layer height differs from the actual height, affecting the prediction results. As an alternative implementation method, such as... Figure 2 As shown, step S1 in this embodiment includes:

[0036] S1.1, Resample the refractive index data in the COSMIC data;

[0037] S1.2, Calculate the refractive index gradient segmented based on the refractive index data after data resampling;

[0038] S1.3, filter the boundary layer tops according to the preset boundary layer top filtering rules to obtain the boundary layer height data of different positions corresponding to each boundary layer top. The preset boundary layer top filtering rules include: Rule (1): The boundary layer top must satisfy: ,in The refractive index gradient corresponding to the top of the boundary layer. The height of the boundary layer top. The refractive index gradient is defined as min, which is the minimum value. Rule (2): The refractive index gradient value corresponding to the top of the boundary layer. Less than a preset threshold; Rule (3): Height of the top of the boundary layer Less than a preset threshold; Rule (4): The number of minimum points satisfying Rules (1) to (3) on a refractive index profile is less than a preset threshold; Rule (5): There are no two minimum points on the refractive index profile whose difference is less than their respective preset proportions, where the preset proportion is less than 1. The boundary layer top is selected according to the preset boundary layer top selection rules. Figure 2 The step of "determining the boundary layer height" yields the boundary layer height data for different locations corresponding to the tops of each boundary layer. Figure 2 The "boundary layer height diagnostic value" is obtained, and then a training dataset can be built. Based on the built training dataset, a machine learning model, including a deep learning algorithm, can be trained to obtain the boundary layer height prediction value.

[0039] In step S1.1 of this embodiment, data resampling refers to using cubic spline interpolation to interpolate the refractive index data in the COSMIC data from the original vertical resolution to obtain a higher precision vertical resolution. Specifically, in this embodiment, the vertical resolution of the original refractive index data in the COSMIC data is 100m, and the vertical resolution is converted to 20m using cubic spline interpolation.

[0040] In step S1.2 of this embodiment, calculating the refractive index gradient segmentally based on the refractive index data after data resampling includes: using a sliding window of a specified size for the refractive index data after data resampling, fitting a fitting curve to the refractive index points within the sliding window (in this embodiment, specifically, a fixed sliding window of 400m is used, i.e., fitting a curve using 20 refractive index points within the window), and calculating the refractive index gradient of each segment of the fitting curve according to the following formula:

[0041] ,

[0042] In the above formula, The fitted curve is in units, representing the change of refractive index with height. is the refractive index gradient (the object of calculation), in units / km; z represents the vertical height, in km; B is a constant coefficient, which is 300 in this embodiment.

[0043] The relevant values ​​in rules (2) to (5) of step S1.3 can be selected according to actual needs. For example, as an optional implementation, the refractive index gradient value corresponding to the top of the boundary layer in rule (2) of step S1.3 can be selected. Less than a preset threshold means the refractive index gradient value corresponding to the top of the boundary layer. satisfy: The height of the boundary layer top in rule (3) Less than the preset threshold means In rule (4), the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than the preset threshold means that the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than 7. In rule (5), the absence of two minimum points with a difference less than their respective preset proportions on the refractive index profile means that there are no two minimum points with a difference less than 30% of their respective minimums on the refractive index profile.

[0044] Since the machine learning model in this embodiment learns the mapping relationship between the input latitude, longitude, temperature, and humidity and the predicted boundary layer height, the possibility of drastic changes in temperature and water vapor can be considered to filter boundary layer tops. Specifically, in step S1.3 of this embodiment, when filtering boundary layer tops according to the preset boundary layer top filtering rules, it also includes calculating the sharpness coefficient S of the filtered boundary layer tops according to the following formula and deleting boundary layer tops whose sharpness coefficient S is less than a preset threshold:

[0045]

[0046] In the above formula, The refractive index gradient at the top of the selected boundary layer, The root mean square of the minimum refractive index gradient within a specified altitude (e.g., 10 km) of the refractive index profile. The sharpness coefficient S characterizes the intensity of the refractive index gradient; the larger the coefficient, the more drastic the changes in temperature and water vapor, and the more accurate the determination of the boundary layer top.

