CN113219465B - Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method - Google Patents

Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method Download PDF

Info

Publication number
CN113219465B
CN113219465B CN202110495408.0A CN202110495408A CN113219465B CN 113219465 B CN113219465 B CN 113219465B CN 202110495408 A CN202110495408 A CN 202110495408A CN 113219465 B CN113219465 B CN 113219465B
Authority
CN
China
Prior art keywords
link
aquatic product
attenuation
microwave
polarization mode
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.)
Active
Application number
CN202110495408.0A
Other languages
Chinese (zh)
Other versions
CN113219465A (en
Inventor
刘西川
蒲康
胡帅
李书磊
高太长
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 University of Defense Technology
Original Assignee
National University of Defense Technology
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 University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202110495408.0A priority Critical patent/CN113219465B/en
Publication of CN113219465A publication Critical patent/CN113219465A/en
Application granted granted Critical
Publication of CN113219465B publication Critical patent/CN113219465B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Electromagnetism (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses an aquatic product identification and microwave frequency automatic optimization method based on polarization attenuation information, which comprises the following steps: s1, extracting an attenuation value caused by dual-polarized precipitation according to the transmitting level and the receiving level of the communication base station; s2, combining the attenuation values to obtain combined characteristic quantities of various frequencies; s3, performing type marking on the aquatic products at each moment to establish a training set and a test set; s4, establishing a plurality of aquatic product classification models based on a machine learning classification algorithm and training; s5, establishing a model performance lookup table by using the test set; s6, establishing a hardware cost lookup table based on the equipment cost; s7, completing automatic microwave frequency optimization based on cost budget; and S8, acquiring the combination characteristic quantity of the area to be detected based on the optimized microwave frequency, and inputting the combination characteristic quantity into the trained aquatic product classification model to obtain the aquatic product type of the area to be detected. The invention can provide an automatic optimal selection scheme of microwave frequency under the condition of cost budget limitation to finish the identification of the aquatic products.

