CN112254866B - Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS - Google Patents
Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS Download PDFInfo
- Publication number
- CN112254866B CN112254866B CN202011104191.8A CN202011104191A CN112254866B CN 112254866 B CN112254866 B CN 112254866B CN 202011104191 A CN202011104191 A CN 202011104191A CN 112254866 B CN112254866 B CN 112254866B
- Authority
- CN
- China
- Prior art keywords
- air pressure
- sea surface
- surface air
- mwhts
- mwts
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L11/00—Measuring steady or quasi-steady pressure of a fluid or a fluent solid material by means not provided for in group G01L7/00 or G01L9/00
- G01L11/002—Measuring steady or quasi-steady pressure of a fluid or a fluent solid material by means not provided for in group G01L7/00 or G01L9/00 by thermal means, e.g. hypsometer
-
- 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
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Radiation Pyrometers (AREA)
Abstract
A method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS comprises establishing a brightness temperature matching pair of MWTS-II observation brightness temperature and MWHTS observation brightness temperature in time and space; establishing a matching data set of the brightness temperature matching pair and the sea surface air pressure in time and space, and forming an analysis data set and a verification data set; training a BP neural network by utilizing the analysis data set, and sequencing the contribution of the observed brightness temperature of each channel to the inversion sea surface air pressure according to the training result; according to the sequence that the contribution of the observed bright temperature of each channel to the inverted sea surface air pressure is from large to small, the observed bright temperatures of the channels are increased one by one, a BP neural network is trained, and the optimal channel combination of MWTS-II and MWHTS fusion inverted sea surface air pressure is established according to the training result. The method can obtain higher inversion accuracy than that of a single satellite-borne microwave radiometer for inverting the sea surface air pressure, and is simple and easy to operate.
Description
Technical Field
The invention relates to a method for remotely sensing sea surface air pressure by satellite-borne microwaves, belongs to the technical field of microwave remote sensing, and particularly relates to a method for inverting the sea surface air pressure by fusion of MWTS-II and MWHTS.
Background
Sea surface air pressure is a basic parameter for describing atmospheric conditions, and plays an important role in applications such as numerical weather forecasting, tropical cyclone analysis and forecasting, and climate change research. The acquisition of high-precision sea surface air pressure value is always one of the more concerned hot spots in the fields of atmospheric science and marine science. At present, the sea surface air pressure data is mainly obtained by direct observation means such as buoys, commercial ships, airborne platform dropsondes and the like. The direct observation data has the defects of low spatial resolution, high detection cost, non-uniform detection precision and the like, so that the direct observation data cannot meet the requirements of meteorological and climatological research and application.
Satellite-borne microwave remote sensing is an important means for realizing global dense detection of sea surface air pressure. The microwave radiometer is used as an important load of satellite-borne remote sensing atmosphere, and the purpose of detecting sea surface air pressure can be realized by measuring the total absorption of the vertical column of oxygen. In the microwave band, the oxygen absorption lines have a distinct frequency division characteristic, with one resonance absorption line at 118GHz and the remaining 45 lines forming a resonance absorption band centered at 60 GHz. At present, a microwave moisture temperature detector (MWHTS) arranged at a 118GHz frequency band, a microwave thermometer II type (MWTS-II) arranged at a 60GHz frequency band, an advanced microwave detection unit (AMSU), an advanced technology microwave detector (ATMS) and other satellite-borne microwave radiometers can realize the detection of sea surface air pressure.
When the atmosphere is remotely sensed, a plurality of sensing platforms or a plurality of sensing frequency bands are used, and atmospheric parameter information richer than that of a single sensing means is obtained. For the detection of sea surface air pressure by the satellite-borne microwave radiometer, the sea surface air pressure inversion fusing 60GHz and 118GHz detection data is not realized at present due to the limitation of a satellite-borne platform. And all 13 channels of the MWTS-II carried on Fengyun three-number C star and D star are arranged in a 60GHz resonance absorption band, the MWHTS carried on the same satellite platform has 8 channels arranged on 118GHz oxygen absorption lines, 2 channels arranged on a window area frequency band and 5 channels arranged on 183 GHz water vapor absorption lines. The on-orbit operation of MWTS-II and MWHTS provides the possibility of sea surface barometric inversion fusing 60GHz and 118GHz detection data. In addition, the correlation between the water vapor absorption and the oxygen absorption also provides a new idea for further improving the inversion accuracy of the sea surface air pressure.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS.
