CN115542279A - Weather radar clutter classification and identification method and device - Google Patents
Weather radar clutter classification and identification method and device Download PDFInfo
- Publication number
- CN115542279A CN115542279A CN202211156539.7A CN202211156539A CN115542279A CN 115542279 A CN115542279 A CN 115542279A CN 202211156539 A CN202211156539 A CN 202211156539A CN 115542279 A CN115542279 A CN 115542279A
- Authority
- CN
- China
- Prior art keywords
- data
- radar
- training
- training data
- meteorological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/411—Identification of targets based on measurements of radar reflectivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/95—Radar or analogous systems specially adapted for specific applications for meteorological use
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/95—Radar or analogous systems specially adapted for specific applications for meteorological use
- G01S13/958—Theoretical aspects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/414—Discriminating targets with respect to background clutter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method and a device for classifying and identifying meteorological radar clutter, wherein the method comprises the steps of obtaining tested meteorological radar data and preprocessing the meteorological radar data; inputting the preprocessed tested meteorological radar data into the trained SegNet network model to obtain a classification recognition result; the training process of the SegNet network model comprises the following steps: acquiring and preprocessing trained meteorological radar data; integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type; respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase; processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set; initializing a SegNet network model, and performing iterative training based on a training data set and a label set; the method can effectively classify and identify the meteorological radar clutter so as to obtain high-quality meteorological radar data.
Description
Technical Field
The invention relates to a method and a device for classifying and identifying clutter of a meteorological radar, and belongs to the technical field of meteorological radars.
Background
The important premise for analyzing and processing the meteorological radar data is to establish an intelligent meteorological radar quality control model. The identification and classification of radar clutter has important application value in a plurality of fields. In the field of aviation, the system not only has an early warning effect on aviation danger brought by complex weather, but also can provide decision basis for route planning; in the field of artificial influence weather, the precision of quantitative detection of rainfall can be improved, and important reference basis can be provided for operation decision and evaluation of artificial influence weather.
In order to obtain high-quality meteorological radar data, a primary problem is to reasonably distinguish meteorological echoes from non-meteorological echoes. The radar clutter classification identification method comprises the following steps: a statistical decision method, a decision graph method, etc. The statistical decision method integrates the polarization characteristics of precipitation particles and clutter particles and the research experience of predecessors, and realizes the classification of the precipitation particles and the clutter particles by setting the polarization parameter threshold values of different precipitation particles and clutter particles, but the threshold value of the method is generally fixed, so when the environment in a researched target area changes, the classification precision is greatly influenced. The decision diagram method classifies the precipitation particles and the clutter particles according to the predetermined type boundary, but the classification accuracy of the decision diagram method is influenced to a certain extent because covariance matrixes of different precipitation particles and clutter particles received by the weather radar are not mutually independent. For the classification and identification tasks of precipitation particles and clutter particles, the problem of low intelligence of the traditional algorithm and manual detection needs to be solved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a method and a device for classifying and identifying meteorological radar clutter, which can effectively classify and identify the meteorological radar clutter so as to obtain high-quality meteorological radar data.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides a method for classifying and identifying meteorological radar clutter, which comprises the following steps:
acquiring and preprocessing tested meteorological radar data;
inputting the preprocessed tested meteorological radar data into the trained SegNet network model to obtain a classification recognition result;
wherein the training process of the SegNet network model comprises the following steps:
acquiring and preprocessing trained meteorological radar data; the meteorological radar data comprise radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase;
integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
initializing a SegNet network model, and performing iterative training based on a training data set and a label set until a preset maximum iteration number is reached or a weight parameter of the SegNet network model is converged.
Optionally, the preprocessing includes data cleansing and scale expansion;
the data cleaning comprises searching for NaN data values and radar reflectivity smaller than zero in meteorological radar data, and respectively setting the NaN data values and the radar reflectivity smaller than zero;
and the scale expansion comprises the step of expanding the meteorological radar data in a mode of aligning the upper left and filling zero in the lower right.