Description

Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method
Technical Field
The invention relates to the technical field of microwave frequency selection in a microwave communication link, in particular to an aqueous composition identification and microwave frequency automatic optimization method based on polarization attenuation information.
Background
Cloud and precipitation are the most active weather phenomena in the troposphere, and the accurate monitoring of cloud and precipitation has important significance for production and life, transportation, aviation flight, military activities and the like. However, due to the complexity of the cloud and precipitation phenomena themselves, accurate remote sensing of their microscopic particles, i.e., aquatic information (e.g., rain, aragonite, hail, etc.), remains a significant obstacle. On one hand, the electromagnetic characteristics of different types of aquatic products are greatly different, and the general rainfall remote sensing algorithm can only ensure the accuracy of measuring a certain type of rainfall. Therefore, it is important to predetermine the type of the aqueous particles. In addition, the identification of the type of the aquatic product has important significance on natural disaster early warning, a numerical mode parameterization scheme, microwave communication transmission, photoelectric weapon efficiency evaluation and the like.
The type of the aquatic product can be identified by utilizing dual-polarization parameter data acquired by a dual-polarization radar through algorithms such as a neural network or fuzzy logic, but the problems of low space-time resolution, low space refinement degree and the like exist; the shape and type of the aquatic product can be accurately judged by utilizing the actually measured aquatic product image, but the shape and type can only represent single-point precipitation and cannot represent large-range precipitation conditions. In recent years, with the development of communication technology, a precipitation information monitoring method based on a commercial communication microwave link appears. The method utilizes link attenuation information to invert the average precipitation intensity of the path, and has the advantages of low cost, high space-time resolution and the like, and a sampling object is close to the ground. Due to the fact that attenuation characteristics of different types of aquatic products are different, more rainfall information can be inverted by utilizing microwave link attenuation information. In the existing method, rainfall types such as layered cloud rainfall and convection cloud rainfall are identified by using microwave link attenuation and polarization information, raindrop spectrum inversion is carried out by using dual-frequency dual-polarization microwave link combination, and then macroscopic rainfall types are identified, but fine information of aquatic products cannot be acquired. The BP neural network or semi-supervised domain adaptation can be used for identifying the types of aquatic objects such as rain, snow, hail and the like through a microwave link, but the types of aquatic objects are few because polarization information is not utilized and the types of aquatic objects are dependent on a specific training set and an empirical model.
In summary, the existing methods have several problems: firstly, the applicability problem of microwave frequency is not considered, not all microwave frequencies can be used for identifying the types of aquatic products, secondly, polarization information of microwaves is not fully utilized, the polarization information can reflect the morphological characteristics of the aquatic products, thirdly, only near-ground rain, snow, hail and the like are considered, and besides, various aquatic product information such as aragonite, wet snow, dry snow, snow particles and the like is also considered, and the research is not carried out at present. Therefore, the microwave frequency is preferred to efficiently and cost effectively install a dual polarized microwave link to identify the type of aquatic product.
Disclosure of Invention
The invention aims to provide an aquatic product identification and microwave frequency automatic optimization method based on polarization attenuation information, which is used in a scheme for monitoring aquatic product types and selecting communication equipment by a microwave link, solves the technical problems in the prior art, can provide a microwave frequency automatic optimization scheme under the condition of cost budget limitation, completes aquatic product identification, and can be widely applied to the field of meteorological information remote sensing such as monitoring aquatic product types of the microwave link.
In order to achieve the purpose, the invention provides the following scheme: the invention provides an aquatic product identification and microwave frequency automatic optimization method based on polarization attenuation information, which comprises the following steps:
s1, extracting an attenuation value caused by dual-polarized precipitation according to the transmitting level and the receiving level of the communication base station;
s2, combining the attenuation values caused by the dual-polarized precipitation obtained in the step S1 to obtain combined characteristic quantities of various frequencies, and carrying out normalization processing on the combined characteristic quantities;
s3, acquiring the type of the aquatic product of each link, performing type labeling on the aquatic product at each moment, and establishing a sample set according to the combined characteristic quantity after normalization processing of each link and the historical data of the type labeling result of the aquatic product; the sample set is divided into a training set and a testing set;
s4, respectively establishing a plurality of single-frequency and/or multi-frequency aquatic product classification models based on a machine learning classification algorithm, and training each aquatic product classification model through the training set to obtain a trained aquatic product classification model;
s5, performing performance test on each aquatic product classification model by using the test set, and establishing a model performance lookup table based on the performance test result;
s6, establishing a hardware cost lookup table based on the cost of the dual-polarized communication equipment with different frequency points;
