CN114112941A - Aviation hyperspectral water eutrophication evaluation method based on support vector regression - Google Patents
Aviation hyperspectral water eutrophication evaluation method based on support vector regression Download PDFInfo
- Publication number
- CN114112941A CN114112941A CN202111526518.5A CN202111526518A CN114112941A CN 114112941 A CN114112941 A CN 114112941A CN 202111526518 A CN202111526518 A CN 202111526518A CN 114112941 A CN114112941 A CN 114112941A
- Authority
- CN
- China
- Prior art keywords
- water
- data
- area
- evaluated
- leaving
- 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.)
- Withdrawn
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 261
- 238000012851 eutrophication Methods 0.000 title claims abstract description 75
- 238000011156 evaluation Methods 0.000 title claims abstract description 45
- 238000002310 reflectometry Methods 0.000 claims abstract description 77
- 239000002352 surface water Substances 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 60
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 36
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 24
- 229930002868 chlorophyll a Natural products 0.000 claims description 22
- 239000000126 substance Substances 0.000 claims description 19
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 18
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 18
- 229910052757 nitrogen Inorganic materials 0.000 claims description 18
- 229910052760 oxygen Inorganic materials 0.000 claims description 18
- 239000001301 oxygen Substances 0.000 claims description 18
- 229910052698 phosphorus Inorganic materials 0.000 claims description 18
- 239000011574 phosphorus Substances 0.000 claims description 18
- 235000016709 nutrition Nutrition 0.000 claims description 12
- 235000003715 nutritional status Nutrition 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 8
- 230000035764 nutrition Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012614 Monte-Carlo sampling Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000002860 competitive effect Effects 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 238000011835 investigation Methods 0.000 abstract description 4
- 238000011282 treatment Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 230000003595 spectral effect Effects 0.000 description 6
- 238000012417 linear regression Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000002798 spectrophotometry method Methods 0.000 description 3
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229940010552 ammonium molybdate Drugs 0.000 description 1
- 239000011609 ammonium molybdate Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QLULGSLAHXLKSR-UHFFFAOYSA-N azane;phosphane Chemical compound N.P QLULGSLAHXLKSR-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000000476 body water Anatomy 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 235000003784 poor nutrition Nutrition 0.000 description 1
- USHAGKDGDHPEEY-UHFFFAOYSA-L potassium persulfate Chemical compound [K+].[K+].[O-]S(=O)(=O)OOS([O-])(=O)=O USHAGKDGDHPEEY-UHFFFAOYSA-L 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to an aviation hyperspectral water eutrophication evaluation method based on support vector regression, which comprises the following steps: collecting hyperspectral data of an area to be evaluated; collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated; acquiring sample data according to the water quality parameters and the water leaving reflectivity data; training sample data and acquiring characteristic wave bands of water quality parameters; constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters; preprocessing the hyperspectral data to obtain the water-leaving reflectivity of the surface water of the area to be evaluated; acquiring the concentration of each water quality parameter of an area to be evaluated according to the water leaving reflectivity of surface water and a corresponding inversion model; and evaluating the water eutrophication of the area to be evaluated according to the concentration, thereby realizing high-precision rapid evaluation, making up for the observation space-time limitation of the traditional remote sensing, being beneficial to improving the evaluation precision and the space scale of the water eutrophication and providing technical support for investigation, monitoring and treatment of the water eutrophication.
Description
Technical Field
The invention belongs to the technical field of water quality evaluation, and particularly relates to an aviation hyperspectral water eutrophication evaluation method based on support vector regression.
Background
Nowadays, the water eutrophication problem directly changes the surrounding ecological environment, which affects the physical and mental health of residents. According to the 'Chinese ecological environment condition bulletin' in 2020, 110 important lakes (reservoirs) in China show that the poor nutrition state accounts for 9.1%, the medium nutrition state accounts for 61.8%, the light eutrophication state accounts for 23.6%, the medium eutrophication state accounts for 4.5%, and the severe eutrophication state accounts for 0.9%. Therefore, it is important to evaluate the eutrophication of water body rapidly and accurately. Different from the traditional eutrophication monitoring method, the remote sensing monitoring method is time-saving and labor-saving, and can acquire large-scale data and find out the spatial distribution condition. The hyperspectral remote sensing technology can further improve the overall monitoring precision, shorten the monitoring period and promote the development of water eutrophication evaluation work. Many scholars develop a series of research works, Suhao utilizes MODIS hyperspectral data and uses a multivariate linear regression method to carry out water quality parameter inversion and eutrophication degree analysis on Daqing reservoirs; zhang soldiers and the like research the mechanicalness of water environment remote sensing, quantitatively invert the water quality of the water body and research and develop a high-spectrum remote sensing monitoring system for the eutrophication of the inland water body.
