CN117434010A - Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm - Google Patents
Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm Download PDFInfo
- Publication number
- CN117434010A CN117434010A CN202011163340.8A CN202011163340A CN117434010A CN 117434010 A CN117434010 A CN 117434010A CN 202011163340 A CN202011163340 A CN 202011163340A CN 117434010 A CN117434010 A CN 117434010A
- Authority
- CN
- China
- Prior art keywords
- pheophytin
- remote sensing
- concentration
- decission
- model
- 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.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 232
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012549 training Methods 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 15
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 14
- 239000002253 acid Substances 0.000 claims description 12
- 238000002310 reflectometry Methods 0.000 claims description 12
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 10
- 238000000691 measurement method Methods 0.000 claims description 7
- 239000006228 supernatant Substances 0.000 claims description 7
- 238000002835 absorbance Methods 0.000 claims description 5
- 238000006731 degradation reaction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000002386 leaching Methods 0.000 claims description 4
- 238000011068 loading method Methods 0.000 claims description 4
- 238000002791 soaking Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 13
- 238000013461 design Methods 0.000 abstract description 6
- 230000009021 linear effect Effects 0.000 description 10
- 238000010521 absorption reaction Methods 0.000 description 9
- 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 description 8
- 230000000694 effects Effects 0.000 description 8
- 229930002875 chlorophyll Natural products 0.000 description 7
- 235000019804 chlorophyll Nutrition 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000031700 light absorption Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- JLVVSXFLKOJNIY-UHFFFAOYSA-N Magnesium ion Chemical compound [Mg+2] JLVVSXFLKOJNIY-UHFFFAOYSA-N 0.000 description 2
- LUTSRLYCMSCGCS-BWOMAWGNSA-N [(3s,8r,9s,10r,13s)-10,13-dimethyl-17-oxo-1,2,3,4,7,8,9,11,12,16-decahydrocyclopenta[a]phenanthren-3-yl] acetate Chemical compound C([C@@H]12)C[C@]3(C)C(=O)CC=C3[C@@H]1CC=C1[C@]2(C)CC[C@H](OC(=O)C)C1 LUTSRLYCMSCGCS-BWOMAWGNSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002378 acidificating effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- -1 hydrogen ions Chemical class 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 229910001425 magnesium ion Inorganic materials 0.000 description 2
- 230000009022 nonlinear effect Effects 0.000 description 2
- 150000004032 porphyrins Chemical group 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 241001465227 Chilena Species 0.000 description 1
- 241000195493 Cryptophyta Species 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229930002868 chlorophyll a Natural products 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011888 foil Substances 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000002798 spectrophotometry method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
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
- G01N21/55—Specular reflectivity
-
- 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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- 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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/314—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry with comparison of measurements at specific and non-specific wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/31—Programming languages or programming paradigms
- G06F8/315—Object-oriented languages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/35—Creation or generation of source code model driven
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Immunology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides an inland lake water pheophytin concentration remote sensing inversion model based on a Decission Tree algorithm, which is a Decission Tree model of Python language and further provides model parameters of the Decission Tree model. The remote sensing inversion method for the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is also provided. The remote sensing inversion model of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm can reduce the error of the calculated result, improve the accuracy of the inversion model of the pheophytin concentration of the water body, has ingenious design, simple and convenient calculation, is easy to realize, has low cost and is suitable for large-scale popularization and application.
Description
Technical Field
The invention relates to the technical field of inland lake water environment monitoring, in particular to the technical field of inland lake water pheophytin concentration measurement, and particularly relates to an inland lake water pheophytin concentration remote sensing inversion model and method based on a Decission Tree algorithm.