In order to realize the technical purpose, the adopted technical scheme is as follows: a method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS comprises the following steps:
the method comprises the following steps: establishing a brightness temperature matching pair of MWTS-II observation brightness temperature and MWHTS observation brightness temperature in time and space;
step two: establishing a matching data set of a bright temperature matching pair and sea surface air pressure in time and space, and dividing the matching data set into an analysis data set and a verification data set;
step three: respectively taking the observed brightness of 13 channels of the MWTS-II in the analysis data set and the observed brightness of 15 channels of the MWHTS as input, taking the sea surface air pressure of the corresponding analysis data set as output, forming 28 training data sets and respectively training a BP neural network, counting the mean square error of each training data set after the BP neural network is trained, and sequencing the contributions of the observed brightness of the 28 channels to the inversion sea surface air pressure from large to small according to the size of the mean square error;
step four: based on the observed bright temperature of the channel which has the largest contribution to the inverted sea surface air pressure, according to the sequence that the observed bright temperatures of 28 channels have the largest contribution to the inverted sea surface air pressure from large to small, the observed bright temperatures of the channels are increased one by one, after the observed bright temperatures of the channels are increased, the observed bright temperature of the formed channel combination is used as the input of a BP neural network, the corresponding sea surface air pressure is used as the output, the BP neural network is trained until the mean square error of the trained BP neural network is not reduced any more, the increase of the observed bright temperatures of the channels is stopped, and the optimal channel combination of the MWTS-II and MWHTS fusion inverted sea surface air pressure is established;
step five: and F, inverting the observed brightness temperature of the optimal channel combination obtained in the step four to obtain the sea surface air pressure.
Matching the MWTS-II and the MWHTS observed brightness temperature according to a matching rule that the time error is less than 0.2 s and the longitude and latitude error is less than 0.01 degrees; and performing quality control on the observed bright temperature obtained by matching according to a screening rule with the value of more than 180K and less than 310K to form a MWTS-II and MWHTS bright temperature matching pair.
And (3) matching the sea surface air pressure with the bright temperature matching pair established in the first step, wherein the matching rule is that the time error is less than 0.5 h and the longitude and latitude error is less than 0.1 DEG, and establishing a matching data set of the bright temperature matching pair of MWTS-II and MWHTS and the sea surface air pressure.
Randomly selecting 80% of the matched data in the matched data set to form an analysis data set, and remaining 20% of the matched data to form a verification data set.
The fourth step of the invention specifically comprises:
on the basis of the observed bright temperatures of the channels which have the largest contribution to the inversion sea surface air pressure, the observed bright temperatures of the channels are increased one by one according to the sequence that the observed bright temperatures of the 28 channels established in the step three have the smallest contribution to the inversion sea surface air pressure, so as to form the observed bright temperatures of the channel combination; training a BP neural network by taking the observed brightness temperature of the channel combination as input and the corresponding sea surface air pressure as output; and stopping increasing the observed bright temperature of the channel when the mean square error of the BP neural network corresponding to the observed bright temperature of the channel combination is not reduced any more with the increase of the observed bright temperature of the channel, wherein the channel combination at the moment is the optimal channel combination of the MWTS-II and the MWHTS fusion inversion sea surface air pressure.
The invention has the beneficial effects that: the method aims at improving the accuracy of the satellite-borne microwave remote sensing data for inverting the sea surface air pressure, uses a BP neural network to count the contribution of the observed bright temperature of each channel of MWTS-II and MWHTS to the inverted sea surface air pressure, and establishes the optimal channel combination of the MWTS-II and MWHTS fusion inverted sea surface air pressure according to the magnitude sequence of the contribution of the observed bright temperature of each channel to the inverted sea surface air pressure. The method realizes the purpose of inverting the sea surface air pressure by fusing the detection data of 60GHz and 118GHz, acquires richer sea surface air pressure information by detecting the sea surface air pressure by using different frequency bands, and has higher precision and simple and easy operation compared with the inversion result of the detection data of a single frequency band.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a graph showing the comparison of the accuracy of sea surface barometric pressure inversion between the bright temperature observed for all channels of MWHTS, the bright temperature observed for all channels of MWTS-II, and the bright temperature observed for the optimal channel combination in example 1.
