CN111123234B - Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity - Google Patents

Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity Download PDF

Info

Publication number
CN111123234B
CN111123234B CN201911321200.6A CN201911321200A CN111123234B CN 111123234 B CN111123234 B CN 111123234B CN 201911321200 A CN201911321200 A CN 201911321200A CN 111123234 B CN111123234 B CN 111123234B
Authority
CN
China
Prior art keywords
clutter
mean value
parameter
amplitude mean
roughness
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
CN201911321200.6A
Other languages
Chinese (zh)
Other versions
CN111123234A (en
Inventor
赵鹏
张玉石
李清亮
朱秀芹
尹志盈
李慧明
许心瑜
张金鹏
黎鑫
张浙东
余运超
夏晓云
李善斌
尹雅磊
万晋通
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.)
China Institute of Radio Wave Propagation CETC 22 Research Institute
Original Assignee
China Institute of Radio Wave Propagation CETC 22 Research Institute
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 China Institute of Radio Wave Propagation CETC 22 Research Institute filed Critical China Institute of Radio Wave Propagation CETC 22 Research Institute
Priority to CN201911321200.6A priority Critical patent/CN111123234B/en
Publication of CN111123234A publication Critical patent/CN111123234A/en
Application granted granted Critical
Publication of CN111123234B publication Critical patent/CN111123234B/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
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/414—Discriminating targets with respect to background clutter
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/411—Identification of targets based on measurements of radar reflectivity
    • G01S7/412—Identification of targets based on measurements of radar reflectivity based on a comparison between measured values and known or stored values

Abstract

The invention discloses a similar bare ground clutter mean value characteristic analogy method based on roughness and humidity, which comprises the following steps of: (1) numbering environment parameters with obvious influence on the clutter amplitude mean value aiming at the bare ground scattering characteristic; (2) analyzing the change trend of the bare land clutter amplitude mean value when each environmental parameter changes independently by using the measured data, and solving the influence coefficient of each parameter on the amplitude mean value according to the parameter change range and the corresponding clutter amplitude mean value change range; (3) giving an analogy formula of the amplitude mean value under the parameter; (4) and giving an analogy formula of the multi-parameter clutter amplitude mean value. The method disclosed by the invention utilizes the clutter amplitude mean value of the known bare land to analogize the amplitude mean value of the bare land clutter with similar characteristics, can overcome the bottleneck problems of difficult actual test in certain areas, insufficient precision of an empirical model and the like, and has important significance for clutter cognition in remote areas with higher timeliness requirement.

