Severe convective weather similarity analysis method

Abstract

The invention discloses a severe convective weather similarity analysis method, and the method comprises the steps: obtaining current echo intensity data and current waveform data in current atmosphere echo data, and obtaining historical echo intensity data of each severe convective weather; preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data; according to the preprocessed echo intensity data and historical echo intensity data of each type of severe convective weather, calculating to obtain a Hamming distance and cosine similarity corresponding to each type of severe convective weather; determining waveform similarity corresponding to each type of severe convection weather according to the preprocessed waveform data; and based on the Hamming distance, the cosine similarity and the waveform similarity, determining the target severe convection weather similarity. According to the invention, the accuracy of judging the severe convection weather can be improved, so that the conditions of misjudgment and missed judgment of the severe convection weather are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of weather monitoring, and in particular to a method for analyzing the similarity of severe convective weather. Background Art

[0002] Severe convective weather, as a very destructive weather phenomenon in nature, is known for its suddenness, high intensity and wide range of impact. This type of weather, such as thunderstorms, gales, hail, short-term heavy rainfall and even tornadoes, often brings huge impacts to the environment and human society in a short period of time. Radar technology plays a vital role in the monitoring and analysis of severe convective weather. Radar can obtain dynamic information of weather systems in real time by emitting electromagnetic waves and receiving signals reflected from weather targets. Among them, echo intensity and waveform are two particularly critical characteristic parameters.

[0003] The existing technology has several defects in the analysis of severe convection similarity, which are mainly reflected in the insufficient quantitative evaluation of echo characteristics and the limitations of waveform analysis methods. Traditional methods usually rely only on simple intensity indicators and fail to deeply explore the temporal changes of echoes, thus limiting the overall understanding and early warning capabilities of complex weather patterns. In addition, existing waveform analysis mostly uses linear models and lacks the capture of nonlinear characteristics, which makes it easy to misjudge and miss severe convective weather in practical applications. Summary of the invention

[0004] The present application aims to propose a severe convective weather similarity analysis method, which can improve the accuracy of judging severe convective weather, thereby reducing the misjudgment and missed judgment of severe convective weather.

[0005] The present application provides a method for analyzing similarity of severe convective weather, the method comprising:

[0006] Obtain current echo intensity data and current waveform data in current atmospheric echo data, and obtain historical echo intensity data of each severe convective weather;

[0007] Preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data;

[0008] According to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, the Hamming distance and cosine similarity corresponding to each severe convective weather are calculated;

[0009] Determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data;

[0010] Based on the Hamming distance, the cosine similarity and the waveform similarity, the target severe convective weather similarity is determined.

[0011] Compared with the prior art, this application has the following beneficial effects:

[0012] This method calculates the Hamming distance and cosine similarity corresponding to each severe convective weather according to the pre-processed echo intensity data and the historical echo intensity data of each severe convective weather, and adopts the method combining the Hamming distance and the cosine similarity to evaluate the similarity of the echo intensity, which can more comprehensively reflect the changing characteristics of the echo intensity. Then, according to the pre-processed waveform data, the waveform similarity corresponding to each severe convective weather is determined, and the target severe convective weather similarity is determined based on the Hamming distance, the cosine similarity and the waveform similarity. In this way, by comprehensively considering the Hamming distance and the cosine similarity calculated based on the echo intensity data, and considering the waveform similarity calculated based on the waveform data, the target severe convective weather similarity is determined together, which can improve the accuracy of the determined target severe convective weather similarity, so as to judge which severe convective weather the current echo intensity data and the current waveform data correspond to according to the accurate target severe convective weather similarity, which can improve the accuracy of judging the severe convective weather, thereby reducing the misjudgment and omission of severe convective weather.

[0013] In some embodiments, the calculating, according to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, the Hamming distance and the cosine similarity corresponding to each severe convective weather includes:

[0014] Representing the preprocessed echo intensity data as a first echo intensity binary sequence, and representing the historical echo intensity data of each severe convective weather as a second echo intensity binary sequence;

[0015] The Hamming distance corresponding to each severe convective weather is calculated according to the first echo intensity binary sequence and the second echo intensity binary sequence.

