CN117408142B - Aerosol optical thickness inversion method based on normalized aerosol index - Google Patents
Aerosol optical thickness inversion method based on normalized aerosol index Download PDFInfo
- Publication number
- CN117408142B CN117408142B CN202311312962.6A CN202311312962A CN117408142B CN 117408142 B CN117408142 B CN 117408142B CN 202311312962 A CN202311312962 A CN 202311312962A CN 117408142 B CN117408142 B CN 117408142B
- Authority
- CN
- China
- Prior art keywords
- aerosol
- data
- optical thickness
- normalized
- index
- 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
- 239000000443 aerosol Substances 0.000 title claims abstract description 101
- 230000003287 optical effect Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000003595 spectral effect Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012795 verification Methods 0.000 claims abstract description 11
- 238000013528 artificial neural network Methods 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000013434 data augmentation Methods 0.000 claims description 4
- 238000003908 quality control method Methods 0.000 claims description 4
- 102000006463 Talin Human genes 0.000 claims description 3
- 108010083809 Talin Proteins 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 241001633942 Dais Species 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000005427 atmospheric aerosol Substances 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- 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
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Remote Sensing (AREA)
- Biochemistry (AREA)
- Computer Hardware Design (AREA)
- Dispersion Chemistry (AREA)
- Astronomy & Astrophysics (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Geometry (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the application provides an aerosol optical thickness inversion method based on a normalized aerosol index, which comprises the steps of performing space and time matching on acquired foundation data, FY-4A/AGRI static satellite data and cloud product data, generating training and verification samples, and performing pretreatment; analyzing the importance of the spectral feature information in the training sample, and eliminating the wave bands with low importance; calculating a normalized aerosol index between the 0.65 μm and 0.83 μm bands; taking the sample data with lower rejection importance wave bands and the normalized aerosol index as the input characteristics of the fully connected neural network to jointly restrict the inversion of the aerosol optical thickness; establishing a fully-connected neural network model to obtain a fixed aerosol optical thickness inversion model; remote sensing data is input into an aerosol optical thickness prediction model to predict the aerosol optical thickness. The invention has the advantages of objective and reasonable satellite observation data, high inversion precision and the like.
Description
Technical Field
The invention relates to the technical field of aerosol remote sensing, in particular to an aerosol optical thickness inversion method based on normalized aerosol indexes.
Background
Aerosol refers to a gaseous dispersion system of solid or liquid particles suspended in a gaseous medium. The aerosols in the atmosphere comprise complex mixtures of various sizes, shapes, chemical compositions. Aerosols can affect radiation balance, global climate, and human health. It is not only one of the important parameters for analyzing global climate change and atmospheric pollution, but also an indispensable factor for researching quantitative remote sensing. The optical thickness of the aerosol is an important optical parameter for characterizing the property and the spatial distribution of the atmospheric aerosol, so that the accurate acquisition of the optical thickness of the aerosol is of great importance.
Although the accuracy of the foundation aerosol optical thickness observation data is high, the space resolution and the station number are insufficient, various uncertainties are included, and a large-range environment monitoring task cannot be realized. The optical thickness of the satellite observation aerosol is lower in time resolution, and the satellite observation aerosol has a great effect on high-time resolution environment monitoring and quantitative remote sensing. The new generation of stationary satellites such as FY-4A/AGRI has high time resolution and can provide near real-time aerosol products with full coverage in a region, but no official aerosol optical thickness products are released at present.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the application provides an aerosol optical thickness inversion method based on normalized aerosol indexes.