Description

Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity
Technical Field
The invention belongs to the field of research on ground clutter characteristics of radar, and particularly relates to a method for analogizing clutter mean value characteristics of ground objects with similar characteristics by using clutter characteristics of known ground objects based on actual measurement environment parameters in the field.
Background
When the clutter characteristics of actual ground objects are researched, the cognition mode is mostly measured data obtained through measurement tests or a clutter model established by referring to scholars at home and abroad, such as an empirical model of scattering of various ground objects disclosed in microwave remote sensing of Wurabi. The clutter test mode is relatively accurate, but the time and the labor are wasted, and the requirements cannot be met timely for certain specific tasks with timeliness requirements; the mode of referring to the empirical model is relatively simple, but due to the complexity of the ground features, a certain difference is often formed between the actual ground features and the model, and the task with higher precision requirement cannot be met. Therefore, a set of ground clutter prediction method needs to be researched to obtain the clutter characteristic of the target ground object timely and accurately.
Disclosure of Invention
The invention aims to provide a similar bare ground clutter mean value characteristic analogy method based on roughness and humidity.
The invention adopts the following technical scheme:
in a method for analogizing similar bare ground clutter mean characteristics based on roughness and humidity, the improvement comprising the steps of:
(1) for the bare earth scattering property, environmental parameters which have significant influence on the clutter amplitude mean value include but are not limited to roughness, water content and dielectric constant, all parameters are numbered as x1, x2 … xM … xM;
(2) analyzing the change trend of the average value of the bare land clutter amplitude when each environmental parameter is independently changed by utilizing the measured data, and recording a trend curve; according to the parameter variation range and the corresponding clutter amplitude mean variation range, the influence coefficient of each parameter on the amplitude mean is solved:
Figure BDA0002327209960000011
wherein, Delta sigma is the variation range of the amplitude mean value, Delta xm is the variation range of the parameter, and for some parameters showing the segment variation trend, kxmShould be represented by a piecewise function;
(3) taking the m-th parameter as an example, an analogy formula of the amplitude mean value under the parameter is given:
Figure BDA0002327209960000012
wherein sigmat(xm) is the average of the amplitudes of the analogized target samples,
Figure BDA0002327209960000021
is the known amplitude mean value of the reference sample, fm(Δ xm) is a fitting formula for the difference in the variables xm;
according to the content of step (2), f is givenm(delta xm) and solving fitting parameters by using a linear regression equation to obtain a fitting formula fm(Δxm)；
(4) According to the content of the step (3), giving an analogy formula of the multi-parameter clutter amplitude mean value:
Figure BDA0002327209960000022
wherein alpha ismThe weight coefficient of the influence of the mth parameter on the clutter amplitude mean value in all the environment parameters, and if the influence of all the M parameters on the scattering coefficient is mutually independent, the weight coefficient alphamCan default to 1; if there are N, N ≦ M parameters whose influence on the scattering coefficient is correlated with each other, k in step 2 may be usedxmAnd (3) calculating:
Figure BDA0002327209960000023
further, in the step (3), fmExplicit expressions of (Δ xm) include, but are not limited to, polynomials or formulas consisting of basis functions.
The invention has the beneficial effects that:
on the basis of the existing research results, the method takes the bare area as a research object, analyzes the influence degree of the parameter changes such as roughness, water content, dielectric property and the like on the average value characteristic (namely scattering coefficient) of the bare area clutter according to the actually measured environmental parameters, provides a quantitative statistical method, initially establishes a similar bare area clutter average value characteristic analogy method, and provides a basis for the subsequent more complex ground clutter prediction. Compared with the method for directly carrying out clutter test, the method is simpler and more convenient, and compared with theoretical calculation and an empirical model, the method has relatively better precision. The method can be applied to various types of ground objects at the later stage, and is helpful for clutter cognition of complex ground objects.
The method of the invention utilizes the clutter amplitude mean value of the known bare land to analogize the amplitude mean value of the bare land clutter with similar characteristics, can overcome the bottleneck problems of difficult actual test in some areas, insufficient precision of empirical models and the like, and has important significance for clutter cognition in remote areas with higher timeliness requirement.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2a is a comparison of measured data for various roughness values at about 9% humidity;
FIG. 2b is a graph comparing measured data for different roughness values at about 5% humidity;
FIG. 3 is a schematic diagram of the variation of the amplitude mean of the measured data with roughness;
FIG. 4a is a comparison of clutter amplitude averages at different soil humidity levels at a root mean square height of about 4 cm;
FIG. 4b is a comparison of clutter amplitude averages at different soil humidity levels at a root mean square height of about 2 cm;
FIG. 5 is a schematic diagram of the variation of the mean clutter amplitude of measured data with humidity;
FIG. 6a is a graph comparing results of analogy to roughness at a humidity of about 5% with measured data;
FIG. 6b is a graph comparing the results of the analogy with measured data at a root mean square height of about 2 cm;
FIG. 7 is a graph comparing multi-parameter analogies with measured data.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The flow chart of the embodiment is shown in fig. 1. In order to show the effect conveniently, the embodiment takes clutter and environmental parameter data tested in a certain bare ground as analogizing samples, a research object is the bare ground with uniform and flat terrain, the frequency range is S wave band, the polarization is HH, the incident angle range is 20-80 degrees, and other related radar parameters are consistent by default in the analogizing process; the analogy includes the citation of some of the prior art documents. The method specifically comprises the following steps:
(1) according to literature data and existing clutter research results, under uniform terrain, main parameters influencing the amplitude average value characteristic of bare ground clutter comprise soil surface roughness, soil humidity, soil dielectric constant and the like, and the soil dielectric constant is mainly influenced by the soil humidity, so that the main influencing factors are the soil roughness and the soil humidity which are respectively numbered as x1 and x 2.
(2) And analyzing the change trend of the bare land clutter amplitude average value when the soil roughness x1 and the soil humidity x2 are independently changed by combining the existing literature and the measured data.
