CN113219466A - Sea surface wind speed determination method and device, electronic equipment and storage medium - Google Patents

Sea surface wind speed determination method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113219466A
CN113219466A CN202110525118.6A CN202110525118A CN113219466A CN 113219466 A CN113219466 A CN 113219466A CN 202110525118 A CN202110525118 A CN 202110525118A CN 113219466 A CN113219466 A CN 113219466A
Authority
CN
China
Prior art keywords
value
wind speed
model
sea surface
radar
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
Application number
CN202110525118.6A
Other languages
Chinese (zh)
Inventor
贾永君
林明森
张有广
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NATIONAL SATELLITE OCEAN APPLICATION SERVICE
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Original Assignee
NATIONAL SATELLITE OCEAN APPLICATION SERVICE
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by NATIONAL SATELLITE OCEAN APPLICATION SERVICE, Southern Marine Science and Engineering Guangdong Laboratory Guangzhou filed Critical NATIONAL SATELLITE OCEAN APPLICATION SERVICE
Priority to CN202110525118.6A priority Critical patent/CN113219466A/en
Publication of CN113219466A publication Critical patent/CN113219466A/en
Pending legal-status Critical Current

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
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Electromagnetism (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The application provides a method and a device for determining sea surface wind speed, electronic equipment and a storage medium, and the method and the device are used for acquiring a value of an incident angle of a radar beam; the incident angle is the angle of the wave beam incident to the sea surface of the area to be measured; obtaining a value of a backscattering coefficient; wherein the value of the backscattering coefficient represents the scattering size generated when the wave beam is incident to the sea surface of the region to be measured; and inputting the value of the incidence angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea surface wind speed of the area to be measured. In the implementation process, the scattering size generated when the wave beam of the radar enters the sea surface is considered to be related to the value of the incident angle of the wave beam and the wind speed of the sea surface, and then the value of the incident angle and the value of the backscattering coefficient are input into the pre-trained wind speed determination model, so that the pre-trained model is used for rapidly determining the wind speed of the sea surface of the region to be measured.

Description

Sea surface wind speed determination method and device, electronic equipment and storage medium
Technical Field
The application relates to the technical field of data processing, in particular to a sea surface wind speed determining method and device, electronic equipment and a storage medium.
Background
Sea surface wind is an important factor influencing factors such as sea waves, ocean currents, water masses and the like, so that sea surface wind speed can have certain influence on the marine transportation industry, the marine fishery industry and the like; secondly, the sea surface wind speed has important value in the research of improving the accuracy of global atmosphere and marine dynamics forecasting modes, and the like, so the method has important significance for determining the sea surface wind speed.
Disclosure of Invention
In view of this, an object of the embodiments of the present application is to provide a method and an apparatus for determining a sea surface wind speed, an electronic device, and a storage medium, so as to determine the sea surface wind speed.
In a first aspect, an embodiment of the present application provides a method for determining a wind speed at a sea surface, where the method includes: acquiring a value of an incident angle of a predetermined radar beam; the incident angle is the angle of the wave beam incident to the sea surface of the area to be measured; obtaining a value of a backscattering coefficient; wherein the value of the backscattering coefficient represents the scattering size generated when the wave beam is incident to the sea surface of the region to be measured; and inputting the value of the incidence angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea surface wind speed of the area to be measured.
In the implementation process, the scattering size generated when the wave beam of the radar enters the sea surface is considered to be related to the value of the incident angle of the wave beam and the wind speed of the sea surface, and then the value of the incident angle and the value of the backscattering coefficient are input into the pre-trained wind speed determination model, so that the pre-trained model is used for rapidly determining the wind speed of the sea surface of the region to be measured.
In a possible design based on the first aspect, the obtaining the value of the backscattering coefficient includes: acquiring a value of the receiving power of a receiving antenna of the radar; acquiring a value of a distance between the radar and the sea surface of the area to be detected; determining a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam; determining the value of the backscattering coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscattering coefficient determination expression.
In the implementation process, the value of the backscattering coefficient is related to the distance between the radar and the sea surface of the area to be measured, the beam coverage area, the receiving power of a receiving antenna of the radar, the incident angle of the beam and the value of the radar parameter, and then the value of the backscattering coefficient is accurately determined based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the receiving power, the value of the radar parameter and a predetermined backscattering coefficient determination expression.
In a possible design based on the first aspect, the radar parameter includes: an antenna gain of the radar, a wavelength of the beam, and a transmit power of the radar; the backscattering coefficient determination expression is as follows:
Figure BDA0003064207850000021
where σ is the backscattering coefficient, PtFor said transmission power, PrAnd theta is the received power, theta is the incident angle, S is the coverage area, lambda is the wavelength, G is the antenna gain, and r is the distance.
