CN116702065B - Method and system for monitoring ecological treatment pollution of black and odorous water based on image data - Google Patents
Method and system for monitoring ecological treatment pollution of black and odorous water based on image data Download PDFInfo
- Publication number
- CN116702065B CN116702065B CN202310629450.6A CN202310629450A CN116702065B CN 116702065 B CN116702065 B CN 116702065B CN 202310629450 A CN202310629450 A CN 202310629450A CN 116702065 B CN116702065 B CN 116702065B
- Authority
- CN
- China
- Prior art keywords
- water body
- black
- data
- image data
- spectrum
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 276
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000002310 reflectometry Methods 0.000 claims abstract description 69
- 238000011160 research Methods 0.000 claims abstract description 58
- 238000009826 distribution Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 238000004140 cleaning Methods 0.000 claims abstract description 21
- 238000007637 random forest analysis Methods 0.000 claims abstract description 5
- 238000001228 spectrum Methods 0.000 claims description 67
- 238000012937 correction Methods 0.000 claims description 45
- 230000005855 radiation Effects 0.000 claims description 33
- 230000003595 spectral effect Effects 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 241000192710 Microcystis aeruginosa Species 0.000 claims description 3
- 238000007667 floating Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 210000000746 body region Anatomy 0.000 claims 1
- 238000003911 water pollution Methods 0.000 abstract description 3
- 230000015572 biosynthetic process Effects 0.000 abstract description 2
- 238000003786 synthesis reaction Methods 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 description 4
- 238000003809 water extraction Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005316 response function Methods 0.000 description 2
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000033116 oxidation-reduction process Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/47—Scattering, i.e. diffuse reflection
- G01N21/4738—Diffuse reflection, e.g. also for testing fluids, fibrous materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1765—Method using an image detector and processing of image signal
- G01N2021/177—Detector of the video camera type
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
-
- 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
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/20—Controlling water pollution; Waste water treatment
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a black and odorous water ecological treatment pollution monitoring method and system based on image data, which relate to the field of water pollution monitoring and are used for carrying out refined extraction on urban and rural water by water characteristic identification in high-resolution remote sensing image data to obtain water distribution data, calculating to obtain apparent reflectivity according to the high-resolution remote sensing image data, then accurately correcting to obtain surface reflectivity, and carrying out band synthesis on black and odorous water indexes, normalized black and odorous water indexes, water cleaning indexes and green light single wave bands to construct a black and odorous water identification model to carry out random forest classification treatment, so that water level data and a water level spatial distribution map of a water area in a research area are obtained. The invention can obtain the water distribution and water level data of the research area, realizes the accurate subdivision of black and odorous water, and has the advantages of high efficiency of monitoring means, comprehensive data, reliable precision and the like.
Description
Technical Field
The invention relates to the field of water pollution monitoring, in particular to a black and odorous water ecological treatment pollution monitoring method and system based on image data.
Background
Black and odorous water body refers to the general name that color blackens and/or emits unpleasant malodorous water body, and the object of the black and odorous water body monitoring and treating gradually extends from a built-up area to a rural area and from a large-area black and odorous water body to a tiny black and odorous water body.
At present, aiming at the identification of urban and rural black and odorous water bodies, monitoring points are reasonably arranged in a monitoring area mainly through mass reporting and data collection, so that a method for carrying out field investigation and acquiring evaluation indexes such as transparency, dissolved oxygen, oxidation-reduction potential, ammonia nitrogen and the like is carried out, and the problem that the monitoring points are scattered and cannot fully reflect the water quality condition of the whole city in the traditional method is solved; in addition, the water sample needs to be collected on site, which is time-consuming and labor-consuming, has low efficiency and has great limitation. The satellite remote sensing technology has the advantages of wide monitoring range, low cost, strong timeliness and the like, and is widely applied to the aspects of water ecological environment protection, water pollution control and treatment, water environment disaster monitoring and early warning. In recent years, more and more scholars transfer the attention point to the remote sensing monitoring of black and odorous water bodies; however, urban and rural water bodies have the technical difficulties that the river channels are complex and are easily covered by partial high-rise buildings and vegetation shadows along the river, and the water body refined extraction and identification are technical difficulties; the purpose of the high-resolution image design is to realize visual interpretation and classification recognition, the radiometric calibration precision of the high-resolution image design cannot meet the requirement of accurate atmospheric correction, in addition, the high-resolution image is lack of a short wave infrared band, the water body is close to a dark target pixel, and the characteristic water body pollution constitution comprises data such as surface reflectivity and the like, and the data are difficult to accurately or completely acquire only through the high-resolution image.
Disclosure of Invention
The invention aims to solve the technical problems that the traditional monitoring method is difficult to fully cover urban rivers and reflect the condition of the whole water quality, and provides a black and odorous water body ecological management pollution monitoring method and system based on image data.