Optionally, the separately calculating the standard deviation of the training data sets corresponding to the radar reflectivity and the differential phase includes:
traversing a training data set corresponding to radar reflectivity, and calculating the standard deviation S of the radar reflectivity within the range of 1km D (Z H )：
In the formula, m (Z) H ) Is radar reflectivity Z in the range of 1km H Average value of (1), n Z The number of data points of radar reflectivity within 1km range;
traversing a training data set corresponding to the differential phase, and calculating the standard deviation of the differential phase within the range of 2km
In the formula, m (phi) DP ) Is differential phase phi in the range of 2km DP Average value of (1), n φ The number of data points of differential phase in the range of 2 km.
Optionally, the processing the training data set and the texture data by using the fuzzy logic algorithm to obtain the tag set of the particle phase type includes:
adopting a trapezoidal function as a membership function of a fuzzy logic algorithm, carrying out fuzzy logic operation by taking training data and texture data in a training data set as input parameters, and obtaining membership corresponding to a particle phase type as fuzzy logic output; the trapezoidal function is:
in the formula, X 1 、X 2 、X 3 、X 4 Is a threshold parameter of a trapezoidal function, P (j) (x i ) The membership degree of the jth input parameter to the ith particle phase state type;
performing defuzzification on the fuzzy logic output by adopting a weighted average judgment method to obtain a membership integrated value corresponding to the particle phase type:
in the formula, S i For membership integrated values, W, of jth input parameter to ith particle phase type ij The weight coefficient of the jth input parameter of the ith particle phase type is obtained, and J is the number of the input parameters;
if the membership integrated value of the input parameter is 0, the particle phase type corresponding to the input parameter is no meteorological echo, and the label of the particle phase type is set to be 0;
if the membership integrated value of the input parameter is greater than the set threshold, the particle phase type corresponding to the input parameter is a clutter, and the label of the particle phase type is set to be 1;
if the membership integrated value of the input parameter is smaller than the set threshold and larger than 0, the particle phase type corresponding to the input parameter is other, and the label of the particle phase type is set to be 2;
and constructing a tag set of the particle phase type according to the tags of the input parameters.
Optionally, the performing iterative training based on the training data set and the label set includes:
an Encoder network downsampling training data based on a SegNet network model to obtain data characteristics;
sampling characteristic data on a Decoder network based on a SegNet network model to obtain a prediction result;
and calculating the loss of the prediction result and the label thereof based on the cross entropy loss function, and updating the weight parameter of the SegNet network model according to loss back propagation.
Optionally, the Encoder network includes:
a first layer consisting of two 64 x 3 convolutions and maximum pooled downsampling in sequence;
a second layer consisting of, in order, two 128 x 3 convolutions and maximum pooled downsampling;
the third layer consists of three convolutions of 256 multiplied by 3 and the maximum pooled downsampling in sequence;
a fourth layer consisting of three 512 x 3 convolutions and maximum pooled downsampling in sequence;
a fifth layer consisting of three 5212 × 3 × 3 convolutions and maximum pooled downsampling in sequence;
the Decoder network includes:
a first layer consisting of, in order, inverse max-pooling upsampling and three 521 × 3 × 3 convolutions;
a second layer consisting of, in order, inverse max-pooling upsampling and three 521 × 3 × 3 convolutions;
the third layer consists of inverse maximum pooling upsampling and two convolutions of 256 multiplied by 3 in turn;
a fourth layer, consisting of inverse maximal pooled upsampling and two 128 × 3 × 3 convolutions in sequence;
the fifth layer, in turn, consists of inverse max pooling upsampling and two 64 x 3 convolutions.
Optionally, in the iterative training process, the Pixel Accuracy is used as an Accuracy evaluation index to obtain the proximity between the prediction result and the label.
In a second aspect, the invention provides a weather radar clutter classification and identification device, comprising:
the preprocessing module is used for acquiring and preprocessing the tested meteorological radar data;
the classification identification module is used for inputting the preprocessed tested meteorological radar data into the trained SegNet network model to obtain a classification identification result;
a model training module to:
acquiring and preprocessing trained meteorological radar data; the meteorological radar data comprise radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase;
integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
initializing a SegNet network model, and performing iterative training based on a training data set and a label set until a preset maximum iteration number is reached or a weight parameter of the SegNet network model is converged.