In the implementation process, the value of the backscattering coefficient is considered to be related to the antenna gain of the radar, the wavelength of the wave beam and the transmitting power of the radar, then the expression of the backscattering coefficient is accurately determined based on the transmitting power, the receiving power, the incident angle, the coverage area, the wavelength, the antenna gain and the distance, and then the value of the backscattering coefficient is accurately determined according to the expression of the backscattering coefficient.
Based on the first aspect, in a possible design, before inputting the value of the incident angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain a sea-surface wind speed of the region to be measured, the method further includes: establishing an original wind speed determination model; obtaining a model training sample; the model training samples include: the method comprises the steps of measuring a true wind speed of a sea surface of a target area and a value of a target backscattering coefficient of the target area corresponding to the values of the true wind speed and a preset incident angle; inputting the value of the preset incidence angle and the value of the target backscattering coefficient into the original wind speed determination model to obtain a model output result; and when the difference value between the model output result and the real wind speed is determined to be larger than a preset threshold value, updating the original wind speed determination model until a new difference value determined by the updated wind speed determination model is smaller than or equal to the preset threshold value, and obtaining the trained wind speed determination model.
In the implementation process, the original wind speed determination model is trained by using the sea surface real wind speed of the target area and the value of the target backscattering coefficient of the target area corresponding to the value of the real wind speed and the preset incident angle, and when the difference value between the model output result and the real wind speed is greater than the preset threshold value, the original wind speed determination model is updated until the new difference value determined by using the updated wind speed determination model is less than or equal to the preset threshold value, so that the prediction precision of the trained wind speed determination model is ensured.
In a possible design based on the first aspect, the incident angle and the preset incident angle both range from 0 to 18 degrees.
In the implementation process, the anisotropy of the backscattering coefficient can be ignored when the value range of the incident angle of the beam of the radar is 0-18 degrees, so that the influence of the anisotropy of the backscattering coefficient is reduced by setting the incident angle and the value range of the preset incident angle to be 0-18 degrees, and the accuracy of the determined backscattering coefficient is further ensured.
Based on the first aspect, in one possible design, the obtaining a model training sample includes: obtaining an initial training sample set of the model; aiming at each initial training sample in the initial training sample set, determining that the initial training sample is unqualified when the GMF model is used for determining that the value of the backscattering coefficient in the initial training sample is abnormal; and removing all unqualified initial training samples in the initial training sample set to obtain the model training sample.
In the implementation process, the GMF model is used for removing unqualified training samples in the initial training sample set so as to ensure the accuracy of the obtained model training samples and further ensure the prediction accuracy of the model determined by the wind speed obtained by training the model training samples.
In a second aspect, an embodiment of the present application provides a sea surface wind speed determination apparatus, including: a first acquisition unit configured to acquire a value of an incident angle of a beam of a radar determined in advance; the incident angle is the angle of the wave beam incident to the sea surface of the area to be measured; a second acquisition unit for acquiring a value of the backscattering coefficient; wherein the value of the backscattering coefficient represents the scattering size generated when the wave beam is incident to the sea surface of the region to be measured; and the wind speed determining unit is used for inputting the incidence angle value and the backscattering coefficient value into a pre-trained wind speed determining model to obtain the sea surface wind speed of the area to be measured.
Based on the second aspect, in one possible design, the second obtaining unit includes: a power acquisition unit for acquiring a value of reception power of a reception antenna of the radar; the distance acquisition unit is used for acquiring the value of the distance between the radar and the sea surface of the area to be detected; an area determination unit configured to determine a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam; a backscatter determining unit configured to determine a value of the backscatter coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscatter coefficient determination expression.
Based on the second aspect, in one possible design, the radar parameters include: an antenna gain of the radar, a wavelength of the beam, and a transmit power of the radar; the backscattering coefficient determination expression is as follows:
Figure BDA0003064207850000041
where σ is the backscattering coefficient, PtFor said transmission power, PrAnd theta is the received power, theta is the incident angle, S is the coverage area, lambda is the wavelength, G is the antenna gain, and r is the distance.
Based on the second aspect, in one possible design, the apparatus further includes: the model establishing unit is used for establishing an original wind speed determining model; the sample acquisition unit is used for acquiring a model training sample; the model training samples include: the method comprises the steps of measuring a true wind speed of a sea surface of a target area and a value of a target backscattering coefficient of the target area corresponding to the values of the true wind speed and a preset incident angle; the input unit is used for inputting the value of the preset incidence angle and the value of the target backscattering coefficient into the original wind speed determination model to obtain a model output result; and the model updating unit is used for updating the original wind speed determination model when the difference between the model output result and the real wind speed is determined to be larger than a preset threshold value until a new difference determined by the updated wind speed determination model is smaller than or equal to the preset threshold value, so that the trained wind speed determination model is obtained.