s7, based on the cost budget, completing the microwave frequency automatic optimization through a model performance lookup table and a hardware cost lookup table;
s8, based on the automatically optimized microwave frequency, obtaining the emission level and the receiving level of the communication base station of the area to be detected, extracting the attenuation value caused by dual-polarized precipitation, obtaining the combined characteristic quantity after normalization processing through the step S2, inputting the combined characteristic quantity after normalization processing into a trained aquatic product classification model, and obtaining the aquatic product type of the area to be detected.
Preferably, the step S1 specifically includes:
s1.1, selecting n communication links for simultaneously transmitting horizontal polarization microwave signals and vertical polarization microwave signals, and acquiring transmitting level and receiving level of each link in a horizontal polarization mode and a vertical polarization mode;
s1.2, calculating the total attenuation of microwave signals of each link based on the transmitting level and the receiving level of each link in different polarization modes;
s1.3, based on the total attenuation and the path length of the microwave signals of each link, obtaining attenuation values caused by precipitation of the unit path length of each link.
Preferably, in step S1.1, the data of the transmission level and the reception level in the horizontal polarization and the vertical polarization include, but are not limited to, using the same microwave transmitter.
Preferably, in step S1.2, the total attenuation of the microwave signal of each link is calculated as follows:
Figure BDA0003054071600000041
in the formula, Aall,h,i、Aall,v,iThe total attenuation of the microwave signals of the ith link is realized in a horizontal polarization mode and a vertical polarization mode respectively; TSLh,i、RSLh,iThe transmission level and the receiving level of the ith link in a horizontal polarization mode are respectively set; TSLv,i、RSLv,iThe transmission level and the receiving level of the ith link in the vertical polarization mode are distinguished.
Preferably, in step S1.3, the attenuation value caused by precipitation per unit path length of each link is calculated as follows:
Figure BDA0003054071600000042
in the formula (I), the compound is shown in the specification,Ah,i、Av,iattenuation values caused by precipitation of the unit path length of the ith link in a horizontal polarization mode and a vertical polarization mode respectively; a. theall,h,i、Aall,v,iThe total attenuation of the microwave signals of the ith link is realized in a horizontal polarization mode and a vertical polarization mode respectively; a. theref,h,i、Aref,v,iRespectively performing baseline attenuation on the ith link in a horizontal polarization mode and a vertical polarization mode; l isiIs the length of the ith link.
Preferably, in step S3, the aquatic species include, but are not limited to, rain, aragonite, and wet snow.
Preferably, in step S3, the aquatic product type of each link is obtained by observing results of precipitation micro physical characteristic measuring instruments deployed on each link; the sample set is [ X ]j',Yj]Wherein X isj' As the combined feature quantity after normalization processing, the combined feature quantity Xj＝Combine{[Ah,i,Av,i]}，YjIs labeled with the type being labeled.
Preferably, in the step S4, the machine learning classification algorithm includes, but is not limited to, transfer learning.
The invention discloses the following technical effects:
according to the transmitting level and the receiving level of the communication base station, the attenuation information caused by dual-polarization precipitation is extracted; combining attenuation values caused by dual-polarized precipitation to obtain multiple frequency combination characteristic quantities; establishing a sample set by combining the types of the aquatic products observed by the rainfall micro physical characteristic measuring instrument; establishing an aquatic product classification model based on a machine learning classification algorithm, and identifying the aquatic product type of the region to be detected through the classification model, so that the polarization difference of extinction characteristics of different aquatic products is fully utilized on the basis of extracting attenuation characteristic quantity caused by precipitation according to level signals recorded by communication equipment, and the effective identification of the aquatic product type is realized; training the classification model through a test set, and evaluating the performance of various combination models; and combining a model performance lookup table and a hardware cost lookup table to realize automatic optimization of microwave frequency. In the application process, the aquatic product type identification system with the optimal cost effectiveness ratio can be established only by selecting communication equipment with proper frequency combination according to the microwave frequency automatic optimization method, so that the microwave frequency automatic optimization scheme can be provided under the condition of cost budget limitation, the aquatic product identification is completed, and the method can be widely applied to the meteorological information remote sensing field such as microwave link aquatic product type monitoring.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of an automatic microwave frequency optimization method based on polarization attenuation information according to the present invention;
FIG. 2 is a flow chart of the present invention for identifying the type of an aqueous composition based on automatically preferred microwave frequencies;
FIGS. 3(a) -3(c) are single-, dual-, and triple-frequency model performance lookup tables, respectively, in an example of the invention;
fig. 4 is a hardware cost look-up table for 8 frequency communication devices in an example of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1 to 4, the present embodiment provides an aqueous identification and microwave frequency automatic optimization method based on polarization attenuation information, including the following steps:
s1, extracting an attenuation value caused by dual-polarized precipitation according to the transmitting level and the receiving level of the communication base station; the method specifically comprises the following steps:
s1.1, selecting n communication links for simultaneously transmitting horizontally polarized and vertically polarized microwave signals, the operating frequencies of which are f1,f2,…,fn(GHz) recording the emission levels in the horizontal polarization mode as TSLh,1,TSLh,2,…,TSLh,n(dB), the emission levels in the vertical polarization mode are TSL respectivelyv,1,TSLv,2,…,TSLv,n(dB), the reception levels in the horizontal polarization mode are RSL respectivelyh,1,RSLh,2,…,RSLh,n(dB), the reception levels in the vertical polarization mode are RSL, respectivelyv,1,RSLv,2,…,RSLv,n(dB). Dual polarized transmit level and receive level data includes, but is not limited to, the use of the same microwave transmitter.
S1.2, calculating the total attenuation (dB) of microwave signals of each link, wherein the total attenuation (dB) is shown as the following formula:
Figure BDA0003054071600000071
in the formula, Aall,h,i、Aall,v,iThe total attenuation of the microwave signals of the ith link is respectively in a horizontal polarization mode and a vertical polarization mode.
S1.3, acquiring attenuation values (dB/km) caused by precipitation of unit path length of each link, wherein the attenuation values are shown as the following formula:
Figure BDA0003054071600000072
in the formula, Ah,i、Av,iAttenuation values caused by precipitation of the unit path length of the ith link in a horizontal polarization mode and a vertical polarization mode respectively; a. theref,h,i、Aref,v,iThe unit of the base line attenuation of the ith link in the horizontal polarization mode and the vertical polarization mode is as follows: dB; l isiIs the ith linkLength of (d), unit: and km.
S2, combining the attenuation values caused by the dual-polarized precipitation obtained in the step S1 to obtain combined characteristic quantities of various frequencies, and carrying out normalization processing on the combined characteristic quantities;
wherein, the combined feature vector X of multiple frequenciesj＝Combine{[Ah,i,Av,i]And recording the combined characteristic quantity after normalization processing as Xj'。
S3, acquiring the type of the aquatic product of each link, performing type labeling on the aquatic product at each moment, and establishing a sample set according to the combined characteristic quantity after normalization processing of each link and historical data of the type labeling result of the aquatic product; the sample set is divided into a training set and a testing set;
the aquatic product type of each link is obtained through the observation result of the rainfall micro-physical characteristic measuring instrument deployed on each link, and the marked type label is marked as YjThe sample set is [ X ]j',Yj]. Aquatic species types include, but are not limited to, rain, aragonite, wet snow.
S4, respectively establishing a plurality of single-frequency and/or multi-frequency aquatic product classification models based on a machine learning classification algorithm, and training each aquatic product classification model through the training set to obtain a trained aquatic product classification model; the machine learning classification algorithm includes, but is not limited to, transfer learning.
Taking zero sample learning in the transfer learning as an example, a basic flow of the aquatic product classification model is explained by adopting a weight selection and matrix decomposition method:
(1) according to normalized combined characteristic quantity X under various frequency combinations in training setj' type with aqueous product YjDetermining the weight coefficients of the normalized combined feature quantities one by one:
Figure BDA0003054071600000091
wherein, wmnWeight coefficient of n characteristic quantity of m type of aquatic product, XmnIs the mth aquatic productN characteristic quantity of object type, p is dimension of characteristic quantity, NsNumber of known types of aqueous substances, NuIs the number of unknown types of aqueous products.
(2) Decomposing the matrix of the original water composition normalization characteristic quantity combination into an element matrix U corresponding to the visual characteristic and the semantic characteristic by adopting a matrix decomposition methodX、UAAnd a factor matrix VX，VA；
(3) Using nearest neighbor method to form factor matrix VX、VAClassifying the samples with the most similar intermediate factor vectors into the same aquatic product type;
(4) in the actual classification process, an objective function is established,
Figure BDA0003054071600000092
wherein, XsFor input visual feature matrices of known type, AsThe method comprises the steps of inputting a known type of semantic feature matrix, Q being a reversible matrix, w being a weight coefficient, and lambda being a parameter for adjusting similarity constraint of the visual feature matrix and the semantic attribute feature matrix.
(5) And circularly optimizing the variables in the objective function by adopting an alternative iteration updating method, and obtaining an optimal classification result of the aquatic products after a preset threshold value is reached.
The aquatic compound classification model comprises a single-frequency model, a double-frequency model, … and an n-frequency model.
S5, performing performance test on each aquatic product classification model by using the test set, and establishing a model performance lookup table based on the performance test result;
s6, establishing a hardware cost lookup table based on the cost of the dual-polarized communication equipment with different frequency points;
s7, based on the cost budget, completing the microwave frequency automatic optimization through a model performance lookup table and a hardware cost lookup table;
s8, based on the automatically optimized microwave frequency, obtaining the emission level and the receiving level of the communication base station of the area to be detected, extracting the attenuation value caused by dual-polarized precipitation, obtaining the combined characteristic quantity after normalization processing through the step S2, inputting the combined characteristic quantity after normalization processing into a trained aquatic product classification model, and obtaining the aquatic product type of the area to be detected.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.

