CN108896456A - Aerosol Extinction inversion method based on feedback-type RBF neural - Google Patents
Aerosol Extinction inversion method based on feedback-type RBF neural Download PDFInfo
- Publication number
- CN108896456A CN108896456A CN201810397787.8A CN201810397787A CN108896456A CN 108896456 A CN108896456 A CN 108896456A CN 201810397787 A CN201810397787 A CN 201810397787A CN 108896456 A CN108896456 A CN 108896456A
- Authority
- CN
- China
- Prior art keywords
- aerosol
- extinction
- rbf neural
- feedback
- detection
- 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.)
- Granted
Links
- 239000000443 aerosol Substances 0.000 title claims abstract description 121
- 230000008033 biological extinction Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000001537 neural effect Effects 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 230000003287 optical effect Effects 0.000 claims description 42
- 238000001514 detection method Methods 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 8
- 239000003292 glue Substances 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000005427 atmospheric aerosol Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
Landscapes
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Dispersion Chemistry (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of Aerosol Extinction inversion methods based on feedback-type RBF neural, including 1) utilize input and desired output Training RBF Neural Network；Using history echo signal power as the input of RBF neural, using the Aerosol Extinction obtained according to history echo-signal as the desired output of RBF neural；2) it is based on feedback-type RBF neural inverting Aerosol Extinction.The present invention is using feedback-type RBF neural come inverting Aerosol Extinction, the inherent mechanism between information is stored in a network by the study of sample mode, it effectively prevents many hypothesis and brings uncertainty, there is faster response speed and preferable robustness.
Description
Technical field
The present invention relates to a kind of Aerosol Extinction inversion methods based on feedback-type RBF neural, and it is molten to belong to gas
Glue field of measuring technique.
Background technique
Atmospheric aerosol be collectively constituted by the object of different phase, suspend in an atmosphere, many kinds of solids or liquid
The heterogeneous system that particle collectively constitutes will affect the occurrence and development variation of many physical and chemical processes in atmospheric environment.Aerosol
The diameter range of particle can stop at least several hours or even several days, to make between 0.001 to 100 μm in an atmosphere
Atmospheric composition ingredient, structure etc. change, and upset and destroy original normal ecosystem.It is mainly distributed on entire atmosphere
In layer, climatic effect will affect, and then influence the health of the mankind.Therefore, improve big compression ring by detecting and studying aerosol
Just there is critically important realistic meaning in border.
Compared to detection means such as satellites, laser radar is because it has many advantages, such as high-spatial and temporal resolution, high measurement accuracy,
As a kind of active remote sensing prospecting tools be widely used in Laser Atmospheric Transmission, global climate detection, aerosol radiative effect with
And the research fields such as atmospheric environment, realize a wide range of real-time monitoring of the parameters such as Aerosol Extinction, grain Spectral structure, shape.
Aerosol detection is being carried out often by radar equation inverting Aerosol Extinction or back scattering using laser radar
Coefficient, and then obtain other characteristics of aerosol.Then in inverting extinction coefficient, since there are multiple changes in radar equation
Amount, for convenience of calculation, many variables often with empirical value or are assumed to replace, such as Aerosol Extinction boundary value, gas are molten
Glue delustring Back-scattering ratio etc., so that there are many uncertain factors for the inverting of extinction coefficient, it is clear that it is molten to be unfavorable for gas
The fine inverting of glue optical characteristics.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of aerosols based on feedback-type RBF neural to disappear
Backscatter extinction logarithmic ratio inversion method.
In order to achieve the above object, the technical scheme adopted by the invention is that：
Aerosol Extinction inversion method based on feedback-type RBF neural, including,
1) input and desired output Training RBF Neural Network are utilized；
It is using history echo signal power as the input of RBF neural, the gas obtained according to history echo-signal is molten
Desired output of the glue extinction coefficient as RBF neural；
Aerosol Extinction obtain process be：Principle based on aerosol optical depth constructs nonlinear equation, benefit
Aerosol extinction Back-scattering ratio is calculated with Chord iterative method, according to aerosol extinction Back-scattering ratio and echo-signal, is used
The extinction coefficient of Fernald method inverting aerosol；
2) it is based on feedback-type RBF neural inverting Aerosol Extinction.