The aim of the invention is achieved by the following technical scheme:
a black and odorous water body ecological treatment pollution monitoring method based on image data comprises the following steps:
s1, acquiring high-resolution remote sensing image data of a research area and a surface reflectivity product corresponding to the high-resolution remote sensing image data;
s2, calculating the apparent reflectivity based on the high-resolution remote sensing image data according to the following method:
s21, calculating zenith spectrum radiance according to the image gray value of the high-resolution remote sensing image data according to the following method:
L i ＝DN×gain i +offsat i the method comprises the steps of carrying out a first treatment on the surface of the Wherein L is i For zenith spectral radiance corresponding to spectrum i image gray value, DN is the image gray value of high-resolution remote sensing image data, gain i Gain absolute radiation correction factor for spectral band i, offsat i An offset absolute radiation correction factor for spectrum segment i;
s22, calculating according to zenith spectrum radiance to obtain apparent reflectivity according to the following method:
wherein ρ is i For spectral band iApparent reflectance, d is distance between earth and sun, E 0，i The irradiance of solar spectrum outside the atmosphere in the spectrum section i is shown, and theta is the solar altitude angle;
s3, selecting a recently unchanged ground object in the research area as sample data, acquiring ground object samples of the sample data to obtain the data of the surface reflectivity of each spectrum section i of the ground object samples, and calculating and obtaining the data of the apparent reflectivity of each spectrum section i of the ground object samples according to a method of the step S2; constructing a relative radiation normalization atmosphere correction model, performing regression fitting on apparent reflectivity data of a spectrum section i of a ground object sample according to pixel correspondence and the apparent reflectivity data of the surface of the spectrum section i to obtain relationship data of the surface of the ground object sample, and performing model training on the relative radiation normalization atmosphere correction model by using the sample data;
inputting the apparent reflectivity of the spectrum section i of the high-resolution remote sensing image data into a relative radiation normalization atmospheric correction model to obtain the surface reflectivity of the spectrum section i corresponding to the high-resolution remote sensing image data, thereby obtaining a high-resolution surface reflectivity product;
s4, constructing a CE-Net water body extraction model, inputting high-resolution remote sensing image data of the research area into the CE-Net water body extraction model, and identifying water body characteristics in the high-resolution remote sensing image data by the CE-Net water body extraction model to obtain water body distribution data of the research area; based on water distribution data of a research area, a high-resolution surface reflectivity product is extracted through a mask to obtain a surface reflectivity distribution database corresponding to water in the research area; the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI and the water body cleaning index WCI are calculated according to the following method, and green light single-band data are extracted:
wherein ρ (B) represents the earth surface reflectivity of the spectrum i in the blue band, ρ (G) represents the earth surface reflectivity of the spectrum i in the green band, ρ (R) represents the earth surface reflectivity of the spectrum i in the red band, λ R 、λ G And lambda (lambda) B Respectively representing the spectrum i as the central wavelength of red light, green light and blue light wave bands;
s5, collecting water samples of the water body in the research area, carrying out water body grading detection, constructing a black and odorous water body sample data set according to the water body grade, wherein the water body grade comprises severe black and odorous water body, mild black and odorous water body and normal water body, obtaining a black and odorous water body index BOI (English is called as Black and Odorous waterIndex, BOI for short), a normalized black and odorous water body index NDBWI (English is called as Normalized difference black-odorous water index, NDBWI for short), a water body cleaning index WCI (English is called as Water Cleanliness Index, WCI for short) and green light single-band data corresponding to the water body according to the method of the step S4, constructing a black and odorous water body identification model comprising a random forest classification method according to the water body grade of the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI, the water body cleaning index WCI, green light single-band data and carrying out model training; and inputting the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI, the water body cleaning index WCI and the green light single-band data of the water body area of the research area into a black and odorous water body identification model to obtain water body level data and a water body level spatial distribution diagram of the water body area of the research area.
In order to better realize the pollution monitoring method for black and odorous water body ecological management based on image data, in the method S5, high-resolution remote sensing image data of a research area are acquired according to time, water body level data of water body areas of the research area are sequentially obtained according to time distribution, and further water body level space-time data of the water body areas of the research area are obtained, and therefore a water body space-time distribution diagram of the water body areas of the research area is obtained.
Preferably, in the method S1, the high-resolution remote sensing image data is sub Mi Jigao resolution remote sensing image data containing metadata files, and the high-resolution remote sensing image data is subjected to preprocessing including image optimization, orthographic correction, image fusion, geometric correction and clipping, and the preprocessing process maintains the original bit depth; the surface reflectance product was the L2A surface reflectance product of Sentinel-2.
Preferably, in the method S4, the CE-Net water extraction model is sequentially composed of an encoder module, a context extractor module, and a feature decoder module, where the encoder module is used to extract water feature information in the image, the water feature information includes spectral features, the context extractor module is used to capture multi-scale deep space information, and the feature decoder module is used to recover features and output a water identification result.
Preferably, the removing treatment of the inner coverage area of shadow, aquatic plants, flare and water bloom floating bath is carried out in the water body area before the high-resolution remote sensing image data are input into the relative radiation normalized atmosphere correction model.
Preferably, in the method S4, the CE-Net water body extraction model includes original data including administrative boundaries, drainage basin distribution data and water system distribution data of the research area.