In a third aspect, the invention provides a weather radar clutter classification and identification device, which comprises a processor and a storage medium;
the storage medium is to store instructions;
the processor is configured to operate in accordance with the instructions to perform the steps according to the above-described method.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.
Compared with the prior art, the invention has the following beneficial effects:
according to the meteorological radar clutter classification and identification method and device, a five-channel training data set is constructed by obtaining radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase, a label set of the training data is obtained through a fuzzy logic algorithm, a SegNet network model is trained through the training data set and the label set, and meteorological radar clutter classification and identification are carried out through the trained SegNet network model, so that meteorological radar clutter can be effectively classified and identified, and high-quality meteorological radar data are obtained.
Drawings
Fig. 1 is a flowchart of a weather radar clutter classification and identification method according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
as shown in fig. 1, the invention provides a method for classifying and identifying meteorological radar clutter, which comprises the following steps:
1. acquiring and preprocessing tested meteorological radar data;
2. inputting the preprocessed tested meteorological radar data into a trained SegNet network model to obtain a classification recognition result;
the training process of the SegNet network model comprises the following steps:
s101, acquiring and preprocessing trained meteorological radar data;
s102, integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
s103, respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
s104, processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
and S105, initializing a SegNet network model, and performing iterative training based on the training data set and the label set until a preset maximum iteration number or a weight parameter of the SegNet network model is converged.
Wherein performing iterative training based on the training data set and the label set comprises:
s201, downsampling training data of an Encoder network based on a SegNet network model to obtain data characteristics;
s202, sampling characteristic data on a Decoder network based on a SegNet network model to obtain a prediction result;
s203, calculating the loss of the prediction result and the label thereof based on the cross entropy loss function, and updating the weight parameter of the SegNet network model according to loss back propagation.
(1) The weather radar data provided by the embodiment comprises radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase, and is stored through a numpy file.
(2) Preprocessing comprises data cleaning and scale expansion;
the data cleaning comprises searching NaN (null data) data values and radar reflectivity smaller than zero in meteorological radar data, and respectively setting the NaN data values and the radar reflectivity to zero;
the scale expansion comprises the step of expanding the meteorological radar data in a mode of upper left alignment and lower right zero padding, the size of the collected data is 336 multiplied by 920, and the expansion is 384 multiplied by 1088 in order to meet the maximum pooling operation of the SegNet network model.
(3) Calculating the standard deviation of the training data set corresponding to the radar reflectivity and the differential phase respectively comprises the following steps:
traversing a training data set corresponding to radar reflectivity, and calculating the standard deviation S of the radar reflectivity within the range of 1km D (Z H )：
In the formula, m (Z) H ) Is radar reflectivity Z in the range of 1km H Average value of (3), n Z The number of data points of radar reflectivity within a range of 1 km;
traversing a training data set corresponding to the differential phase, and calculating the standard deviation of the differential phase within the range of 2km
In the formula, m (phi) DP ) Is differential phase phi in the range of 2km DP Average value of (1), n φ The number of data points of the differential phase in the range of 2 km.
(4) Processing the training data set and the texture data by adopting a fuzzy logic algorithm to obtain a particle phase state type label set comprises the following steps:
adopting a trapezoidal function as a membership function of a fuzzy logic algorithm, carrying out fuzzy logic operation by taking training data and texture data in a training data set as input parameters, and obtaining membership corresponding to particle phase state types as fuzzy logic output; the trapezoidal function is:
in the formula, X 1 、X 2 、X 3 、X 4 Is a threshold parameter of a trapezoidal function, P (j) (x i ) The membership degree of the jth input parameter to the ith particle phase state type;
and (3) performing defuzzification on the fuzzy logic output by adopting a weighted average judgment method to obtain a membership integrated value corresponding to the particle phase type:
in the formula, S i For membership integrated values, W, of jth input parameter to ith particle phase type ij The weight coefficient of the jth input parameter of the ith particle phase type is obtained, and J is the number of the input parameters;
if the membership integrated value of the input parameter is 0, the particle phase type corresponding to the input parameter is no meteorological echo, and the label of the particle phase type is set to be 0;
if the membership integrated value of the input parameter is greater than the set threshold, the particle phase type corresponding to the input parameter is a clutter, and the label of the particle phase type is set to be 1;
if the membership integration value of the input parameter is smaller than the set threshold and larger than 0, the particle phase type corresponding to the input parameter is other, and the label of the particle phase type is set to be 2;
and constructing a tag set of the particle phase type according to the tags of the input parameters.