[0047] The machine learning model constructed in step S3 of this embodiment is a Long Short-Term Memory (LSTM) network. LSTM is a special type of Recurrent Neural Network (RNN) model. Through its unique design, it effectively solves the problems of long-term dependency and gradient explosion that may be encountered in general RNN and artificial neural network models, making it suitable for time series prediction problems with long time intervals. In this embodiment, after calculating the boundary layer height using COSMIC data, the global boundary layer height is predicted based on the LSTM network. The process of constructing and training the LSTM network is as follows: 1) Data preprocessing: The boundary layer height dataset obtained in the above diagnostic process is organized into tabular data in chronological order, and normalized with feature dimensions such as temperature, humidity, and latitude and longitude to eliminate the influence of dimensions. 2) Model definition: Following the classic LSTM network model already available online, the model is defined using Python's built-in library, including its number of layers, learning rate, and other parameters, and the prediction step size is set to 24 hours (the prediction step size can be set according to actual needs). 3) Model Training and Visualization: Due to the large amount of data used, training is performed in batches, and the optimal model parameters are saved and plotted. After training the Long Short-Term Memory (LSTM) network using the training dataset to establish a mapping relationship between the input latitude, longitude, temperature, and humidity and the predicted boundary layer height, the network parameters of the LSTM network are saved. This allows the LSTM network to be used to predict the boundary layer height of any target location based on its latitude, longitude, temperature, and humidity.

[0048] To verify the boundary layer height diagnosis and prediction method based on COSMIC data in this embodiment, the predicted boundary layer height at the target location obtained by the Long Short-Term Memory (LSTM) network is compared with the boundary layer height at the target location 24 hours later obtained by boundary layer height diagnosis based on COSMIC data. The results are as follows: Figure 3 As shown, the red curve represents the boundary layer height prediction of the target location obtained from the Long Short-Term Memory (LSTM) network, while the blue curve represents the boundary layer height of the target location 24 hours later, obtained through boundary layer height diagnosis based on COSMIC data. See also... Figure 3 It can be seen that the boundary layer height prediction value of the target location obtained by the Long Short-Term Memory Network (LSTM) in this embodiment is basically the same as the boundary layer height fluctuation of the target location 24 hours later obtained by boundary layer height diagnosis based on COSMIC data. This indicates that the LSTM in this embodiment can accurately predict the boundary layer height prediction value of the target location.

[0049] In summary, considering that COSMIC occultation detection technology is unaffected by weather and can detect global boundary layer information, generating data with high coverage and high resolution, the method in this embodiment, based on COSMIC data for boundary layer height diagnosis to obtain boundary layer height data at different locations, can obtain accurate and comprehensive data, thereby improving the accuracy of boundary layer height prediction. Furthermore, the advanced "open-loop" tracking technology employed in this embodiment significantly solves the atmospheric multipath problem, facilitating the acquisition of more accurate boundary layer heights. This embodiment's method has fewer formulas; it only requires data processing and transformation, and the boundary layer top height can be determined based on threshold conditions, making it simple, convenient, and fast in calculation. In addition, this embodiment's method uses a mature Long Short-Term Memory (LSTM) network, ensuring prediction accuracy.

[0050] Furthermore, this embodiment also provides a boundary layer height diagnostic prediction system based on COSMIC data, including a microprocessor and a memory interconnected, wherein the microprocessor is programmed or configured to execute a boundary layer height diagnostic prediction method based on COSMIC data.

[0051] Furthermore, this embodiment also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute a boundary layer height diagnostic prediction method based on COSMIC data via a processor.

[0052] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute a boundary layer height diagnostic prediction method based on COSMIC data via a processor.