[0016] In some implementations, the Hamming distance corresponding to each severe convective weather is calculated according to the first echo intensity binary sequence and the second echo intensity binary sequence in the following manner:

[0017]

[0018] Wherein, A represents the first echo intensity binary sequence, B represents the second echo intensity binary sequence, a i represents the i-th element in the first echo intensity binary sequence, b i represents the i-th element in the second echo intensity binary sequence, and n represents the total number of elements in the echo intensity binary sequence.

[0019] In some embodiments, the calculating, according to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, the Hamming distance and the cosine similarity corresponding to each severe convective weather includes:

[0020] Representing the preprocessed echo intensity data as a first echo intensity vector, and representing the historical echo intensity data of each severe convective weather as a second echo intensity vector;

[0021] The cosine similarity corresponding to each severe convective weather is calculated based on the first echo intensity vector and the second echo intensity vector.

[0022] In some implementations, the cosine similarity corresponding to each severe convective weather is calculated according to the first echo intensity vector and the second echo intensity vector in the following manner:

[0023]

[0024] Wherein, X represents the first echo intensity vector, Y represents the second echo intensity vector, and x i represents the i-th component of the first echo intensity vector, y i represents the i-th component in the second echo intensity vector, and k represents the total number of components in the echo intensity vector.

[0025] In some implementations, determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data includes:

[0026] The preprocessed waveform data is input into a trained BP neural network model to obtain the waveform similarity corresponding to each severe convective weather output by the trained BP neural network model; wherein the trained BP neural network model is trained using waveform data of different single severe convective weather units.

[0027] In some implementations, determining the target severe convective weather similarity based on the Hamming distance, the cosine similarity, and the waveform similarity includes:

[0028] Obtaining the Hamming distance, cosine similarity and waveform similarity corresponding to each severe convective weather;

[0029] Based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather, the severe convective weather similarity corresponding to each severe convective weather is calculated;

[0030] The severe convective weather similarities corresponding to each severe convective weather are sorted, and the maximum severe convective weather similarity is selected as the target severe convective weather similarity.

[0031] In some implementations, the similarity of the severe convective weather corresponding to each severe convective weather is calculated based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather in the following manner:

[0032] S=αS H +βS C +γS BP

[0033] Where S represents the similarity of severe convective weather, α, β and γ represent weight coefficients, S H represents the Hamming distance, S C represents the cosine similarity, S BP Indicates the waveform similarity.

[0034] In some implementations, preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data includes:

[0035] De-noising the current echo intensity data and the current waveform data to obtain de-noised echo intensity data and de-noised waveform data;

[0036] Normalizing the denoised echo intensity data and the denoised waveform data to obtain normalized echo intensity data and normalized waveform data;

[0037] Feature extraction is performed on the normalized echo intensity data and the normalized waveform data to obtain preprocessed echo intensity data and preprocessed waveform data.

[0038] In some embodiments, the denoised echo intensity data and the denoised waveform data are normalized in the following manner:

[0039]

[0040] Wherein, x1' represents the normalized echo intensity data, x1 represents the denoised echo intensity data, and x1 min Indicates the minimum value of the echo intensity data after denoising, x1 max represents the maximum value of the denoised echo intensity data, x2' represents the normalized waveform data, x2 represents the denoised waveform data, x2 min represents the minimum value in the denoised waveform data, x2 max Indicates the maximum value in the denoised waveform data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0042] Figure 1 It is a flowchart of an embodiment of a method for analyzing similarity of severe convective weather provided by the present application;

[0043] Figure 2 It is a flow chart of a best embodiment of a severe convective weather similarity analysis method provided by the present application;

[0044] Figure 3 It is a radar echo map in an embodiment of a severe convective weather similarity analysis method provided in the present application. DETAILED DESCRIPTION

[0045] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0046] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0047] In the description of the present application, it should be understood that the descriptions involving orientation, such as the orientation or positional relationship indicated as up, down, etc., are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0048] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0049] Severe convective weather, as a very destructive weather phenomenon in nature, is known for its suddenness, high intensity and wide range of impact. This type of weather, such as thunderstorms, gales, hail, short-term heavy rainfall and even tornadoes, often brings huge impacts to the environment and human society in a short period of time. Radar technology plays a vital role in the monitoring and analysis of severe convective weather. Radar can obtain dynamic information of weather systems in real time by emitting electromagnetic waves and receiving signals reflected from weather targets. Among them, echo intensity and waveform are two particularly critical characteristic parameters.