The hyperspectral quantitative inversion of the water quality parameters is the basis for realizing the evaluation of the eutrophication of the hyperspectral water body, and the accuracy of the inversion result determines the accuracy of the evaluation result. At present, there are many water quality parameter inversion methods based on water body spectral characteristics, such as: multiple linear regression, least squares regression, neural networks, and the like. However, the aviation hyperspectral data has the characteristics of high band redundancy, large flight area difference and the like, and a high-precision aviation hyperspectral water quality parameter inversion model is difficult to obtain, so that the eutrophication evaluation of the water body is inaccurate. So far, some progress has been made in quantitative inversion of water quality parameters and evaluation of water eutrophication based on aviation hyperspectrum, but limitations and disadvantages still exist, and mainly appear as follows:
(1) water quality parameter inversion modeling is performed on water body spectra measured by an instrument in most of the existing researches: the water body spectrum measured by the instrument contains various information, and the accuracy of the inversion model can be higher only by obtaining the water body water-leaving reflectivity by removing other interference useless for inversion.
(2) The existing research is based on a simple method to carry out water quality parameter inversion, and the exploration of hyperspectral data is insufficient: the hyperspectral data has multidimensional spectral information, the information quantity is huge, redundancy exists, and the hyperspectral data is easily interfered by noise. Most of the existing methods can effectively reduce the dimension and reduce the information quantity, but some fine and gradual spectral information is lost, which may affect the subsequent modeling precision. Due to the complex relation between the water quality parameters and the hyperspectral data, the accuracy of the inversion result completely depends on the accuracy of the model, and a simple linear regression model cannot be fully fitted, so that the required accuracy cannot be met.
(3) The existing research on water eutrophication based on aviation hyperspectrum has single use index: the water eutrophication evaluation is a comprehensive evaluation, and the water eutrophication evaluation is carried out by adopting proper water quality parameter indexes in combination with the practical conditions of inland water in China.
Therefore, a new aviation hyperspectral water eutrophication evaluation method based on support vector regression needs to be designed based on the technical problems.
Disclosure of Invention
The invention aims to provide an aviation hyperspectral water eutrophication evaluation method based on support vector regression.
In order to solve the technical problems, the invention provides an aviation hyperspectral water eutrophication evaluation method, which comprises the following steps:
collecting hyperspectral data of an area to be evaluated;
collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated;
acquiring sample data according to the water quality parameters and the water leaving reflectivity data;
training sample data and acquiring characteristic wave bands of water quality parameters;
constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters;
preprocessing the hyperspectral data to obtain the water leaving reflectivity of the surface water body of the area to be evaluated;
acquiring the concentration of each water quality parameter of an area to be evaluated according to the water body water-leaving reflectivity and the corresponding inversion model; and
and evaluating the water eutrophication of the area to be evaluated according to the concentration.
Further, the method for collecting the hyperspectral data of the area to be evaluated comprises the following steps:
and (4) performing hyperspectral data acquisition on the area to be evaluated by a hyperspectral imager.
Further, the method for acquiring the water quality parameters and the water-leaving reflectivity data of the sample water body of the area to be evaluated comprises the following steps:
collecting the surface water body water-leaving reflectivity and the surface water sample of the area to be evaluated while collecting the hyperspectral data;
acquiring chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data according to a surface water sample;
the surface water sample is a water body with a preset depth below the water surface.
Further, the method for acquiring the sample data according to the water quality parameters and the water-leaving reflectivity data comprises the following steps:
and matching the water-leaving reflectivity of the water sample with chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data to form sample data.
Further, the method for training the sample data and acquiring the characteristic wave band of each water quality parameter includes:
training the sample data according to a competitive adaptive re-weighting algorithm, i.e.
And (3) taking the water-leaving reflectivity of the sample data and the data of each corresponding water quality parameter as input, setting a maximum extraction principle, a cross validation group and Monte Carlo sampling times, and outputting and acquiring a characteristic band corresponding to each water quality parameter.
Further, the method for constructing the corresponding inversion model according to the characteristic wave bands of the water quality parameters comprises the following steps:
modeling is carried out according to a least square support vector regression method;
performing parameter optimization according to a quantum particle group algorithm to obtain an inversion model of each water quality parameter, and performing precision verification;
the precision verification comprises the following steps: determining the coefficient R2And root mean square error, RMSE;
wherein n is the number of samples; y isiThe actual measured value of the ith sample;
is the average of the actual measurements; y isi' is the inverse model prediction value.
Further, the method for preprocessing the hyperspectral data to acquire the out-of-water reflectivity of the surface water of the area to be evaluated comprises the following steps:
and carrying out radiometric calibration, atmospheric correction and geometric correction on the hyperspectral data to obtain the water leaving reflectivity of the surface water body of the area to be evaluated.