Detailed Description
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.
A method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS comprises the following steps:
the method comprises the following steps: and establishing a brightness temperature matching pair of MWTS-II observation brightness temperature and MWHTS observation brightness temperature in time and space.
Step two: and establishing a matching data set of the bright temperature matching pair and the sea surface air pressure in time and space, and forming an analysis data set and a verification data set.
Step three: firstly, respectively taking the observed brightness temperature of 13 MWTS-II channels and 15 MWHTS channels in an analysis data set as input, and taking the corresponding sea surface air pressure in the analysis data set as output to form 28 training data sets; then, respectively training the BP neural networks by using 28 training data sets, wherein the 28 BP neural networks all use three-layer BP neural network structures, namely an input layer, an output layer and a hidden layer, and the mean square error representing the training performance of the BP neural networks is minimized by adjusting the number of neurons in the hidden layers in the BP neural networks; finally, the mean square deviations of 28 BP neural networks corresponding to 28 training data sets are counted, the smaller the mean square deviation value is, the larger the contribution of the observed bright temperature of the channel corresponding to the mean square deviation to the inversion sea surface air pressure is, and the contributions of the observed bright temperatures of the 28 channels to the inversion sea surface air pressure are sorted according to the order from large to small by taking the magnitude of the mean square deviation as the basis.
Step four: on the basis of the observed bright temperatures of the channels which have the largest contribution to the inversion sea surface air pressure, the observed bright temperatures of the channels are increased one by one according to the sequence that the observed bright temperatures of the 28 channels established in the step three have the smallest contribution to the inversion sea surface air pressure, so as to form the observed bright temperatures of the channel combination; training a BP neural network by taking the observed brightness temperature of the channel combination as input and the corresponding sea surface air pressure as output; and stopping increasing the observed bright temperature of the channel when the mean square error of the BP neural network corresponding to the observed bright temperature of the channel combination is not reduced any more with the increase of the observed bright temperature of the channel, wherein the channel combination at the moment is the optimal channel combination of the MWTS-II and the MWHTS fusion inversion sea surface air pressure.
Step five: and F, inverting the observed brightness temperature of the optimal channel combination obtained in the step four to obtain the sea surface air pressure.
The first step specifically comprises: matching the MWTS-II and the MWHTS observed brightness temperature according to a matching rule that the time error is less than 0.2 s and the longitude and latitude error is less than 0.01 degrees; and performing quality control on the observed bright temperature obtained by matching according to a screening rule with the value of more than 180K and less than 310K to form a MWTS-II and MWHTS bright temperature matching pair.
The second step specifically comprises:
using an European middle-term weather forecast center (ECMWF) to re-analyze the sea surface air pressure in the data set ERA-Interim to be matched with the bright temperature matching pair established in the first step, wherein the matching rule is that the time error is less than 0.5 h and the longitude and latitude error is less than 0.1 degrees, and establishing a matching data set of the bright temperature matching pair of MWTS-II and MWHTS and the sea surface air pressure; randomly selecting 80% of the matched data in the matched data set to form an analysis data set, and remaining 20% of the matched data to form a verification data set.
Example 1
The light temperature was observed using Fengyun three D star MWTS-II and MWHTS, over a time period of 2018 for 9 months to 2019 for 8 months, and over a geographical range of (25 ℃ N-45 ℃ N, 160 ℃ E-220 ℃ E). And matching the MWTS-II and MWHTS observed brightness temperature data according to a matching rule that the time error is less than 0.2 s and the longitude and latitude error is less than 0.01 degrees, then performing quality control on the observed brightness temperature in the matched data according to a screening rule that the observed brightness temperature in the matched data is more than 180K and less than 310K, and if any observed brightness temperature in the matched data is less than 180K or more than 310K, discarding the group of matched data to finally form an MWTS-II and MWHTS brightness temperature matching pair of 1060162 pairs.