In a possible design based on the second aspect, the incident angle and the preset incident angle both range from 0 to 18 degrees.
Based on the second aspect, in one possible design, the sample obtaining unit is specifically configured to obtain an initial training sample set of a model; and for each initial training sample in the initial training sample set, determining that the initial training sample is unqualified when the GMF model is used for determining that the value of the backscattering coefficient in the initial training sample is abnormal; and removing all unqualified initial training samples in the initial training sample set to obtain the model training sample.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory connected to the processor, where a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device is caused to perform the method of the first aspect.
In a fourth aspect, an embodiment of the present application provides a storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method of the first aspect.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart of a method for determining a sea-surface wind speed according to an embodiment of the present disclosure.
Fig. 2 is a schematic structural diagram of a sea surface wind speed determination device according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Icon: 200-sea surface wind speed determination device; 210-a first obtaining unit; 220-a second acquisition unit; 230-a wind speed determination unit; 300-an electronic device; 301-a processor; 302-a memory; 303-communication interface.
Detailed Description
The technical solution in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flowchart of a method for determining a sea surface wind speed according to an embodiment of the present application, the method employs an electronic device 300 shown in fig. 3, and the flowchart shown in fig. 1 will be described in detail below, and the method includes the steps of: S11-S13.
S11: acquiring a value of an incident angle of a predetermined radar beam; the incident angle is an angle of the wave beam incident to the sea surface of the area to be measured.
S12: obtaining a value of a backscattering coefficient; wherein the value of the backscattering coefficient is used for representing the scattering size generated when the wave beam is incident to the sea surface of the region to be measured.
S13: and inputting the value of the incidence angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea surface wind speed of the area to be measured.
The above method is described in detail below.
S11: acquiring a value of an incident angle of a predetermined radar beam; the incident angle is an angle of the wave beam incident to the sea surface of the area to be measured.
Wherein the incidence angle ranges from 0 to 18 degrees.
In one embodiment, the range of the incident angle may also be 18 to 20 degrees.
S12: obtaining a value of a backscattering coefficient; wherein the value of the backscattering coefficient is used for representing the scattering size generated when the wave beam is incident to the sea surface of the region to be measured.
As an embodiment, S12 includes the steps of: A1-A4.
A1: and acquiring the value of the receiving power of a receiving antenna of the radar.
In practical implementation, a1 may be implemented by using a radar in a three-dimensional imaging altimeter to transmit a beam to the sea surface of an area to be measured at predetermined values of transmission power and incidence angle, specifically, the beam is transmitted by the radar through a transmission antenna, the number of the transmission antennas is one, the transmission antenna is mounted on the radar, and a receiving antenna of the radar is used to receive an echo signal, wherein the number of the receiving antennas is 2, the receiving antenna is mounted on the radar, the echo signal is a signal generated after the beam reaches the sea surface, and then the value of the reception power is determined according to the received echo signal. The specific implementation of determining the received power according to the echo signal is well known in the art, and therefore, will not be described herein.
A2: and acquiring a value of the distance between the radar and the sea surface of the area to be detected.
In practical implementation, a2 may be implemented by determining a value of the height of the radar compared to the sea surface of the area to be measured, i.e., a value of the distance, based on the predetermined world coordinates of the radar and the world coordinates of the sea surface of the area to be measured.
The execution sequence of steps a1 and a2 is not limited.
After the value of the distance is acquired, step a3 is performed.
A3: determining a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam.
The specific implementation of determining the value of the coverage area of the beam based on the value of the distance and the predetermined width of the beam is well known in the art, and therefore, details are not described herein.
After the values of the coverage area, the distance, and the received power are determined, step a4 is performed.
A4: determining the value of the backscattering coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscattering coefficient determination expression.
Wherein the radar parameters include: an antenna gain of the radar, a wavelength of the beam, and a transmit power of the radar; the backscattering coefficient determination expression is as follows:
Figure BDA0003064207850000081
where σ is the backscattering coefficient, PtFor said transmission power, PrAnd theta is the received power, theta is the incident angle, S is the coverage area, lambda is the wavelength, G is the antenna gain, and r is the distance.
In practical implementation, a4 may be implemented by inputting the values of the transmission power, the reception power, the incident angle, the coverage area, the wavelength, the antenna gain and the distance into the backscattering coefficient determination expression
Figure BDA0003064207850000082
Obtaining a value of the backscattering coefficient.
As an embodiment, the radar parameter includes: an effective receiving area of a receiving antenna of the radar, a wavelength of the beam, and a transmission power of the radar; the backscattering coefficient determination expression is as follows:
Figure BDA0003064207850000083
where σ is the backscattering coefficient, PtFor said transmission power, PrFor the received power, θ is the incident angle, S is the coverage area, λ is the wavelength, A is the effective receive area, and r is the distance.