Background
Pheophytin refers to Pheophytin (Pheophytin) obtained by replacing magnesium ions in the center of porphyrin ring of chlorophyll molecule with two hydrogen ions under acidic condition, and is characterized by the chlorophyll content in inanimate state in water. It is generally considered that after the planktonic algae cells in the water body die, chlorophyll is free, the free chlorophyll is unstable and sensitive to light and heat, and magnesium ions in the center of porphyrin rings of chlorophyll molecules are replaced by two hydrogen ions under the acidic condition to be converted into pheophytin, and the higher the content is, the worse the water quality is. When the pheophytin content in the water body is higher, the absorption characteristics of phytoplankton are inevitably changed, and the important influence is brought to the identification of the biological optical information of the water body. It has been found that the presence of pheophytin shifts the blue light absorption peak of phytoplankton to short wavelengths, and the height of the absorption peak also varies due to the difference in absorption coefficients of pheophytin and chlorophyll a. Bricud et al found that the blue light absorption peak of some phytoplankton absorption curves was around 420nm and indicated to be caused by the effect of pheophytin (Bricud A, babin M, andre Morel, et al Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization [ J ]. Journal of Geophysical Research Oceans,1995,100); the shift of blue light absorption peaks to short wavelengths in phytoplankton absorption curves was also observed in Babin et al, stuart et al, and is believed to be the result of pheophytin removal (Bricud A, babin M, andre Morel, et al Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization [ J ]. Journal of Geophysical Research Oceans,1995,100;Stuart V,Ulloa O,Gadiel Alarc Mn, et al Bio-optical characteristics of phytoplankton populations in the upwelling system off the coast of Chile [ J ]. Revista Chilena de Historia Natural,2004,77 (1): 87-105). The investigation data of Dalianwan in 2007 also demonstrated that the presence of pheophytin resulted in a shift in the blue light absorption peak of the phytoplankton absorption curve from 440nm to 412nm (Wang Lin, zhao Dongzhi, xing Xiao, etc.. The effect of pheophytin on phytoplankton absorption properties [ J ]. Sea and lake, 2009,40 (5): 596-602).
In conclusion, the inversion of the pheophytin concentration is very important for the ecological environment protection and water quality management of inland lake water bodies. The inland water has complex optical characteristics and various components, and the rapid quantitative estimation of the pheophytin concentration in the inland lake water by using hyperspectral and multispectral remote sensing technologies becomes a difficulty.
At present, the work of remote sensing quantitative inversion of pheophytin concentration is developed, and the main method comprises the steps of establishing a single-band model, a band ratio model, a first-order differential model and the like of the pheophytin concentration based on a linear model, and constructing the linear model or constructing a linear equation by using the value of the pheophytin concentration.
The method mostly adopts characteristic wave band data in the process of constructing the pheophytin concentration inversion model. The inland lake water components and the optical characteristics are complex, and because of the superposition phenomenon and mutual influence of the respective characteristic wave bands of the complex water components, the characteristic wave band 'drift' phenomenon of pheophytin is caused, and the characteristic wave bands of pheophytin concentration in different water bodies cannot be accurately determined. In addition, when the model is built, most models are based on the linear effect (or generalized linear effect) between the characteristic wave band and the pheophytin concentration, and in the nature, not only a pure linear effect or generalized linear effect exists between the substance concentration and the characteristic wave band, but also a nonlinear effect exists, and the precision of the pheophytin concentration inversion model built only by using the linear effect needs to be further improved and perfected.
Therefore, it is desirable to provide an inland lake water pheophytin concentration remote sensing inversion model, which can reduce calculation result errors and improve the accuracy of the inversion model of the water pheophytin concentration.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide an inland lake water pheophytin concentration remote sensing inversion model based on a Decission Tree algorithm, which can reduce calculation result errors, improve the accuracy of the inversion model of the water pheophytin concentration and is suitable for large-scale popularization and application.
The invention further aims to provide an inland lake water body pheophytin concentration remote sensing inversion model based on a Decission Tree algorithm, which is ingenious in design, simple and convenient to calculate, easy to implement, low in cost and suitable for large-scale popularization and application.
The invention further aims to provide an inland lake water pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm, which can reduce calculation result errors, improves inversion accuracy of the water pheophytin concentration, and is suitable for large-scale popularization and application.
The invention further aims to provide an inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm, which is ingenious in design, simple and convenient to operate, low in cost and suitable for large-scale popularization and application.
In order to achieve the above objective, in a first aspect of the present invention, an inland lake water pheophytin concentration remote sensing inversion model based on a precision tree algorithm is provided, which is characterized in that the inland lake water pheophytin concentration remote sensing inversion model based on the precision tree algorithm is a precision tree model of Python language, and model parameters of the precision tree model are as follows: ' min_samples_leaf ' 1, ' max_leaf_nodes ' 386, ' split ', ' min_samples_split ' 2, ' min_weight_fraction_leaf ' 0.005488135039273248, ' max_depth ' 384, ' ccp_alpha ' 0.0004695476192547066, ' min_input_degradation ' 0.0002021839744032572, ' criterion ' mse ' and ' min_input_split ' 0.0007103605819788694, ' max_features ' auto ' and ' presort ' decrepitation '.