Further, the method for evaluating the water eutrophication of the area to be evaluated according to the concentration comprises the following steps:
applying the inversion model to the water-leaving reflectivity data of the surface water body of the area to be evaluated to obtain chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand parameter concentration of the area to be evaluated;
evaluating the water eutrophication of the area to be evaluated through concentration according to a comprehensive nutritional state index method;
wherein TLI (Sigma) is the index of comprehensive nutrition state; w is aj(ii) a relative weight of the nutritional status index for the jth parameter; TLI (j) is the index for nutritional status for the jth parameter.
In a second aspect, the invention further provides an aviation hyperspectral water eutrophication evaluation system, which comprises:
the high-altitude acquisition module is used for acquiring high-spectrum data of an area to be evaluated;
the water quality acquisition module is used for acquiring water quality parameters and water leaving reflectivity data of a sample water body of an area to be evaluated;
the sample construction module is used for acquiring sample data according to the water quality parameters and the water-leaving reflectivity data;
the training module is used for training the sample data and acquiring the characteristic wave band of each water quality parameter;
the model construction module is used for constructing a corresponding inversion model according to the characteristic wave band of each water quality parameter;
the preprocessing module is used for preprocessing the hyperspectral data to acquire the water leaving reflectivity of the surface water body of the area to be evaluated;
the concentration acquisition module is used for acquiring the concentration of each water quality parameter of the area to be evaluated according to the water-leaving reflectivity of the water body and the corresponding inversion model; and
and the evaluation module is used for evaluating the water eutrophication of the area to be evaluated according to the concentration.
In a third aspect, the present invention further provides a water eutrophication evaluation apparatus, which includes:
the acquisition device is suitable for acquiring hyperspectral data of an area to be evaluated and water quality parameters and water leaving reflectivity data of a sample water body;
and the server is suitable for evaluating the water eutrophication of the area to be evaluated according to the acquired hyperspectral data, the water quality parameters of the sample water body and the water leaving reflectivity data.
The method has the advantages that the hyperspectral data of the area to be evaluated are collected; collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated; acquiring sample data according to the water quality parameters and the water leaving reflectivity data; training sample data and acquiring characteristic wave bands of water quality parameters; constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters; preprocessing the hyperspectral data to obtain the water leaving reflectivity of the surface water body of the area to be evaluated; acquiring the concentration of each water quality parameter of an area to be evaluated according to the water leaving reflectivity of the water body and the corresponding inversion model; and evaluating the water eutrophication of the area to be evaluated according to the concentration, thereby realizing high-precision rapid evaluation, making up for the observation space-time limitation of the traditional remote sensing, being beneficial to improving the evaluation precision and the space scale of the water eutrophication and providing technical support for the investigation, monitoring and treatment of the water eutrophication.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the method for evaluating the eutrophication of an aviation hyperspectral water body;
FIG. 2 is a detailed flow chart of the method for evaluating the eutrophication of the aerial hyperspectral water body;
FIG. 3 is a water sampling distribution diagram of the working area of the present invention;
FIG. 4 is a sample data scatter plot of 5 water quality parameters of the present invention;
FIG. 5 is a graph of the inversion results of chlorophyll a concentration according to the present invention;
FIG. 6 is a graph of the inversion results of total phosphorus concentration according to the present invention;
FIG. 7 is a graph of the inversion results of total nitrogen concentration according to the present invention;
FIG. 8 is a graph of transparency concentration inversion results according to the present invention;
FIG. 9 is a graph of the inversion results of COD concentration according to the present invention;
FIG. 10 is a diagram showing the results of water eutrophication evaluation according to the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in figure 1, the invention provides an aviation hyperspectral water eutrophication evaluation method, which comprises the following steps: collecting hyperspectral data of an area to be evaluated; collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated; acquiring sample data according to the water quality parameters and the water leaving reflectivity data; training sample data and acquiring characteristic wave bands of water quality parameters; constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters; preprocessing the hyperspectral data to obtain the water leaving reflectivity of the surface water body of the area to be evaluated; acquiring the concentration of each water quality parameter of an area to be evaluated according to the water leaving reflectivity of the water body and the corresponding inversion model; and the eutrophication of the water body in the area to be evaluated is evaluated according to the concentration, so that the high-precision quick evaluation is realized, the observation time and space limitations of the traditional remote sensing are overcome, the evaluation precision and the space scale of the eutrophication of the water body are improved, and the technical support is provided for the investigation, monitoring and treatment of the eutrophication of the water body.
As shown in fig. 2, in this embodiment, the method for collecting hyperspectral data of an area to be evaluated includes: performing hyperspectral data acquisition on an area to be evaluated through a hyperspectral imager; and selecting a proper aviation flight platform to carry a hyperspectral imager according to the range of the target area, and acquiring hyperspectral data of the target area (area to be evaluated).