Specifically, a4 may be implemented by assigning a value of the transmit power, a value of the receive power,the value of the incident angle, the value of the coverage area, the value of the wavelength, the value of the effective receiving area, and the value of the distance are input to the backscattering coefficient determination expression
Figure BDA0003064207850000084
Obtaining a value of the backscattering coefficient.
After the values of the incident angle and the backscattering coefficient are determined, S13 is performed.
S13: and inputting the value of the incidence angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea surface wind speed of the area to be measured.
Wherein the wind speed determination model is a neural network model. In the present embodiment, the wind speed determination model is a BP neural network model based on (Levenberg-Marquardt, LM) algorithm.
As an embodiment, before S13, the method further includes: determining a value of a first backscattering coefficient of the sea surface of the region to be measured corresponding to the value of the incident angle of the beam by using a Geophysical Model Function (GMF) Model, and determining that the difference between the value of the first backscattering coefficient and the value of the backscattering coefficient is less than or equal to a preset difference.
As an embodiment, before S13, the method further includes the steps of: B1-B4.
B1: and establishing an original wind speed determination model.
Wherein the raw wind speed determination model is a neural network model. In this embodiment, the raw wind speed determination model is a BP neural network model based on the (Levenberg-Marquardt, LM) algorithm.
B2: obtaining a model training sample; the model training samples include: a true wind speed of a sea surface of a target area, and a value of a target backscattering coefficient of the target area corresponding to the value of the true wind speed and a preset incident angle.
Wherein the preset incidence angle ranges from 0 to 18 degrees.
The real sea surface wind speed of the target area, the value of the preset incidence angle and the value of the target backscattering coefficient of the target area are in one-to-one correspondence; it is worth mentioning that the real wind speed at a certain moment on the sea surface of the target area corresponds to the backscattering coefficient of scattering generated by transmitting the beam to the sea surface of the target area at the moment with a value of the preset incident angle.
The target region and the region to be measured may be the same region or different regions.
If the target area includes a plurality of sub-target areas, the model training sample may include: the real wind speed of the sea surface of each of the plurality of sub-target areas at any one time, the value of the preset incident angle corresponding to the real wind speed of each sub-target area, and the value of the backscattering coefficient.
If the target region is a region, the model training samples may include: the real wind speed of the sea surface of the target area at different moments in a plurality of moments, and the values of the preset incident angle and the backscattering coefficient corresponding to the real wind speeds at the different moments.
It is worth mentioning that the vegetation of the rainforest is mainly composed of the dense forest, the vegetation is located near the equator and is slightly influenced by seasonal changes, and the backscattering coefficient of the rainforest is stable in space and time, so that the rainforest is selected as a target area to ensure the prediction accuracy of the trained model.
In this embodiment, the selected target region belongs to amazon rainforest and congo rainforest.
As an embodiment, step B2 includes the steps of: B21-B23.
B21: an initial training sample set of the model is obtained.
The initial training sample set comprises a plurality of initial training samples, and for each initial training sample, the geographic area corresponding to each initial training sample, the value of a preset incidence angle and the value of at least one factor in time are different; the portion of the geographic area involved in the initial training sample set comprises the target area.
As an embodiment, for an initial training sample, the initial training sample includes: the real wind speed of the sea surface of the sample region at a moment, and the value of a backscattering coefficient corresponding to the values of the real wind speed and the preset incidence angle of the sample region at the moment; the sample region may or may not be a target region.
As an embodiment, for an initial training sample, the initial training sample includes: the real wind speed of the sea surface of the sample region at a moment, the value of the preset incidence angle corresponding to the real wind speed of the sample region at the moment and the value of the backscattering coefficient.
After the initial training sample set is acquired, step B22 is performed.
B22: and for each initial training sample in the initial training sample set, determining that the initial training sample is unqualified when the GMF model is used for determining that the value of the backscattering coefficient in the initial training sample is abnormal.
In an actual implementation process, B22 may be implemented by, for each initial training sample in the initial training sample set, determining, by using the GMF model, the value of the preset incident angle in the initial training sample, and the wind speed at the sea surface, the value of the backscatter coefficient corresponding to the acquisition time and the geographic area, determining that the value of the backscatter coefficient in the initial training sample is abnormal when it is determined that the difference between the value of the corresponding backscatter coefficient and the value of the backscatter coefficient in the initial training sample is greater than a preset difference value, and then determining that the initial training sample is unqualified; otherwise, the initial training sample is determined to be qualified. In this embodiment, the preset difference is 0.2dB, and in other embodiments, the preset difference may also be 0.3 dB.