The black and odorous water body ecological treatment pollution monitoring system based on the image data comprises a data acquisition input module, a calculation processing system and a data output module, wherein the data acquisition input module is used for acquiring high-resolution remote sensing image data of a research area and earth surface reflectivity products corresponding to the high-resolution remote sensing image data; the computing processing system comprises an apparent reflectance computing module, a relative radiation normalization atmospheric correction model, a CE-Net water body extraction model and a black and odorous water body recognition model; the apparent reflectance calculation module is used for calculating zenith spectral radiance and apparent reflectance according to the image gray level of the high-resolution remote sensing image data, and the relative radiation normalization atmospheric correction model is used for correcting according to the apparent reflectance of the spectral band i to obtain the corresponding spectral band i earth surface reflectance; the CE-Net water body extraction model is used for recognizing water body characteristics in high-resolution remote sensing image data, obtaining water body distribution data of a research area, calculating to obtain black and odorous water body indexes, normalizing the black and odorous water body indexes and water body cleaning indexes, and extracting green light single-band data; the black and odorous water body identification model is used for obtaining water body level data of a water body area of a research area according to black and odorous water body indexes, normalized black and odorous water body indexes, water body cleaning indexes and green light single-band data; the data output module is used for outputting the water level data and making a visual chart.
Compared with the prior art, the invention has the following advantages:
according to the invention, the urban and rural water body is finely extracted by recognizing the water body characteristics in the high-resolution remote sensing image data, the water body distribution data is obtained, the apparent reflectivity is calculated according to the high-resolution remote sensing image data, the surface reflectivity is obtained by accurate correction, the black and odorous water body recognition model is constructed by wave band synthesis based on the black and odorous water body index, the normalized black and odorous water body index, the water body cleaning index and the green light single wave band, and random forest classification processing is carried out, so that the water body level data and the water body level space distribution map of the water body area in the research area are obtained, and the method has the advantages of high efficiency in monitoring means, comprehensive data, reliable precision and the like.
Drawings
FIG. 1 is a schematic flow chart of a method for monitoring pollution of black and odorous water body ecological management based on image data;
FIG. 2 is a schematic diagram of a method for monitoring pollution of black and odorous water body ecological management based on image data;
FIG. 3 is a graph of apparent reflectance data for the blue band of the example;
FIG. 4 is a graph of apparent reflectance data for the green band in the examples;
FIG. 5 is a graph of apparent reflectance data for the red band of the example;
FIG. 6 is a spatial distribution diagram of water sample points of a water body in an investigation region in an embodiment;
FIG. 7 is a water distribution diagram of an investigation region in an embodiment;
FIG. 8 is a diagram showing the distribution of black and odorous water body in the investigation region in the example
FIG. 9 is a schematic block diagram of a pollution monitoring system for ecologically treating black and odorous water based on image data;
FIG. 10 illustrates an example of an out-of-atmosphere solar spectral irradiance curve in an embodiment;
FIG. 11 is a schematic block diagram of a CE-Net water extraction model in an embodiment.
Detailed Description
The invention is further illustrated by the following examples:
example of implementation
As shown in fig. 1 to 8, a black and odorous water body ecological treatment pollution monitoring method based on image data comprises the following steps:
s1, acquiring high-resolution remote sensing image data of a research area and a surface reflectivity product corresponding to the high-resolution remote sensing image data, wherein gain absolute radiation correction coefficient gain of spectrum section i is recorded in the high-resolution remote sensing image data i And an offset absolute radiation correction factor for spectrum bin i.
In some implementations, the high-resolution remote sensing image data is sub-Mi Jigao resolution remote sensing image data containing metadata files (domestic main stream sub-Mi Jigao resolution remote sensing image data with no cloud and better quality in a research area is acquired in a period to be monitored, such as high-resolution two, jilin one and the like), and the high-resolution remote sensing image data is subjected to preprocessing including image optimization, orthographic correction, image fusion, geometric correction and clipping, and the preprocessing process keeps the original bit depth. The surface reflectivity product is the L2A surface reflectivity product of Sentinel-2 (which can be obtained through a GEE or Copernicus Open Access Hub platform). On the basis of the L1-level product, the high-resolution remote sensing image data is preprocessed by control point and homonymous point acquisition and optimization, orthographic correction, image fusion, geometric correction, cutting and the like to obtain a product with original bit depth; on the other hand, the metadata file (mate. Xml) of the L1-level product is saved for use in subsequent atmospheric corrections.
S2, calculating the apparent reflectivity based on the high-resolution remote sensing image data according to the following method:
s21, calculating zenith spectrum radiance according to the image gray value of the high-resolution remote sensing image data according to the following method:
L i ＝DN×gain i +offsat i the method comprises the steps of carrying out a first treatment on the surface of the Wherein L is i Zenith spectrum corresponding to spectrum i image gray valueRadiance (unit is w/(m) 2 Sr·μm), DN is an image gray value of the high-resolution remote sensing image data, gain i Gain absolute radiation correction factor for spectral band i, offsat i For the offset absolute radiation correction factor of spectrum i, the gain absolute radiation correction factor of spectrum i and the offset absolute radiation correction factor of spectrum i are stored in the high-resolution remote sensing image data (generally stored and recorded in a metadata file), for example, the absolute radiation correction information is recorded in the metadata file of the L1 level product (high-resolution remote sensing image data), and the gain and offset of spectrum are respectively recorded in the metadata file<AbsCalibrationGain>And<AbsCalibrationBias>respectively annotating the annotations.