Preferably, the precision tree model is trained by adopting a data set of inland lake water, the data set comprises water remote sensing reflectance and pheophytin concentration of m sample points of the inland lake water, the m sample points are uniformly distributed on the inland lake water, and the water remote sensing reflectance is that of n characteristic wave bands.
More preferably, m is 32, n characteristic bands are 751 characteristic bands, and 751 characteristic bands are from 350nm band to 1100nm band.
In a second aspect of the invention, an inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm is provided, and is characterized by comprising the following steps:
(1) Measuring the water body remote sensing reflectance of the inland lake water body;
(2) Measuring the pheophytin concentration C of the inland lake water body Phaeo :
(3) Taking the water remote sensing reflectance as input data, calculating by adopting a precision tree model of Python language to obtain an inversion value, and calculating a determination coefficient R according to the inversion value and the pheophytin concentration 2 Changing the value of the model parameters of the Decission Tree model, R 2 The larger the change of the model parameters is, the larger the importance of the model parameters is, and the model parameters are arranged from big to small according to the importance to construct a model parameter tuning rank matrix;
(4) Training the Decission Tree model by taking the water remote sensing reflectance as the input data and the pheophytin concentration as the output result, and sequentially tuning the model parameters according to the model parameter tuning rank order matrix to obtain tuning values of the model parameters;
(5) And training the Decission Tree model by taking the water body remote sensing reflectance as the input data and the pheophytin concentration as the output result and adopting the optimal value of the model parameter, obtaining an inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm after the Decission Tree model is trained, storing the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a save method, and loading the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a load method if the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm is needed.
Preferably, in the step (1), the step of measuring the remote sensing reflectance of the inland lake water body specifically includes:
measuring water spectrum data L of inland lake water sw Sky diffuse scattered light L of inland lake water body sky Reflected light L of standard plate p Calculating the remote sensing reflectance of the water body:
Rrs=(L sw -r sky *L sky )/(L p *π/ρ p ),
wherein Rrs is the water remote sensing reflectance; r is (r) sky The reflectivity of the air surface of the inland lake water body is 0.022 to 0.028, and r is the value when the inland lake water body is on calm water surface sky Take the value of 0.022, r at the wind speed of 5m/s sky The value is 0.025, and the value is 0.026-0.028 at the wind speed of 10m/s, ρ p Is the reflectivity of the standard plate.
More preferably, in the step (1), the measurement is performed by using a portable ground object spectrometer, the portable ground object spectrometer uses a lens with a field angle of 25 °, the measurement is performed by using a measurement method above the water surface, and the observation geometry of the measurement method above the water surface is set as follows: phi (phi) v =135°, v=40°, the standard plate being a standard white plate with a reflectivity of 10%.
Preferably, in the step (2), the pheophytin concentration C of the inland lake water body is measured Phaeo The method specifically comprises the following steps:
collecting a water sample of the inland lake water body, filtering the water sample by adopting filter paper to obtain a filter paper sample, extracting the filter paper sample by adopting a pheophytin extraction solution, centrifuging, taking a supernatant, adding acid for treatment, and measuring absorbance A of the supernatant at 665nm and 750nm 665 And A 750 Calculating the pheophytin concentration C of the inland lake water body by using the following formula Phaeo :
C Phaeo =27.9*(A 665 -A 750 )*V 1 /V 2 ,
Wherein V is 1 Is the volume of the pheophytin extraction solution, V 2 Is the volume of the water sample.
More preferably, in the step (2), the filter paper is Whatman GF/F filter paper, the pheophytin extraction solution is 90% ethanol, the extraction is soaking and leaching for 8 hours at 4 ℃ in dark, the acid is 1mol/L hydrochloric acid solution, the adding amount of the hydrochloric acid solution is 1-2 drops, and the acid adding treatment time is 1 minute.