As shown in table 1, a table is recorded for the environmental parameters of a certain bare ground clutter test. Where roughness rms is the root mean square height of the surface, typically characterizing the roughness of the ground; soil moisture is expressed in weight percent. Table 2 shows the mean values of the ground clutter scattering coefficients tested accordingly, with the polarization HH polarization, the incidence angle range of 20 ° to 80 °, and the step 5 °. And (5) performing parameter change analysis by using the actually measured data as a sample and combining a relevant theory and a literature conclusion.
Figure BDA0002327209960000031
Table 1 bare soil parameter test table
Figure BDA0002327209960000041
TABLE 2 average amplitude σ of bare ground clutter0(dB) recording meter
(21) Variable x1Clutter mean change caused by soil roughness.
According to the related conclusion of scattering coefficients along with the root mean square height and the incidence angle in Ulaby microwave remote sensing, the following rules are provided: when the root mean square height is in the range of 1cm to 4.5cm, the scattering coefficient tends to increase approximately linearly with the increase of the root mean square height after the incident angle is larger than 10 degrees. And (4) analyzing by utilizing the measured data by combining the rule.
Comparing the environmental parameters in table 1, test data with equivalent humidity (within 2% humidity difference) and significant roughness change are selected for comparison. Using the above principle, 1011 and 1013, 1102 and 1014, respectively, were selected for comparative analysis. As shown in fig. 2a and 2b, for the comparison of the measured clutter data with different roughness, it can be seen that there is a significant difference between the average amplitudes with different roughness, and the difference varies with the incident angle. And according to the relation between the scattering coefficient difference variation and the incidence angle, carrying out sectional analysis on the incidence angle range.
As shown in fig. 3, the range of incidence angles is given as 20 ° to 50 ° and 55 ° to 80 °, and the variation of the amplitude mean with the roughness is given. According to the roughness variation range and the corresponding clutter amplitude mean variation range, calculating the influence coefficient kx1：
Figure BDA0002327209960000042
(22) Variable x2Mean change in clutter due to soil moisture.
Similarly, the mean amplitude (dB) of the bare land appears to vary approximately linearly with soil moisture, as determined by other parameters, according to the literature.
Comparing the environmental parameters in table 1, test data with substantially equivalent roughness (within 1cm of roughness) and significant changes in humidity were selected for comparison. Using the above principle, 1010 and 1014, 1011 and 1102 are respectively selected for comparative analysis. As shown in fig. 4a and 4b, the clutter amplitude average values of different soil humidity are compared, and as can be seen from the comparison result, the bare land clutter amplitude average value with larger humidity is larger on the whole. The variation trend of the scattering coefficient difference value along with the incident angle is not obvious, the variation degree of the amplitude mean value along with the soil humidity can be assumed to be consistent within the range of 20-80 degrees, and all angle data can be subjected to statistical analysis.
As shown in fig. 5, the variation of the mean amplitude value with the percentage of soil moisture is given. According to the humidity variation range and the corresponding clutter amplitude mean variation range, the influence coefficient is calculated
Figure BDA0002327209960000057
Figure BDA0002327209960000051
(3) An analogy formula for the amplitude mean value of a single parameter is given, taking the mth parameter as an example:
Figure BDA0002327209960000052
wherein sigmat(xm) is the average of the amplitudes of the analogized target samples,
Figure BDA0002327209960000053
being the known amplitude mean of the reference sample, Δ xm is the difference between the m parameters of the target sample and the reference sample.
For the roughness parameter x1, according to the analysis result in the step (2), the clutter amplitude average value approximately linearly changes with the roughness within a certain roughness range, and the clutter amplitude average value approximately takes a segmented form within different incidence angle ranges, so that the fitting formula f related to the delta x11(Δ x1) is a linear equation that can be expressed in segments:
Figure BDA0002327209960000054
according to the data shown in fig. 2a and 2b, the parameters in the formula (8) are solved by using a linear regression equation, and then a fitting formula can be obtained. With respect to the variable x in view of the amplitude mean σ1Linearly changing, coefficient k in fitting formulax1,1The coefficient value of equation (5) can be used directly, with constant a defaulted to 0, with respect to variable x1The analogy formula of the roughness parameter is as follows:
Figure BDA0002327209960000055
wherein, x1 which is more than or equal to 2cm and less than or equal to 12cm is the limited range of the formula for the roughness.
Similarly, the humidity parameter x2And analogy formulas can also be obtained using the above-mentioned ideas and the data of figures 4a and 4b,
Figure BDA0002327209960000056
wherein x2 is more than or equal to 4% and less than or equal to 15% is the limited range of the formula for humidity.
The following gives an example of single-parameter analogy according to formulas (9) and (10), wherein the roughness single-parameter analogy takes 1102 data in table 1 as a reference sample and 1014 data as a target sample; the humidity single-parameter analogy takes 1102 data as a reference sample and 1011 data as a target sample. The pair of the analogical result and the actual measurement result is shown in fig. 6a and 6 b. The average difference between the roughness analogizing result and the actually measured data is-0.8187 dB, and the average difference between the humidity analogizing result and the actually measured data is 0.0797dB, which indicates that the analogizing result of a single parameter is closer to the actually measured data.
(4) And (4) giving an analogy formula of the multi-parameter clutter amplitude mean value according to the content of the step (3):
Figure BDA0002327209960000061
using k in step (2)mAnd equation (4) calculating the weight coefficient αm。
According to past experience, there is no obvious correlation between the roughness variable and the humidity variable, so that the two variables of roughness and humidity can be considered to be independent of each other, and therefore alpha1And alpha2Default to 1, and the analogy formula is:
Figure BDA0002327209960000062
an analogy example is given by taking 1014 data in table 1 as a reference sample and 1010 data as a target sample according to formula (12) and the parameters in table 1. The result is shown in fig. 7, the curve of the analogy result is very close to the curve of the target data, the average error of the overall amplitude mean value is-0.63 dB, and the analogy formula is proved to have good applicability in a limited range.
In the embodiment, the sample parameters are less, the limited range is more, and the formula (12) cannot be used as an analogy formula of all bare grounds. With the increase of the number of samples, the formula is gradually perfected, and the applicability is wider.