S22, calculating according to zenith spectrum radiance to obtain apparent reflectivity according to the following method:
wherein ρ is i The apparent reflectivity of the spectrum section i is dimensionless; d is the distance between the sun and the earth (astronomical unit), E 0，i Solar spectrum irradiance outside atmosphere in spectrum section i (unit is W/(m 2. Mu.m)), theta is solar altitude angle (unit is DEG, solar altitude angle is recorded in metadata file of high-resolution remote sensing image data<SolarElevation>In (c) a). Each wave band (namely spectrum i) of the external sunlight irradiance E of the atmosphere is recorded in the high-resolution remote sensing image data 0，i In general, a product manual or a user manual of a domestic mainstream high-resolution satellite provides calculated solar irradiance E outside the atmosphere in each wave band 0,i External sunlight irradiance E 0，i Is calculated according to a solar spectrum irradiance curve data file NEWKUR.dat carried by MODTRAN and by combining spectral response functions of each wave band of a satellite sensor, and is shown in figure 10.
S3, constructing a ground feature of the research area as sample data, acquiring ground feature samples of the sample data to obtain spectrum i surface reflectivity data corresponding to the ground feature samples, and calculating and obtaining spectrum i apparent reflectivity data corresponding to the ground feature samples according to a step S2. And constructing a relative radiation normalization atmosphere correction model, performing regression fitting on apparent reflectivity data of a spectrum section i of the ground object sample according to pixel correspondence and the apparent reflectivity data of a spectrum section i to obtain relationship data of the two, and performing model training on the relative radiation normalization atmosphere correction model by using the sample data. In some embodiments, the relative radiation normalized atmosphere correction model may be model trained using the following method:
A. the L2A surface reflectance product of the corresponding (or similar time) Sentinel-2 was selected as an auxiliary product based primarily on two factors: firstly, the accuracy of the Sentinel-2 radiometric calibration is higher, the spatial resolution is high (10 m), and the surface reflectivity product is acknowledged to have higher accuracy; and secondly, the wave band setting and the spectral response function of the high-resolution second-order and Jilin first-order sub-meter satellites are consistent with those of the sensor-2, so that the correlation of the reflectivity of ground features observed by the wave band is strong.
B. Selecting a sample: selecting some ground features (such as building roofs, roads, bare soil, playgrounds and the like) which cannot be changed in a short period from the image, and assigning the ground surface reflectivity value of one Sentinel-2 pixel to all pixels of the high-resolution image corresponding to the pixel on the assumption that the ground surface reflectivity of the ground features and the ground surface reflectivity of the high-resolution image are approximately unchanged. The single sample at the time of regression fit construction is represented by one dot: and cutting the high-resolution image by using a rectangular frame, converting all cut high-resolution pixels into a sample point (pixel center point), and extracting the surface reflectance value (Sentinel-2 image) and TOA value (apparent reflectance calculated by high-resolution image alignment) of all sample points.
The following should be noted in selecting the samples: firstly, checking whether the spatial positions of the high-resolution data and the auxiliary sensor-2 data are deviated or not; secondly, when the sample is selected, a single sample is represented by a rectangular frame, and the size of the rectangular frame is ensured to be in one Sentinel-2 pixel; thirdly, the selected sample is a pure pixel as far as possible in the sensor-2 image, which requires that the ground object corresponding to the pixel is as large as possible, and the periphery of the selected pixel is the ground object; fourthly, the selected sample is homogeneous as far as possible in the high-resolution image; fifth, the sample covers as many different colors as possible.
C. Regression fitting was performed to obtain data of the relationship between the surface reflectance values (note: sentinel-2 surface reflectance data, multiplied by a 0.0001 coefficient, converted to decimal) of all samples (sample samples) and their TOA values (apparent reflectance calculated for high resolution image).
And (3) inputting the apparent reflectivity of the spectrum section i of the high-resolution remote sensing image data into a relative radiation normalization atmosphere correction model to obtain the surface reflectivity of the spectrum section i corresponding to the high-resolution remote sensing image data (preferably, removing the shadow, aquatic plants, flare and water bloom floating bath in the inner coverage area before inputting the high-resolution remote sensing image data into the relative radiation normalization atmosphere correction model), thereby obtaining the high-resolution surface reflectivity product.
S4, constructing a CE-Net water body extraction model (preferably, the CE-Net water body extraction model internally comprises administrative boundaries, drainage basin distribution data and original data including water system distribution data of a research area), inputting high-resolution remote sensing image data of the research area into the CE-Net water body extraction model, and recognizing water body characteristics in the high-resolution remote sensing image data by the CE-Net water body extraction model to obtain water body distribution data of the research area. As shown in fig. 11, the CE-Net water extraction model is sequentially composed of an encoder module, a context extractor module, and a feature decoder module, where the encoder module is used to extract water feature information in an image, the water feature information includes spectral features, the context extractor module is used to capture multi-scale deep space information, and the feature decoder module is used to recover the features and output a water recognition result (as shown in fig. 6). The data input of the CE-Net water body extraction model training stage comprises image slices with fixed sizes and corresponding sample labels, the output of the prediction stage is a global water body identification result, the CE-Net water body extraction model can realize the refined extraction and identification of different water systems, and the obtained water body extraction result has good topological connectivity and integrity. Based on water distribution data of a research area, a high-resolution surface reflectivity product is extracted through a mask to obtain a surface reflectivity distribution database corresponding to water in the research area; the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI and the water body cleaning index WCI are calculated according to the following method, and green light single-band data are extracted:
wherein ρ (B) represents the earth surface reflectivity of the spectrum i in the blue band, ρ (G) represents the earth surface reflectivity of the spectrum i in the green band, ρ (R) represents the earth surface reflectivity of the spectrum i in the red band, λ R 、λ G And lambda (lambda) B The spectrum i is shown as the center wavelength of the red, green and blue bands, respectively.