The sea surface air pressure in the data set ERA-Interim was re-analyzed using the european mid-range weather forecast center (ECMWF) over a time range of 2018 months to 2019 months 8, a geographic range of (25 ° N-45 ° N, 160 ° E-220 ° E), and a data resolution of 0.5 ° x 0.5 °. Matching the sea surface air pressure with the 1060162 pair brightness temperature matching pair established in the first step, wherein the matching rule is that the time error is less than 0.5 h and the longitude and latitude error is less than 0.1 DEG, and establishing a matching data set (386279 group) of MWTS-II and MWHTS brightness temperature matching pair and sea surface air pressure; randomly selected 80% of the matched data in the matched data set forms the analyzed data set (309023 groups), and the remaining 20% of the matched data forms the verified data set (77256 groups).
Firstly, respectively taking the observed brightness temperature of 13 MWTS-II channels and 15 MWHTS channels in an analysis data set as input, and taking the corresponding sea surface air pressure in the analysis data set as output to form 28 training data sets; then, respectively training the BP neural networks by using 28 training data sets, wherein the 28 BP neural networks all use three-layer BP neural network structures, namely an input layer, an output layer and a hidden layer, and the mean square error representing the training performance of the BP neural networks is minimized by adjusting the number of neurons in the hidden layers in the BP neural networks; finally, the mean square deviations of 28 BP neural networks corresponding to 28 training data sets are counted, the smaller the mean square deviation value is, the larger the contribution of the observed bright temperature of the channel corresponding to the mean square deviation to the inversion sea surface air pressure is, and the contributions of the observed bright temperatures of the 28 channels to the inversion sea surface air pressure are sorted according to the order from large to small by taking the magnitude of the mean square deviation as the basis. The observed light temperatures of the 28 channels contribute to the inverted sea surface barometric pressure as shown in table 1. Wherein each channel of MWTS-II is represented by MWTS-II-n, n =1, 2, 3 … 13; the individual channels of MWHTS are denoted by MWHTS-m, m =1, 2, 3 … 15. The sequence of the contributions of the observed light temperatures of the 28 channels to the inverted sea surface barometric pressure from large to small is shown as the sequence numbers in table 1.
Sequencing the contributions of observed light temperatures of 128 channels to inversion of sea surface barometric pressure
In the analysis data set, based on the observed bright temperatures of the MWTS-II-7 channel which has the largest contribution to the inverted sea surface air pressure, the observed bright temperatures of the 28 channels shown in the table 1 are added one by one according to the sequence number in the table 1 from large to small to form the observed bright temperatures of the channel combination; and training the BP neural network by taking the observed brightness temperature of the channel combination as input and the corresponding sea surface air pressure as output. With the increase of the channels one by one, after the channel combination is added with the channel MWTS-II-13 corresponding to the sequence number 22, the mean square error of the BP neural network trained by the newly formed channel combination observation light temperature is 10.24. When the channel MWHTS-9 corresponding to the sequence number 23 is added to the channel combination, the mean square error of the BP neural network trained by the observed brightness and temperature of the corresponding channel combination is 12.4. After the channels are continuously added according to the serial numbers in table 1, the mean square error of the BP neural network trained by the observed brightness temperature of the corresponding channel combination is continuously increased. Then the channel combinations corresponding to sequence numbers 1-22 in table 1, that is, the channel combinations: the MWTS-II total channel and the MWHTS-3, MWHTS-4, MWHTS-5, MWHTS-7, MWHTS-8, MWHTS-10, MWHTS-13, MWHTS-14 and MWHTS-15 are the optimal channel combination for the fusion inversion of sea surface air pressure by the MWTS-II and the MWHTS.