B23: and removing all unqualified initial training samples in the initial training sample set to obtain the model training sample.
After the model training samples are obtained, step B3 is performed.
B3: and inputting the value of the preset incidence angle and the value of the target backscattering coefficient into the original wind speed determination model to obtain a model output result.
In an actual implementation process, B3 may be implemented in such a way that, when an initial training sample is included in the model training sample, the value of the preset incident angle and the value of the backscattering coefficient in the initial training sample are input into the original wind speed determination model, and a model output result, that is, the predicted wind speed, is obtained.
In an actual implementation process, B3 may be implemented in such a manner that, when the model training samples include at least two initial training samples, one initial training sample is selected from the at least two initial training samples, and a value of a preset incident angle and a value of a backscattering coefficient in the selected initial training sample are input into the original wind speed determination model, so as to obtain a model output result, that is, a predicted wind speed.
As an embodiment, when the model training samples include at least two initial training samples, for each of the at least two initial training samples, the B3 may be implemented in such a manner that a value of a preset incident angle and a value of a backscatter coefficient in the initial training sample are input into the original wind speed determination model, and a model output result corresponding to the initial training sample is obtained.
As an embodiment, B3 may be implemented in such a manner that, when the model training samples include at least two initial training samples, 70% of the initial training samples are selected from the at least two initial training samples to perform model training, and for each of the 70% of the selected initial training samples, a value of a preset incident angle and a value of a backscatter coefficient in the initial training sample are input to the original wind speed determination model, so as to obtain a model output result corresponding to the initial training sample.
B4: and when the difference value between the model output result and the real wind speed is determined to be larger than a preset threshold value, updating the original wind speed determination model until a new difference value determined by the updated wind speed determination model is smaller than or equal to the preset threshold value, and obtaining the trained wind speed determination model.
In the present embodiment, the preset threshold may be 0.6m/s, and in other embodiments, the preset threshold may also be 0.5m/s, 0.7m/s, and the like, where the smaller the preset threshold, the higher the prediction accuracy of the trained wind speed determination model is.
In an actual implementation process, when the model training sample includes an initial training sample, B4 may be implemented in the following manner, to determine whether a difference between the model output result and the real wind speed in the selected initial training sample is greater than a preset threshold, if so, update a value of a model parameter in the original wind speed determination model to obtain an updated wind speed determination model, then train the updated wind speed determination model by using the model training sample, and so on until a new difference determined by using the updated wind speed determination model is less than or equal to the preset threshold, to obtain the trained wind speed determination model.
As an implementation manner, when the model training samples include at least two initial training samples, B4 may be implemented in a manner that determines whether a difference between the output result of the model and the real wind speed in the selected initial training sample is greater than a preset threshold, if so, updates a value of a model parameter in the original wind speed determination model to obtain an updated wind speed determination model, then randomly selects one initial training sample from the remaining initial training samples in the model training samples, trains the updated wind speed determination model, and so on until a new difference determined by using the updated wind speed determination model is less than or equal to the preset threshold, to obtain the trained wind speed determination model.
As an implementation manner, when the model training samples include at least two initial training samples, and step B3 obtains at least two model output results, B4 may be implemented as follows, for each of the at least two model output results, determine a difference between the model output result and the corresponding real wind speed, then determine whether a mean value of the difference corresponding to the at least two model output results is greater than a preset threshold, if so, update a value of a model parameter in the original wind speed determination model, then train the updated wind speed determination model from the model training samples, and so on until a new mean value determined by using the updated wind speed determination model is less than or equal to the preset threshold, so as to obtain the trained wind speed determination model.
As an implementation manner, when the model training samples include at least two initial training samples, and step B3 obtains at least two model output results, B4 may be implemented as follows, for each of the at least two model output results, determining a difference between the model output result and the corresponding real wind speed, then determining whether a mean value of the difference corresponding to the at least two model output results is greater than a preset threshold, and determining whether a mean square error of the difference corresponding to the at least two model output results is greater than a preset error, if the mean value is greater than the preset threshold or the mean square error of the difference is greater than the preset error, updating a value of a model parameter in the original wind speed determination model, then continuing to train the updated wind speed determination model using the model training samples, and so on, until a new mean value determined by using the updated wind speed determination model is less than or equal to the preset threshold, and when the new mean square error is less than or equal to a preset error, obtaining the trained wind speed determination model.
In the present embodiment, the preset error may be 1.8m/s, and in other embodiments, the preset error may also be 1.7m/s, 2m/s, and the like, where the smaller the preset error is, the higher the prediction accuracy of the trained wind speed determination model is.