The aerosol optical thickness inversion method based on the normalized aerosol index comprises the following steps: acquiring remote sensing data of FY-4A/AGRI stationary satellites, wherein the remote sensing data comprises satellite data and cloud product data, the satellite data comprises wave band data, solar zenith angles, satellite zenith angles and relative azimuth angles of satellites and the sun, and the cloud product data comprises cloud mask data;
based on aerosol automatic observation network foundation data and solar radiometer observation network foundation data and remote sensing data of FY-4A/AGRI stationary satellites, a sample set is generated, and the sample set is divided into a training sample and a verification sample, wherein the proportion is 7:3, a step of;
preprocessing a training sample in a sample set, wherein the preprocessing comprises normalization, quality control and data augmentation;
analyzing spectral characteristic information in the data of the preprocessed training sample by using XGBoost, and rejecting the bands of 1.38 mu m, 3.75 mu m, 10.7 mu m and 13.5 mu m;
determining an aerosol index based on the spectral reflectance in the 0.65 μm band and the spectral reflectance in the 0.83 μm band, the aerosol index being used to characterize the FY-4A/AGRI stationary satellite band spectral reflectance difference;
normalizing the aerosol index to determine a normalized aerosol index;
based on the normalized aerosol index and the training sample, training an aerosol optical thickness prediction model by using a fully connected neural network through selecting a relu activation function, data batch normalization, L2 regularization, dropout and fully connected layer parameter setting and performing multiple iterations, and performing accuracy verification on the prediction model by using a verification sample;
inputting the remote sensing data into a pre-trained aerosol optical thickness prediction model to predict the aerosol optical thickness.
In some possible implementations, the normalized aerosol index is determined, calculated according to the following formula:
wherein NDAI characterizes a normalized aerosol index, band2 characterizes a spectral reflectance of a 0.65 μm Band, and Band3 characterizes a spectral reflectance of a 0.83 μm Band.
In some possible implementations, the normalized aerosol index value is between 0-1.
By the method provided by the invention, the constraint condition of aerosol optical thickness inversion is increased by utilizing the normalized aerosol index and combining the spectral information characteristics, and a high-precision aerosol optical thickness product can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an overall flow of aerosol optical thickness inversion based on normalized aerosol index according to an embodiment of the present application;
FIG. 2 is a schematic illustration of the importance of a spectral feature provided by an embodiment of the present application;
FIG. 3 is a plot of inversion results without using normalized aerosol indices provided by an embodiment of the present application;
fig. 4 is a plot of inversion results using normalized aerosol indices provided by an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The term "and/or" herein is an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. The symbol "/" herein indicates that the associated object is or is a relationship, e.g., A/B indicates A or B.
The terms "first" and "second" and the like in the description and in the claims are used for distinguishing between different objects and not for describing a particular sequential order of objects. For example, the first response message and the second response message, etc. are used to distinguish between different response messages, and are not used to describe a particular order of response messages.
In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality of" means two or more, for example, a plurality of processing units means two or more processing units and the like; the plurality of elements means two or more elements and the like.
For the purpose of facilitating an understanding of the embodiments of the present application, reference will now be made to the following description of specific embodiments, taken in conjunction with the accompanying drawings, which are not intended to limit the embodiments of the invention.
First, technical terms involved in the embodiments of the present application will be described:
1. remote Sensing (Remote Sensing) refers to non-contact, remote detection techniques. Generally refers to the detection of the radiation and reflection characteristics of electromagnetic waves from an object using sensors/remote sensors.
2. Inversion is a method for inverting physical and chemical parameters of object features by known remote sensing observation data.
3. The cloud mask is a process for marking pixels affected by the cloud, and is a basis for correctly using remote sensing data.
Next, the technical solution provided in the embodiments of the present application will be described.
When measuring aerosol optical thickness, the accuracy of the foundation aerosol optical thickness observation data is high, but the space resolution and the station number of the foundation are insufficient, and the foundation aerosol optical thickness observation data contains various uncertainties, so that a large-range environment monitoring task cannot be realized. For example, in the ocean and coastal zone areas, there are fewer foundation sites, which results in less than ideal accuracy of inversion of aerosol optical thickness in the ocean area. The optical thickness of the aerosol observed by the satellite is lower in time resolution, and the method has a great effect on high-time resolution environment monitoring and quantitative remote sensing.
The Fengyun No. A star (code: FY-4A) is the first star of the new generation of stationary satellites in China. The carried interference type atmosphere vertical detector and the static orbit scanning imaging radiometer are connected by hand, so that three-dimensional atmosphere monitoring on the static orbit is realized for the first time in the world. In addition, "cloud No. four" can provide continuous monitoring data for land, water, lightning, space weather. The new generation of stationary satellites such as FY-4A/AGRI has high time resolution and can provide near real-time aerosol products with full coverage in a region, but no official aerosol optical thickness products are released at present.
In view of this, the embodiment of the application provides an aerosol optical thickness inversion method based on normalized aerosol index, which provides information support for atmospheric environment monitoring and quantitative remote sensing by using FY-4A/AGRI stationary satellite data.