[0050] The existing technology has several defects in the analysis of severe convection similarity, which are mainly reflected in the insufficient quantitative evaluation of echo characteristics and the limitations of waveform analysis methods. Traditional methods usually rely only on simple intensity indicators and fail to deeply explore the temporal changes of echoes, thus limiting the overall understanding and early warning capabilities of complex weather patterns. In addition, existing waveform analysis mostly uses linear models and lacks the capture of nonlinear characteristics, which makes it easy to misjudge and miss severe convective weather in practical applications.

[0051] In order to solve the above-mentioned problem that the linear model lacks the capture of nonlinear characteristics, which leads to the problem of misjudgment and omission of severe convective weather in practical applications, the present application proposes a severe convective weather similarity analysis method.

[0052] Reference Figure 1 , the embodiment of the present application provides a method for analyzing the similarity of severe convective weather, the method comprising the following steps:

[0053] Step S100, obtaining current echo intensity data and current waveform data in current atmospheric echo data, and obtaining historical echo intensity data of each severe convective weather;

[0054] Step S200, preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data;

[0055] Step S300, calculating the Hamming distance and cosine similarity corresponding to each severe convective weather according to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather;

[0056] Step S400, determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data;

[0057] Step S500: Determine the target severe convective weather similarity based on the Hamming distance, cosine similarity and waveform similarity.

[0058] In this embodiment, the Hamming distance and cosine similarity corresponding to each severe convective weather are calculated according to the pre-processed echo intensity data and the historical echo intensity data of each severe convective weather, and the method combining the Hamming distance and the cosine similarity is used to evaluate the similarity of the echo intensity, which can more comprehensively reflect the change characteristics of the echo intensity. Then, according to the pre-processed waveform data, the waveform similarity corresponding to each severe convective weather is determined, and the target severe convective weather similarity is determined based on the Hamming distance, the cosine similarity and the waveform similarity. In this way, by comprehensively considering the Hamming distance and the cosine similarity calculated based on the echo intensity data, and considering the waveform similarity calculated based on the waveform data, the target severe convective weather similarity is determined together, which can improve the accuracy of the determined target severe convective weather similarity, thereby judging which severe convective weather the current echo intensity data and the current waveform data correspond to according to the accurate target severe convective weather similarity, which can improve the accuracy of judging the severe convective weather, thereby reducing the situation of misjudgment and missed judgment of the severe convective weather.

[0059] The above-mentioned acquisition of current echo intensity data and current waveform data in current atmospheric echo data, as well as acquisition of historical echo intensity data of each severe convective weather, can be by acquiring the current echo intensity data and current waveform data in current atmospheric echo data through radar, as well as acquisition of historical echo intensity data of each severe convective weather.

[0060] The above-mentioned preprocessing of the current echo intensity data and the current waveform data may be preprocessing the current echo intensity data and the current waveform data by using a denoising, normalization or other method.

[0061] The above method of determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data may be to vectorize the preprocessed waveform data and the historical waveform data of each severe convective weather, and then use cosine similarity to calculate the waveform similarity corresponding to each severe convective weather according to the vectorized waveform data and the historical waveform data of each severe convective weather. A neural network model may also be used to predict the preprocessed waveform data to determine the waveform similarity corresponding to each severe convective weather. The neural network model may be a neural network model in the prior art known to those skilled in the art, such as a BP neural network model.

[0062] In some embodiments, the Hamming distance and cosine similarity corresponding to each severe convective weather are calculated based on the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, including:

[0063] The pre-processed echo intensity data are represented as a first echo intensity binary sequence, and the historical echo intensity data of each severe convective weather is represented as a second echo intensity binary sequence;

[0064] According to the binary sequence of the first echo intensity and the binary sequence of the second echo intensity, the Hamming distance corresponding to each severe convective weather is calculated.