Respectively using observation bright temperatures corresponding to the combination of the MWHTS all channels, the MWTS-II all channels, the MWHTS all channels, the MWTS-II all channels and the optimal channel in the analysis data set as input, and corresponding sea surface air pressure as output, and training a BP neural network; the observed light temperatures corresponding to the verification data set of all channels of MWHTS, all channels of MWTS-II, and the optimal channel combination are respectively input to the corresponding trained neural network, respectively obtain the inversion values of the corresponding sea surface barometric pressure, and calculate the root mean square error between the sea surface barometric pressure inversion values and the corresponding sea surface barometric pressure values in the verification data set, as shown in fig. 2. As can be seen from FIG. 2, the observed brightness temperature of all channels of the MWHTS in the validation data set inverts the sea surface barometric pressure to an accuracy of 4.69 hPa; verifying that the precision of the observed brightness temperature inversion sea surface air pressure of all channels of the MWTS-II in the data set is 3.92 hPa; when the sea surface barometric pressure is inverted by using the observed bright temperature of all the MWHTS channels in the verification data set and the observed bright temperature of all the MWTS-II channels, the obtainable precision is 3.73 hPa; when the optimal channel combination established by the method is used for observing the brightness temperature and inverting the sea surface air pressure, the obtainable precision is 3.19 hPa. Although the precision higher than that of the MWHTS or MWTS-II can be obtained when the observed bright temperature of all the channels of the MWHTS and the observed bright temperature of all the channels of the MWTS-II invert the sea surface barometric pressure together, the precision of the sea surface barometric pressure inversion by the observed bright temperature of the optimal channel combination established by the method can be further improved by 0.5 hPa.
Claims (4)
1. A method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS is characterized by comprising the following steps:
the method comprises the following steps: establishing a brightness temperature matching pair of MWTS-II observation brightness temperature and MWHTS observation brightness temperature in time and space;
step two: establishing a matching data set of a bright temperature matching pair and sea surface air pressure in time and space, and dividing the matching data set into an analysis data set and a verification data set;
step three: respectively taking the observed brightness of 13 channels of the MWTS-II in the analysis data set and the observed brightness of 15 channels of the MWHTS as input, taking the sea surface air pressure of the corresponding analysis data set as output, forming 28 training data sets and respectively training a BP neural network, counting the mean square error of each training data set after the BP neural network is trained, and sequencing the contributions of the observed brightness of the 28 channels to the inversion sea surface air pressure from large to small according to the size of the mean square error;
step four: on the basis of the observed bright temperatures of the channels which have the largest contribution to the inversion sea surface air pressure, the observed bright temperatures of the channels are increased one by one according to the sequence that the observed bright temperatures of the 28 channels established in the step three have the smallest contribution to the inversion sea surface air pressure, so as to form the observed bright temperatures of the channel combination; training a BP neural network by taking the observed brightness temperature of the channel combination as input and the corresponding sea surface air pressure as output; with the increase of the observed brightness temperature of the channel, stopping increasing the observed brightness temperature of the channel when the mean square error of the BP neural network corresponding to the observed brightness temperature of the channel combination is not reduced any more, wherein the channel combination at the moment is the optimal channel combination of the MWTS-II and the MWHTS fusion inversion sea surface air pressure;
step five: and F, inverting the observed brightness temperature of the optimal channel combination obtained in the step four to obtain the sea surface air pressure.
2. The method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS according to claim 1, wherein: matching the MWTS-II and the MWHTS observed brightness temperature according to a matching rule that the time error is less than 0.2 s and the longitude and latitude error is less than 0.01 degrees; and performing quality control on the observed bright temperature obtained by matching according to a screening rule with the value of more than 180K and less than 310K to form a MWTS-II and MWHTS bright temperature matching pair.
3. The method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS according to claim 1, wherein: and (3) matching the sea surface air pressure with the bright temperature matching pair established in the first step, wherein the matching rule is that the time error is less than 0.5 h and the longitude and latitude error is less than 0.1 DEG, and establishing a matching data set of the bright temperature matching pair of MWTS-II and MWHTS and the sea surface air pressure.