As an embodiment, B4 may be implemented by determining that the difference between the model output result and the real wind speed is greater than a preset threshold value, updating the values of the model parameters in the original wind speed determination model, training the updated wind speed determination model by using the selected 70% of initial training samples until the new difference determined by using the updated wind speed determination model is less than or equal to the preset threshold value to obtain a preliminarily trained wind speed determination model, then using the samples except the selected 70% of initial training samples in the model training samples, and testing the preliminarily trained wind speed determination model, and determining the preliminarily trained wind speed determination model as the trained wind speed determination model when the test result represents that the difference value determined by using the preliminarily trained wind speed determination model is less than or equal to the preset threshold value. The specific test method may refer to step B3, and therefore, is not described herein again.
Referring to fig. 2, fig. 2 is a block diagram of a sea surface wind speed determination device 200 according to an embodiment of the present disclosure. The block diagram of fig. 2 will be explained, and the apparatus shown comprises:
a first acquisition unit 210 for acquiring a value of an incident angle of a beam of a predetermined radar; the incident angle is an angle of the wave beam incident to the sea surface of the area to be measured.
A second obtaining unit 220, configured to obtain a value of a backscattering coefficient; wherein the value of the backscattering coefficient is used for representing the scattering size generated when the wave beam is incident to the sea surface of the region to be measured.
And the wind speed determining unit 230 is configured to input the value of the incident angle and the value of the backscattering coefficient into a pre-trained wind speed determining model to obtain a sea-surface wind speed of the region to be measured.
As an implementation manner, the second obtaining unit 220 includes: a power acquisition unit for acquiring a value of reception power of a reception antenna of the radar; the distance acquisition unit is used for acquiring the value of the distance between the radar and the sea surface of the area to be detected; an area determination unit configured to determine a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam; a backscatter determining unit configured to determine a value of the backscatter coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscatter coefficient determination expression.
As an embodiment, the radar parameter includes: an antenna gain of the radar, a wavelength of the beam, and a transmit power of the radar; the backscattering coefficient determination expression is as follows:
Figure BDA0003064207850000141
where σ is the backscattering coefficient, PtFor said transmission power, PrAnd theta is the received power, theta is the incident angle, S is the coverage area, lambda is the wavelength, G is the antenna gain, and r is the distance.
As an embodiment, the apparatus further comprises: the model establishing unit is used for establishing an original wind speed determining model; the sample acquisition unit is used for acquiring a model training sample; the model training samples include: the method comprises the steps of measuring a true wind speed of a sea surface of a target area and a value of a target backscattering coefficient of the target area corresponding to the values of the true wind speed and a preset incident angle; the input unit is used for inputting the value of the preset incidence angle and the value of the target backscattering coefficient into the original wind speed determination model to obtain a model output result; and the model updating unit is used for updating the original wind speed determination model when the difference between the model output result and the real wind speed is determined to be larger than a preset threshold value until a new difference determined by the updated wind speed determination model is smaller than or equal to the preset threshold value, so that the trained wind speed determination model is obtained.
In one embodiment, the incident angle and the preset incident angle range from 0 to 18 degrees.
As an embodiment, the sample obtaining unit is specifically configured to obtain an initial training sample set of a model; and for each initial training sample in the initial training sample set, determining that the initial training sample is unqualified when the GMF model is used for determining that the value of the backscattering coefficient in the initial training sample is abnormal; and removing all unqualified initial training samples in the initial training sample set to obtain the model training sample.
For the process of implementing each function by each functional unit in this embodiment, please refer to the content described in the embodiment shown in fig. 1, which is not described herein again.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device 300 according to an embodiment of the present disclosure, where the electronic device 300 may be a personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), or the like.
The electronic device 300 may include: memory 302, processor 301, communication interface 303, and a communication bus for enabling the connection communications of these components.
The Memory 302 is used for storing various data such as a computer program instruction corresponding to the Memory management method and apparatus provided in the embodiment of the present application, where the Memory 302 may be, but is not limited to, a random access Memory (ram), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.
The processor 301 is configured to read and run computer program instructions corresponding to the sea surface wind speed determination method and apparatus stored in the memory, so as to obtain the sea surface wind speed of the area to be predicted.
The processor 301 may be an integrated circuit chip having signal processing capabilities. The Processor 301 may be a general-purpose Processor including a CPU, a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
A communication interface 303 for receiving or transmitting data.
In addition, a storage medium is provided in an embodiment of the present application, and a computer program is stored in the storage medium, and when the computer program runs on a computer, the computer is caused to execute the method provided in any embodiment of the present application.