S5, collecting water samples of the water body in the research area for water body grading detection, constructing a black and odorous water body sample data set according to the water sample, covering a key water body area or a water area to be concerned when the water sample is selected in the research area, meanwhile, ensuring the construction of the sample quantity of heavy black and odorous light black odorous normal water body, and the whole area in the research area is shown in the figure 6, wherein the research area comprises a water body area (including rivers and water flows), ground features (such as building roofs, roads and playgrounds), and the sample point of the water sample is selected for detection, and the water body level comprises heavy black odorous light black odorous normal water body. And (4) obtaining black and odorous water body index BOI, normalized black and odorous water body index NDBWI, water body cleaning index WCI and green light single-band data corresponding to the water sample according to the method of the step (S4), constructing a black and odorous water body identification model containing a random forest classification method according to the black and odorous water body index BOI, normalized black and odorous water body index NDBWI, water body cleaning index WCI, green light single-band data and the water level of the water sample, and performing model training. The black and odorous water body index BOI, the normalized black and odorous water body index NDBWI, the water body cleaning index WCI and the green light single-band data of the water body area of the research area are input into a black and odorous water body identification model to obtain water body level data and a water body level spatial distribution diagram (shown in figure 7) of the water body area of the research area.
In some embodiments, the method can acquire the high-resolution remote sensing image data of the research area according to time and sequentially acquire the water level data of the water area of the research area according to time distribution, so as to acquire the water level space-time data of the water area of the research area and acquire the water space-time distribution map of the water area of the research area.
According to the invention, urban and rural water bodies are automatically extracted by mining a context coding and decoding network (CE-Net) model of water body multi-scale depth information in the remote sensing image, and relative radiation normalization atmosphere correction is carried out on the high-resolution image by means of high-precision surface reflectivity data (Sentinel-2L 2A) in similar time, so that the problem of inaccurate surface reflectivity of the high-resolution image water body caused by atmosphere correction based on FLAASH and the like is solved. The method has the advantages that a finer classification standard is provided for the monitoring of the black and odorous water body, a method for further subdividing the black and odorous water body into severe black and odorous water body and mild black and odorous water body is provided, and the classification result is more meaningful; the invention adopts a machine learning method to fully mine rules among the original data, and improves the prediction precision of the model.
As shown in fig. 9, the pollution monitoring system for black and odorous water body ecological management based on image data comprises a data acquisition input module, a calculation processing system and a data output module, wherein the data acquisition input module is used for acquiring high-resolution remote sensing image data of a research area and earth surface reflectivity products corresponding to the high-resolution remote sensing image data; the computing processing system comprises an apparent reflectance computing module, a relative radiation normalization atmospheric correction model, a CE-Net water body extraction model and a black and odorous water body recognition model; the apparent reflectance calculation module is used for calculating zenith spectral radiance and apparent reflectance according to the image gray level of the high-resolution remote sensing image data, and the relative radiation normalization atmospheric correction model is used for correcting according to the apparent reflectance of the spectral band i to obtain the corresponding spectral band i earth surface reflectance; the CE-Net water body extraction model is used for recognizing water body characteristics in high-resolution remote sensing image data, obtaining water body distribution data of a research area, calculating to obtain black and odorous water body indexes, normalizing the black and odorous water body indexes and water body cleaning indexes, and extracting green light single-band data; the black and odorous water body identification model is used for obtaining water body level data of a water body area of a research area according to black and odorous water body indexes, normalized black and odorous water body indexes, water body cleaning indexes and green light single-band data; the data output module is used for outputting the water level data and making a visual chart as shown in fig. 8.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. A black and odorous water body ecological treatment pollution monitoring method based on image data is characterized by comprising the following steps of: the method comprises the following steps:
s1, acquiring high-resolution remote sensing image data of a research area and a surface reflectivity product corresponding to the high-resolution remote sensing image data;
s2, calculating the apparent reflectivity based on the high-resolution remote sensing image data according to the following method:
s21, calculating zenith spectrum radiance according to the image gray value of the high-resolution remote sensing image data according to the following method:
L i ＝DN×gain i +offsat i the method comprises the steps of carrying out a first treatment on the surface of the Wherein L is i For zenith spectral radiance corresponding to spectrum i image gray value, DN is the image gray value of high-resolution remote sensing image data, gain i Gain absolute radiation correction factor for spectral band i, offsat i An offset absolute radiation correction factor for spectrum segment i;
s22, calculating according to zenith spectrum radiance to obtain apparent reflectivity according to the following method:
wherein ρ is i Apparent reflectance of spectrum i, d is distance between earth and sun, E 0，i Is spectral band i solar spectrum irradiance outside the atmosphere, theta is solarA height angle;
s3, selecting a recently unchanged feature in the research area as sample data, acquiring feature samples of the sample data to obtain feature sample each spectral section i surface reflectivity data, and calculating and obtaining feature sample each spectral section i apparent reflectivity data according to a step S2; constructing a relative radiation normalization atmosphere correction model, performing regression fitting on apparent reflectivity data of a spectrum section i of a ground object sample according to pixel correspondence and the apparent reflectivity data of the surface of the spectrum section i to obtain relationship data of the surface of the ground object sample, and performing model training on the relative radiation normalization atmosphere correction model by using the sample data;
inputting the apparent reflectivity of the spectrum section i of the high-resolution remote sensing image data into a relative radiation normalization atmospheric correction model to obtain the surface reflectivity of the spectrum section i corresponding to the high-resolution remote sensing image data, thereby obtaining a high-resolution surface reflectivity product;
s4, constructing a CE-Net water body extraction model, inputting high-resolution remote sensing image data of the research area into the CE-Net water body extraction model, and identifying water body characteristics in the high-resolution remote sensing image data by the CE-Net water body extraction model to obtain water body distribution data of the research area; based on water distribution data of a research area and high-resolution surface reflectivity products, extracting a mask to obtain a surface reflectivity distribution database corresponding to water in the research area; the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI and the water body cleaning index WCI are calculated according to the following method, and green light single-band data are extracted:
wherein ρ (B) represents the earth surface reflectivity of the spectrum i in the blue band, ρ (G) represents the earth surface reflectivity of the spectrum i in the green band, ρ (R) represents the earth surface reflectivity of the spectrum i in the red band, λ R 、λ G And lambda (lambda) B Respectively representing the spectrum i as the central wavelength of red light, green light and blue light wave bands;
s5, collecting water samples of the water body in the research area, carrying out water body grading detection, constructing a black and odorous water body ground sample data set according to the water sample, wherein the water body grade comprises severe black and odorous water body, mild black and odorous water body and normal water body, obtaining black and odorous water body index BOI, normalized black and odorous water body index NDBWI, water body cleaning index WCI and green light single-band data corresponding to the water sample according to the method of the step S4, constructing a black and odorous water body identification model containing a random forest classification method according to the black and odorous water body index BOI, normalized black and odorous water body index NDBWI, water body cleaning index WCI, green light single-band data and the water body grade of the water sample, and carrying out model training; and inputting the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI, the water body cleaning index WCI and the green light single-band data of the water body area of the research area into a black and odorous water body identification model to obtain water body level data and a water body level spatial distribution diagram of the water body area of the research area.
2. The method for monitoring pollution of black and odorous water body ecological management based on image data according to claim 1, wherein the method comprises the following steps: in the method S5, high-resolution remote sensing image data of the research area are acquired according to time, water level data of the water body area of the research area are sequentially acquired according to time distribution, and further water level space-time data of the water body area of the research area are acquired, and therefore a water body space-time distribution map of the water body area of the research area is acquired.
3. The method for monitoring pollution of black and odorous water body ecological management based on image data according to claim 1, wherein the method comprises the following steps: in the method S1, the high-resolution remote sensing image data is sub Mi Jigao resolution remote sensing image data containing metadata files, and the high-resolution remote sensing image data is subjected to preprocessing including image optimization, orthographic correction, image fusion, geometric correction and clipping, wherein the preprocessing process keeps the original bit depth; the surface reflectance product was the L2A surface reflectance product of Sentinel-2.
4. The method for monitoring pollution of black and odorous water body ecological management based on image data according to claim 1, wherein the method comprises the following steps: in the method S4, the CE-Net water body extraction model is sequentially composed of an encoder module, a context extractor module and a feature decoder module, wherein the encoder module is used for extracting water body feature information in an image, the water body feature information comprises spectrum features, the context extractor module is used for capturing multi-scale deep space information, and the feature decoder module is used for recovering features and outputting a water body recognition result.
5. The method for monitoring pollution of black and odorous water body ecological management based on image data according to claim 1, wherein the method comprises the following steps: and removing the shadow, the aquatic plants, the flare and the water bloom floating bath in the water body region before the high-resolution remote sensing image data are input into the relative radiation normalized atmosphere correction model.
6. The method for monitoring pollution of black and odorous water body ecological management based on image data according to claim 1, wherein the method comprises the following steps: in the method S4, the CE-Net water body extraction model internally contains original data including administrative boundaries, drainage basin distribution data and water system distribution data of a research area.