Claims (2)

1. A similar bare ground clutter mean value characteristic analogy method based on roughness and humidity is characterized by comprising the following steps:
(1) for the bare earth scattering property, environmental parameters which have significant influence on the clutter amplitude mean value include but are not limited to roughness, water content and dielectric constant, all parameters are numbered as x1, x2 … xM … xM;
(2) analyzing the change trend of the average value of the bare land clutter amplitude when each environmental parameter is independently changed by utilizing the measured data, and recording a trend curve; according to the parameter variation range and the corresponding clutter amplitude mean variation range, the influence coefficient of each parameter on the clutter amplitude mean is calculated:
Figure FDA0003153034910000011
wherein, Delta sigma is the variation range of clutter amplitude mean value, Delta xm is the variation range of parameters, and for some parameters presenting segment variation trend, kxmShould be represented by a piecewise function;
(3) taking the m-th parameter as an example, an analogy formula of the clutter amplitude mean value under the parameter is given:
Figure FDA0003153034910000012
wherein sigmat(xm) is the average of the clutter amplitudes of the analogized target samples,
Figure FDA0003153034910000013
is the mean value of the clutter amplitude of the known reference sample, fm(Δ xm) is a fitting formula for the difference in the variables xm;
according to the content of step (2), f is givenm(delta xm) and solving fitting parameters by using a linear regression equation to obtain a fitting formula fm(Δxm)；
(4) According to the content of the step (3), giving an analogy formula of the multi-parameter clutter amplitude mean value:
Figure FDA0003153034910000014
wherein alpha ismThe weight coefficient of the influence of the mth parameter on the clutter amplitude mean value in all the environment parameters, and if the influence of all the M parameters on the scattering coefficient is mutually independent, the weight coefficient alphamCan default to 1; if there are N, N ≦ M parameters whose influence on the scattering coefficient is correlated with each other, k in step 2 may be usedxmAnd (3) calculating:
Figure FDA0003153034910000021
2. the roughness and humidity based similar bare ground clutter mean characteristic analogy method according to claim 1, characterized in that: in step (3), fmExplicit expressions of (Δ xm) include, but are not limited to, polynomials or formulas consisting of basis functions.
CN201911321200.6A 2019-12-20 2019-12-20 Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity Active CN111123234B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911321200.6A CN111123234B (en) 2019-12-20 2019-12-20 Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911321200.6A CN111123234B (en) 2019-12-20 2019-12-20 Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity

Publications (2)

Publication Number Publication Date
CN111123234A CN111123234A (en) 2020-05-08
CN111123234B true CN111123234B (en) 2021-09-17

Family

ID=70500349

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911321200.6A Active CN111123234B (en) 2019-12-20 2019-12-20 Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity

Country Status (1)

Country Link
CN (1) CN111123234B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937075A (en) * 2010-08-16 2011-01-05 北京海兰信数据科技股份有限公司 Signal processing method and system of ship navigation radar
US7952511B1 (en) * 1999-04-07 2011-05-31 Geer James L Method and apparatus for the detection of objects using electromagnetic wave attenuation patterns
CN106291482A (en) * 2016-09-29 2017-01-04 三峡大学 A kind of wind turbine blade radar echo signal Doppler frequency spectrum method for solving
CN106405462A (en) * 2016-08-30 2017-02-15 中国电子科技集团公司第十三研究所 On-chip scattering parameter source tracing and uncertainty assessment method
CN106650689A (en) * 2016-12-30 2017-05-10 厦门理工学院 Coastal city time sequence land utilization information extracting method
CN106772300A (en) * 2016-12-02 2017-05-31 中国电波传播研究所（中国电子科技集团公司第二十二研究所） A kind of microwave over-the-horizon radar reflectogram computational methods
WO2018197254A1 (en) * 2017-04-28 2018-11-01 Koninklijke Philips N.V. Power doppler imaging system and method with improved clutter supperssion
CN110503348A (en) * 2019-09-09 2019-11-26 中南大学 A kind of individual air Pollution exposure analog measurement method based on location matches