[0065] In this embodiment, the Hamming distance is used to measure the number of different bits between two binary strings, which can directly reflect the difference between echo intensity data. The Hamming distance can measure the difference between two sets of echo data from a discrete perspective, focusing on the existence of echo data, and is suitable for processing discrete features.

[0066] In some embodiments, the Hamming distance corresponding to each severe convective weather is calculated according to the first echo intensity binary sequence and the second echo intensity binary sequence in the following manner:

[0067]

[0068] Among them, A represents the first echo intensity binary sequence, B represents the second echo intensity binary sequence, a i represents the i-th element in the binary sequence of the first echo intensity, b i represents the i-th element in the second echo intensity binary sequence, and n represents the total number of elements in the echo intensity binary sequence.

[0069] In some embodiments, the Hamming distance and cosine similarity corresponding to each severe convective weather are calculated based on the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, including:

[0070] The pre-processed echo intensity data is represented as a first echo intensity vector, and the historical echo intensity data of each severe convective weather is represented as a second echo intensity vector;

[0071] According to the first echo intensity vector and the second echo intensity vector, the cosine similarity corresponding to each severe convective weather is calculated.

[0072] In this embodiment, the cosine similarity evaluates the similarity between two vectors by calculating the cosine value of the angle between them. It is insensitive to the magnitude of the data, pays more attention to the difference in direction, and takes into account the directionality and overall trend of the data.

[0073] In some implementations, the cosine similarity corresponding to each severe convective weather is calculated based on the first echo intensity vector and the second echo intensity vector in the following manner:

[0074]

[0075] Where X represents the first echo intensity vector, Y represents the second echo intensity vector, and x i represents the i-th component in the first echo intensity vector, yi represents the i-th component in the second echo intensity vector, and k represents the total number of components in the echo intensity vector.

[0076] In some implementations, determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data includes:

[0077] The preprocessed waveform data is input into the trained BP neural network model to obtain the waveform similarity corresponding to each severe convective weather output by the trained BP neural network model; wherein the trained BP neural network model is trained using waveform data of different single severe convective weathers.

[0078] In this embodiment, the BP neural network model, as a powerful pattern recognition tool, can extract deep features from complex waveform data and conduct in-depth analysis of waveform features through its nonlinear mapping capability. Through BP neural network training, the trained BP neural network model can accurately identify waveform features under different weather conditions, thereby improving the accuracy of waveform similarity calculation.

[0079] In some implementations, determining the target severe convective weather similarity based on the Hamming distance, the cosine similarity, and the waveform similarity includes:

[0080] Obtain the Hamming distance, cosine similarity and waveform similarity corresponding to each severe convective weather;

[0081] Based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather, the similarity of severe convective weather corresponding to each severe convective weather is calculated;

[0082] The severe convective weather similarities corresponding to each severe convective weather are sorted, and the maximum severe convective weather similarity is selected as the target severe convective weather similarity.

[0083] In this embodiment, by comprehensively considering the Hamming distance and cosine similarity calculated based on the echo intensity data, and considering the waveform similarity calculated based on the waveform data, the target severe convective weather similarity is determined together, and the accuracy of the determined target severe convective weather similarity can be improved. According to the accurate target severe convective weather similarity, it is judged which severe convective weather the current echo intensity data and the current waveform data correspond to, which can improve the accuracy of judging severe convective weather, thereby reducing the situation of misjudgment and missed judgment of severe convective weather.

[0084] In some implementations, the similarity of severe convective weather corresponding to each severe convective weather is calculated based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather in the following manner:

[0085] S=αSH +βS C +γS BP

[0086] Among them, S represents the similarity of severe convective weather, α, β and γ represent weight coefficients, S H represents the Hamming distance, S C represents the cosine similarity, S BP Indicates waveform similarity.

[0087] In some implementations, preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data includes:

[0088] De-noising the current echo intensity data and the current waveform data to obtain de-noised echo intensity data and de-noised waveform data;

[0089] Normalizing the denoised echo intensity data and the denoised waveform data to obtain normalized echo intensity data and normalized waveform data;

[0090] Feature extraction is performed on the normalized echo intensity data and the normalized waveform data to obtain preprocessed echo intensity data and preprocessed waveform data.