(5) The numpy-type training data set is converted into (5 × 384 × 1088) tensor-type data, and the training data and its corresponding label are combined into one dataset. Setting the batch of the training data set to 1, loading the tenor with the size of (1 × channel × 384 × 1088) by using the DataLoader method in the pytorch, wherein the channel of the training data is 5 (training data of 5 data types as 5 input channel data), and the channel of the label is 1.
The Encoder network is designed to have the structure as follows:
a first layer consisting of two 64 x 3 convolutions and maximum pooled downsampling in sequence;
a second layer consisting of, in order, two 128 x 3 convolutions and maximum pooled downsampling;
the third layer consists of three 256 multiplied by 3 convolutions and maximum pooled downsampling in sequence;
a fourth layer consisting of three 512 x 3 convolutions and maximum pooled downsampling in sequence;
a fifth layer consisting of three 5212 × 3 × 3 convolutions and maximum pooled downsampling in sequence;
according to the network structure, the training data of (1 × 5 × 384 × 1088) is processed to obtain the feature data of (1 × 512 × 6 × 17), wherein 512 represents the number of feature channels.
The design of the Decoder network structure is as follows:
a first layer consisting of, in order, inverse max-pooling upsampling and three 521 × 3 × 3 convolutions;
a second layer consisting of, in order, inverse max-pooling upsampling and three 521 × 3 × 3 convolutions;
the third layer consists of inverse maximum pooling upsampling and two convolutions of 256 multiplied by 3 in sequence;
a fourth layer consisting of inverse maximal pooled upsampling and two 128 x 3 convolutions in sequence;
the fifth layer, in turn, consists of inverse max pooling upsampling and two 64 x 3 convolutions.
According to the network structure, (1 × 512 × 6 × 17) feature data is processed to obtain (1 × 3 × 384 × 1088) prediction data, where 3 represents three categories of labels corresponding to the number of channels.
Wherein, the Encoder network further includes:
setting the parameter size of convolution kernel of Encoder network in SegNet network model as 3, stride as 1, padding parameter as 1, representing that using square convolution kernel with 3 x 3 moving step as 1, when convolution operation surpasses data edge, filling a circle of zero around data to prevent boundary-crossing abnormity. Adopting the same convolution for different convolution layers to extract training data characteristics; the expression for the convolution operation is as follows:
in the formula, H in Indicates the length of the input data, W in Representing the width of the input data, K H Representing the length of the convolution kernel, K W Representing the width of the convolution kernel, P the number of zero-filled turns, and S the shift step of the convolution kernel.
Because the data distribution characteristics after each convolution are inconsistent, the latter convolution layer needs to continuously adapt to the output change of the former convolution layer, and the decoupling between layers in the network is reduced. And the data before convolution is normalized by batch standardization, and the distribution characteristics of the data are fixed, so that the network learning is more stable. The batch normalization expression is as follows:
wherein (x) i ) (b) B representing input of current batch th Layer i of sample th Value of input node, μ (x) i ) Is the mean value of the input data, σ (x) i ) For the standard deviation of the input data, e is the minimum value to prevent the introduction of the divide-by-zero, and γ and β are the scale and shift parameters to be learned.
And a Relu activation function is used to increase the nonlinear relation between the convolution layers and avoid the situation of gradient disappearance. Relu will make a part of convolution output 0, thus causing sparsity of the network, reducing interdependence relation of parameters and alleviating the occurrence of overfitting problem. The expression for Relu is as follows:
f(x)＝max(0,x)
and carrying out maximum pooling downsampling on the data after Relu, picking the data points with more information, effectively removing redundant information and realizing the extraction of the characteristics. And storing index information of the maximum value while downsampling, wherein the expression of maximum pooling is as follows:
where f represents the size of the pooled kernel and s represents the step size of the pooled kernel movement.