In summary, in the method, the apparatus, the electronic device, and the storage medium for determining the sea surface wind speed provided by the embodiments of the present application, the scattering size generated when the radar beam is incident on the sea surface is considered to be related to the incident angle value of the beam and the sea surface wind speed, and then the incident angle value and the backscattering coefficient value are input into the pre-trained wind speed determination model, so that the pre-trained model is used to quickly determine the sea surface wind speed of the region to be measured.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

Claims (10)

1. A method of determining sea surface wind speed, the method comprising:
acquiring a value of an incident angle of a predetermined radar beam; the incident angle is the angle of the wave beam incident to the sea surface of the area to be measured;
obtaining a value of a backscattering coefficient; wherein the value of the backscattering coefficient represents the scattering size generated when the wave beam is incident to the sea surface of the region to be measured;
and inputting the value of the incidence angle and the value of the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea surface wind speed of the area to be measured.
2. The method of claim 1, wherein the obtaining the value of the backscatter coefficient comprises:
acquiring a value of the receiving power of a receiving antenna of the radar;
acquiring a value of a distance between the radar and the sea surface of the area to be detected;
determining a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam;
determining the value of the backscattering coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscattering coefficient determination expression.
3. The method of claim 2, wherein the radar parameters comprise: an antenna gain of the radar, a wavelength of the beam, and a transmit power of the radar; the backscattering coefficient determination expression is as follows:
Figure FDA0003064207840000011
wherein σ is the rearCoefficient of backscatter, PtFor said transmission power, PrAnd theta is the received power, theta is the incident angle, S is the coverage area, lambda is the wavelength, G is the antenna gain, and r is the distance.
4. The method of claim 1, wherein before inputting the values of the incidence angle and the backscattering coefficient into a pre-trained wind speed determination model to obtain the sea-surface wind speed of the region under test, the method further comprises:
establishing an original wind speed determination model;
obtaining a model training sample; the model training samples include: the method comprises the steps of measuring a true wind speed of a sea surface of a target area and a value of a target backscattering coefficient of the target area corresponding to the values of the true wind speed and a preset incident angle;
inputting the value of the preset incidence angle and the value of the target backscattering coefficient into the original wind speed determination model to obtain a model output result;
and when the difference value between the model output result and the real wind speed is determined to be larger than a preset threshold value, updating the original wind speed determination model until a new difference value determined by the updated wind speed determination model is smaller than or equal to the preset threshold value, and obtaining the trained wind speed determination model.
5. The method of claim 4, wherein the incident angle and the predetermined incident angle range from 0 to 18 degrees.
6. The method of claim 4, wherein the obtaining model training samples comprises:
obtaining an initial training sample set of the model;
aiming at each initial training sample in the initial training sample set, determining that the initial training sample is unqualified when the GMF model is used for determining that the value of the backscattering coefficient in the initial training sample is abnormal;
and removing all unqualified initial training samples in the initial training sample set to obtain the model training sample.
7. A sea surface wind speed determining apparatus, the apparatus comprising:
a first acquisition unit configured to acquire a value of an incident angle of a beam of a radar determined in advance; the incident angle is the angle of the wave beam incident to the sea surface of the area to be measured;
a second acquisition unit for acquiring a value of the backscattering coefficient; wherein the value of the backscattering coefficient represents the scattering size generated when the wave beam is incident to the sea surface of the region to be measured;
and the wind speed determining unit is used for inputting the incidence angle value and the backscattering coefficient value into a pre-trained wind speed determining model to obtain the sea surface wind speed of the area to be measured.
8. The apparatus of claim 7, wherein the first obtaining unit comprises:
a power acquisition unit for acquiring a value of reception power of a reception antenna of the radar;
the distance acquisition unit is used for acquiring the value of the distance between the radar and the sea surface of the area to be detected;
an area determination unit configured to determine a value of a coverage area of the beam based on the value of the distance and a predetermined width of the beam;
a backscatter determining unit configured to determine a value of the backscatter coefficient based on the value of the distance, the value of the coverage area, the value of the incident angle, the value of the received power, a predetermined value of a radar parameter of the radar, and a predetermined backscatter coefficient determination expression.
9. An electronic device comprising a memory and a processor, the memory having stored therein computer program instructions that, when read and executed by the processor, perform the method of any of claims 1-6.
10. A storage medium having stored thereon computer program instructions which, when read and executed by a computer, perform the method of any one of claims 1-6.