In this embodiment, the method for acquiring water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated includes: collecting the water-leaving reflectivity and the surface water sample of the surface water body of the area to be evaluated while collecting the hyperspectral data; the surface water body water leaving reflectivity measurement adopts a ground spectrometer, the wavelength range is 350-2500nm, the spectral resolution is 1nm, and the water leaving reflectivity of the water body is measured by using an above-water method; acquiring chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data according to a surface water sample; the surface water sample is a water body with a preset depth (0.5m) below the water surface; the method for determining the concentration of the water quality parameters comprises the following steps: chlorophyll a-grinding acetone spectrophotometry, total phosphorus-ammonium molybdate spectrophotometry, total nitrogen-alkaline potassium persulfate digestion ultraviolet spectrophotometry, transparency-Secker disk method, chemical oxygen demand-dichromate method; compared with the water body spectral data measured by a direct using instrument, modeling is carried out, the water leaving reflectivity is used as modeling data, other interference factors such as skylight and the like are eliminated, the relevant information of water quality parameter inversion is enhanced, and the accuracy of a water quality parameter inversion model is improved, so that the water body eutrophication evaluation result is more accurate.
In this embodiment, the method for obtaining sample data according to the water quality parameter and the water-leaving reflectivity data includes: and matching the water-leaving reflectivity of the water sample with chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data to form sample data.
In this embodiment, the method for training sample data and acquiring a characteristic band of each water quality parameter includes: training sample data by using a Competitive Adaptive weighted Sampling (CARS) algorithm, selecting characteristic wave bands of all water quality parameters, namely taking the water-leaving reflectivity of the sample data and the data of corresponding parameters (such as chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration) as input, setting a maximum extraction principle, a cross validation group and Monte Carlo Sampling times, and outputting and acquiring the characteristic wave bands corresponding to all water quality parameters.
In this embodiment, the method for constructing a corresponding inversion model according to the characteristic band of each water quality parameter includes: based on the characteristic wave band data of each water quality parameter, modeling is carried out by using a Least Square Support Vector Regression (LSSVR) method, parameter Optimization is carried out by using a Quantum Particle group algorithm (Quantum-weighted Particle Swarm Optimization, QPSO), and finally an inversion model of each water quality parameter is obtained and precision verification is carried out; taking the sample characteristic band data and corresponding water quality parameter indexes as input, selecting a radial basis function as a kernel function, setting regularization parameters and kernel function width, and outputting to obtain an inverse model of each water quality parameter; the parameter optimization by using a quantum particle group algorithm comprises the following steps: setting the number of particle groups, the maximum iteration times, the regularization parameter range and the kernel function width range, and outputting the optimal regularization parameter and the kernel function width through search calculation; the precision verification comprises the following steps: determining the coefficient R2And root mean square error, RMSE;
wherein n is the number of samples; y isiThe actual measured value of the ith sample;
is the average of the actual measurements; y isi' is an inverse model prediction value; the characteristic wave band selection is carried out on the sample data by using a Competitive Adaptive weighted Sampling (CARS), on the basis of retaining characteristic information, a large amount of redundant information is effectively removed, the data dimension is reduced, the hyperspectral data information is fully mined, the data utilization rate is improved, and the operation time is reduced; the method is different from a traditional linear Regression model, the method accurately fits the complex relation between the water quality parameters and the aviation hyperspectral data, and obtains the water quality parameter concentration quickly with high precision, so that the accurate water eutrophication evaluation result is obtained.
In this embodiment, the method for preprocessing the hyperspectral data to acquire the out-of-water reflectivity of the surface water body of the area to be evaluated includes: and carrying out radiometric calibration, atmospheric correction and geometric correction on the hyperspectral data to obtain the water-leaving reflectivity data of the surface water body of the area to be evaluated.
In this embodiment, the method for evaluating the eutrophication of the water body in the area to be evaluated according to the concentration includes: applying the inversion model to the water-leaving reflectivity data of the surface water body of the area to be evaluated to obtain chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand parameter concentration of the area to be evaluated; evaluating the water eutrophication of the area to be evaluated through concentration according to a comprehensive nutritional state index method;
wherein TLI (Sigma) is the index of comprehensive nutrition state; w is aj(ii) a relative weight of the nutritional status index for the jth parameter; TLI (j) is the index of nutritional status for the jth parameter; water eutrophication is carried out by using comprehensive nutrition state index method based on aviation hyperspectral dataComprehensive evaluation, which adopts chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand as indexes, and adopts single factor evaluation for comparison, can fully reflect the water eutrophication condition, and realize large-range, low-cost, rapid and high-precision water eutrophication evaluation and monitoring.