The Decoder network further includes:
and (5) performing inverse pooling on the feature data after the convolution operation, and gradually recovering the size of the data. Since the maximum pooling records the index of the maximum value, the data at the index position is directly restored during the inverse pooling, and 0 is filled in other positions, so that the original size of the data is gradually restored. The expression for anti-pooling is as follows:
X out ＝(X in -1)×s+f
the Decoder network adopts same convolution to reduce data characteristic channels after inverse pooling, the parameter size of a convolution kernel is 3, stride is 1, padding parameter is 1, the length and width of data before and after convolution of different convolution layers do not occur, and only the number of the characteristic channels is changed. For the data after convolution, the distribution characteristics of batch standardized stable data are adopted, and the learning ability of the network is improved. And secondly, a Relu activation function is used to increase the nonlinearity between convolution layers and avoid the situation of gradient disappearance.
(6) Calculating the loss of the prediction result and the label thereof based on the cross entropy loss function comprises the following steps:
and calculating the probability of each category of the predicted data by using a softmax function, wherein the sum of the probabilities of corresponding positions on each channel is 1, and the index of the channel to which the maximum probability belongs is the predicted label of the data point. The expression for Softmax is as follows:
in the formula, X i Is i th Data points on the channel.
And calculating cross entropy loss between the predicted data and the label as loss between a predicted value and a true value, and updating the gradient and parameter values of the weight in the SegNet network model by using a back propagation mechanism in the pytorch, so that the prediction precision of SegNet is improved. The expression of the cross entropy loss function is as follows:
in the formula, p i Is the true tag value, q i Is the predicted data value after softmax calculation.
(7) In the iterative training process, a Pixel Accuracy is used as an Accuracy evaluation index to obtain the approximation degree of a prediction result and a label;
and selecting proper training times according to the value of the hyper-parameter learning rate, and continuously training the SegNet network model. And in the training iteration process, saving the model parameter with the minimum current loss. And after the network training is finished, loading an optimal network model, inputting a test data set to obtain prediction data, and checking the approximation degree of the prediction data and the actual value of the label by using the Pixel Accuracy as an Accuracy evaluation index. The expression for the Pixel Accuracy calculation is as follows:
wherein k is the number of target classes, P ii Number of pixel points, P, of prediction pairs ij The number of pixel points classified as i-type but j-type.
The second embodiment:
the embodiment of the invention provides a meteorological radar clutter classification and identification device, which comprises:
the preprocessing module is used for acquiring and preprocessing the tested meteorological radar data;
the classification identification module is used for inputting the preprocessed tested meteorological radar data into the trained SegNet network model to obtain a classification identification result;
a model training module to:
acquiring and preprocessing trained meteorological radar data; the meteorological radar data comprise radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase;
integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
initializing a SegNet network model, and performing iterative training based on a training data set and a label set until a preset maximum iteration number is reached or a weight parameter of the SegNet network model is converged.
Example three:
based on the first embodiment, the embodiment of the invention provides a meteorological radar clutter classification and identification device, which comprises a processor and a storage medium, wherein the processor is used for processing a weather radar clutter classification and identification signal;
a storage medium to store instructions;
the processor is configured to operate in accordance with instructions to perform steps in accordance with the above-described method.
Example four:
based on the first embodiment, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program realizes the steps of the above method when being executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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 means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
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 such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A meteorological radar clutter classification and identification method is characterized by comprising the following steps:
acquiring and preprocessing tested meteorological radar data;
inputting the preprocessed tested meteorological radar data into a trained SegNet network model to obtain a classification recognition result;
wherein the training process of the SegNet network model comprises the following steps:
acquiring and preprocessing trained meteorological radar data; the meteorological radar data comprise radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase;
integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
initializing a SegNet network model, and performing iterative training based on a training data set and a label set until a preset maximum iteration number is reached or a weight parameter of the SegNet network model is converged.
2. The weather radar clutter classification and identification method according to claim 1, wherein the preprocessing comprises data cleaning and scale expansion;
the data cleaning comprises searching for NaN data values and radar reflectivity smaller than zero in meteorological radar data, and respectively setting the NaN data values and the radar reflectivity smaller than zero;
and the scale expansion comprises the step of expanding the meteorological radar data in a mode of upper left alignment and lower right zero padding.
