CN108875905A - A kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles - Google Patents
A kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles Download PDFInfo
- Publication number
- CN108875905A CN108875905A CN201810323166.5A CN201810323166A CN108875905A CN 108875905 A CN108875905 A CN 108875905A CN 201810323166 A CN201810323166 A CN 201810323166A CN 108875905 A CN108875905 A CN 108875905A
- Authority
- CN
- China
- Prior art keywords
- neural network
- sample
- visibility function
- atmospheric physics
- parameter
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Electromagnetism (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of visibility function Direct Inverse Methods of Atmosphere and humidity profiles to obtain the Atmosphere and humidity profiles physical parameter of inverting including the visibility function of actual observation to be input in trained BP neural network；The training of BP neural network includes：Sample atmospheric physics parameter is obtained using Numerical Weather mode, forward modeling is carried out to sample atmospheric physics parameter using synthetic aperture microwave radiometer model, obtains the corresponding visibility function of sample atmospheric physics parameter；Using sample atmospheric physics parameter and the corresponding visibility function training BP neural network of sample atmospheric physics parameter, trained BP neural network is obtained.The present invention changes the bright temperature of visibility-- atmospheric physics parameter two step methods of inversion that current synthetic aperture microwave radiometer remote sensing atmosphere physical parameter needs, propose visibility-atmospheric physics parameter direct inversion method, simplify flow chart of data processing, inversion error is reduced, to obtain more accurate atmospheric physics parameter.
Description
Technical field
The invention belongs to Atmospheric Microwave remote sensing and detection technology fields, more particularly, to a kind of Atmosphere and humidity profiles
Visibility function Direct Inverse Method.
Background technique
The atmospheric parameters such as warm and humid profile, water-vapo(u)r density, pressure are the important parameters of climate monitoring and weather forecast field.It removes
Except this, these atmospheric parameters are to the fields such as weather modification, flood control commanding and decision-making also important role.
In current climate and weather research, because it is with high financial profit, search coverage is covered for space remote sensing observation
Gai Guang, horizontal resolution be high, can continuous observation and the advantages that the intensive observation in the whole world, become the important hand of air-derived information acquisition
Section.Cloud, haze and the sand and dust etc. in atmosphere can be penetrated due to microwave, and are not influenced by solar radiation, therefore satellite-borne microwave
Radiometer has unique advantage in atmospheric remote sensing.Wherein spaceborne synthetic aperture microwave radiometer is a large amount of sparse using one
Small-bore aerial array synthesizes a big observation aperture, greatly reduces the volume and weight of antenna, effectively alleviates big day
String holes diameter and high-resolution contradiction.And synthetic aperture microwave radiometer imaging is without scanning, and theoretically imaging time is just etc.
In the time of integration, can the considerable degree of contradiction for alleviating sensitivity, resolution ratio and imaging time, meet the application of high speed imaging
Demand.
But synthetic aperture microwave radiometer, by interferometry, acquisition is the visibility sampled in spatial frequency domain
Function.And the information such as atmospheric temperature, humidity and cloud water parameter are extracted, need the Earth-atmospheric system detected from satellite-borne microwave radiometer
The bright temperature information of radiation is got.Therefore, synthetic aperture microwave radiometer obtains atmospheric parameters information, usually first with bright temperature point
The Fourier transformation relationship that cloth and visibility function are in is seen by Fourier inversion or other mathematical operations come inverting
Bright temperature is surveyed, then the information such as atmospheric temperature, humidity and cloud water parameter are extracted from bright temperature information by the method for inverting.It can be seen that
Existing synthetic aperture radiometer obtains atmospheric parameters and needs two step refutation processes of the bright temperature of visibility-- atmospheric physics parameter, and two
Secondary inverting requires to solve ill-condition equation, and the approximate solution acquired every time can all amplify error of input data, introduces additional anti-
Drill error.
It can be seen that synthetic aperture microwave radiometer acquisition atmospheric physics parameter is needed by two step invertings in the prior art
Process causes error of input data to be amplified, and introduces additional inversion error.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the present invention provides a kind of visibilitys of Atmosphere and humidity profiles
Function Direct Inverse Method, thus solve in the prior art synthetic aperture microwave radiometer obtain atmospheric physics parameter need by
Two step refutation processes, the technical issues of causing error of input data to be amplified, introduce additional inversion error.
To achieve the above object, the present invention provides a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles,
Including：
The visibility function of actual observation is input in trained BP neural network, the Atmosphere And Humidity for obtaining inverting is wide
Line physical parameter；
The training of the BP neural network includes：
(1) sample atmospheric physics parameter is obtained using Numerical Weather mode, utilizes synthetic aperture microwave radiometer model pair
Sample atmospheric physics parameter carries out forward modeling, obtains the corresponding visibility function of sample atmospheric physics parameter；
(2) sample atmospheric physics parameter and the corresponding visibility function training BP nerve net of sample atmospheric physics parameter are utilized
Network obtains trained BP neural network.
Further, step (1) includes：
(1-1) obtains the sample atmospheric physics parameter in visual field using Numerical Weather mode, utilizes Synthetic Aperture Microwave spoke
It penetrates meter model and forward modeling is carried out to sample atmospheric physics parameter, obtain the forward modeling bright temperature image in visual field；
(1-2) carries out Fourier transformation to the forward modeling bright temperature image in visual field, obtains the sample atmosphere object on spatial frequency domain
Manage the corresponding sample visibility function of parameter.
Further, step (2) includes：
(2-1) using sample atmospheric physics parameter and the corresponding visibility function of sample atmospheric physics parameter as sample set,
The frequency of training of BP neural network is set；
(2-2) using sample set training BP neural network, every training is primary, corrects BP neural network according to backpropagation
Each layer parameter obtains trained BP neural network until reaching frequency of training or continuing training generation negative effect of optimization.
Scaled Conjugate Gradient Method is used when further, using sample set training BP neural network.
Further, the real part imaginary part of the visibility function in sample set is respectively as two variables in one group of input,
To realize with plural number training BP neural network.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, can obtain down and show
Beneficial effect：
(1) the method for the present invention realizes visibility-atmospheric physics parameter direct inversion method, simplifies flow chart of data processing,
Inversion error is reduced, to obtain more accurate atmospheric physics parameter.Thus Synthetic Aperture Microwave radiation in the prior art is solved
Meter obtains atmospheric physics parameter and needs to cause error of input data to be amplified by two step refutation processes, introduces additional inverting and misses
The technical problem of difference.
(2) present invention is it will be seen that degree function trains BP neural network as input data, and visibility function is plural number.It is logical
Often training BP neural network can only receive real number as input data, and the present invention is anti-for visibility function-atmospheric physics parameter
The special applications scene drilled, it will be seen that degree function real part imaginary part is respectively as two variables in one group of input, to realize use
Plural input data training BP neural network.
(3) bright temperature-atmospheric physics parametric inversion BP neural network is often the decline of learning rate changing momentum gradient with training algorithm
Algorithm, RPROP (elastic BP) algorithm, Regularization algorithms.And the present invention using sample set training BP neural network when adopt
With Scaled Conjugate Gradient Method (Scaled Conjugate Gradient, SCG), so that training process algorithm calculation amount of the present invention
Smaller, training speed is fast.
Detailed description of the invention
Fig. 1 is a kind of process of the visibility function Direct Inverse Method of Atmosphere and humidity profiles provided in an embodiment of the present invention
Figure；
Fig. 2 is visibility function-atmospheric temperature direct inversion RMSE figure that the embodiment of the present invention 1 provides；
Fig. 3 is the RMSE figure for the two step inverting of tradition that the embodiment of the present invention 1 provides.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
As shown in Figure 1, a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles, including：
The visibility function of actual observation is input in trained BP neural network, the Atmosphere And Humidity for obtaining inverting is wide
Line physical parameter；
The training of the BP neural network includes：
(1) the sample atmospheric physics parameter in visual field is obtained using Numerical Weather mode, is radiated using Synthetic Aperture Microwave
It counts model and forward modeling is carried out to sample atmospheric physics parameter, obtain the forward modeling bright temperature image in visual field；To the bright temperature of forward modeling in visual field
Image carries out Fourier transformation, obtains the corresponding sample visibility function of sample atmospheric physics parameter on spatial frequency domain.
(2) using sample atmospheric physics parameter and the corresponding visibility function of sample atmospheric physics parameter as sample set, sample
The real part imaginary part of the visibility function of this concentration is respectively as two variables in one group of input, to realize with plural number training BP
Neural network.The frequency of training of BP neural network is set；BP neural network is trained using sample set using Scaled Conjugate Gradient Method,
Every training is primary, and each layer parameter of BP neural network is corrected according to backpropagation, until reaching frequency of training or continuing to train production
Until raw negative effect of optimization, trained BP neural network is obtained.
Embodiment 1
The visibility function Direct Inverse Method of Atmosphere and humidity profiles provided by the invention, for the warm and humid profile of microwave remote sensing
The real-time application rebuild, can effectively simplify flow chart of data processing, reduce its computation complexity and reduce inversion error, be
A kind of novel Atmosphere and humidity profiles inversion method.Embodiment 1 is on November 12nd, 2017, east longitude 150-160 degree, north latitude 15-
For the Atmosphere and humidity profiles in 25 degree of sea areas.
The first step selects the one-dimensional sparse aperture synthesis array of Unit 25 to simulate spaceborne one-dimensional Synthetic Aperture Microwave spoke
Meter is penetrated, which can generate 137 baselines in spatial frequency domain.
Second step, NWP are based on microwave radiation transmission RT mode forward modeling and generate frequency to be totally 8 channels 50.3-57.29GHz
Bright temperature image TB, by the bright temperature image TB in 8 channels be input to synthetic aperture radiometer forward direction observation model simulation meter
Calculate the visibility function V of 8 frequencies of actual observation.Last common property gives birth to 2700 groups of samples totally 2700 × 8 × 137 visibilitys
Function V.The real and imaginary parts of visibility function are taken respectively, and every group of input sample size is 8 × 137 × 2.
Third step is obtained pair with WRF (Weather Research and Forecasting, Numerical Weather mode) mode
The atmosphere temperature profile answered, every 100 pixels are one group of sample, and corresponding different zones spatially, each sample has 40 layers,
Corresponding different height, raw 2700 × 40 × 100 atmospheric temperature values of common property.
4th step, it is 1 that BP neural network hidden layer number to be trained, which is arranged, the number of hidden nodes 25.Supervised training algorithm is adopted
It is Scaled Conjugate Gradient Method (Scaled Conjugate Gradient, SCG), which is based on optimization algorithm feature
It is that calculation amount is smaller, maximum frequency of training is set as 3000 times, and the maximum frequency of failure is 15.The 2700 groups of atmospheric temperature samples obtained
Originally with visibility function sample, wherein 90% is used as training group, 10% is used as test group.
5th step inputs BP neural network with 8 × 137 visibility functions of each visibility function sample, it is desirable to obtain
Corresponding 40 × 100 atmospheric temperature values of corresponding temperature samples.Every training is primary, is joined according to each layer of backpropagation corrective networks
Number, until reaching scheduled frequency of training or continuing training generation negative effect of optimization.
It is square to calculate 300 groups of test sample invertings with the validity of the network of test group sample verifying training for 6th step
Difference takes the atmospheric temperature retrieval mean square deviation of each layer height to be averaged, and obtains atmosphere temperature profile inversion error RMSE, such as Fig. 2
It is shown.
7th step, the atmospheric parameters for choosing same region of same time solve atmospheric temperature with the process of traditional two step invertings
Profile, and the average rear inversion error RMSE of atmosphere temperature profile is found out, as shown in Figure 3.
8th step compares the RMSE that direct inversion of the invention obtains and the RMSE that traditional two step invertings obtain,
As shown in Figures 2 and 3.
As can be seen from the above results：The inversion error obtained using new visibility-atmospheric temperature Direct Inverse Method,
Most of atmosphere all than two step refutation processes of the bright temperature of traditional visibility-- atmospheric physics parameter generate inversion error than
It is small.It is not only effectively simplified data handling procedure, reduces calculation amount, also substantially increases the inversion accuracy of atmosphere temperature profile.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (5)
1. a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles, which is characterized in that including：
The visibility function of actual observation is input in trained BP neural network, the Atmosphere and humidity profiles object of inverting is obtained
Manage parameter；
The training of the BP neural network includes：
(1) sample atmospheric physics parameter is obtained using Numerical Weather mode, using synthetic aperture microwave radiometer model to sample
Atmospheric physics parameter carries out forward modeling, obtains the corresponding visibility function of sample atmospheric physics parameter；
(2) BP neural network is trained using sample atmospheric physics parameter and the corresponding visibility function of sample atmospheric physics parameter,
Obtain trained BP neural network.
2. a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles as described in claim 1, which is characterized in that institute
Stating step (1) includes：
(1-1) obtains the sample atmospheric physics parameter in visual field using Numerical Weather mode, utilizes synthetic aperture microwave radiometer
Model carries out forward modeling to sample atmospheric physics parameter, obtains the forward modeling bright temperature image in visual field；
(1-2) carries out Fourier transformation to the forward modeling bright temperature image in visual field, obtains the sample atmospheric physics on spatial frequency domain and joins
Measure corresponding sample visibility function.
3. a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles as claimed in claim 1 or 2, feature exist
In the step (2) includes：
(2-1) is using sample atmospheric physics parameter and the corresponding visibility function of sample atmospheric physics parameter as sample set, setting
The frequency of training of BP neural network；
(2-2) using sample set training BP neural network, every training is primary, and each layer of BP neural network is corrected according to backpropagation
Parameter obtains trained BP neural network until reaching frequency of training or continuing training generation negative effect of optimization.
4. a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles as claimed in claim 3, which is characterized in that institute
Scaled Conjugate Gradient Method is used when stating using sample set training BP neural network.
5. a kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles as claimed in claim 3, which is characterized in that institute
The real part imaginary part of the visibility function in sample set is stated respectively as two variables in one group of input, to realize with plural number instruction
Practice BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810323166.5A CN108875905B (en) | 2018-04-09 | 2018-04-09 | Direct inversion method for visibility function of atmospheric temperature and humidity profile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810323166.5A CN108875905B (en) | 2018-04-09 | 2018-04-09 | Direct inversion method for visibility function of atmospheric temperature and humidity profile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108875905A true CN108875905A (en) | 2018-11-23 |
| CN108875905B CN108875905B (en) | 2021-04-20 |
Family
ID=64326284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810323166.5A Active CN108875905B (en) | 2018-04-09 | 2018-04-09 | Direct inversion method for visibility function of atmospheric temperature and humidity profile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875905B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109725317A (en) * | 2018-12-18 | 2019-05-07 | 中国人民解放军国防科技大学 | Sea surface bright temperature imaging simulation method based on one-dimensional synthetic aperture microwave radiometer |
| CN109725316A (en) * | 2018-12-18 | 2019-05-07 | 中国人民解放军国防科技大学 | One-dimensional synthetic aperture microwave radiometer-based sea surface temperature physical inversion method |
| CN109829547A (en) * | 2018-12-18 | 2019-05-31 | 中国人民解放军国防科技大学 | Depth learning-based SST (stimulated Raman Scattering) inversion method for one-dimensional synthetic aperture microwave radiometer |
| CN110632599A (en) * | 2019-09-03 | 2019-12-31 | 华中科技大学 | Atmospheric temperature profile direct inversion method and system |
| CN110633650A (en) * | 2019-08-22 | 2019-12-31 | 首都师范大学 | Convolutional neural network face recognition method and device based on privacy protection |
| CN110826693A (en) * | 2019-10-29 | 2020-02-21 | 华中科技大学 | Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network |
| CN111126591A (en) * | 2019-10-11 | 2020-05-08 | 重庆大学 | Magnetotelluric deep neural network inversion method based on space constraint technology |
| CN111651934A (en) * | 2020-05-25 | 2020-09-11 | 华中科技大学 | Ice cloud profile inversion method |
| CN112197865A (en) * | 2020-09-02 | 2021-01-08 | 华中科技大学 | Estimation method and system for observation brightness temperature data error of satellite-borne microwave radiometer |
| CN115270068A (en) * | 2022-09-27 | 2022-11-01 | 山东省科学院海洋仪器仪表研究所 | Method for quickly estimating atmospheric moisture delay of offshore inclined path based on buoy platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504256A (en) * | 2014-12-12 | 2015-04-08 | 中国电子科技集团公司第二十二研究所 | Estimation algorithm for accurately inverting boundary layer temperature profile |
| CN105652284A (en) * | 2016-01-05 | 2016-06-08 | 中国科学院遥感与数字地球研究所 | Determination method and device of long-wave downward radiation |
| US20160257893A1 (en) * | 2013-12-18 | 2016-09-08 | Battelle Memorial Institute | Methods and Systems for Acoustically-Assisted Hydroprocessing at Low Pressure |
-
2018
- 2018-04-09 CN CN201810323166.5A patent/CN108875905B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160257893A1 (en) * | 2013-12-18 | 2016-09-08 | Battelle Memorial Institute | Methods and Systems for Acoustically-Assisted Hydroprocessing at Low Pressure |
| CN104504256A (en) * | 2014-12-12 | 2015-04-08 | 中国电子科技集团公司第二十二研究所 | Estimation algorithm for accurately inverting boundary layer temperature profile |
| CN105652284A (en) * | 2016-01-05 | 2016-06-08 | 中国科学院遥感与数字地球研究所 | Determination method and device of long-wave downward radiation |
Non-Patent Citations (2)
| Title |
|---|
| JON M.JENKINS 等: "《Microwave Remote Sensing of The Temperature and Distribution of Sulfur Compounds in the Lower Atmosphere of Venus》", 《ICARUS》 * |
| 车云飞 等: "《云对地基微波辐射计反演湿度廓线的影响》", 《应用气象学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109725317A (en) * | 2018-12-18 | 2019-05-07 | 中国人民解放军国防科技大学 | Sea surface bright temperature imaging simulation method based on one-dimensional synthetic aperture microwave radiometer |
| CN109725316A (en) * | 2018-12-18 | 2019-05-07 | 中国人民解放军国防科技大学 | One-dimensional synthetic aperture microwave radiometer-based sea surface temperature physical inversion method |
| CN109829547A (en) * | 2018-12-18 | 2019-05-31 | 中国人民解放军国防科技大学 | Depth learning-based SST (stimulated Raman Scattering) inversion method for one-dimensional synthetic aperture microwave radiometer |
| CN109829547B (en) * | 2018-12-18 | 2020-10-09 | 中国人民解放军国防科技大学 | Depth learning-based SST (stimulated Raman Scattering) inversion method for one-dimensional synthetic aperture microwave radiometer |
| CN110633650A (en) * | 2019-08-22 | 2019-12-31 | 首都师范大学 | Convolutional neural network face recognition method and device based on privacy protection |
| CN110632599A (en) * | 2019-09-03 | 2019-12-31 | 华中科技大学 | Atmospheric temperature profile direct inversion method and system |
| CN111126591A (en) * | 2019-10-11 | 2020-05-08 | 重庆大学 | Magnetotelluric deep neural network inversion method based on space constraint technology |
| CN110826693A (en) * | 2019-10-29 | 2020-02-21 | 华中科技大学 | Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network |
| CN110826693B (en) * | 2019-10-29 | 2022-10-14 | 华中科技大学 | Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network |
| CN111651934A (en) * | 2020-05-25 | 2020-09-11 | 华中科技大学 | Ice cloud profile inversion method |
| CN111651934B (en) * | 2020-05-25 | 2024-03-22 | 华中科技大学 | Ice cloud profile inversion method |
| CN112197865A (en) * | 2020-09-02 | 2021-01-08 | 华中科技大学 | Estimation method and system for observation brightness temperature data error of satellite-borne microwave radiometer |
| CN112197865B (en) * | 2020-09-02 | 2021-08-20 | 华中科技大学 | Estimation method and system for observation brightness temperature data error of satellite-borne microwave radiometer |
| CN115270068A (en) * | 2022-09-27 | 2022-11-01 | 山东省科学院海洋仪器仪表研究所 | Method for quickly estimating atmospheric moisture delay of offshore inclined path based on buoy platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108875905B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875905A (en) | A kind of visibility function Direct Inverse Method of Atmosphere and humidity profiles | |
| WO2021073210A1 (en) | Spatial autocorrelated machine learning satellite precipitation data downscaling method and system | |
| Wang et al. | Temperature error correction based on BP neural network in meteorological wireless sensor network | |
| Du et al. | Impact of urban expansion on land surface temperature in Fuzhou, China using Landsat imagery | |
| CN108009989A (en) | A kind of microwave remote sensing image super-resolution rebuilding method based on SRCNN | |
| CN111666656A (en) | Rainfall estimation method and rainfall monitoring system based on microwave rainfall attenuation | |
| CN105184076A (en) | Space-time integrated fusion method for remote sensing earth surface temperature data | |
| CN112016696B (en) | PM integrating satellite observation and ground observation 1 Concentration inversion method and system | |
| CN111210483B (en) | Simulated satellite cloud picture generation method based on generation of countermeasure network and numerical mode product | |
| CN111191673B (en) | Ground surface temperature downscaling method and system | |
| CN109297605A (en) | A kind of Surface Temperature Retrieval method with Thermal Infrared Data infrared based in | |
| CN106779067A (en) | Soil moisture method for reconstructing and system based on multi- source Remote Sensing Data data | |
| CN109871637A (en) | Temperature evaluation method near the ground under the conditions of a kind of skies | |
| Alerskans et al. | Exploring machine learning techniques to retrieve sea surface temperatures from passive microwave measurements | |
| CN115795399A (en) | Self-adaptive fusion method and system for multi-source remote sensing precipitation data | |
| CN114371519B (en) | Foundation microwave radiometer atmospheric temperature and humidity profile inversion method based on unbiased bright temperature | |
| CN114417646A (en) | High-dimensional heterogeneous precipitation data fusion method and system | |
| Su et al. | Detect and identify earth rock embankment leakage based on UAV visible and infrared images | |
| CN106932777A (en) | Interfering synthetic aperture radar based on temperature baselines is to optimum option method | |
| CN108335263A (en) | A kind of microwave remote sensing image super-resolution rebuilding method based on VDSR | |
| CN117710508A (en) | Near-surface temperature inversion method and device for generating countermeasure network based on improved condition | |
| CN109344769A (en) | A kind of photovoltaic plant detection method and system based on remote sensing image | |
| Zhang et al. | Pixel-CRN: A new machine learning approach for convective storm nowcasting | |
| Lee et al. | Estimation of maximum daily fresh snow accumulation using an artificial neural network model | |
| CN117911883A (en) | GEE time sequence analysis-based large-area ecological vulnerability remote sensing dynamic assessment method |
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 |