Specifically, the method described above is explained with actual data in this embodiment: in 2020, from 10 months to 22 months and from 9 months to 10 months, the aviation hyperspectral data acquisition work is carried out in a working area of a Gaoyou lake, 137 survey lines are flown in total, and the data with the maximum line curvature less than or equal to 3 percent reaches 100 percent; the data with the maximum rollover angle less than or equal to 3 degrees accounts for 97.52% on average, and the accuracy and the use of the data are not influenced due to the fact that the wind speed of the lake surface is large; the average flying height of each measuring line is between 778m and 829m and is within 5 percent of the variation range of the average flying height 803 m; the maximum rising/falling speed of the single measuring line is 5.9m/s at the maximum value, and the average value is 2.23 m/s; wherein the average value of the data ratio of the maximum pitch angle of each measuring line less than or equal to 3 degrees is 99.88 percent. All the flying frames are implemented on clear sky days, rains do not appear in three days before aerial photography, the ground surface is dry, and the earliest aerial photography time is 9 a.m.: 30, the latest time is 3 pm: and 30, the quality of the hyperspectral original data is good.
The flying process is carried out synchronously to carry out the water-leaving reflectivity and surface water sample collection of the surface water body; the distribution of sampling points is shown in fig. 3, and the number of sampling points is 78. The method comprises the following steps of (1) collecting the water leaving reflectivity of a surface water body by using a FieldSpec-4 type portable ground object spectrometer, wherein the output spectral range is 350-2500nm, the interval is 1nm, the clear and calm moment is selected during collection, and the collection method is a measurement method above the water surface; surface water sampling is generally carried out by sinking the container to a position 0.3 to 0.5m below the water surface, and attention is paid to the fact that other substances floating on the water surface cannot be mixed. And (3) sending the collected water sample to a laboratory within 8 hours for measuring the concentrations of chlorophyll a, total phosphorus, total nitrogen and chemical oxygen demand, and measuring transparency data by using a Seitschnikov disk when the water sample is collected.
Matching the water-leaving reflectivity of a water sample with chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data to form sample data, and distributing the sample data according to the proportion of 3:1, wherein 59 training samples are obtained, and 19 testing samples are obtained.
And (3) training 78 sample data by using CARS to select characteristic wave bands of water quality parameters. The sample water-leaving reflectivity and corresponding water quality parameter indexes are used as input, the maximum extraction principle is set to be 10, the cross validation group is set to be 30, the Monte Carlo sampling frequency is set to be 1000, and the obtained characteristic wave band numbers corresponding to chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand are respectively 19, 36, 41, 32 and 39.
Based on characteristic wave band data corresponding to each water quality parameter of a training sample, modeling is carried out by using an LSSVR method, a radial basis function is selected as a kernel function, wherein a regularization parameter and a kernel function width are optimized by a QPSO method, the number of particle groups is set to be 20, the maximum iteration number is 200, the regularization parameter range is 0-1, the kernel function width range is 1-1000, the optimal regularization parameter and the kernel function width are output through search calculation, and finally an inversion model of each water quality parameter is obtained. Will determine the coefficient (R)2) And Root Mean Square Error (RMSE) is used as a judgment index, the inversion model is used for carrying out concentration inversion on each water quality parameter of the test sample, and a scattered point distribution diagram of each water quality parameter of sample points is shown in figure 4.
And performing radiometric calibration on the acquired aviation hyperspectral data, performing atmospheric correction on the data subjected to radiometric calibration by using a FLAASH atmospheric radiation transmission model to obtain the water-leaving reflectivity data of the surface water body, and then performing geometric correction to obtain the water-leaving reflectivity data of the surface water body with accurate geographic coordinates.
And applying the inversion model to the water-leaving reflectivity data of the surface water body of the working area to obtain the parameters and concentrations of chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand of the water body of the working area, and obtaining the results as shown in figures 5-9.
And (3) performing eutrophication evaluation on the water body by adopting a comprehensive nutritional state index method based on the chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data of the inversion water body, and obtaining a result shown in a figure 10.
The comprehensive nutrition state index method comprises the following steps:
in the formula: TLI (Sigma) is the index of the integrated nutrient status, wjThe relevant weight tli (j) for the nutritional status index of the jth parameter is the nutritional status index of the jth parameter. Taking chlorophyll a as a reference parameter, the normalized correlation weight calculation formula of the jth parameter is as follows:
in the formula: r isijThe correlation coefficient of the jth parameter and the reference parameter chlorophyll a is shown, and m is the number of evaluation parameters; the correlation coefficients between chlorophyll a used and other parameters are shown in table 1 below:
table 1: correlation of partial parameters with chlorophyll a
| Parameter(s) | Chlorophyll a | Total phosphorus | Total nitrogen | Transparency | Chemical Oxygen Demand (COD) |
| |
1 | 0.84 | 0.82 | -0.83 | 0.83 |
| |
1 | 0.7056 | 0.6724 | 0.6889 | 0.6889 |
Each nutritional status index is calculated as follows:
TLI(chla)＝10*(2.5+1.806lnchla)；
TLI(TP)＝10*(9.436+1.624lnTP)；
TLI(TN)＝10*(5.453+1.694lnTN)；
TLI(SD)＝10*(5.118-1.94lnSD)；
TLI(COD)＝10*(0.109+2.661lnchla)；
in the formula: chlorophyll a unit is mg/L, and the transparency unit is m; other index units are mg/L. The comprehensive eutrophication evaluation of the water body has the advantages of high precision and small space-time limitation in the aspect of large-scale and rapid evaluation of the water body nutrition state, can effectively evaluate and monitor the water body nutrition state, provides scientific and technological support for analyzing the structure function of an ecological system and developing ecological restoration, and provides basic data for the management decision of relevant government departments.