Claims (5)

1. The method for identifying the aquatic products and automatically optimizing the microwave frequency based on the polarization attenuation information is characterized by comprising the following steps of:
s1, extracting an attenuation value caused by dual-polarized precipitation according to the transmitting level and the receiving level of the communication base station;
s2, combining the attenuation values caused by the dual-polarized precipitation obtained in the step S1 to obtain combined characteristic quantities of various frequencies, and carrying out normalization processing on the combined characteristic quantities;
s3, acquiring the type of the aquatic product of each link, performing type labeling on the aquatic product at each moment, and establishing a sample set according to the combined characteristic quantity after normalization processing of each link and the historical data of the type labeling result of the aquatic product; the sample set is divided into a training set and a testing set;
s4, respectively establishing a plurality of single-frequency and/or multi-frequency aquatic product classification models based on a machine learning classification algorithm, and training each aquatic product classification model through the training set to obtain a trained aquatic product classification model;
s5, performing performance test on each aquatic product classification model by using the test set, and establishing a model performance lookup table based on the performance test result;
s6, establishing a hardware cost lookup table based on the cost of the dual-polarized communication equipment with different frequency points;
s7, based on the cost budget, completing the microwave frequency automatic optimization through a model performance lookup table and a hardware cost lookup table;
s8, extracting an attenuation value caused by dual-polarized precipitation based on the transmitting level and the receiving level of the communication base station of the area to be detected, which are obtained through automatic optimization, obtaining a combined characteristic quantity after normalization processing through the step S2, inputting the combined characteristic quantity after normalization processing into a trained aquatic product classification model, and obtaining the aquatic product type of the area to be detected;
step S1 specifically includes:
s1.1, selecting n communication links for simultaneously transmitting horizontal polarization microwave signals and vertical polarization microwave signals, and acquiring transmitting level and receiving level of each link in a horizontal polarization mode and a vertical polarization mode;
s1.2, calculating the total attenuation of microwave signals of each link based on the transmitting level and the receiving level of each link in different polarization modes;
s1.3, acquiring attenuation values caused by precipitation of each link unit path length based on total attenuation and path length of each link microwave signal;
in step S1.2, the calculation of the total attenuation of the microwave signal of each link is shown as follows:
Figure FDA0003550813710000021
in the formula, Aall,h,i、Aall,v,iThe total attenuation of the microwave signals of the ith link is realized in a horizontal polarization mode and a vertical polarization mode respectively; TSLh,i、RSLh,iThe transmission level and the receiving level of the ith link in a horizontal polarization mode are respectively set; TSLv,i、RSLv,iThe transmission level and the receiving level of the ith link in a vertical polarization mode are respectively set;
in step S1.3, the method for calculating the attenuation value due to precipitation per unit path length of each link is shown as follows:
Figure FDA0003550813710000022
in the formula, Ah,i、Av,iAttenuation values caused by precipitation of the unit path length of the ith link in a horizontal polarization mode and a vertical polarization mode respectively; a. theall,h,i、Aall,v,iAre respectively provided withThe total attenuation of the microwave signals of the ith link is realized in a horizontal polarization mode and a vertical polarization mode; a. theref,h,i、Aref,v,iRespectively performing baseline attenuation on the ith link in a horizontal polarization mode and a vertical polarization mode; l isiIs the length of the ith link.
2. The method for identifying aquatic products and automatically optimizing microwave frequencies according to the polarization attenuation information of claim 1, wherein the data of the transmission level and the reception level in the horizontal polarization and the vertical polarization comprises but is not limited to the same microwave transmitter in step S1.1.
3. The method for identifying aquatic products and automatically optimizing microwave frequency based on polarization attenuation information according to claim 1, wherein in step S3, the aquatic product types include but are not limited to rain, aragonite, and wet snow.
4. The method for identifying aquatic products and automatically optimizing microwave frequencies based on polarization attenuation information of claim 1, wherein in step S3, the aquatic product type of each link is obtained through observation results of precipitation micro-physical characteristic measuring instruments deployed on each link; the sample set is [ X ]j',Yj]Wherein X isj' As the combined feature quantity after normalization processing, the combined feature quantity Xj＝Combine{[Ah,i,Av,i]}，YjIs labeled with the type being labeled.
5. The method for identifying aquatic products and automatically optimizing microwave frequencies according to claim 1, wherein in step S4, the machine learning classification algorithm includes but is not limited to transfer learning.
CN202110495408.0A 2021-05-07 2021-05-07 Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method Active CN113219465B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110495408.0A CN113219465B (en) 2021-05-07 2021-05-07 Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110495408.0A CN113219465B (en) 2021-05-07 2021-05-07 Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method