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
NL1031761C2 (en) * 2006-05-08 2007-11-13 Thales Nederland Bv Method for filtering sea clutter in a radar echo by using a hydrographic model.
AU2014232487A1 (en) * 2013-03-15 2015-10-01 Polaris Sensor Technologies, Inc. Long wave infrared imaging polarimeter, and method of assembly
US10249025B2 (en) * 2015-07-06 2019-04-02 The United States Of America As Represented By The Secretary Of The Navy Atmospheric channel characterization system and method using target image information

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7952511B1 (en) * 1999-04-07 2011-05-31 Geer James L Method and apparatus for the detection of objects using electromagnetic wave attenuation patterns
CN101937075A (en) * 2010-08-16 2011-01-05 北京海兰信数据科技股份有限公司 Signal processing method and system of ship navigation radar
CN106405462A (en) * 2016-08-30 2017-02-15 中国电子科技集团公司第十三研究所 On-chip scattering parameter source tracing and uncertainty assessment method
CN106291482A (en) * 2016-09-29 2017-01-04 三峡大学 A kind of wind turbine blade radar echo signal Doppler frequency spectrum method for solving
CN106772300A (en) * 2016-12-02 2017-05-31 中国电波传播研究所（中国电子科技集团公司第二十二研究所） A kind of microwave over-the-horizon radar reflectogram computational methods
CN106650689A (en) * 2016-12-30 2017-05-10 厦门理工学院 Coastal city time sequence land utilization information extracting method
WO2018197254A1 (en) * 2017-04-28 2018-11-01 Koninklijke Philips N.V. Power doppler imaging system and method with improved clutter supperssion
CN110503348A (en) * 2019-09-09 2019-11-26 中南大学 A kind of individual air Pollution exposure analog measurement method based on location matches

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"裸地散射特性分析";汤明;《电波科学学报》;19941231;第9卷(第4期);第69-75页 *

Also Published As

Publication number Publication date
CN111123234A (en) 2020-05-08

Similar Documents

Publication Publication Date Title
Chen et al. Partitioning of daily evapotranspiration using a modified shuttleworth-wallace model, random Forest and support vector regression, for a cabbage farmland
CN103048339B (en) Soil moisture detection method and soil moist detection device
CN114018833B (en) Method for estimating heavy metal content of soil based on hyperspectral remote sensing technology
Zahid et al. Terahertz characterisation of living plant leaves for quality of life assessment applications
CN111123234B (en) Similar bare ground clutter mean value characteristic analogy method based on roughness and humidity
CN112651173B (en) Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system
Seidel et al. Soil moisture effects on predictive VNIR and MIR modeling of soil organic carbon and clay content
Cao et al. Hyperspectral estimation of soil organic matter content using grey relational local regression model
CN107504909A (en) White light reflectance measurement film thickness adaptive approach based on Regularization algorithms
CN109765247B (en) Soil moisture inversion method for wheat crop coverage areas at different growth stages
CN113111799B (en) Cultivated land soil fertility level monitoring method based on ensemble empirical mode decomposition
Jing et al. Using temporal and spatial scales to unravel the effects of climatic factors on vegetation variations in China
CN113065221B (en) Large ground-wiping corner undersea clutter model, model construction system and simulation method
CN113959979B (en) Near infrared spectrum model migration method based on deep Bi-LSTM network
CN105092509A (en) Sample component measurement method based on PCR-ELM algorithm
CN115392120A (en) LSTM-based soil organic matter content high-spectrum modeling method
CN113011600A (en) Method for correcting evaporation waveguide prediction model based on machine learning
Mayne et al. Acquisition, analysis and application of wind loading data
CN111950198B (en) Ground clutter simulation method based on neural network
CN103616346A (en) Method for rapidly detecting quality of ample flow pears
Wang et al. Nonlinear correction of pressure sensor based on depth neural network
Randriamarolaza et al. Extreme temperatures detection and attribution related to external forcing in Madagascar
CN113191073B (en) Optical characteristic parameter inversion method based on BP neural network
Ren et al. An improved Boosting-BiPLS models based on weight adjustment for soil heavy metal content prediction
Kim et al. Real-time measurement and monitoring system for the fruit ripening process with a wireless, low-power and long-distance communication

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