[0091] In this embodiment, by preprocessing the current echo intensity data and the current waveform data, a good data foundation can be laid for the subsequent calculation of Hamming distance and cosine similarity, waveform similarity calculation, and determination of target severe convective weather similarity, thereby ensuring the accuracy of the echo intensity data and waveform data.

[0092] In some embodiments, the denoised echo intensity data and the denoised waveform data are normalized as follows:

[0093]

[0094] Among them, x1' represents the normalized echo intensity data, x1 represents the denoised echo intensity data, and x1 min Indicates the minimum value of the echo intensity data after denoising, x1 max represents the maximum value of the echo intensity data after denoising, x2' represents the normalized waveform data, x2 represents the denoised waveform data, and x2 min Indicates the minimum value in the denoised waveform data, x2 max Indicates the maximum value in the denoised waveform data.

[0095] To facilitate understanding by those skilled in the art, a set of best embodiments is provided below:

[0096] This embodiment effectively evaluates the change of echo intensity by combining Hamming distance and cosine similarity, and uses BP neural network model to deeply analyze waveform characteristics, and uses its powerful nonlinear mapping and pattern recognition capabilities to achieve more accurate analysis of severe convective weather. Through self-learning and optimization process, BP neural network model can automatically extract key features in waveform, and establish a mapping relationship between echo waveform and severe convective weather type, so as to improve the accuracy and efficiency of weather forecast.

[0097] In summary, refer to Figure 2 The purpose of this embodiment is to overcome the shortcomings of the existing technology and to achieve more accurate and comprehensive monitoring and analysis of severe convective weather by introducing new analysis methods and algorithms, thereby enhancing the ability to respond to the impact of severe convective weather.

[0098] 1. Data preprocessing.

[0099] (1) Data acquisition and extraction.

[0100] The echo data in the atmosphere obtained by radar mainly includes echo intensity data and waveform information (i.e. waveform data). The echo intensity reflects the reflection ability of the target object, while the waveform provides more detailed characteristics of the target object. The raw data of echo intensity is the radar echo map, refer to Figure 3 .

[0101] (2) Data denoising.

[0102] Filtering technology (e.g., Gaussian filtering) is used to denoise the raw data (i.e., echo intensity data and waveform data obtained by radar) to remove noise caused by environmental factors or equipment errors to ensure the accuracy of data points. Gaussian filtering uses Gaussian functions to perform weighted averaging on data to make the data smoother.

[0103] (3) Data normalization.

[0104] Normalize the denoised echo intensity data and waveform data to the same scale range, usually 0,1, to facilitate subsequent similarity calculation and model training. The normalization formula is:

[0105]

[0106] Among them, x1' represents the normalized echo intensity data, x1 represents the denoised echo intensity data, and x1 min Indicates the minimum value of the echo intensity data after denoising, x1 max represents the maximum value of the echo intensity data after denoising, x2' represents the normalized waveform data, x2 represents the denoised waveform data, and x2 minIndicates the minimum value in the denoised waveform data, x2 max Indicates the maximum value in the denoised waveform data.

[0107] (4) Feature extraction

[0108] Feature values ​​are extracted from the normalized data, including statistical features such as peak value, mean value and variance extracted from the echo intensity data, and features such as frequency component extracted from the waveform data. The waveform is converted from the time domain to the frequency domain through Fourier transform to obtain the frequency component.

[0109] 2. Echo intensity similarity calculation.

[0110] The echo intensity similarity calculation adopts a method combining Hamming distance and cosine similarity to ensure accurate comparison of echo intensities of different severe convective weather.

[0111] (1) Hamming distance calculation.

[0112] The currently acquired echo intensity data is represented as a binary sequence (i.e., the first echo intensity binary sequence) a1, a2, ..., a n , the historical echo intensity data is represented as a binary sequence (i.e., the second echo intensity binary sequence) b1, b2, ..., b n The Hamming distance is used to measure the degree of difference between two binary sequences.

[0113]

[0114] Among them, A represents the first echo intensity binary sequence, B represents the second echo intensity binary sequence, a i represents the i-th element in the binary sequence of the first echo intensity, b i represents the i-th element in the second echo intensity binary sequence, n represents the total number of elements in the echo intensity binary sequence, d(A, B) is the obtained Hamming distance, and the closer the d(A, B) value is to 0, the better the similarity.