Example 2
On the basis of embodiment 1, this embodiment 2 further provides an aviation hyperspectral water eutrophication evaluation system, which includes: the high-altitude acquisition module is used for acquiring high-spectrum data of an area to be evaluated; the water quality acquisition module is used for acquiring water quality parameters and water leaving reflectivity data of a sample water body of an area to be evaluated; the sample construction module is used for acquiring sample data according to the water quality parameters and the water-leaving reflectivity data; the training module is used for training the sample data and acquiring the characteristic wave band of each water quality parameter; the model construction module is used for constructing a corresponding inversion model according to the characteristic wave band of each water quality parameter; the preprocessing module is used for preprocessing the hyperspectral data to acquire the water leaving reflectivity of the surface water body of the area to be evaluated; the concentration acquisition module is used for acquiring the concentration of each water quality parameter of the area to be evaluated according to the water-leaving reflectivity of the water body and the corresponding inversion model; and the evaluation module is used for evaluating the water eutrophication of the area to be evaluated according to the concentration.
In this embodiment, specific functions of each module have been described in detail in embodiment 1, and are not described in detail in this embodiment.
Example 3
On the basis of embodiment 1, this embodiment 3 further provides a water eutrophication evaluation apparatus, including: the acquisition device is suitable for acquiring hyperspectral data of an area to be evaluated and water quality parameters and water leaving reflectivity data of a sample water body; and the server is suitable for evaluating the water eutrophication of the area to be evaluated according to the acquired hyperspectral data, the water quality parameters of the sample water body and the water leaving reflectivity data.
In this embodiment, the server is adapted to evaluate the water eutrophication of the area to be evaluated by using the aviation hyperspectral water eutrophication evaluation method provided in embodiment 1.
In summary, the hyperspectral image data of the area to be evaluated are collected; collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated; acquiring sample data according to the water quality parameters and the water leaving reflectivity data; training sample data and acquiring characteristic wave bands of water quality parameters; constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters; preprocessing the hyperspectral data to obtain the water leaving reflectivity of the surface water body of the area to be evaluated; acquiring the concentration of each water quality parameter of an area to be evaluated according to the water leaving reflectivity of the water body and the corresponding inversion model; and the eutrophication of the water body in the area to be evaluated is evaluated according to the concentration, so that the high-precision quick evaluation is realized, the observation time and space limitations of the traditional remote sensing are overcome, the evaluation precision and the space scale of the eutrophication of the water body are improved, and the technical support is provided for the investigation, monitoring and treatment of the eutrophication of the water body.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. An aviation hyperspectral water eutrophication evaluation method is characterized by comprising the following steps:
collecting hyperspectral data of an area to be evaluated;
collecting water quality parameters and water-leaving reflectivity data of a sample water body of an area to be evaluated;
acquiring sample data according to the water quality parameters and the water leaving reflectivity data;
training sample data and acquiring characteristic wave bands of water quality parameters;
constructing a corresponding inversion model according to the characteristic wave bands of the water quality parameters;
preprocessing the hyperspectral data to obtain the water-leaving reflectivity of the surface water of the area to be evaluated;
acquiring the concentration of each water quality parameter of an area to be evaluated according to the water leaving reflectivity of surface water and a corresponding inversion model; and
and evaluating the water eutrophication of the area to be evaluated according to the concentration.
2. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 1,
the method for collecting the hyperspectral data of the area to be evaluated comprises the following steps:
and (4) performing hyperspectral data acquisition on the area to be evaluated by a hyperspectral imager.
3. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 2,
the method for acquiring the water quality parameters and the water-leaving reflectivity data of the sample water body of the area to be evaluated comprises the following steps:
collecting the water-leaving reflectivity and the surface water sample of the surface water body of the area to be evaluated while collecting the hyperspectral data;
acquiring chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data according to a surface water sample;
the surface water sample is a water body with a preset depth below the water surface.
4. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 3,
the method for acquiring the sample data according to the water quality parameters and the water leaving reflectivity data comprises the following steps:
and matching the water-leaving reflectivity of the water sample with chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand concentration data to form sample data.
5. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 4,
the method for training the sample data and acquiring the characteristic wave band of each water quality parameter comprises the following steps:
training the sample data according to a competitive adaptive re-weighting algorithm, i.e.
And (3) taking the water-leaving reflectivity of the sample data and the data of each corresponding water quality parameter as input, setting a maximum extraction principle, a cross validation group and Monte Carlo sampling times, and outputting and acquiring a characteristic band corresponding to each water quality parameter.
6. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 5,
the method for constructing the corresponding inversion model according to the characteristic wave bands of the water quality parameters comprises the following steps:
modeling is carried out according to a least square support vector regression method;
performing parameter optimization according to a quantum particle group algorithm to obtain an inversion model of each water quality parameter, and performing precision verification;
the precision verification comprises the following steps: determining the coefficient R2And root mean square error, RMSE;
wherein n is the number of samples; y isiThe actual measured value of the ith sample;
is the average of the actual measurements; y isi' is the inverse model prediction value.
7. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 6,
the method for preprocessing the hyperspectral data to acquire the out-of-water reflectivity of the surface water of the area to be evaluated comprises the following steps:
and carrying out radiometric calibration, atmospheric correction and geometric correction on the hyperspectral data to obtain the water-leaving reflectivity data of the surface water of the area to be evaluated.
8. The method for evaluating the eutrophication of an airborne hyperspectral water body according to claim 7,
the method for evaluating the water eutrophication of the area to be evaluated according to the concentration comprises the following steps:
applying the inversion model to the water-leaving reflectivity data of the surface water body of the area to be evaluated to obtain chlorophyll a, total phosphorus, total nitrogen, transparency and chemical oxygen demand parameter concentration of the area to be evaluated;
evaluating the water eutrophication of the area to be evaluated through concentration according to a comprehensive nutritional state index method;
wherein TLI (Sigma) is the index of comprehensive nutrition state; w is aj(ii) a relative weight of the nutritional status index for the jth parameter; TLI (j) is the index for nutritional status for the jth parameter.
9. An aviation hyperspectral water eutrophication evaluation system is characterized by comprising:
the high-altitude acquisition module is used for acquiring high-spectrum data of an area to be evaluated;
the water quality acquisition module is used for acquiring water quality parameters and water leaving reflectivity data of a sample water body of an area to be evaluated;
the sample construction module is used for acquiring sample data according to the water quality parameters and the water-leaving reflectivity data;
the training module is used for training the sample data and acquiring the characteristic wave band of each water quality parameter;
the model construction module is used for constructing a corresponding inversion model according to the characteristic wave band of each water quality parameter;
the preprocessing module is used for preprocessing the hyperspectral data to acquire the water leaving reflectivity of the surface water body of the area to be evaluated;
the concentration acquisition module is used for acquiring the concentration of each water quality parameter of the area to be evaluated according to the water-leaving reflectivity of the water body and the corresponding inversion model; and
and the evaluation module is used for evaluating the water eutrophication of the area to be evaluated according to the concentration.
10. A water eutrophication evaluation device is characterized by comprising:
the acquisition device is suitable for acquiring hyperspectral data of an area to be evaluated and water quality parameters and water leaving reflectivity data of a sample water body;
and the server is suitable for evaluating the water eutrophication of the area to be evaluated according to the acquired hyperspectral data, the water quality parameters of the sample water body and the water leaving reflectivity data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111526518.5A CN114112941A (en) | 2021-12-14 | 2021-12-14 | Aviation hyperspectral water eutrophication evaluation method based on support vector regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111526518.5A CN114112941A (en) | 2021-12-14 | 2021-12-14 | Aviation hyperspectral water eutrophication evaluation method based on support vector regression |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114112941A true CN114112941A (en) | 2022-03-01 |
Family
ID=80364438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111526518.5A Withdrawn CN114112941A (en) | 2021-12-14 | 2021-12-14 | Aviation hyperspectral water eutrophication evaluation method based on support vector regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114112941A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115524294A (en) * | 2022-09-19 | 2022-12-27 | 南京中科深瞳科技研究院有限公司 | Water leaving type real-time intelligent remote sensing water quality monitoring method |
| CN116306322A (en) * | 2023-05-18 | 2023-06-23 | 天津中科谱光信息技术有限公司 | Water total phosphorus concentration inversion method and device based on hyperspectral data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672805A (en) * | 2019-10-08 | 2020-01-10 | 核工业北京地质研究院 | Reservoir water quality parameter quantitative inversion method based on aviation hyperspectral data |
| CN112014324A (en) * | 2020-09-04 | 2020-12-01 | 中国水利水电科学研究院 | Water body nutrition state evaluation method based on multi-source monitoring data |
-
2021
- 2021-12-14 CN CN202111526518.5A patent/CN114112941A/en not_active Withdrawn
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672805A (en) * | 2019-10-08 | 2020-01-10 | 核工业北京地质研究院 | Reservoir water quality parameter quantitative inversion method based on aviation hyperspectral data |
| CN112014324A (en) * | 2020-09-04 | 2020-12-01 | 中国水利水电科学研究院 | Water body nutrition state evaluation method based on multi-source monitoring data |
Non-Patent Citations (4)
| Title |
|---|
| 吴廷宽;贺中华;梁虹;杨朝晖;曾信波;刘绥华;陈栋为;焦树林;李秋华;: "基于高光谱技术的湖泊富营养化综合评价研究――以贵阳市百花湖为例", 水文, no. 02, 25 April 2016 (2016-04-25), pages 2 - 3 * |
| 烟贯发 等: "基于改进的PSO优化LSSVM 参数的松花江江哈尔滨段悬浮物的遥感反演", 环境科学学报, vol. 34, no. 8, 31 August 2014 (2014-08-31) * |
| 石剑龙 等: "航空高光谱遥感技术在生态环境地质调查中的应用", 第十六届华东六省一市地学科技论坛论文集, 29 August 2020 (2020-08-29), pages 3 * |
| 袁自然;魏立飞;张杨熙;余铭;闫芯茹;: "优化CARS结合PSO-SVM算法农田土壤重金属砷含量高光谱反演分析", 光谱学与光谱分析, no. 02, 15 February 2020 (2020-02-15) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115524294A (en) * | 2022-09-19 | 2022-12-27 | 南京中科深瞳科技研究院有限公司 | Water leaving type real-time intelligent remote sensing water quality monitoring method |
| CN116306322A (en) * | 2023-05-18 | 2023-06-23 | 天津中科谱光信息技术有限公司 | Water total phosphorus concentration inversion method and device based on hyperspectral data |
| CN116306322B (en) * | 2023-05-18 | 2023-08-25 | 天津中科谱光信息技术有限公司 | Water total phosphorus concentration inversion method and device based on hyperspectral data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108593569B (en) | EO-1 hyperion water quality parameter quantitative inversion method based on spectrum morphological feature | |
| Duan et al. | Comparison of different semi-empirical algorithms to estimate chlorophyll-a concentration in inland lake water | |
| CN114112941A (en) | Aviation hyperspectral water eutrophication evaluation method based on support vector regression | |
| CN111597756A (en) | Water quality parameter inversion method based on multispectral data of unmanned aerial vehicle | |
| CN110531054B (en) | Soil organic carbon prediction uncertainty estimation method based on Bootstrap sampling | |
| CN113203694B (en) | MSI lake eutrophication index remote sensing estimation method | |
| CN114372707A (en) | High-cold-wetland degradation degree monitoring method based on remote sensing data | |
| CN105486655A (en) | Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model | |
| CN114241331B (en) | Remote sensing modeling method for ground biomass of reed in wetland by taking UAV as ground and Septinel-2 medium | |
| CN113252583B (en) | Method for calculating alpine hay coverage based on hay vegetation index | |
| Pu et al. | Applications of imaging spectrometry in inland water quality monitoring—a review of recent developments | |
| CN113436153A (en) | Method for predicting carbon components of undisturbed soil profile based on hyperspectral imaging and support vector machine technology | |
| Hang et al. | Estimation of chlorophyll-a concentration in Lake Taihu from Gaofen-1 wide-field-of-view data through a machine learning trained algorithm | |
| CN115494007A (en) | Random forest based high-precision rapid detection method and device for soil organic matters | |
| CN115294147A (en) | Method for estimating aboveground biomass of single trees and forests based on unmanned aerial vehicle laser radar | |
| Nouchi et al. | Effects of non-uniform vertical constituent profiles on remote sensing reflectance of oligo-to mesotrophic lakes | |
| Mollaee | Estimation of phytoplankton chlorophyll-a concentration in the western basin of Lake Erie using Sentinel-2 and Sentinel-3 data | |
| CN116757099B (en) | Soil salinity inversion and salinization risk assessment method, device and equipment | |
| CN117035174A (en) | Method and system for estimating biomass on single-woodland of casuarina equisetifolia | |
| CN116773516A (en) | Soil carbon content analysis system based on remote sensing data | |
| CN116911183A (en) | Karst wetland water chlorophyll a inversion method, system, equipment and medium | |
| Lu et al. | An operational approach for large-scale mapping of water clarity levels in inland lakes using landsat images based on optical classification | |
| Cięzkowski et al. | Long-term water quality monitoring using Sentinel-2 data, Głuszyńskie Lake case study | |
| Wong et al. | Modeling water quality using Terra/MODIS 500 m satellite images | |
| Alsahli et al. | Modeling Secchi Disk Depth Over the North Arabian Gulf Waters Using MODIS and MERIS Images |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220301 |
|
| WW01 | Invention patent application withdrawn after publication |