Publications (2)

Publication Number Publication Date
CN113219465A CN113219465A (en) 2021-08-06
CN113219465B true CN113219465B (en) 2022-04-29

Family

ID=77091463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110495408.0A Active CN113219465B (en) 2021-05-07 2021-05-07 Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method

Country Status (1)

Country Link
CN (1) CN113219465B (en)

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106548613A (en) * 2016-11-02 2017-03-29 中国人民解放军理工大学 For the region microwave link networking signal pickup assembly and method of Rainfall estimation
US11204443B2 (en) * 2017-08-14 2021-12-21 Ramot At Tel-Aviv University Ltd. Relating rain intensity and dynamic range in commercial microwave links
CN107843884B (en) * 2017-09-13 2021-09-14 成都信息工程大学 Method for improving accuracy of thunderstorm weather early warning forecast based on dual-polarization radar observation
CN109581546B (en) * 2018-10-30 2020-10-16 中国人民解放军国防科技大学 Rainfall type identification method based on microwave link attenuation and polarization information
CN110543893A (en) * 2019-08-07 2019-12-06 河海大学 Microwave attenuation precipitation particle type identification method based on BP neural network
CN111474606B (en) * 2020-03-30 2022-04-05 中国人民解放军国防科技大学 Rainfall and water vapor comprehensive measurement device and method based on dual-frequency dual-polarization microwave link
CN111366931B (en) * 2020-05-19 2023-06-30 范思睿 Cloud precipitation refined inversion method based on cloud radar

Also Published As

Publication number Publication date
CN113219465A (en) 2021-08-06

Similar Documents

Publication Publication Date Title
CN109581546B (en) Rainfall type identification method based on microwave link attenuation and polarization information
Bukovčić et al. Polarimetric radar relations for quantification of snow based on disdrometer data
Testud et al. The concept of “normalized” distribution to describe raindrop spectra: A tool for cloud physics and cloud remote sensing
Marzano et al. Investigating precipitation microphysics using ground-based microwave remote sensors and disdrometer data
CN113177360B (en) Rain intensity self-adaptive estimation system and method based on clustering rain attenuation relation
CN110543893A (en) Microwave attenuation precipitation particle type identification method based on BP neural network
CN112906310A (en) Method for optimizing BP neural network microwave remote sensing soil moisture inversion by considering firefly algorithm
Carr et al. The influence of surface and precipitation characteristics on TRMM Microwave Imager rainfall retrieval uncertainty
Fetterer et al. Sea ice type maps from Alaska synthetic aperture radar facility imagery: An assessment
Houston et al. Thunderstorm Observation by Radar (ThOR): An algorithm to develop a climatology of thunderstorms
CN111274911B (en) Dense fog monitoring method based on wireless microwave attenuation characteristic transfer learning
Adewumi et al. Characterization and modeling of vegetation effects on UHF propagation through a long forested channel
CN115443889A (en) Accurate irrigation method and device for crops
Riera et al. Preprocessing and assessment of rain drop size distributions measured with a K-band Doppler radar and an optical disdrometer
CN113219465B (en) Polarization attenuation information-based aquatic product identification and microwave frequency automatic optimization method
CN110516552B (en) Multi-polarization radar image classification method and system based on time sequence curve
Kuster et al. Using ZDR columns in forecaster conceptual models and warning decision-making
CN110082500A (en) A kind of crops drought remote sensing monitoring method quickly determined based on dry and wet side
KR20150059864A (en) method of hydrometeor classification using raw data of X band dual polarization radar
CN115902812B (en) Automatic discriminating method, system, equipment and terminal for short-time heavy rain weather background
Di Michele et al. Physically based statistical integration of TRMM microwave measurements for precipitation profiling
CN111860562B (en) Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link
CN114384487A (en) XGboost-based weather radar ground object echo identification method
Pejcic et al. Polarimetric radar-based methods for evaluation of hydrometeor mixtures in numerical weather prediction models
Zohidov et al. Retrieval of rainfall fields in urban areas using attenuation measurements from mobile phone networks: A modeling feasibility study

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
GR01 Patent grant
GR01 Patent grant