4. The method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS according to claim 1, wherein: randomly selecting 80% of the matched data in the matched data set to form an analysis data set, and remaining 20% of the matched data to form a verification data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104191.8A CN112254866B (en) | 2020-10-15 | 2020-10-15 | Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104191.8A CN112254866B (en) | 2020-10-15 | 2020-10-15 | Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112254866A CN112254866A (en) | 2021-01-22 |
| CN112254866B true CN112254866B (en) | 2022-08-02 |
Family
ID=74242328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011104191.8A Active CN112254866B (en) | 2020-10-15 | 2020-10-15 | Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112254866B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822345B (en) * | 2021-09-09 | 2024-03-29 | 南京中科逆熵科技有限公司 | Method and system for inverting cloud water content by fusing MWHTS and MWTS-II |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651934A (en) * | 2020-05-25 | 2020-09-11 | 华中科技大学 | Ice cloud profile inversion method |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7353690B2 (en) * | 2005-01-24 | 2008-04-08 | Radiometrics Corporation | Atmospheric refractivity profiling apparatus and methods |
| CN102589714A (en) * | 2012-02-23 | 2012-07-18 | 南昌航空大学 | Temperature measuring device based on high-pressure gas Rayleigh-Brillouin scattering spectrum |
| WO2014194482A1 (en) * | 2013-06-05 | 2014-12-11 | 中国科学院微电子研究所 | Gas recognition method based on compressive perception theory |
| CN107870043A (en) * | 2017-10-25 | 2018-04-03 | 中国科学院国家空间科学中心 | A kind of extra large table parameter synchronization inverting optimization method |
| CN108051872B (en) * | 2017-12-13 | 2020-03-24 | 湖北省气象服务中心（湖北省专业气象服务台） | Method and device for inverting water vapor phase change process in cloud based on foundation microwave radiometer |
| CN108827878B (en) * | 2018-04-08 | 2021-05-18 | 中国科学院国家空间科学中心 | Passive microwave remote sensing detection method for surface air pressure |
| CN109580003B (en) * | 2018-12-18 | 2021-01-12 | 成都信息工程大学 | Method for estimating near-ground atmospheric temperature by thermal infrared data of stationary meteorological satellite |
| 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 |
-
2020
- 2020-10-15 CN CN202011104191.8A patent/CN112254866B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651934A (en) * | 2020-05-25 | 2020-09-11 | 华中科技大学 | Ice cloud profile inversion method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112254866A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446739B (en) | Surface temperature multi-channel thermal infrared remote sensing inversion method | |
| CN112051222A (en) | River and lake water quality monitoring method based on high-resolution satellite image | |
| CN112329334B (en) | MWHTS and MWTS-II fusion inversion sea surface air pressure method based on simulated bright temperature | |
| CN111737913B (en) | MWHTS clear sky observation bright temperature selection method based on cloud water content inversion | |
| CN110826693B (en) | Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network | |
| CN108827878B (en) | Passive microwave remote sensing detection method for surface air pressure | |
| CN111737912B (en) | MWHTS (metal wrap through) simulated bright temperature calculation method based on deep neural network | |
| CN113108918B (en) | Method for inverting air temperature by using thermal infrared remote sensing data of polar-orbit meteorological satellite | |
| CN101936877A (en) | Method for inverting atmospheric water vapor content from MODIS (Moderate Resolution Imaging Spectroradiometer) data | |
| CN113552080B (en) | Real-time inversion algorithm for ultra-spectrum remote sensing earth surface atmosphere relative humidity | |
| CN112254866B (en) | Method for inverting sea surface air pressure by fusion of MWTS-II and MWHTS | |
| AU2021105183A4 (en) | A Method for Estimating Near-surface Air Temperature From Remote Sensing Data Based on Machine Learning | |
| CN101655564A (en) | Method for inversing surface temperature and emissivity from MODIS data | |
| CN115758667A (en) | Method for jointly detecting and inverting sea atmosphere temperature and humidity profile | |
| Niu et al. | Performances between the FY‐4A/GIIRS and FY‐4B/GIIRS long‐wave infrared (LWIR) channels under clear‐sky and all‐sky conditions | |
| Zhao et al. | Comparison of two split-window methods for retrieving land surface temperature from MODIS data | |
| CN102495943B (en) | Modeling method for geophysical model | |
| CN112345151B (en) | Sensitivity test method of MWTS-II to sea surface air pressure based on natural atmosphere | |
| CN110991087A (en) | Wind field inversion method and system based on multi-incidence-angle networking SAR satellite data | |
| Tian et al. | Cloud detection and classification for S-NPP FSR CRIS data using supervised machine learning | |
| CN113311509B (en) | Sensitivity test method of MWHTS (metal wrap through) to sea surface air pressure based on neural network | |
| CN117172149A (en) | Evaporation waveguide prediction method based on data feature classification and neural network model | |
| CN113822345B (en) | Method and system for inverting cloud water content by fusing MWHTS and MWTS-II | |
| AU2021105233A4 (en) | Method of Retrieving Surface Temperature from Passive Microwave Remote Sensing Data AMSR E | |
| CN115950832A (en) | Method for inverting near-surface nitrogen dioxide concentration based on satellite data |
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 |