[0115] (2) Cosine similarity calculation.

[0116] The currently acquired echo intensity data and the historical echo intensity data are represented as vector X (ie, the first echo intensity vector) and vector Y (ie, the second echo intensity vector), and the cosine similarity is used to measure the similarity between the two vectors.

[0117]

[0118] Among them, x j and iThey represent the i-th component of vector X and vector Y respectively. cos(x,y) represents the cosine of the angle between variables x and y. If the variables are closely correlated, the angle is close to 0 and the cosine is close to 1; otherwise, it is close to 0.

[0119] 3. Waveform similarity analysis.

[0120] The waveform similarity analysis uses the BP neural network model to identify the similarity of waveforms by training the model.

[0121] (1) Construction of BP neural network model.

[0122] 1) Network structure.

[0123] The construction of BP neural network (Back propagation neural network) refers to building a multi-layer perceptron model and training it through the back propagation algorithm to solve the nonlinear mapping problem. The process includes defining the number of layers, number of nodes, activation function, weight initialization, error calculation and training method of the network.

[0124] Input layer: The number of nodes is n, which represents the dimension of the input waveform data.

[0125] Hidden layer: one or more hidden layers. The number of nodes in each layer can be set according to actual needs, generally m.

[0126] Output layer: The number of nodes is 1, indicating waveform similarity.

[0127] 2) Activation function.

[0128] The activation function is used for nonlinear transformation between the hidden layer and the output layer. Common activation functions include Sigmoid function and ReLU function. Sigmoid function is suitable for scenarios where the output value is between (0, 1), while ReLU function is suitable for processing high-dimensional data. By introducing the activation function, the BP neural network can capture the nonlinear patterns in severe convective weather data, especially the complex relationship between echo intensity and time and space.

[0129] (2) BP neural network training.

[0130] 1) Forward propagation.

[0131] Forward propagation is the process by which the model calculates the output based on the input data. The output of each layer of nodes is added by weight and bias, and then processed by the activation function and passed to the output layer layer by layer. The formula for calculating the output of each node is:

[0132]

[0133] Among them, jis the output of the jth hidden layer node, w ij is the weight from the input layer to the hidden layer, x i is the input, b j is the bias and f is the activation function.

[0134] 2) Error calculation.

[0135] The error of the output layer refers to the difference between the model output and the actual target, which is often calculated using the mean square error (MSE). The formula for calculating the error of the output layer is:

[0136]

[0137] Where E is the error function, y k is the expected output, o k is the actual output.

[0138] 3) Error back propagation.

[0139] Error back propagation is the process of adjusting weights and biases layer by layer according to the output error. The BP algorithm calculates the gradient of the error and updates the parameters of each layer in reverse, so that the network gradually approaches the target output. According to the error back propagation algorithm, the weight and bias gradients are calculated and updated. The formula is:

[0140]

[0141] Where η is the learning rate, Represents the bias, which updates the weights and bias inversely by calculating the error between the output and the true value.

[0142] 4. Comprehensive analysis of similarity.

[0143] The echo intensity similarity (Hamming distance and cosine similarity) is combined with the waveform similarity (BP neural network output) to calculate the comprehensive similarity, thereby achieving accurate identification of severe convective weather.

[0144] S=αS H +βS C +γS BP

[0145] Among them, S H represents the Hamming distance similarity, which represents the binary difference of echo intensity; S C represents cosine similarity, which indicates the vector similarity of echo intensity; S BP Represents the waveform similarity of the BP neural network output; α, β and γ are weight coefficients, satisfying α+β+γ=1. According to actual needs and historical data, the weight coefficients are determined through experiments, and the weights are optimized using machine learning algorithms to improve the accuracy and robustness of similarity calculation.

[0146] In this embodiment, echo intensity is an important indicator for identifying severe convective weather. By combining the Hamming distance and cosine similarity, the similarity of echo intensity can be evaluated more comprehensively. The Hamming distance can measure the difference between two sets of echo data from a discrete perspective, focusing on the presence or absence of echo data, and is suitable for processing discrete features. The cosine similarity, on the other hand, evaluates the vector angle of the echo data from an angle, mainly considering the directionality and overall trend of the data. The combination of the two enables the echo intensity analysis to focus on both local differences and overall similarities, forming a multi-dimensional and three-dimensional basis for identifying severe convective weather.