7. The utility model provides a black and odorous water ecological management pollution monitoring system based on image data which characterized in that: the system comprises a data acquisition input module, a calculation processing system and a data output module, wherein the data acquisition input module is used for acquiring high-resolution remote sensing image data of a research area and earth surface reflectivity products corresponding to the high-resolution remote sensing image data; the computing processing system comprises an apparent reflectance computing module, a relative radiation normalization atmospheric correction model, a CE-Net water body extraction model and a black and odorous water body recognition model; the apparent reflectance calculation module is used for calculating zenith spectral radiance and apparent reflectance according to the image gray level of the high-resolution remote sensing image data, and calculating the zenith spectral radiance according to the following method:
L i ＝DN×gain i +offsat i the method comprises the steps of carrying out a first treatment on the surface of the Wherein L is i For zenith spectral radiance corresponding to spectrum i image gray value, DN is the image gray value of high-resolution remote sensing image data, gain i Gain absolute radiation correction factor for spectral band i, offsat i An offset absolute radiation correction factor for spectrum segment i;
the apparent reflectivity is calculated as follows:
wherein ρ is i Apparent reflectance of i spectrum i, d is distance between earth and sun, E 0，i The irradiance of solar spectrum outside the atmosphere in the spectrum section i is shown, and theta is the solar altitude angle;
the relative radiation normalization atmospheric correction model is used for correcting the apparent reflectivity of the spectrum section i to obtain the corresponding surface reflectivity of the spectrum section i; the CE-Net water body extraction model is used for recognizing water body characteristics in high-resolution remote sensing image data, obtaining water body distribution data of a research area, calculating to obtain black and odorous water body indexes, normalizing the black and odorous water body indexes and water body cleaning indexes, and extracting green light single-band data; the black and odorous water body index BOI, the normalized black and odorous water body index NDBWI and the water body cleaning index WCI are calculated according to the following method, and green light single-band data are extracted:
wherein ρ (B) represents the earth surface reflectivity of the spectrum i in the blue band, ρ (G) represents the earth surface reflectivity of the spectrum i in the green band, ρ (R) represents the earth surface reflectivity of the spectrum i in the red band, λ R 、λ G And lambda (lambda) B Respectively representing the spectrum i as the central wavelength of red light, green light and blue light wave bands;
the black and odorous water body identification model is used for obtaining water body level data of a water body area of a research area according to black and odorous water body indexes, normalized black and odorous water body indexes, water body cleaning indexes and green light single-band data; the data output module is used for outputting the water level data and making a visual chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310629450.6A CN116702065B (en) | 2023-05-30 | 2023-05-30 | Method and system for monitoring ecological treatment pollution of black and odorous water based on image data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310629450.6A CN116702065B (en) | 2023-05-30 | 2023-05-30 | Method and system for monitoring ecological treatment pollution of black and odorous water based on image data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116702065A CN116702065A (en) | 2023-09-05 |
| CN116702065B true CN116702065B (en) | 2024-04-16 |
Family
ID=87838543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310629450.6A Active CN116702065B (en) | 2023-05-30 | 2023-05-30 | Method and system for monitoring ecological treatment pollution of black and odorous water based on image data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702065B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118015487B (en) * | 2024-03-26 | 2024-06-07 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Method and system for comprehensively examining black and odorous water body based on river network intensive areas |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108333148A (en) * | 2018-01-11 | 2018-07-27 | 中国科学院遥感与数字地球研究所 | A kind of recognition methods of black and odorous water and device |
| CN110688909A (en) * | 2019-09-05 | 2020-01-14 | 南京有春科技有限公司 | Method, device and equipment for identifying urban black and odorous water body and storage medium |
| CN110987955A (en) * | 2019-12-05 | 2020-04-10 | 南京师范大学 | Urban black and odorous water body grading method based on decision tree |
| CN111007039A (en) * | 2019-11-29 | 2020-04-14 | 航天东方红卫星有限公司 | Automatic extraction method and system for sub-pixel level water body of medium-low resolution remote sensing image |
| CN112766075A (en) * | 2020-12-31 | 2021-05-07 | 中国冶金地质总局矿产资源研究院 | Hyperspectral remote sensing black and odorous water body grading method based on semi-supervised learning strategy |
| CN112884672A (en) * | 2021-03-04 | 2021-06-01 | 南京农业大学 | Multi-frame unmanned aerial vehicle image relative radiation correction method based on contemporaneous satellite images |
| EP3828528A1 (en) * | 2019-11-28 | 2021-06-02 | Anton Paar GmbH | Determination of an impairment of an optical surface for ir-spectroscopy |
| WO2021184891A1 (en) * | 2020-03-20 | 2021-09-23 | 中国科学院深圳先进技术研究院 | Remotely-sensed image-based terrain classification method, and system |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN114332133A (en) * | 2022-01-06 | 2022-04-12 | 福州大学 | New coronary pneumonia CT image infected area segmentation method and system based on improved CE-Net |
| WO2023273094A1 (en) * | 2021-06-30 | 2023-01-05 | 奥比中光科技集团股份有限公司 | Method, apparatus, and device for determining spectral reflectance |