Utilize the calculation formula and radar surveying aerosol optical depth of heliograph measurement aerosol optical depth
Calculation formula constructs nonlinear equation, calculates aerosol extinction Back-scattering ratio using Chord iterative method.
Heliograph measurement aerosol optical depth calculation formula be,
Wherein, SAODFor the aerosol optical depth of heliograph detection, SALLFlood for heliograph detection is big
Gas optical thickness, SMODFor the optical thickness of atmospheric molecule in effective scope of detection, raIt is effective detection range, σmIt (r) is atmosphere
The extinction coefficient of molecule.
The calculation formula of radar surveying aerosol optical depth is,
Wherein, LR is the aerosol optical depth of radar detection, σa(r) be aerosol extinction coefficient, be one about
Aerosol extinction Back-scattering ratio SaWith the function of detection range r.
The nonlinear equation of building is,
Wherein, LR is the aerosol optical depth of radar detection, σa(r) be aerosol extinction coefficient, be one about
Aerosol extinction Back-scattering ratio SaWith the function of detection range r, SAODFor heliograph detection aerosol optical depth,
SALLFor the whole atmosphere optical thickness of heliograph detection, SMODFor the optical thickness of atmospheric molecule in effective scope of detection,
raIt is effective detection range, σmIt (r) is the extinction coefficient of atmospheric molecule.
Using input and desired output Training RBF Neural Network, current echo-signal is inputted into trained RBF nerve net
Network obtains current Aerosol Extinction, calculates aerosol optical depth AOD according to current Aerosol Extinctionlidar, by its
With the current aerosol optical depth AOD of heliograph measurementsunIt is compared, if it exists error, corrects current aerosol and disappear
Backscatter extinction logarithmic ratio, using revised Aerosol Extinction with corresponding echo-signal as new sample, to feedback-type RBF nerve net
Network carries out second training.
Amendment Aerosol Extinction formula be,
AECcorrected=Networkoutput×(1+ω)
Wherein, AECcorrectedFor revised Aerosol Extinction, NetworkoutputDisappear for the aerosol before amendment
Backscatter extinction logarithmic ratio, ω are error.
The beneficial effects obtained by the present invention are as follows：1, the present invention utilizes feedback-type RBF neural inverting aerosol extinction system
Number is stored the inherent mechanism between information in a network by the study of sample mode, is effectively prevented many hypothesis and is brought
Uncertainty, simultaneously because joined the dynamical feedback adjustment process for approaching apparatus measures, so that the confidence level of inversion result is big
It is big to increase, realize quick, the accurate inverting of Aerosol Extinction；2, the present invention combines echo-signal and heliograph to visit
Measured data is constructed the equation about delustring Back-scattering ratio, is solved using Secant Method, pass through the delustring Back-scattering ratio meter
Aerosol Extinction is calculated, delustring Back-scattering ratio bring error is avoided to a certain extent, improves aerosol detection
Precision.
Detailed description of the invention
Fig. 1 is the structure principle chart based on feedback-type RBF neural inverting Aerosol Extinction；
Fig. 2 is the determination method flow diagram of aerosol extinction Back-scattering ratio；
Fig. 3 is the acquisition flow chart of training sample；
Fig. 4 is feedback-type RBF neural inversion result figure；
Fig. 5 is cloudy feedback-type RBF neural inversion result figure；
Fig. 6 is fine day feedback-type RBF neural inversion result figure.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, a kind of Aerosol Extinction inversion method based on feedback-type RBF neural, including it is following
Step：
Step 1, training sample is obtained.
Training sample includes that input and desired output will using history echo signal power as the input of RBF neural
Desired output of the Aerosol Extinction obtained according to history echo-signal as RBF neural.
In order to guarantee that network finally obtains extinction coefficient precision, desired output should be accurate as far as possible, therefore, is using
When Fernald method obtains desired output, it is thus necessary to determine that high-precision aerosol extinction Back-scattering ratio, to obtain high-precision
Aerosol Extinction.
In order to obtain high-precision aerosol extinction Back-scattering ratio, nonlinear equation can be constructed, Chord iterative method is utilized
Calculate aerosol extinction Back-scattering ratio, detailed process：Utilize the calculation formula of heliograph measurement aerosol optical depth
With the calculation formula of radar (being here laser radar) measurement aerosol optical depth, nonlinear equation is constructed, Secant Method is utilized
Iterate to calculate aerosol extinction Back-scattering ratio.