3. The method for classifying and identifying weather radar clutter according to claim 1, wherein the calculating the standard deviation of the training data set corresponding to radar reflectivity and differential phase respectively comprises:
traversing a training data set corresponding to the radar reflectivity, and calculating the standard deviation S of the radar reflectivity within 1km range D (Z H )：
In the formula, m (Z) H ) Is radar reflectivity Z in the range of 1km H Average value of (1), n Z The number of data points of radar reflectivity within a range of 1 km;
traversing a training data set corresponding to the differential phase, and calculating the standard deviation of the differential phase within the range of 2km
In the formula, m (phi) DP ) Is differential phase phi in the range of 2km DP Average value of (3), n φ The number of data points of differential phase in the range of 2 km.
4. The weather radar clutter classification and identification method according to claim 1, wherein the processing the training data set and the texture data by the fuzzy logic algorithm to obtain the tag set of the particle phase type comprises:
adopting a trapezoidal function as a membership function of a fuzzy logic algorithm, carrying out fuzzy logic operation by taking training data and texture data in a training data set as input parameters, and obtaining membership corresponding to a particle phase type as fuzzy logic output; the trapezoidal function is:
in the formula, X 1 、X 2 、X 3 、X 4 Is a threshold parameter of a trapezoidal function, P (j) (x i ) The membership degree of the jth input parameter to the ith particle phase state type;
and (3) performing defuzzification on the fuzzy logic output by adopting a weighted average judgment method to obtain a membership integrated value corresponding to the particle phase type:
in the formula, S i Membership level integration value, W, of ith particle phase type for jth input parameter ij The weight coefficient of the jth input parameter of the ith particle phase type is obtained, and J is the number of the input parameters;
if the membership integrated value of the input parameter is 0, the particle phase type corresponding to the input parameter is no meteorological echo, and the label of the particle phase type is set to be 0;
if the membership integrated value of the input parameter is greater than the set threshold, the particle phase type corresponding to the input parameter is a clutter, and the label of the particle phase type is set to be 1;
if the membership integration value of the input parameter is smaller than the set threshold and larger than 0, the particle phase type corresponding to the input parameter is other, and the label of the particle phase type is set to be 2;
and constructing a tag set of the particle phase type according to the tags of the input parameters.
5. The weather radar clutter classification and identification method according to claim 1, wherein the iterative training based on the training data set and the tag set comprises:
an Encoder network downsampling training data based on a SegNet network model to obtain data characteristics;
sampling characteristic data on a Decoder network based on a SegNet network model to obtain a prediction result;
and calculating the loss of the prediction result and the label thereof based on the cross entropy loss function, and updating the weight parameter of the SegNet network model according to the loss back propagation.
6. The weather radar clutter classification and identification method according to claim 5, wherein the Encoder network comprises:
a first layer consisting of two 64 x 3 convolutions and maximum pooled downsampling in sequence;
a second layer consisting of, in order, two 128 x 3 convolutions and maximum pooled downsampling;
the third layer consists of three convolutions of 256 multiplied by 3 and the maximum pooled downsampling in sequence;
a fourth layer consisting of three 512 x 3 convolutions and maximum pooled downsampling in sequence;
a fifth layer consisting of three 5212 × 3 × 3 convolutions and maximum pooled downsampling in sequence;
the Decoder network includes:
a first layer consisting of, in order, inverse max-pooling upsampling and three 521 × 3 × 3 convolutions;
a second layer consisting of, in order, inverse maximal pooled upsampling and three 521 × 3 × 3 convolutions;
the third layer consists of inverse maximum pooling upsampling and two convolutions of 256 multiplied by 3 in turn;
a fourth layer consisting of inverse maximal pooled upsampling and two 128 x 3 convolutions in sequence;
the fifth layer, in turn, consists of inverse max pooling upsampling and two 64 x 3 convolutions.
7. The weather radar clutter classification and identification method according to claim 5, wherein in the iterative training process, the Pixel Accuracy is used as an Accuracy evaluation index to obtain the proximity of the prediction result and the tag.