Preferably, in the step (3), the model parameter tuning rank order matrix is:
Params={'min_samples_leaf','max_leaf_nodes','splitter','min_samples_split','min_weight_fraction_leaf','max_depth','ccp_alpha','min_impurity_decrease','criterion','min_impurity_split','max_features','presort'}。
more preferably, in the step (4), the tuning value of the model parameter is:
'min_samples_leaf':1,'max_leaf_nodes':386,'splitter':'random','min_samples_split':2,'min_weight_fraction_leaf':0.005488135039273248,'max_depth':384,'ccp_alpha':0.0004695476192547066,'min_impurity_decrease':0.0002021839744032572,'criterion':'mse','min_impurity_split':0.0007103605819788694,'max_features':'auto','presort':'deprecated'。
preferably, in the step (1), the step of measuring the water remote sensing reflectance of the inland lake water body is specifically to measure the water remote sensing reflectance of m samples of the inland lake water body,the m sample points are uniformly distributed on the inland lake water body, and the water body remote sensing reflectance is of n characteristic wave bands; in the step (2), the pheophytin concentration C of the inland lake water body is measured Phaeo Specifically, the pheophytin concentration C of the m sample points is measured Phaeo 。
More preferably, in the step (1), m is 32, the n characteristic bands are 751 characteristic bands, and the 751 characteristic bands are from 350nm band to 1100nm band.
The beneficial effects of the invention are mainly as follows:
1. the remote sensing inversion model of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is a Decission Tree model of Python language, and model parameters of the Decission Tree model are as follows: the model was checked for R by ' min_samples_leaf ' 1, ' max_leaf_nodes ' 386, ' split ', ' min_samples_split ' 2, ' min_weight_fraction_leaf ' 0.005488135039273248, ' max_depth ' 384, ' ccp_alpha ' 0.0004695476192547066, ' min_input_degradation ' 0.0002021839744032572, ' criterion ' mse ' and ' min_input_split ' 0.0007103605819788694, ' max_features ' auto ' and ' presort ' decreed ' and R 2 The method is above 0.85, so that the calculation result error can be reduced, the accuracy of an inversion model of the pheophytin concentration of the water body is improved, and the method is suitable for large-scale popularization and application.
2. The remote sensing inversion model of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is a Decission Tree model of Python language, and model parameters of the Decission Tree model are as follows: the model was checked for R by ' min_samples_leaf ' 1, ' max_leaf_nodes ' 386, ' split ', ' min_samples_split ' 2, ' min_weight_fraction_leaf ' 0.005488135039273248, ' max_depth ' 384, ' ccp_alpha ' 0.0004695476192547066, ' min_input_degradation ' 0.0002021839744032572, ' criterion ' mse ' and ' min_input_split ' 0.0007103605819788694, ' max_features ' auto ' and ' presort ' decreed ' and R 2 Above 0.85, therefore, the method has the advantages of ingenious design, simple and convenient calculation, easy realization and low cost, and is suitable for large-scale popularization and application.
3. The invention discloses an inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm, which comprises the following steps: measuring the water body remote sensing reflectance of the inland lake water body; measurement of pheophytin concentration C in inland lake Water Phaeo : the remote sensing reflectance of water body is used as input data, and a precision tree model of Python language is adopted for calculation to determine a coefficient R 2 Constructing a model parameter tuning rank matrix; training a Decission Tree model by taking the remote sensing reflectance of the water body as input data and the pheophytin concentration as output result, and sequentially adjusting and optimizing the model parameters according to the model parameter adjusting and optimizing rank matrix to obtain an adjusting and optimizing value of the model parameters; taking the water body remote sensing reflectance as input data, taking the pheophytin concentration as output result, training a Decission Tree model by adopting the tuning value of model parameters to obtain an inland lake water body pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm, checking the model, and R 2 The method is above 0.85, so that the method can reduce calculation result errors, improve inversion accuracy of the pheophytin concentration of the water body, and is suitable for large-scale popularization and application.
4. The invention discloses an inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm, which comprises the following steps: measuring the water body remote sensing reflectance of the inland lake water body; measurement of pheophytin concentration C in inland lake Water Phaeo : the remote sensing reflectance of water body is used as input data, and a precision tree model of Python language is adopted for calculation to determine a coefficient R 2 Constructing a model parameter tuning rank matrix; training a Decission Tree model by taking the remote sensing reflectance of the water body as input data and the pheophytin concentration as output result, and sequentially adjusting and optimizing the model parameters according to the model parameter adjusting and optimizing rank matrix to obtain an adjusting and optimizing value of the model parameters; taking the water body remote sensing reflectance as input data, taking the pheophytin concentration as output result, training a Decission Tree model by adopting the tuning value of model parameters to obtain an inland lake water body pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm, checking the model, and R 2 Above 0.85, so that the design is ingenious, the operation is simple and convenient, and the product is finishedThe method is low in cost and suitable for large-scale popularization and application.