Heliograph measurement aerosol optical depth calculation formula be：
Wherein, SAODFor the aerosol optical depth of heliograph detection, SALLFlood for heliograph detection is big
Gas optical thickness, SMODFor the optical thickness of atmospheric molecule in effective scope of detection, raIt is effective detection range, σmIt (r) is atmosphere
The extinction coefficient of molecule is the function of a detection range r, can be obtained according to United States standard atmosphere molecular extinction mode.
The calculation formula of radar surveying aerosol optical depth is,
Wherein, LR is the aerosol optical depth of radar detection, σa(r) be aerosol extinction coefficient, be one about
Aerosol extinction Back-scattering ratio SaWith the function of detection range r.
The method of above two measurement aerosol optical depth is mutually indepedent, therefore constitutes and combine using both methods
Inverting constructs the nonlinear equation about delustring Back-scattering ratio：
Aerosol extinction Back-scattering ratio is calculated as shown in Fig. 2, selecting two o'clock in value interval using Chord iterative method
As iterative initial value, then according to the iterative formula of Secant Method, sequence of iterations is generated, is judged by iteration stopping condition, most
Aerosol extinction Back-scattering ratio is obtained eventually.
In conclusion obtaining the process of training sample as shown in Figure 3：Principle building based on aerosol optical depth is non-thread
Property equation, using Chord iterative method calculate aerosol extinction Back-scattering ratio, according to aerosol extinction Back-scattering ratio and echo
Signal, using the extinction coefficient of Fernald method inverting aerosol.
Step 2, input and desired output Training RBF Neural Network are utilized.
Define X=(x1,x2,…,xn)TFor net input vector, Y=(y1,y2,…,ys)TFor network output, φi(*) is
The radial basis function of i-th of hidden layer node.The distribution function of RBF neural is：
Wherein, m is hidden layer neuron number of nodes, i.e. radial basis function Center Number, coefficient wiFor connection weight.
Wherein, φ (*) is radial basis function, | | x-ci| | it is euclideam norm, ciFor i-th of center of RBF, ξiFor
I-th of radius of RBF, can obtain network output is：
Therefore, the matrix expression of RBF network can be expressed as：
D=HW+E
Wherein, desired output vector is D=(d1,d2,…,dp)T, desired output and network output between error vector
For E=(e1,e2,…,ep)T, weight vectors W=(w1,w2,…,wm)T, regression matrix H=(h1,h2,…,hm)T。
In view of the influence of all training samples, ci、ξiAnd wiAdjustment amount be：
In formula, φi(xj) it is i-th of implicit node to xjInput, η1, η2, η3Respectively corresponding learning rate, ci
(t) and ciIt (t+1) is respectively the t times and c when t+1 iterationi, ξi(t) and ξiIt (t+1) is respectively the t times and t+1 iteration
When ξi, wi(t) and wiIt (t+1) is respectively the t times and w when t+1 iterationi.Mean square error is obtained according to cost function E,
Terminate trained condition with this.When reality output and the mean square error of desired output are less than the threshold value of setting, then network is considered
Training is completed.
Step 3, current echo-signal is inputted into trained RBF neural, obtains current Aerosol Extinction.
Step 4, aerosol optical depth AOD is calculated according to current Aerosol Extinctionlidar, by itself and heliograph
The current aerosol optical depth AOD of measurementsunIt is compared, if it exists error, is then exported according to correction formula corrective networks
(i.e. current Aerosol Extinction), correction formula is as follows：
AECcorrected=Networkoutput×(1+ω)
Wherein, AECcorrectedFor revised Aerosol Extinction, NetworkoutputDisappear for the aerosol before amendment
Backscatter extinction logarithmic ratio, ω are error；
Using revised Aerosol Extinction and corresponding echo-signal as new sample, to Feedback Neural Network into
Row second training, so that the output Step wise approximation apparatus measures result of Feedback Neural Network.
Fig. 4 is feedback-type RBF neural inversion result figure, is detected using test sample to network performance, is tested
Sample equally includes input and desired output, and output and desired output after as can be seen from the figure correcting have higher one
Cause property.In order to make the inverting of network-adaptive different weather, the inverting for having carried out cloudy day and fine day is tested, as it can be seen in figures 5 and 6, two
Higher consistency is all remain between kind weather condition, with desired output, it was confirmed that the feasibility of this method.
The above method, come inverting Aerosol Extinction, passes through the study of sample mode using feedback-type RBF neural
In a network by the inherent mechanism storage between information, many hypothesis are effectively prevented and brings uncertainty, simultaneously because being added
The dynamical feedback adjustment process for approaching apparatus measures so that the confidence level of inversion result greatly increases realizes aerosol and disappears
Quick, the accurate inverting of backscatter extinction logarithmic ratio；The above method combination echo-signal and heliograph detection data simultaneously are constructed about disappearing
The equation of light Back-scattering ratio, is solved using Secant Method, calculates Aerosol Extinction by the delustring Back-scattering ratio,
Delustring Back-scattering ratio bring error is avoided to a certain extent, improves the precision of aerosol detection.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (7)
1. the Aerosol Extinction inversion method based on feedback-type RBF neural, it is characterised in that：Including,
1) input and desired output Training RBF Neural Network are utilized；
Using history echo signal power as the input of RBF neural, the aerosol obtained according to history echo-signal is disappeared
Desired output of the backscatter extinction logarithmic ratio as RBF neural；
Aerosol Extinction obtain process be：Principle based on aerosol optical depth constructs nonlinear equation, utilizes string
The method of cutting iterates to calculate aerosol extinction Back-scattering ratio, according to aerosol extinction Back-scattering ratio and echo-signal, uses
The extinction coefficient of Fernald method inverting aerosol；
2) it is based on feedback-type RBF neural inverting Aerosol Extinction.
2. the Aerosol Extinction inversion method according to claim 1 based on feedback-type RBF neural, feature
It is：Utilize the calculation formula of heliograph measurement aerosol optical depth and the calculating of radar surveying aerosol optical depth
Formula constructs nonlinear equation, calculates aerosol extinction Back-scattering ratio using Chord iterative method.
3. the Aerosol Extinction inversion method according to claim 2 based on feedback-type RBF neural, feature
It is：Heliograph measurement aerosol optical depth calculation formula be,
Wherein, SAODFor the aerosol optical depth of heliograph detection, SALLFor the whole atmosphere light of heliograph detection
Learn thickness, SMODFor the optical thickness of atmospheric molecule in effective scope of detection, raIt is effective detection range, σmIt (r) is atmospheric molecule
Extinction coefficient.
4. the Aerosol Extinction inversion method according to claim 2 based on feedback-type RBF neural, feature
It is：The calculation formula of radar surveying aerosol optical depth is,
Wherein, LR is the aerosol optical depth of radar detection, σa(r) it is the extinction coefficient of aerosol, is one about aerosol
Delustring Back-scattering ratio SaWith the function of detection range r.
5. the Aerosol Extinction inversion method according to claim 2 based on feedback-type RBF neural, feature
It is：The nonlinear equation of building is,
Wherein, LR is the aerosol optical depth of radar detection, σa(r) it is the extinction coefficient of aerosol, is one about aerosol
Delustring Back-scattering ratio SaWith the function of detection range r, SAODFor the aerosol optical depth of heliograph detection, SALLFor too
The whole atmosphere optical thickness of positive photometer detection, SMODFor the optical thickness of atmospheric molecule in effective scope of detection, raIt is effective
Detection range, σmIt (r) is the extinction coefficient of atmospheric molecule.
6. the Aerosol Extinction inversion method according to claim 1 based on feedback-type RBF neural, feature
It is：Using input and desired output Training RBF Neural Network, current echo-signal is inputted into trained RBF neural,
Current Aerosol Extinction is obtained, aerosol optical depth AOD is calculated according to current Aerosol Extinctionlidar, by its with
The current aerosol optical depth AOD of heliograph measurementsunIt is compared, if it exists error, corrects current aerosol extinction
Coefficient, using revised Aerosol Extinction with corresponding echo-signal as new sample, to feedback-type RBF neural
Carry out second training.
7. the Aerosol Extinction inversion method according to claim 6 based on feedback-type RBF neural, feature
It is：Amendment Aerosol Extinction formula be,
AECcorrected=Networkoutput×(1+ω)
Wherein, AECcorrectedFor revised Aerosol Extinction, NetworkoutputFor the aerosol extinction system before amendment
Number, ω is error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810397787.8A CN108896456B (en) | 2018-04-28 | 2018-04-28 | Aerosol extinction coefficient inversion method based on feedback type RBF neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810397787.8A CN108896456B (en) | 2018-04-28 | 2018-04-28 | Aerosol extinction coefficient inversion method based on feedback type RBF neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108896456A true CN108896456A (en) | 2018-11-27 |
| CN108896456B CN108896456B (en) | 2020-07-31 |
Family
ID=64342521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810397787.8A Active CN108896456B (en) | 2018-04-28 | 2018-04-28 | Aerosol extinction coefficient inversion method based on feedback type RBF neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108896456B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109149A (en) * | 2019-05-08 | 2019-08-09 | 南京信息工程大学 | A kind of laser radar low layer extinction coefficient profile bearing calibration |
| CN110108672A (en) * | 2019-04-12 | 2019-08-09 | 南京信息工程大学 | A kind of Aerosol Extinction inversion method based on deepness belief network |
| CN113009437A (en) * | 2021-03-03 | 2021-06-22 | 云南大学 | Method for solving dynamic radar ratio of laser radar according to real-time aerosol distribution |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102944503A (en) * | 2012-10-11 | 2013-02-27 | 中国科学院安徽光学精密机械研究所 | PM2.5 mass concentration value automatic inversion algorithm based on sun photometer and lidar |
| CN103175759A (en) * | 2013-02-25 | 2013-06-26 | 中国科学院安徽光学精密机械研究所 | Method for acquiring complex refractive index of urban aerosol on basis of various ground-based remote sensing technologies |
| CN103278479A (en) * | 2013-04-23 | 2013-09-04 | 中国科学院安徽光学精密机械研究所 | Atmospheric radiation transmission correction system and correction method |
| CN107144829A (en) * | 2017-06-29 | 2017-09-08 | 南京信息工程大学 | A kind of efficient laser radar echo signal antinoise method |
| CN107421917A (en) * | 2017-05-17 | 2017-12-01 | 南京信息工程大学 | A kind of multifunction high-precision atmosphere visibility meter and visibility measurement method |
| CN107728163A (en) * | 2017-09-05 | 2018-02-23 | 兰州大学 | Atmospheric Characteristics layer detection method and device |
| CN108845306A (en) * | 2018-07-05 | 2018-11-20 | 南京信息工程大学 | Laser radar echo signal antinoise method based on variation mode decomposition |
| CN109696412A (en) * | 2018-12-20 | 2019-04-30 | 南京信息工程大学 | Infrared gas sensor and atmospheric pressure compensating method based on AGNES Optimized BP Neural Network |
-
2018
- 2018-04-28 CN CN201810397787.8A patent/CN108896456B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102944503A (en) * | 2012-10-11 | 2013-02-27 | 中国科学院安徽光学精密机械研究所 | PM2.5 mass concentration value automatic inversion algorithm based on sun photometer and lidar |
| CN103175759A (en) * | 2013-02-25 | 2013-06-26 | 中国科学院安徽光学精密机械研究所 | Method for acquiring complex refractive index of urban aerosol on basis of various ground-based remote sensing technologies |
| CN103278479A (en) * | 2013-04-23 | 2013-09-04 | 中国科学院安徽光学精密机械研究所 | Atmospheric radiation transmission correction system and correction method |
| CN107421917A (en) * | 2017-05-17 | 2017-12-01 | 南京信息工程大学 | A kind of multifunction high-precision atmosphere visibility meter and visibility measurement method |
| CN107144829A (en) * | 2017-06-29 | 2017-09-08 | 南京信息工程大学 | A kind of efficient laser radar echo signal antinoise method |
| CN107728163A (en) * | 2017-09-05 | 2018-02-23 | 兰州大学 | Atmospheric Characteristics layer detection method and device |
| CN108845306A (en) * | 2018-07-05 | 2018-11-20 | 南京信息工程大学 | Laser radar echo signal antinoise method based on variation mode decomposition |
| CN109696412A (en) * | 2018-12-20 | 2019-04-30 | 南京信息工程大学 | Infrared gas sensor and atmospheric pressure compensating method based on AGNES Optimized BP Neural Network |
Non-Patent Citations (1)
| Title |
|---|
| 韩道文等: "基于Madaline网络的气溶胶消光系数反演算法", 《光学学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110108672A (en) * | 2019-04-12 | 2019-08-09 | 南京信息工程大学 | A kind of Aerosol Extinction inversion method based on deepness belief network |
| CN110108672B (en) * | 2019-04-12 | 2021-07-06 | 南京信息工程大学 | Aerosol extinction coefficient inversion method based on deep belief network |
| CN110109149A (en) * | 2019-05-08 | 2019-08-09 | 南京信息工程大学 | A kind of laser radar low layer extinction coefficient profile bearing calibration |
| CN110109149B (en) * | 2019-05-08 | 2022-11-25 | 南京信息工程大学 | Laser radar low-layer extinction coefficient profile correction method |
| CN113009437A (en) * | 2021-03-03 | 2021-06-22 | 云南大学 | Method for solving dynamic radar ratio of laser radar according to real-time aerosol distribution |
| CN113009437B (en) * | 2021-03-03 | 2023-10-03 | 云南大学 | Method for solving dynamic radar ratio of laser radar according to real-time aerosol distribution |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108896456B (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Performance of optimally merged multisatellite precipitation products using the dynamic Bayesian model averaging scheme over the Tibetan Plateau | |
| Abbaszadeh et al. | The quest for model uncertainty quantification: A hybrid ensemble and variational data assimilation framework | |
| Stoffelen | A simple method for calibration of a scatterometer over the ocean | |
| CN108896456A (en) | Aerosol Extinction inversion method based on feedback-type RBF neural | |
| Deshler et al. | Retrieval of aerosol size distributions from in situ particle counter measurements: Instrument counting efficiency and comparisons with satellite measurements | |
| Wang et al. | Geostationary satellite retrievals of aerosol optical thickness during ACE‐Asia | |
| CN112232554A (en) | Construction method of local short-term rainfall forecast model based on BP neural network | |
| CN113344149B (en) | PM2.5 hourly prediction method based on neural network | |
| Zhang et al. | An observational analysis of ocean surface waves in tropical cyclones in the western North Pacific Ocean | |
| Zheng et al. | Improved forecast skill through the assimilation of dropsonde observations from the Atmospheric River Reconnaissance program | |
| Bust et al. | Scientific investigations using IDA4D and EMPIRE | |
| CN112180369B (en) | Depth learning-based sea surface wind speed inversion method for one-dimensional synthetic aperture radiometer | |
| CN113468799A (en) | Method and system for acquiring near-ground PM2.5 concentration in static meteorological satellite observation | |
| Trinquet et al. | A statistical model to forecast the profile of the index structure constant | |
| CN110108672B (en) | Aerosol extinction coefficient inversion method based on deep belief network | |
| CN115270608A (en) | Coastal zone ground settlement prediction method based on ARIMA and LSTM | |
| Hoffman et al. | Error estimates for ocean surface winds: Applying Desroziers diagnostics to the cross-calibrated, multiplatform analysis of wind speed | |
| CN112329334B (en) | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated bright temperature | |
| Guermoui et al. | Daily global solar radiation modelling using multi-layer perceptron neural networks in semi-arid region | |
| Konakoğlu et al. | A Study on 2D similarity transformation using multilayer perceptron neural networks and a performance comparison with conventional and robust outlier detection methods. | |
| Ettalbi et al. | Soil Moisture Retrieval in Bare Agricultural Areas Using Sentinel-1 Images | |
| Abdollahipour et al. | Evaluating the hydrological utility of satellite-based rainfall products using neural network models over the Ghare Ghieh River basin, Iran | |
| Rajanayaka et al. | Upscaling point-scale soil hydraulic properties for application in a catchment model using Bayesian calibration: An application in two agricultural regions of New Zealand | |
| Shi et al. | A Grey Model for Short-Term Prediction of the Ionospheric TEC | |
| Herring et al. | The algorithm theoretical basis document for the atmospheric delay correction to GLAS laser altimeter ranges |
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 |