[0147] However, echo intensity is only part of the characteristics of severe convective weather. In order to further improve the recognition accuracy, it is particularly important to add BP neural network to perform waveform similarity analysis. As a powerful pattern recognition tool, BP neural network can extract deep features from complex waveform data and conduct in-depth analysis of waveform features through its nonlinear mapping ability. Through training, BP neural network can accurately identify waveform features under different weather conditions, thereby improving the accuracy of waveform similarity calculation.

[0148] This comprehensive similarity calculation method that combines echo intensity similarity with waveform similarity reflects the multi-level data fusion in severe convective weather analysis. By effectively integrating information at different levels, the comprehensive similarity calculation not only improves the reliance on a single data source, but also enhances the accuracy and reliability of the analysis through cross-validation and complementarity of multi-source information. Especially in complex meteorological phenomena such as severe convective weather, the traditional single similarity calculation method is often insufficient to cope with its high complexity and nonlinear changes, while this comprehensive similarity method can comprehensively analyze the weather evolution process from multiple angles, greatly improving the ability to accurately identify severe convective weather.

[0149] Combining the traditional Hamming distance and cosine similarity with the BP neural network breaks the limitations of single similarity calculation and constructs a new recognition framework that integrates statistics, geometry and deep learning. This method is not only unique in the precise analysis of severe convective weather, but also provides an expandable and innovative direction for future applications in other complex meteorological systems. By combining the BP neural network with the Hamming distance and cosine similarity, it is not only possible to preliminarily evaluate the echo intensity changes, but also to further capture the complex nonlinear relationship of waveform characteristics through deep learning. This multi-level and multi-dimensional similarity analysis method provides an innovative solution for the precise prediction and evaluation of severe convective weather, and effectively improves the scientificity and practicality of similarity analysis of severe convective weather.

[0150] Compared with the prior art, this embodiment has the following beneficial effects:

[0151] 1) Comprehensively evaluate the echo strength.

[0152] The embodiment of the present application adopts a method combining Hamming distance and cosine similarity to evaluate the similarity of echo intensity. Hamming distance is used to measure the number of different bits between two binary strings, which can intuitively reflect the difference between echo intensity data; while cosine similarity evaluates their similarity by calculating the cosine value of the angle between two vectors, which is insensitive to the magnitude of the data and pays more attention to the difference in direction. The combination of the two can more comprehensively reflect the changing characteristics of echo intensity.

[0153] 2) Waveform feature extraction and classification.

[0154] The embodiment of the present application uses BP neural network (Back Propagation Neural Network) to extract and classify the waveform features of radar echoes. BP neural network has powerful nonlinear mapping and pattern recognition capabilities, can automatically extract key features from waveform data, and establish a mapping relationship between waveforms and severe convective weather types. This method can effectively cope with complex and changeable waveform patterns and improve the accuracy and efficiency of classification.

[0155] 3) Similarity analysis method.

[0156] Based on the above analysis of echo intensity and waveform, the embodiment of the present application proposes a new similarity analysis method for evaluating the similarity between different severe convective weather processes. This method not only takes into account the change in echo intensity, but also integrates the information of waveform characteristics, which can more comprehensively reflect the evolution law and characteristics of the weather system.

[0157] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A severe convective weather similarity analysis method, characterized in that: The method comprises: Obtain current echo intensity data and current waveform data in current atmospheric echo data, and obtain historical echo intensity data of each severe convective weather; Preprocessing the current echo intensity data and the current waveform data to obtain preprocessed echo intensity data and preprocessed waveform data; According to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather, the Hamming distance and cosine similarity corresponding to each severe convective weather are calculated; Determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data; Based on the Hamming distance, the cosine similarity and the waveform similarity, the target severe convective weather similarity is determined.