8. A weather radar clutter classification and identification device is characterized in that the device comprises:
the preprocessing module is used for acquiring and preprocessing the tested meteorological radar data;
the classification identification module is used for inputting the preprocessed tested meteorological radar data into the trained SegNet network model to obtain a classification identification result;
a model training module to:
acquiring and preprocessing trained meteorological radar data; the meteorological radar data comprise radar reflectivity, differential propagation phase shift rate, correlation coefficient and differential phase;
integrating the preprocessed meteorological radar data into a corresponding training data set based on the data type;
respectively calculating the standard deviation of a training data set corresponding to the radar reflectivity and the differential phase as texture data of the radar reflectivity and the differential phase;
processing training data and texture data in the training data set by adopting a fuzzy logic algorithm to obtain a particle phase state type label set;
initializing a SegNet network model, and performing iterative training based on a training data set and a label set until a preset maximum iteration number is reached or a weight parameter of the SegNet network model is converged.
9. A meteorological radar clutter classification and identification device is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
10. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156539.7A CN115542279A (en) | 2022-09-22 | 2022-09-22 | Weather radar clutter classification and identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156539.7A CN115542279A (en) | 2022-09-22 | 2022-09-22 | Weather radar clutter classification and identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115542279A true CN115542279A (en) | 2022-12-30 |
Family
ID=84730461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211156539.7A Pending CN115542279A (en) | 2022-09-22 | 2022-09-22 | Weather radar clutter classification and identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115542279A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118033548A (en) * | 2024-04-12 | 2024-05-14 | 成都远望科技有限责任公司 | Dual-transmitting dual-receiving top-sweeping cloud radar same-frequency interference identification method and device |
-
2022
- 2022-09-22 CN CN202211156539.7A patent/CN115542279A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118033548A (en) * | 2024-04-12 | 2024-05-14 | 成都远望科技有限责任公司 | Dual-transmitting dual-receiving top-sweeping cloud radar same-frequency interference identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898432B (en) | Pedestrian detection system and method based on improved YOLOv3 algorithm | |
| CN114120102A (en) | Boundary-optimized remote sensing image semantic segmentation method, device, equipment and medium | |
| CN113065594B (en) | Road network extraction method and device based on Beidou data and remote sensing image fusion | |
| CN113392931B (en) | Hyperspectral open set classification method based on self-supervision learning and multitask learning | |
| CN112465001B (en) | Classification method and device based on logistic regression | |
| CN112861915A (en) | Anchor-frame-free non-cooperative target detection method based on high-level semantic features | |
| Li et al. | Automatic road extraction from remote sensing imagery using ensemble learning and postprocessing | |
| CN114821022A (en) | Credible target detection method integrating subjective logic and uncertainty distribution modeling | |
| CN112949009A (en) | Active power distribution network distributed state estimation method and system based on transfer learning | |
| CN115393631A (en) | Hyperspectral image classification method based on Bayesian layer graph convolution neural network | |
| CN115542279A (en) | Weather radar clutter classification and identification method and device | |
| CN110705631B (en) | SVM-based bulk cargo ship equipment state detection method | |
| CN117274355A (en) | Drainage pipeline flow intelligent measurement method based on acceleration guidance area convolutional neural network and parallel multi-scale unified network | |
| CN115565115A (en) | Outfitting intelligent identification method and computer equipment | |
| CN115794805A (en) | Medium-low voltage distribution network measurement data supplementing method | |
| CN115238789A (en) | Financial industry special data prediction method and system based on improved GRU | |
| CN115496137A (en) | Small sample classification method based on label propagation and distribution conversion and related device | |
| CN114693997A (en) | Image description generation method, device, equipment and medium based on transfer learning | |
| Ali et al. | Pavement Crack Detection by Convolutional AdaBoost Architecture | |
| Rao et al. | Markov random field classification technique for plant leaf disease detection | |
| CN111382761B (en) | CNN-based detector, image detection method and terminal | |
| Patil et al. | Road detection from high resolution images using fully convolutional network | |
| CN116434080A (en) | Image change area detection method and device, storage medium and electronic equipment | |
| Sheikh et al. | DEEP LEARNING APPROACH FOR ROAD EXTRACTION FROM REMOTE SENSING IMAGERY. | |
| CN115689985A (en) | Abrasive particle chain segmentation method and system based on improved Mask-RCNN network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |