CN111737912A - MWHTS simulated bright temperature calculation method based on deep neural network - Google Patents
MWHTS simulated bright temperature calculation method based on deep neural network Download PDFInfo
- Publication number
- CN111737912A CN111737912A CN202010543078.3A CN202010543078A CN111737912A CN 111737912 A CN111737912 A CN 111737912A CN 202010543078 A CN202010543078 A CN 202010543078A CN 111737912 A CN111737912 A CN 111737912A
- Authority
- CN
- China
- Prior art keywords
- data set
- mwhts
- neural network
- cloud
- deep neural
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 61
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 38
- 238000012795 verification Methods 0.000 claims abstract description 75
- 238000004458 analytical method Methods 0.000 claims abstract description 44
- 230000005540 biological transmission Effects 0.000 claims abstract description 43
- 230000005855 radiation Effects 0.000 claims abstract description 43
- 238000003062 neural network model Methods 0.000 claims abstract description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 25
- 238000004088 simulation Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000003908 quality control method Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012950 reanalysis Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000005085 air analysis Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004001 molecular interaction Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004291 sulphur dioxide Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/045—Combinations of networks
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiation Pyrometers (AREA)
Abstract
A MWHTS simulation bright temperature calculation method based on a deep neural network comprises the steps of establishing a matched data set of MWHTS observation bright temperature and a climatology data set in space and time; dividing the matching data set into a clear-sky data set, a cloud data set and a rain data set according to the cloud water content, and respectively forming a corresponding analysis data set and a corresponding verification data set; training a deep neural network model by using three analysis data sets, inputting the atmospheric parameters in the corresponding verification data set into the trained deep neural network model, and calculating MWHTS simulated brightness temperature; and inputting the atmospheric parameters in the three verification data sets into a radiation transmission model to calculate the MWHTS simulated bright temperature, comparing the calculation precision with that of the MWHTS simulated bright temperature based on the deep neural network, and selecting MWHTS channels with higher precision to form an MWHTS simulated bright temperature calculation result. The method uses the deep neural network to model the interaction of the microwave and the atmospheric molecules, obtains higher calculation precision than the RTTOV of the business radiation transmission model, and is simple and easy to operate.
Description
Technical Field
The invention relates to a calculation method of MWHTS simulated bright temperature, belongs to the technical field of microwave remote sensing, and particularly relates to a calculation method of MWHTS simulated bright temperature based on a deep neural network.
Background
In the field of microwave remote sensing, the problem to be processed can be divided into forward modeling and inversion. For satellite-borne microwave remote sensing, forward modeling is to calculate the observed bright temperature of a satellite-borne microwave radiometer by modeling the radiation transmission process of microwaves in the atmosphere, and inversion is generally a mathematical calculation for inverting a radiation transmission model, that is, a process of acquiring atmospheric parameters by using the observed bright temperature of the satellite-borne microwave radiometer. The radiation transmission model of the microwave in the atmosphere is not only the theoretical basis of satellite effective load development, but also the key point of a satellite-borne microwave remote sensing instrument for detecting earth atmosphere temperature and humidity parameters, cloud and rain parameters and earth surface parameters, and the calculation precision of the radiation transmission model on the simulated bright temperature is directly related to the inversion application of the satellite observation bright temperature.
At present, business radiation transmission models are developed based on physical mechanisms of the effects of microwave emission, absorption, scattering and the like in the atmosphere, wherein a radiation transmission model RTTOV is a typical representative of the business radiation transmission models and is widely applied to satellite data inversion and assimilation systems. The current understandings of microwave and atmospheric molecular interactions are the main cause of radiation transmission model errors. Particularly, under the cloud and rain atmosphere condition, the nonlinearity of the radiation transmission equation is increased, and the modeling difficulty of the radiation transmission model on the cloud and rain scattering effect is higher, so that the calculation accuracy of the simulated brightness and temperature is poorer. However, aiming at the nonlinear relation between the atmospheric parameters and the observed brightness temperature of the satellite-borne microwave radiometer, the strong nonlinear mapping capability of the deep neural network can provide a new idea for the calculation of the simulated brightness temperature of the satellite-borne microwave radiometer.
The microwave wet temperature detector (MWHTS) is an important load on Fengyun No. three (FY-3) C star and D star, is the first international microwave radiometer integrating a hygrometer and a thermometer, and has eight temperature detection channels (channel 2-channel 9), five humidity detection channels (channel 11-channel 15) and two window area channels (channel 1 and channel 10), so that the atmospheric temperature and water vapor parameters can be detected simultaneously. The calculation of the MWHTS simulated brightness temperature is important for the application of the data in the fields of numerical weather forecast, current weather stability analysis, climate change research and the like.
Disclosure of Invention
In order to solve the technical problems, the invention provides an MWHTS bright temperature simulation calculation method based on a deep neural network, wherein the deep neural network is used for modeling the interaction between microwaves and atmospheric molecules, the calculation precision is higher than that of a business radiation transmission model RTTOV, and the operation is simple and easy.
In order to realize the technical purpose, the adopted technical scheme is as follows: an MWHTS simulation bright temperature calculation method based on a deep neural network comprises the following steps:
the method comprises the following steps: establishing a matching data set of the MWHTS observed bright temperature and the atmospheric parameters of the climatology data set in time and space;
step two: dividing the matching data set established in the step one into a clear sky data set, a cloud data set and a rain data set according to the cloud water content, and respectively forming a corresponding clear sky analysis data set and a clear sky verification data set, a cloud analysis data set and a cloud verification data set, a rain analysis data set and a rain verification data set;
step three: respectively training a deep neural network model by using the clear sky analysis data set, the cloud analysis data set and the rain analysis data set formed in the step two, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into the corresponding trained deep neural network model, and calculating MWHTS simulated brightness temperature;
step four: and (3) respectively inputting the atmosphere parameters of the clear sky verification data set, the cloud verification data set and the rain verification data set formed in the second step into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, comparing the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV with the calculation precision of the MWHTS simulated bright temperature based on the deep neural network, and selecting the simulated bright temperature in the MWHTS channel with higher precision to form the calculation result of the MWHTS simulated bright temperature.
The first step specifically comprises the following steps: the first atmospheric parameters in the selected climatological data set were: temperature profile, humidity profile, cloud water profile, surface temperature, surface humidity, surface pressure, 10m wind speed, and cloud water content; matching the atmospheric parameters in the climatology data set with the MWHTS observed brightness temperature in time and space according to a matching rule that the time error is less than 10 minutes and the longitude and latitude error is less than 0.1 degrees; and finally, performing quality control on the matched data, namely deleting the matched data of which the MWHTS observation bright temperature and the climatology data set have abnormal values, wherein the MWHTS bright temperature value is less than 180K or more than 310K, and the negative values in the climatology data set are all judged as the abnormal values, and the matched data after the quality control form the matched data set.
The second step specifically comprises: selecting matching data with a cloud water content value of zero as a clear-sky data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the clear-sky data set to form a clear-sky analysis data set, and forming a clear-sky verification data set by the rest matching data; selecting matching data with cloud water content larger than zero and smaller than 0.5mm as a cloud data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the cloud data set to form a cloud analysis data set, and forming a cloud verification data set by the rest matching data; and in the matching data set formed in the first step, selecting matching data with cloud water content of more than or equal to 0.5mm as a rain data set, randomly selecting 80% of matching data in the rain data set to form a rain analysis data set, and forming a rain verification data set by the rest matching data.
The third step specifically comprises: firstly, taking atmospheric parameters in a clear sky verification data set, a cloudy verification data set and a rainy verification data set as the input of a deep neural network model, observing bright temperature by using MWHTS as the output of the deep neural network model, and training the deep neural network model by respectively utilizing a clear sky analysis data set, a cloudy analysis data set and a rainy analysis data set to respectively obtain a clear sky deep neural network model, a cloudy deep neural network model and a rainy deep neural network model; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into corresponding clear sky deep neural network models, cloud deep neural network models and rain deep neural network models to obtain MWHTS simulated bright temperatures under corresponding clear sky, cloud and rain atmospheric conditions; and finally, respectively calculating the root mean square error between the MWHTS simulated bright temperature and the observed bright temperature under the conditions of clear sky, cloud and rainy atmosphere, and respectively taking the root mean square error as the calculation precision of the MWHTS simulated bright temperature based on the deep neural network under the conditions of clear sky, cloud and rainy atmosphere.
The fourth step specifically comprises: firstly, selecting a radiation transmission model RTTOV based on physical mechanism modeling as a radiation transmission model for calculating MWHTS simulated brightness temperature; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, and respectively obtaining the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the conditions of clear sky, cloud and rain; and finally, respectively comparing the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network under the clear air, cloud and rainy atmosphere conditions with the calculation accuracy of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the corresponding atmosphere conditions, and selecting the simulated bright temperature in the MWHTS channel with higher accuracy to form the final result of the MWHTS simulated bright temperature.
The invention has the beneficial effects that: the invention aims to overcome the difficulty that physical modeling is inaccurate when microwaves are transmitted in the atmosphere, improve the calculation accuracy of MWHTS simulated bright temperature, model the nonlinear relation between atmospheric parameters and MWHTS observed bright temperature by adopting a deep neural network, further compare the calculation accuracy of MWHTS simulated bright temperature of a radiation transmission model RTTOV based on a physical method with the calculation accuracy of MWHTS simulated bright temperature based on the deep neural network, and preferentially select the simulated bright temperature with higher accuracy in an MWHTS channel to form the final result of the MWHTS simulated bright temperature. The method has higher MWHTS simulation bright temperature calculation precision and is simple and easy to operate.
Drawings
FIG. 1 is a flow chart of a MWHTS simulated bright temperature calculation method based on a deep neural network according to the present invention;
FIG. 2 is a graph comparing the accuracy of MWHTS simulated bright temperature based on deep neural network with the accuracy of MWHTS simulated bright temperature based on radiation transmission model RTTOV in a clear air atmosphere in example 1;
FIG. 3 is a graph comparing the accuracy of MWHTS simulated bright temperature based on deep neural network with the accuracy of MWHTS simulated bright temperature based on radiation transmission model RTTOV in the cloud atmosphere condition in example 1;
fig. 4 is a graph comparing the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network under the rainy atmosphere condition in example 1 with the calculation accuracy of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV.
Detailed Description
An MWHTS simulation bright temperature calculation method based on a deep neural network comprises the following steps:
the method comprises the following steps: establishing a matching data set of the MWHTS observed bright temperature and the atmospheric parameters of the climatology data set in time and space;
the first step specifically comprises the following steps: the first atmospheric parameters in the selected climatological data set were: temperature profile, humidity profile, cloud water profile, surface temperature, surface humidity, surface pressure, 10m wind speed, and cloud water content; matching the atmospheric parameters in the climatology data set with the MWHTS observed brightness temperature in time and space according to a matching rule that the time error is less than 10 minutes and the longitude and latitude error is less than 0.1 degrees; and finally, performing quality control on the matched data, namely deleting the matched data of which the MWHTS observation bright temperature and the climatology data set have abnormal values, wherein the MWHTS bright temperature value is less than 180K or more than 310K, and the negative values in the climatology data set are all judged as the abnormal values, and the matched data after the quality control form the matched data set.
Step two: dividing the matching data set established in the first step into a clear-sky data set, a cloud data set and a rain data set according to the cloud water content, wherein the clear-sky data set forms a corresponding clear-sky analysis data set and a clear-sky verification data set, the cloud data set forms a corresponding cloud analysis data set and a cloud verification data set, and the rain data set forms a corresponding rain analysis data set and a rain verification data set;
the second step specifically comprises: selecting matching data with a cloud water content value of zero as a clear-sky data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the clear-sky data set to form a clear-sky analysis data set, and forming a clear-sky verification data set by the rest matching data; selecting matching data with cloud water content larger than zero and smaller than 0.5mm as a cloud data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the cloud data set to form a cloud analysis data set, and forming a cloud verification data set by the rest matching data; and in the matching data set formed in the first step, selecting matching data with cloud water content of more than or equal to 0.5mm as a rain data set, randomly selecting 80% of matching data in the rain data set to form a rain analysis data set, and forming a rain verification data set by the rest matching data.
Step three: respectively training a deep neural network model by using the clear sky analysis data set, the cloud analysis data set and the rain analysis data set formed in the step two, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into the corresponding trained deep neural network model, and calculating MWHTS simulated brightness temperature;
the third step specifically comprises: firstly, taking atmospheric parameters in a clear sky verification data set, a cloudy verification data set and a rainy verification data set as the input of a deep neural network model, observing bright temperature by using MWHTS as the output of the deep neural network model, and training the deep neural network model by respectively utilizing a clear sky analysis data set, a cloudy analysis data set and a rainy analysis data set to respectively obtain a clear sky deep neural network model, a cloudy deep neural network model and a rainy deep neural network model; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into corresponding clear sky deep neural network models, cloud deep neural network models and rain deep neural network models to obtain MWHTS simulated bright temperatures under corresponding clear sky, cloud and rain atmospheric conditions; and finally, respectively calculating the root mean square error between the MWHTS simulated bright temperature and the observed bright temperature under the conditions of clear sky, cloud and rainy atmosphere, and respectively taking the root mean square error as the calculation precision of the MWHTS simulated bright temperature based on the deep neural network under the conditions of clear sky, cloud and rainy atmosphere.
Step four: and (3) respectively inputting the atmosphere parameters of the clear sky verification data set, the cloud verification data set and the rain verification data set formed in the second step into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, comparing the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV with the calculation precision of the MWHTS simulated bright temperature based on the deep neural network, and selecting the simulated bright temperature in the MWHTS channel with higher precision to form the calculation result of the MWHTS simulated bright temperature.
The fourth step specifically comprises: firstly, selecting a radiation transmission model RTTOV based on physical mechanism modeling as a radiation transmission model for calculating MWHTS simulated brightness temperature; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, and respectively obtaining the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the conditions of clear sky, cloud and rain; and finally, respectively comparing the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network under the clear air, cloud and rainy atmosphere conditions with the calculation accuracy of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the corresponding atmosphere conditions, and selecting the simulated bright temperature in the MWHTS channel with higher accuracy to form the final result of the MWHTS simulated bright temperature.
The present invention is further described with reference to the following examples and the accompanying drawings, which are not intended to limit the scope of the invention as claimed.
Example 1
The climatology data set is selected as a reanalysis data set ERA-Interim of a European middle-term weather forecast center (ECMWF), the ECMWF reanalysis data set ERA-Interim is used for calculating a time range from 2018 to 2019 and 8 months, a geographical range is (25 degrees N-45 degrees N, 160 degrees E-220 degrees E), a data resolution is 0.5 degrees multiplied by 0.5 degrees, and simulated brightness temperature is calculated by using a temperature profile, a humidity profile, a cloud water profile, a surface temperature, surface humidity, surface pressure, 10m wind speed and cloud water content in the data set. And establishing a matching data set (1060162 groups) with the FY-3D/MWHTS observed brightness temperature according to a matching rule that the time error is less than 10 minutes and the longitude and latitude error is less than 0.1 degrees. Selecting a clear air data set in the matching data set according to the cloud water content of 0, and respectively establishing a clear air analysis data set (13810 groups) and a clear air verification data set (3453 groups); selecting a cloud data set according to the cloud water content of more than 0 and less than 0.5mm, and respectively establishing a cloud analysis data set (796457 group) and a cloud verification data set (199114 group); rain data sets are selected according to the cloud water content being greater than or equal to 0.5mm, and a rain analysis data set (37862 groups) and a rain verification data set (9466 group) are formed respectively.
And respectively using the atmospheric parameters in the clear sky analysis data set, the cloudy analysis data set and the rainy analysis data set as input, using the corresponding MWHTS observation bright temperature as output, and training the deep neural network to obtain a clear sky deep neural network model, a cloudy deep neural network model and a rainy deep neural network model. And respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into the corresponding clear sky deep neural network model, the cloud deep neural network model and the rain deep neural network model, and respectively obtaining the MWHTS simulated brightness temperature and the MWHTS simulated brightness temperature calculation accuracy under the clear sky, cloud and rain atmospheric conditions.
And respectively inputting the atmospheric parameters in the clear sky verification data set, the cloudy verification data set and the rainy verification data set into a radiation transmission model RTTOV, and calculating the MWHTS simulated bright temperature and the MWHTS simulated bright temperature calculation accuracy under the clear sky, cloudy and rainy atmospheric conditions. The comparison of the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network and the calculation accuracy of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the clear air condition, the cloud air condition and the rain air condition is respectively shown in FIG. 2, FIG. 3 and FIG. 4.
Under the condition of clear air, as can be seen from fig. 2, the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network is better than that of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV in 15 channels of the MWHTS, and particularly, the calculation accuracy is improved remarkably in the channels 1 to 6, 9, 10 and 15 of the MWHTS, and can be improved by 2.4K to the maximum.
Under the condition of cloud atmosphere, as can be seen from fig. 3, the computation accuracy of the MWHTS simulated bright temperature based on the deep neural network is obviously improved compared with that of the RTTOV except that the computation accuracy of the MWHTS channels 11 and 13 is slightly higher than that of the RTTOV of the radiation transmission model.
Under rainy atmospheric conditions, as can be seen from fig. 4, the deep neural network-based calculation method has a significant improvement in the calculation accuracy of the channel 1 and the channel 10 in the window area compared to the RTTOV, while the improvement in the calculation accuracy is significant in the channels 7, 8, 9, and 15, whereas the calculation accuracy in the channels 4 and 5 is not as good as the RTTOV.
In conclusion, under the conditions of clear sky and cloud atmosphere, the calculation result of the MWHTS based on the deep neural network is selected as the simulated bright temperature of the MWHTS; under the condition of rain atmosphere, the MWHTS channels 4 and 5 select the result of calculating the simulated light temperature by using the radiation transmission model RTTOV, and the rest channels use the result of calculating the simulated light temperature by using the MWHTS based on the deep neural network.
Claims (5)
1. An MWHTS simulation bright temperature calculation method based on a deep neural network is characterized by comprising the following steps:
the method comprises the following steps: establishing a matching data set of the MWHTS observed bright temperature and the atmospheric parameters of the climatology data set in time and space;
step two: dividing the matching data set established in the step one into a clear sky data set, a cloud data set and a rain data set according to the cloud water content, and respectively forming a corresponding clear sky analysis data set and a clear sky verification data set, a cloud analysis data set and a cloud verification data set, a rain analysis data set and a rain verification data set;
step three: respectively training a deep neural network model by using the clear sky analysis data set, the cloud analysis data set and the rain analysis data set formed in the step two, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into the corresponding trained deep neural network model, and calculating MWHTS simulated brightness temperature;
step four: and (3) respectively inputting the atmosphere parameters of the clear sky verification data set, the cloud verification data set and the rain verification data set formed in the second step into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, comparing the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV with the calculation precision of the MWHTS simulated bright temperature based on the deep neural network, and selecting the simulated bright temperature in the MWHTS channel with higher precision to form the calculation result of the MWHTS simulated bright temperature.
2. The MWHTS simulation bright temperature calculation method based on the deep neural network as claimed in claim 1, wherein the step one specifically comprises:
the first atmospheric parameters in the selected climatological data set were: temperature profile, humidity profile, cloud water profile, surface temperature, surface humidity, surface pressure, 10m wind speed, and cloud water content; matching the atmospheric parameters in the climatology data set with the MWHTS observed brightness temperature in time and space according to a matching rule that the time error is less than 10 minutes and the longitude and latitude error is less than 0.1 degrees; and finally, performing quality control on the matched data, namely deleting the matched data of which the MWHTS observation bright temperature and the climatology data set have abnormal values, wherein the MWHTS bright temperature value is less than 180K or more than 310K, and the negative values in the climatology data set are all judged as the abnormal values, and the matched data after the quality control form the matched data set.
3. The MWHTS simulation bright temperature calculation method based on the deep neural network as claimed in claim 1, wherein the second step specifically comprises:
selecting matching data with a cloud water content value of zero as a clear-sky data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the clear-sky data set to form a clear-sky analysis data set, and forming a clear-sky verification data set by the rest matching data; selecting matching data with cloud water content larger than zero and smaller than 0.5mm as a cloud data set in the matching data set formed in the first step, randomly selecting 80% of the matching data in the cloud data set to form a cloud analysis data set, and forming a cloud verification data set by the rest matching data; and in the matching data set formed in the first step, selecting matching data with cloud water content of more than or equal to 0.5mm as a rain data set, randomly selecting 80% of matching data in the rain data set to form a rain analysis data set, and forming a rain verification data set by the rest matching data.
4. The MWHTS simulation bright temperature calculation method based on the deep neural network as claimed in claim 1, wherein the third step specifically comprises:
firstly, taking atmospheric parameters in a clear sky verification data set, a cloudy verification data set and a rainy verification data set as the input of a deep neural network model, observing bright temperature by using MWHTS as the output of the deep neural network model, and training the deep neural network model by respectively utilizing a clear sky analysis data set, a cloudy analysis data set and a rainy analysis data set to respectively obtain a clear sky deep neural network model, a cloudy deep neural network model and a rainy deep neural network model; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into corresponding clear sky deep neural network models, cloud deep neural network models and rain deep neural network models to obtain MWHTS simulated bright temperatures under corresponding clear sky, cloud and rain atmospheric conditions; and finally, respectively calculating the root mean square error between the MWHTS simulated bright temperature and the observed bright temperature under the conditions of clear sky, cloud and rainy atmosphere, and respectively taking the root mean square error as the calculation precision of the MWHTS simulated bright temperature based on the deep neural network under the conditions of clear sky, cloud and rainy atmosphere.
5. The MWHTS simulation bright temperature calculation method based on the deep neural network as claimed in claim 1, wherein the fourth step specifically comprises:
firstly, selecting a radiation transmission model RTTOV based on physical mechanism modeling as a radiation transmission model for calculating MWHTS simulated brightness temperature; then, respectively inputting the atmospheric parameters in the clear sky verification data set, the cloud verification data set and the rain verification data set into a radiation transmission model RTTOV to calculate the MWHTS simulated bright temperature, and respectively obtaining the calculation precision of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the conditions of clear sky, cloud and rain; and finally, respectively comparing the calculation accuracy of the MWHTS simulated bright temperature based on the deep neural network under the clear air, cloud and rainy atmosphere conditions with the calculation accuracy of the MWHTS simulated bright temperature based on the radiation transmission model RTTOV under the corresponding atmosphere conditions, and selecting the simulated bright temperature in the MWHTS channel with higher accuracy to form the final result of the MWHTS simulated bright temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543078.3A CN111737912B (en) | 2020-06-15 | 2020-06-15 | MWHTS (metal wrap through) simulated bright temperature calculation method based on deep neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010543078.3A CN111737912B (en) | 2020-06-15 | 2020-06-15 | MWHTS (metal wrap through) simulated bright temperature calculation method based on deep neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111737912A true CN111737912A (en) | 2020-10-02 |
| CN111737912B CN111737912B (en) | 2024-01-23 |
Family
ID=72649196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010543078.3A Active CN111737912B (en) | 2020-06-15 | 2020-06-15 | MWHTS (metal wrap through) simulated bright temperature calculation method based on deep neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111737912B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329334A (en) * | 2020-10-15 | 2021-02-05 | 洛阳师范学院 | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated brightness temperature |
| CN112345151A (en) * | 2020-10-15 | 2021-02-09 | 洛阳师范学院 | Sensitivity test method of MWTS-II to sea surface air pressure based on natural atmosphere |
| CN113311510A (en) * | 2021-05-11 | 2021-08-27 | 洛阳师范学院 | MWHTS bright temperature observation classification method based on simulated bright temperature |
| CN113311509A (en) * | 2021-05-11 | 2021-08-27 | 洛阳师范学院 | Sensitivity test method of MWHTS (metal wrap-through magnetic field resonance) to sea surface air pressure based on neural network |
| CN113435119A (en) * | 2021-06-29 | 2021-09-24 | 北京华云星地通科技有限公司 | Global ocean surface brightness temperature determination method and system |
| CN114252834A (en) * | 2021-12-23 | 2022-03-29 | 国家卫星海洋应用中心 | Satellite-borne microwave radiometer external calibration method and device based on ocean target |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030078901A1 (en) * | 2001-10-22 | 2003-04-24 | Coppola Emery J. | Neural network based predication and optimization for groundwater / surface water system |
| CN108919151A (en) * | 2018-04-03 | 2018-11-30 | 西安空间无线电技术研究所 | A kind of microwave radiometer cross polarization error correcting method |
| CN109580003A (en) * | 2018-12-18 | 2019-04-05 | 成都信息工程大学 | A kind of stationary weather satellite Thermal Infrared Data estimation Air Close To The Earth Surface temperature methods |
| 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 |