2. The severe convective weather similarity analysis method according to claim 1, characterized in that: The method of calculating the Hamming distance and cosine similarity corresponding to each severe convective weather according to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather includes: Representing the preprocessed echo intensity data as a first echo intensity binary sequence, and representing the historical echo intensity data of each severe convective weather as a second echo intensity binary sequence; The Hamming distance corresponding to each severe convective weather is calculated according to the first echo intensity binary sequence and the second echo intensity binary sequence.

3. The severe convective weather similarity analysis method according to claim 2, characterized in that: The Hamming distance corresponding to each severe convective weather is calculated according to the first echo intensity binary sequence and the second echo intensity binary sequence in the following manner: Wherein, A represents the first echo intensity binary sequence, B represents the second echo intensity binary sequence, a i represents the i-th element in the first echo intensity binary sequence, b i represents the i-th element in the second echo intensity binary sequence, and n represents the total number of elements in the echo intensity binary sequence.

4. The severe convective weather similarity analysis method according to claim 1, characterized in that: The method of calculating the Hamming distance and cosine similarity corresponding to each severe convective weather according to the preprocessed echo intensity data and the historical echo intensity data of each severe convective weather includes: Representing the preprocessed echo intensity data as a first echo intensity vector, and representing the historical echo intensity data of each severe convective weather as a second echo intensity vector; The cosine similarity corresponding to each severe convective weather is calculated based on the first echo intensity vector and the second echo intensity vector.

5. The severe convective weather similarity analysis method according to claim 4, characterized in that: The cosine similarity corresponding to each severe convective weather is calculated according to the first echo intensity vector and the second echo intensity vector in the following manner: Wherein, X represents the first echo intensity vector, Y represents the second echo intensity vector, and x i represents the i-th component of the first echo intensity vector, y i represents the i-th component in the second echo intensity vector, and k represents the total number of components in the echo intensity vector.

6. The severe convective weather similarity analysis method according to claim 1, characterized in that: Determining the waveform similarity corresponding to each severe convective weather according to the preprocessed waveform data includes: The preprocessed waveform data is input into a trained BP neural network model to obtain the waveform similarity corresponding to each severe convective weather output by the trained BP neural network model; wherein the trained BP neural network model is trained using waveform data of different single severe convective weather units.

7. The severe convective weather similarity analysis method according to claim 1, characterized in that: The determining the target severe convective weather similarity based on the Hamming distance, the cosine similarity and the waveform similarity includes: Obtaining the Hamming distance, cosine similarity and waveform similarity corresponding to each severe convective weather; Based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather, the severe convective weather similarity corresponding to each severe convective weather is calculated; The severe convective weather similarities corresponding to each severe convective weather are sorted, and the maximum severe convective weather similarity is selected as the target severe convective weather similarity.

8. The severe convective weather similarity analysis method according to claim 7, characterized in that: The similarity of the severe convective weather corresponding to each severe convective weather is calculated based on the waveform similarity, Hamming distance and cosine similarity corresponding to each severe convective weather in the following manner: S=αS H +βS c +γS BP Where S represents the similarity of severe convective weather, α, β and γ represent weight coefficients, S H represents the Hamming distance, S C represents the cosine similarity, S BP Indicates the waveform similarity.

9. The severe convective weather similarity analysis method according to claim 1, characterized in that: The preprocessing of the current echo intensity data and the current waveform data to obtain the preprocessed echo intensity data and the preprocessed waveform data includes: De-noising the current echo intensity data and the current waveform data to obtain de-noised echo intensity data and de-noised waveform data; Normalizing the denoised echo intensity data and the denoised waveform data to obtain normalized echo intensity data and normalized waveform data; Feature extraction is performed on the normalized echo intensity data and the normalized waveform data to obtain preprocessed echo intensity data and preprocessed waveform data.

10. The severe convective weather similarity analysis method according to claim 9, characterized in that: The denoised echo intensity data and the denoised waveform data are normalized in the following manner: Wherein, x1' represents the normalized echo intensity data, x1 represents the denoised echo intensity data, and x1 min Indicates the minimum value of the echo intensity data after denoising, x1 max represents the maximum value of the denoised echo intensity data, x2' represents the normalized waveform data, x2 represents the denoised waveform data, x2 min represents the minimum value in the denoised waveform data, x2 max Indicates the maximum value in the denoised waveform data.

Images