Illustratively, FIG. 1 shows a schematic overall flow chart of an aerosol optical thickness inversion based on normalized aerosol index provided by an embodiment of the present application, the method being directed to FY-4A/AGRI stationary satellites. As shown in fig. 1, the overall flow of aerosol optical thickness inversion based on normalized aerosol index may include the following steps:
(1) Remote sensing data of the FY-4A/AGRI stationary satellite is obtained, the remote sensing data comprise satellite data and cloud product data, the satellite data comprise wave band data, solar zenith angles, satellite zenith angles and relative azimuth angles of the satellite and the sun, and the cloud product data comprise cloud mask data.
(2) Based on aerosol automatic observation network foundation data (AERONET) and solar radiometer observation network (SONET) foundation data and remote sensing data of the FY-4A/AGRI stationary satellite, generating a sample set, and dividing the sample set into a training sample and a verification sample, wherein the proportion is 7:3.
(3) And preprocessing the training samples in the sample set, wherein the preprocessing comprises normalization, quality control and data augmentation.
In some possible implementations, quality control may include culling samples of cloud, ice, snow, and the like.
In some possible implementations, the data in the training samples may be augmented in view of fewer samples with aerosol optical thicknesses greater than 1.3. Data augmentation may include adding 2% gaussian noise to the data in the training samples.
(4) Spectral signature information in the data of the pre-processed training samples was analyzed using XGBoost and bands of 1.38 μm, 3.75 μm, 10.7 μm, and 13.5 μm were removed.
In this embodiment, the spectral feature information may include spectral reflectance, luminance temperature, zenith angles of satellites and sun, azimuth angles, and the like. FIG. 2 is a schematic diagram of the importance of a spectral feature provided in an embodiment of the present application. As shown in fig. 2, there are 14 total bands of importance of solar zenith angle, satellite zenith angle, and relative azimuth angle. The bands Band4, band7, band12 and Band14 have low importance and can be removed. The corresponding wavelengths were 1.38 μm, 3.75 μm, 10.7 μm, 13.5 μm, respectively.
(5) An aerosol index is determined based on the spectral reflectance of the 0.65 μm band and the spectral reflectance of the 0.83 μm band, the aerosol index being used to characterize the FY-4A/AGRI stationary satellite band spectral reflectance difference.
(6) And normalizing the aerosol index to determine a normalized aerosol index.
In some possible implementations, the normalized aerosol index is determined, calculated according to the following formula:
wherein NDAI characterizes a normalized aerosol index, band2 characterizes a spectral reflectance of a 0.65 μm Band, and Band3 characterizes a spectral reflectance of a 0.83 μm Band.
In this embodiment, after the DAI is calculated using different bands, different DAIs may be obtained. The prediction model obtained after the aerosol optical thickness prediction model is trained through different DAIs is used for verifying the prediction result by using a verification sample in a training set, and the aerosol prediction model has the best effect when the spectral reflectances of the wave bands of 0.65 mu m and 0.83 mu m are used.
(7) Based on the normalized aerosol index and the training sample, a fully connected neural network is utilized, an aerosol optical thickness prediction model is trained through multiple iterations by selecting a relu activation function, data batch normalization, L2 regularization, dropout and fully connected layer parameter setting, and accuracy verification is carried out on the prediction model by utilizing a verification sample.
(8) And inputting the remote sensing data into a pre-trained aerosol optical thickness prediction model to predict the aerosol optical thickness.
The above is an introduction to an aerosol optical thickness inversion method based on normalized aerosol index provided in the embodiments of the present application. According to the embodiment, the neural network is trained through the calculated aerosol index to obtain an aerosol optical thickness prediction model based on the normalized aerosol index, so that the aerosol optical thickness is inverted. By the method, the FY-4A/AGRI aerosol optical thickness with higher precision can be obtained.
It should be understood that, the sequence number of each step in the foregoing embodiment does not mean the execution sequence, and the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way. In addition, in some possible implementations, each step in the foregoing embodiments may be selectively performed according to practical situations, and may be partially performed or may be performed entirely, which is not limited herein. All or part of any features of any of the embodiments of the present application may be freely, and arbitrarily combined without conflict. The combined technical scheme is also within the scope of the application.
FIG. 3 is a plot of inversion results without using normalized aerosol indices provided by an embodiment of the present application. As shown in fig. 3, the abscissa (x-axis) of the graph is the base aerosol optical thickness, and the ordinate (y-axis) is the predicted aerosol optical thickness. The diagonal line y=x, and the ideal value should fall on this function line. On both sides of the straight line y=x, for the desired error line EE, in the embodiment of the present application, EE takes 15%, i.e. the desired error is 15%, the witin EE represents a value within 15% of the desired error, the value is 54.2%, the above EE represents a value above 15% of the desired error, the value is 24.2%, the below EE represents a value below 15% of the desired error, and the value is 21.6%. The number of samples N is 1995, the root mean square error RMSE is 0.2727, the mean absolute error MAE is 0.1618, R represents the fitting degree of the measured linear regression, R 2 0.6436. A function of the fitness is available as y=0.645x+0.124.
Fig. 4 is a plot of inversion results using normalized aerosol indices provided by an embodiment of the present application. On both sides of the straight line y=x, for the desired error line EE, in the embodiment of the present application, EE takes 15%, i.e. the desired error is 15%, the witin EE represents a value within 15% of the desired error, the value is 56.5%, the above EE represents a value above 15% of the desired error, the value is 22.8%, the below EE represents a value below 15% of the desired error, and the value is 20.7%. The number of samples N is 1995, the root mean square error RMSE is 0.2322, the mean absolute error MAE is 0.1447, R represents the fitting degree of the measured linear regression, R 2 0.7382. A function of the fitness is available as y=0.734x+0.102.
By comparing the fitting degree of the prediction results of fig. 3 and fig. 4, it is obvious that the result predicted by the prediction model using the NDAI is more accurate when predicting the optical thickness of the aerosol.
It will be appreciated that the various numerical numbers referred to in the embodiments of the present application are merely for ease of description and are not intended to limit the scope of the embodiments of the present application.
Claims (3)
1. An aerosol optical thickness inversion method based on normalized aerosol index, characterized in that it is applied to FY-4A/AGRI stationary satellites, the method comprising:
acquiring remote sensing data of the FY-4A/AGR I stationary satellite, wherein the remote sensing data comprises satellite data and cloud product data, the satellite data comprises wave band data, solar zenith angles, satellite zenith angles and relative azimuth angles of satellites and the sun, and the cloud product data comprises cloud mask data;
based on aerosol automatic observation network foundation data and solar radiometer observation network foundation data and remote sensing data of the FY-4A/AGRI stationary satellite, generating a sample set, and dividing the sample set into a training sample and a verification sample, wherein the proportion is 7:3, a step of;
preprocessing the training samples in the sample set, wherein the preprocessing comprises normalization, quality control and data augmentation;
analyzing spectral characteristic information in the data of the preprocessed training sample by using XGBoost, and rejecting the bands of 1.38 mu m, 3.75 mu m, 10.7 mu m and 13.5 mu m;
determining an aerosol index based on the spectral reflectance of the 0.65 μm band and the spectral reflectance of the 0.83 μm band, the aerosol index being used to characterize the FY-4A/AGRI stationary satellite band spectral reflectance difference;
normalizing the aerosol index to determine a normalized aerosol index;
based on the normalized aerosol index and the training sample, training an aerosol optical thickness prediction model by using a fully connected neural network through selecting a relu activation function, data batch normalization, L2 regularization, dropout and fully connected layer parameter setting and performing multiple iterations, and performing accuracy verification on the prediction model by using a verification sample;
and inputting the remote sensing data into a pre-trained aerosol optical thickness prediction model to predict the aerosol optical thickness.
2. The method of claim 1, wherein said determining said normalized aerosol index is calculated according to the formula:
wherein NDAI characterizes a normalized aerosol index, band2 characterizes a spectral reflectance of a 0.65 μm Band, and Band3 characterizes a spectral reflectance of a 0.83 μm Band.