| CN115825338A (en) * | 2022-11-03 | 2023-03-21 | 浙江时空智子大数据有限公司 | Ozone monitoring downscaling method, device, equipment and computer readable storage medium |
| CN116012726A (en) * | 2022-12-29 | 2023-04-25 | 中科宇图科技股份有限公司 | Deep learning-based black and odorous water body remote sensing monitoring and grading method |
| WO2023087630A1 (en) * | 2021-11-22 | 2023-05-25 | 浙江大学 | Method for estimating soil salinity of straw residue farmland by using remote sensing construction index |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101732111B1 (en) * | 2016-06-30 | 2017-05-02 | 서울시립대학교 산학협력단 | Apparatus for oil slick detection using satellite images and Method Thereof |
-
2023
- 2023-05-30 CN CN202310629450.6A patent/CN116702065B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108333148A (en) * | 2018-01-11 | 2018-07-27 | 中国科学院遥感与数字地球研究所 | A kind of recognition methods of black and odorous water and device |
| CN110688909A (en) * | 2019-09-05 | 2020-01-14 | 南京有春科技有限公司 | Method, device and equipment for identifying urban black and odorous water body and storage medium |
| EP3828528A1 (en) * | 2019-11-28 | 2021-06-02 | Anton Paar GmbH | Determination of an impairment of an optical surface for ir-spectroscopy |
| CN111007039A (en) * | 2019-11-29 | 2020-04-14 | 航天东方红卫星有限公司 | Automatic extraction method and system for sub-pixel level water body of medium-low resolution remote sensing image |
| CN110987955A (en) * | 2019-12-05 | 2020-04-10 | 南京师范大学 | Urban black and odorous water body grading method based on decision tree |
| WO2021184891A1 (en) * | 2020-03-20 | 2021-09-23 | 中国科学院深圳先进技术研究院 | Remotely-sensed image-based terrain classification method, and system |
| CN112766075A (en) * | 2020-12-31 | 2021-05-07 | 中国冶金地质总局矿产资源研究院 | Hyperspectral remote sensing black and odorous water body grading method based on semi-supervised learning strategy |
| CN112884672A (en) * | 2021-03-04 | 2021-06-01 | 南京农业大学 | Multi-frame unmanned aerial vehicle image relative radiation correction method based on contemporaneous satellite images |
| WO2023273094A1 (en) * | 2021-06-30 | 2023-01-05 | 奥比中光科技集团股份有限公司 | Method, apparatus, and device for determining spectral reflectance |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| WO2023087630A1 (en) * | 2021-11-22 | 2023-05-25 | 浙江大学 | Method for estimating soil salinity of straw residue farmland by using remote sensing construction index |
| CN114332133A (en) * | 2022-01-06 | 2022-04-12 | 福州大学 | New coronary pneumonia CT image infected area segmentation method and system based on improved CE-Net |
| CN115825338A (en) * | 2022-11-03 | 2023-03-21 | 浙江时空智子大数据有限公司 | Ozone monitoring downscaling method, device, equipment and computer readable storage medium |
| CN116012726A (en) * | 2022-12-29 | 2023-04-25 | 中科宇图科技股份有限公司 | Deep learning-based black and odorous water body remote sensing monitoring and grading method |
Non-Patent Citations (2)
| Title |
|---|
| 不同辐射校正水平下植被指数特征对比分析;赵娟娟;谈树成;杨林;;云南地理环境研究;20171215(06);2+7-14 * |
| 基于GF-2影像的沈阳市黑臭水体遥感分级识别;七珂珂;申茜;罗小军;李家国;姚月;杨崇;;遥感技术与应用;20200420(第02期);160-170 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116702065A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919875B (en) | High-time-frequency remote sensing image feature-assisted residential area extraction and classification method | |
| Tomppo et al. | The multi-source national forest inventory of Finland-methods and results 2011 | |
| CN109993237B (en) | Water body rapid extraction method and system based on high-resolution satellite optical remote sensing data | |
| Omran | Detection of land-use and surface temperature change at different resolutions | |
| Apan | Land cover mapping for tropical forest rehabilitation planning using remotely-sensed data | |
| CN104851087A (en) | Multi-scale forest dynamic change monitoring method | |
| CN116702065B (en) | Method and system for monitoring ecological treatment pollution of black and odorous water based on image data | |
| Fang et al. | Atmospheric effects on the performance and threshold extrapolation of multi-temporal Landsat derived dNBR for burn severity assessment | |
| Manakos et al. | Comparison between atmospheric correction modules on the basis of worldview-2 imagery and in situ spectroradiometric measurements | |
| CN109406361B (en) | Arid region dust-haze pollution early warning method based on remote sensing technology | |
| CN117218531B (en) | Sea-land ecological staggered zone mangrove plant overground carbon reserve estimation method | |
| CN113887493A (en) | Black and odorous water body remote sensing image identification method based on ID3 algorithm | |
| CN112329790A (en) | Rapid extraction method for urban impervious surface information | |
| Tew et al. | Urban expansion analysis using Landsat images in Penang, Malaysia | |
| CN115761493A (en) | Water body extraction method based on combined water body index frequency | |
| Morakinyo et al. | Mapping of land cover and estimation of their emissivity values for gas flaring sites in the Niger Delta | |
| Kennaway et al. | Mapping land cover and estimating forest structure using satellite imagery and coarse resolution lidar in the Virgin Islands | |
| CN114021900A (en) | Method for inverting soil heavy metal pollution risk level | |
| Wu et al. | Integrated vegetation cover of typical steppe in China based on mixed decomposing derived from high resolution remote sensing data | |
| CN117054484A (en) | Soil salinization prediction method based on multi-source remote sensing data | |
| CN117589692A (en) | Mangrove forest ecosystem carbon storage amount evaluation method based on remote sensing and deep LabV3+ | |
| Liu et al. | Fractional vegetation cover estimation algorithm based on recurrent neural network for MODIS 250 m reflectance data | |
| CN116229459A (en) | Domestic satellite multispectral image pixel-by-pixel quality marking method | |
| CN115527108A (en) | Method for rapidly identifying water and soil loss artificial disturbance plots based on multi-temporal Sentinel-2 | |
| Pisek et al. | Assessment of a global leaf area index product from SPOT-4 VEGETATION data over selected sites in Canada |
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 |