[0053] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A boundary layer height diagnostic prediction method based on COSMIC data, characterized in that, Includes the following steps: S1, perform boundary layer height diagnosis based on COSMIC data to obtain boundary layer height data at different locations; S2 uses boundary layer height data at different locations as labels, collects the latitude and longitude of the corresponding locations, as well as the temperature and humidity at times before the specified prediction step, to build a training dataset; S3, Construct a machine learning model, using a training dataset to train and establish a mapping relationship between the input latitude, longitude, temperature, and humidity, and the predicted boundary layer height value, so as to predict the boundary layer height value of the target location based on the latitude, longitude, temperature, and humidity of any target location; Step S1 includes: S1.1, Resample the refractive index data in the COSMIC data; S1.2, Calculate the refractive index gradient segmented based on the refractive index data after data resampling; S1.3, filter the boundary layer tops according to the preset boundary layer top filtering rules to obtain the boundary layer height data of different positions corresponding to each boundary layer top. The preset boundary layer top filtering rules include: Rule (1): The boundary layer top must satisfy: ,in The refractive index gradient corresponding to the top of the boundary layer. The height of the boundary layer top. The refractive index gradient is defined as min, which is the minimum value. Rule (2): The refractive index gradient value corresponding to the top of the boundary layer. Less than a preset threshold; Rule (3): Height of the top of the boundary layer Less than the preset threshold; Rule (4): The number of minimum points of a refractive index profile that satisfy Rules (1) to (3) is less than the preset threshold; Rule (5): There are no two minimum points on the refractive index profile whose difference is less than their respective preset proportions, where the preset proportion is less than 1.

2. The boundary layer height diagnosis and prediction method based on COSMIC data according to claim 1, characterized in that, The data resampling in step S1.1 refers to using cubic spline interpolation to interpolate the refractive index data in the COSMIC data from the original vertical resolution to obtain a higher precision vertical resolution.

3. The boundary layer height diagnosis and prediction method based on COSMIC data according to claim 1, characterized in that, Step S1.2, which calculates the refractive index gradient segment by segment based on the refractive index data after data resampling, includes: using a sliding window of a specified size for the refractive index data after data resampling, fitting a fitting curve to the refractive index points within the sliding window, and calculating the refractive index gradient of each segment of the fitting curve according to the following formula: ， In the above formula, For the fitted curve, Let z be the refractive index gradient, z represent the vertical height, and B be a constant coefficient.

4. The boundary layer height diagnosis and prediction method based on COSMIC data according to claim 1, characterized in that, The refractive index gradient value corresponding to the top of the boundary layer in rule (2) of step S1.3 Less than a preset threshold means the refractive index gradient value corresponding to the top of the boundary layer. satisfy: The height of the boundary layer top in rule (3) Less than the preset threshold means In rule (4), the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than the preset threshold means that the number of minimum points of a refractive index profile that satisfies rules (1) to (3) is less than 7. In rule (5), the absence of two minimum points with a difference less than their respective preset proportions on the refractive index profile means that there are no two minimum points with a difference less than 30% of their respective minimums on the refractive index profile.

5. The boundary layer height diagnosis and prediction method based on COSMIC data according to claim 1, characterized in that, Step S1.3, when filtering boundary layer tops according to the preset boundary layer top filtering rules, also includes calculating the sharpness coefficient S of the filtered boundary layer tops according to the following formula, and deleting boundary layer tops whose sharpness coefficient S is less than a preset threshold: In the above formula, The refractive index gradient at the top of the selected boundary layer, The root mean square of the minimum refractive index gradient within a specified height of the refractive index profile.

6. The boundary layer height diagnosis and prediction method based on COSMIC data according to claim 1, characterized in that, The machine learning model constructed in step S3 is a Long Short-Term Memory (LSTM) network.

7. A boundary layer height diagnostic prediction system based on COSMIC data, comprising a microprocessor and a memory interconnected, characterized in that, The microprocessor is programmed or configured to execute the boundary layer height diagnostic prediction method based on COSMIC data as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the boundary layer height diagnostic prediction method based on COSMIC data as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the boundary layer height diagnostic prediction method based on COSMIC data as described in any one of claims 1 to 6.

Images