3. The method according to any one of claims 1 or 2, wherein the normalized aerosol index value is between 0 and 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311312962.6A CN117408142B (en) | 2023-10-11 | 2023-10-11 | Aerosol optical thickness inversion method based on normalized aerosol index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311312962.6A CN117408142B (en) | 2023-10-11 | 2023-10-11 | Aerosol optical thickness inversion method based on normalized aerosol index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117408142A CN117408142A (en) | 2024-01-16 |
| CN117408142B true CN117408142B (en) | 2024-03-22 |
Family
ID=89488118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311312962.6A Active CN117408142B (en) | 2023-10-11 | 2023-10-11 | Aerosol optical thickness inversion method based on normalized aerosol index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117408142B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105674901A (en) * | 2016-04-08 | 2016-06-15 | 电子科技大学 | Statistical segmentation based inversion method for atmospheric aerosol |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261873A (en) * | 2019-05-29 | 2019-09-20 | 电子科技大学 | A kind of atmospheric aerosol inversion method based on segmentation statistics |
-
2023
- 2023-10-11 CN CN202311312962.6A patent/CN117408142B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105674901A (en) * | 2016-04-08 | 2016-06-15 | 电子科技大学 | Statistical segmentation based inversion method for atmospheric aerosol |
Non-Patent Citations (3)
| Title |
|---|
| 利用云下阴影实现陆地上空气溶胶和地表反射率的同时反演――理论方法和模拟;段民征, 吕达仁, 崔克俭, 郝文强;遥感学报;20021010(第05期);全文 * |
| 基于暗目标法的Landsat-8 OLI数据气溶胶光学厚度反演;王钰;何红艳;谭伟;齐文雯;;航天返回与遥感;20180415(第02期);全文 * |
| 深度置信网络算法反演Landsat 8 OLI气溶胶光学厚度;贾臣;孙林;陈允芳;张熙空;王伟燕;王永吉;;遥感学报;20201025(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117408142A (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112051222A (en) | River and lake water quality monitoring method based on high-resolution satellite image | |
| CN110174359B (en) | Aviation hyperspectral image soil heavy metal concentration assessment method based on Gaussian process regression | |
| Li et al. | Atmospheric correction of geostationary satellite ocean color data under high solar zenith angles in open oceans | |
| CN109917098A (en) | Shenzhen waters quality evaluation method and system | |
| CN111597756A (en) | Water quality parameter inversion method based on multispectral data of unmanned aerial vehicle | |
| CN115356249A (en) | Satellite polarization PM2.5 estimation method and system based on machine learning fusion model | |
| CN110221360A (en) | A kind of power circuit thunderstorm method for early warning and system | |
| CN111783555A (en) | Deep learning satellite data cloud detection algorithm using unified samples | |
| CN115690632A (en) | Water environment monitoring method for inland river water body | |
| CN110186851A (en) | It is a kind of based on the semi-supervised Hyperspectral imaging heavy metal-polluted soil concentration evaluation method from Coded Analysis | |
| CN111612241A (en) | Comprehensive evaluation method for realizing intelligent ship path planning function | |
| CN110595968A (en) | PM2.5 concentration estimation method based on geostationary orbit satellite | |
| CN111241991B (en) | Water quality classification method based on remote sensing image | |
| CN113108918B (en) | Method for inverting air temperature by using thermal infrared remote sensing data of polar-orbit meteorological satellite | |
| CN115166750A (en) | Quantitative precipitation estimation method based on dual-polarization Doppler radar data | |
| CN110991087A (en) | Wind field inversion method and system based on multi-incidence-angle networking SAR satellite data | |
| CN114880933A (en) | Atmospheric temperature and humidity profile inversion method and system for non-exploration-site foundation microwave radiometer based on reanalysis data | |
| CN111079835A (en) | Himapari-8 atmospheric aerosol inversion method based on deep full-connection network | |
| CN109902877A (en) | A kind of gradually rating method of maritime peril target drift forecasting model parameter | |
| CN117408142B (en) | Aerosol optical thickness inversion method based on normalized aerosol index | |
| CN117710508A (en) | Near-surface temperature inversion method and device for generating countermeasure network based on improved condition | |
| Liu et al. | Research on generic optical remote sensing products: A review of scientific exploration, technology research, and engineering application | |
| CN110321528B (en) | Hyperspectral image soil heavy metal concentration assessment method based on semi-supervised geospatial regression analysis | |
| CN116911183A (en) | Karst wetland water chlorophyll a inversion method, system, equipment and medium | |
| Arnone et al. | Validation of the VIIRS ocean color |
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 |