-
2020
- 2020-06-15 CN CN202010543078.3A patent/CN111737912B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030078901A1 (en) * | 2001-10-22 | 2003-04-24 | Coppola Emery J. | Neural network based predication and optimization for groundwater / surface water system |
| CN108919151A (en) * | 2018-04-03 | 2018-11-30 | 西安空间无线电技术研究所 | A kind of microwave radiometer cross polarization error correcting method |
| CN109580003A (en) * | 2018-12-18 | 2019-04-05 | 成都信息工程大学 | A kind of stationary weather satellite Thermal Infrared Data estimation Air Close To The Earth Surface temperature methods |
| 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 |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329334A (en) * | 2020-10-15 | 2021-02-05 | 洛阳师范学院 | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated brightness temperature |
| CN112345151A (en) * | 2020-10-15 | 2021-02-09 | 洛阳师范学院 | Sensitivity test method of MWTS-II to sea surface air pressure based on natural atmosphere |
| CN112345151B (en) * | 2020-10-15 | 2022-01-07 | 洛阳师范学院 | Sensitivity test method of MWTS-II to sea surface air pressure based on natural atmosphere |
| CN112329334B (en) * | 2020-10-15 | 2024-01-23 | 洛阳师范学院 | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated bright temperature |
| CN113311510A (en) * | 2021-05-11 | 2021-08-27 | 洛阳师范学院 | MWHTS bright temperature observation classification method based on simulated bright temperature |
| CN113311509A (en) * | 2021-05-11 | 2021-08-27 | 洛阳师范学院 | Sensitivity test method of MWHTS (metal wrap-through magnetic field resonance) to sea surface air pressure based on neural network |
| CN113435119A (en) * | 2021-06-29 | 2021-09-24 | 北京华云星地通科技有限公司 | Global ocean surface brightness temperature determination method and system |
| CN114252834A (en) * | 2021-12-23 | 2022-03-29 | 国家卫星海洋应用中心 | Satellite-borne microwave radiometer external calibration method and device based on ocean target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111737912B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111737912B (en) | MWHTS (metal wrap through) simulated bright temperature calculation method based on deep neural network | |
| CN111737913B (en) | MWHTS clear sky observation bright temperature selection method based on cloud water content inversion | |
| CN108875254B (en) | One-dimensional variation inversion method of atmospheric temperature wet profile | |
| CN111579504B (en) | Atmospheric pollution component vertical distribution inversion method based on optical remote sensing | |
| CN110174359B (en) | Aviation hyperspectral image soil heavy metal concentration assessment method based on Gaussian process regression | |
| CN104820250A (en) | Processing method for detecting clouds on sea by polar orbit meteorological satellite visible and infrared radiometer (VIRR) | |
| CN112329334B (en) | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated bright temperature | |
| CN110595968B (en) | PM2.5 concentration estimation method based on geostationary orbit satellite | |
| CN111737641B (en) | MWHTS channel weight function calculation method based on neural network | |
| CN111665218B (en) | Method for improving inversion accuracy of carbon dioxide differential absorption laser radar | |
| CN113552080B (en) | Real-time inversion algorithm for ultra-spectrum remote sensing earth surface atmosphere relative humidity | |
| CN112364940A (en) | Atmospheric pollutant source analysis method based on multi-source data, storage medium and equipment | |
| CN110968926B (en) | Method for predicting atmospheric parameters based on improved background error covariance matrix | |
| CN112345151B (en) | Sensitivity test method of MWTS-II to sea surface air pressure based on natural atmosphere | |
| CN116258101B (en) | Method for rapidly calculating emission source intensity based on gas concentration monitoring data | |
| CN113532652A (en) | Infrared remote sensing sensor absolute calibration method based on buoy and atmospheric reanalysis data | |
| Czajkowski et al. | Estimating environmental variables using thermal remote sensing | |
| CN113311509B (en) | Sensitivity test method of MWHTS (metal wrap through) to sea surface air pressure based on neural network | |
| CN114757103B (en) | Earth surface O based on space-time light gradient intensifier 3 Concentration estimation method | |
| CN112254866B (en) | Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS | |
| CN113311510B (en) | MWHTS (metal wrap through) observation bright temperature classification method based on simulated bright temperature | |
| CN113822345B (en) | Method and system for inverting cloud water content by fusing MWHTS and MWTS-II | |
| CN116341352B (en) | Static satellite land infrared bright temperature simulation method based on earth surface temperature observation information constraint | |
| CN115795781B (en) | Atmospheric water vapor content estimation method and system based on ground infrared radiometer | |
| CN111460637B (en) | Urban ventilation potential quantitative evaluation method based on numerical 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 |