CN202110525118.6A 2021-05-13 2021-05-13 Sea surface wind speed determination method and device, electronic equipment and storage medium Pending CN113219466A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110525118.6A CN113219466A (en) 2021-05-13 2021-05-13 Sea surface wind speed determination method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110525118.6A CN113219466A (en) 2021-05-13 2021-05-13 Sea surface wind speed determination method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113219466A true CN113219466A (en) 2021-08-06

Family

ID=77095623

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110525118.6A Pending CN113219466A (en) 2021-05-13 2021-05-13 Sea surface wind speed determination method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113219466A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114580309A (en) * 2022-05-09 2022-06-03 深圳市朗诚科技股份有限公司 Drift speed prediction method, drift speed prediction device, calculation equipment and storage medium
CN117849797A (en) * 2024-01-29 2024-04-09 中国船舶集团风电发展有限公司 Method and device for inverting sea surface wind speed according to synthetic aperture radar
CN117969881A (en) * 2024-03-29 2024-05-03 中国石油大学(华东) Method, device and medium for inverting typhoon sea state and sea surface wind speed based on remote sensing data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102495943A (en) * 2011-10-31 2012-06-13 国家卫星海洋应用中心 Modeling method for geophysical model
CN106021864A (en) * 2016-05-09 2016-10-12 国家卫星海洋应用中心 Calibration method and device of back scattering coefficient of space-borne scatterometer
CN111638521A (en) * 2020-06-17 2020-09-08 中国人民解放军海军潜艇学院 Sea surface wind speed inversion method of remote sensing data of imaging altimeter

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102495943A (en) * 2011-10-31 2012-06-13 国家卫星海洋应用中心 Modeling method for geophysical model
CN106021864A (en) * 2016-05-09 2016-10-12 国家卫星海洋应用中心 Calibration method and device of back scattering coefficient of space-borne scatterometer
CN111638521A (en) * 2020-06-17 2020-09-08 中国人民解放军海军潜艇学院 Sea surface wind speed inversion method of remote sensing data of imaging altimeter

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
张力 等: "26.3 数据采集与预处理", 《数字化核电厂人因可靠性》 *
徐华平 等: "3.2.2 扩展目标散射", 《微波成像雷达信号统计特性——随机过程理论的应用》 *
潘德炉 等: "2.1.2 雷达方程", 《海洋微波遥感与应用》 *
艾未华 等: "C波段机载合成孔径雷达海面风场反演新方法", 《物理学报》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114580309A (en) * 2022-05-09 2022-06-03 深圳市朗诚科技股份有限公司 Drift speed prediction method, drift speed prediction device, calculation equipment and storage medium
CN114580309B (en) * 2022-05-09 2022-08-05 深圳市朗诚科技股份有限公司 Drift speed prediction method, drift speed prediction device, calculation equipment and storage medium
CN117849797A (en) * 2024-01-29 2024-04-09 中国船舶集团风电发展有限公司 Method and device for inverting sea surface wind speed according to synthetic aperture radar
CN117969881A (en) * 2024-03-29 2024-05-03 中国石油大学(华东) Method, device and medium for inverting typhoon sea state and sea surface wind speed based on remote sensing data
CN117969881B (en) * 2024-03-29 2024-06-25 中国石油大学(华东) Method, device and medium for inverting typhoon sea state and sea surface wind speed based on remote sensing data

Similar Documents

Publication Publication Date Title
CN113219466A (en) Sea surface wind speed determination method and device, electronic equipment and storage medium
CN116593989B (en) Troposphere waveguide inversion method and system based on radar sea clutter
CN111507429A (en) Intelligent ship multi-source perception data ship-side fusion method and device and decision system
CN112505644A (en) Sensor measurement correction method and device, terminal equipment and storage medium
CN110531337A (en) Target confidence level calculation method and device based on degree of membership analysis
CN113281709A (en) Radar performance evaluation method based on area coupling forecasting system
CN111337910A (en) Radar inspection method and device
CN115097451A (en) Sea wave multi-parameter inversion method and system based on SAR satellite data
CN105046706B (en) SAR image ship detection method based on rational polynominal Function Fitting sea clutter
CN115877345B (en) Method and device for supplementing missing measurement data of wind profile radar
CN112966656A (en) Data processing method and device
Grande et al. Simplified formulae for the estimation of offshore wind turbines clutter on marine radars
CN112730314A (en) Multi-frequency terahertz detector channel selection method for atmospheric temperature and humidity detection
CN115932773A (en) Target angle detection method, device, equipment and medium based on spectrum shape characteristics
CN112986940B (en) Method for predicting radar sea clutter power in horizontal distance
CN110751103A (en) Microwave signal classification method and system for object internal detection
CN114488107A (en) Method and device for sea clutter space-time distribution and influence grading product manufacturing
CN112990170B (en) Phased array radar target identification method and system, electronic device and medium
CN115166754A (en) Laser radar point cloud processing method and device, electronic equipment and medium
CN109254273A (en) The treating method and apparatus of wind profile radar echo-signal
CN113687321B (en) Radar target detection distance evaluation method and device
CN113960551A (en) Clutter image generation method and target detection method for SAR image
CN117031366B (en) Method and system for monitoring rough sea surface electromagnetic wave propagation
CN115629552B (en) Method and device for checking main target identification all-link model of radio frequency detection system
CN117784042B (en) Calibration alignment error correction method under foil cloud measurement scene

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210806