These and other objects, features and advantages of the present invention will become more fully apparent from the following detailed description, the accompanying drawings and the claims, and may be learned by the practice of the invention as set forth hereinafter, the apparatus and the combination thereof as set forth hereinafter.
Drawings
Fig. 1 is a schematic flow chart of a specific embodiment of an inland lake water body pheophytin concentration remote sensing inversion method based on a precision tree algorithm.
Fig. 2 is a schematic view of the above-water observation geometry of the spectrometer of the embodiment shown in fig. 1.
FIG. 3 is a schematic diagram of a model building flow for the embodiment shown in FIG. 1.
FIG. 4 is a schematic diagram of the model test results for the embodiment shown in FIG. 1, wherein the units of predicted and measured values are μg/L.
Detailed Description
Aiming at the defects of the existing pheophytin concentration inversion model, the inventor provides an inland lake water pheophytin concentration remote sensing inversion model based on a Decission Tree algorithm, wherein the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm is a Decission Tree model of Python language, and model parameters of the Decission Tree model are as follows: ' min_samples_leaf ' 1, ' max_leaf_nodes ' 386, ' split ', ' min_samples_split ' 2, ' min_weight_fraction_leaf ' 0.005488135039273248, ' max_depth ' 384, ' ccp_alpha ' 0.0004695476192547066, ' min_input_degradation ' 0.0002021839744032572, ' criterion ' mse ' and ' min_input_split ' 0.0007103605819788694, ' max_features ' auto ' and ' presort ' decrepitation '.
The precision tree model can be trained by adopting any suitable data set, preferably, the precision tree model is trained by adopting a data set of inland lake water, the data set comprises water remote sensing reflectance and pheophytin concentration of m sample points of the inland lake water, the m sample points are uniformly distributed on the inland lake water, and the water remote sensing reflectance is water remote sensing reflectance of n characteristic wave bands.
The m and the n are positive integers, and can be determined according to the need, more preferably, the m is 32, the n characteristic wave bands are 751 characteristic wave bands, and the 751 characteristic wave bands are from 350nm wave bands to 1100nm wave bands.
The invention also provides an inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm, which comprises the following steps:
(1) Measuring the water body remote sensing reflectance of the inland lake water body;
(2) Measuring the pheophytin concentration C of the inland lake water body Phaeo :
(3) Taking the water remote sensing reflectance as input data, calculating by adopting a precision tree model of Python language to obtain an inversion value, and calculating a determination coefficient R according to the inversion value and the pheophytin concentration 2 Changing the value of the model parameters of the Decission Tree model, R 2 The larger the change of the model parameters is, the larger the importance of the model parameters is, and the model parameters are arranged from big to small according to the importance to construct a model parameter tuning rank matrix;
(4) Training the Decission Tree model by taking the water remote sensing reflectance as the input data and the pheophytin concentration as the output result, and sequentially tuning the model parameters according to the model parameter tuning rank order matrix to obtain tuning values of the model parameters;
(5) And training the Decission Tree model by taking the water body remote sensing reflectance as the input data and the pheophytin concentration as the output result and adopting the optimal value of the model parameter, obtaining an inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm after the Decission Tree model is trained, storing the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a save method, and loading the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a load method if the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm is needed.
In the step (1), the step of measuring the remote sensing reflectance of the inland lake water body may specifically include any suitable method, and preferably, in the step (1), the step of measuring the remote sensing reflectance of the inland lake water body specifically includes:
measuring water spectrum data L of inland lake water sw Sky diffuse scattered light L of inland lake water body sky Reflected light L of standard plate p Calculating the remote sensing reflectance of the water body:
Rrs=(L sw -r sky *L sky )/(L p *π/ρ p ),
wherein Rrs is the water remote sensing reflectance; r is (r) sky The reflectivity of the air surface of the inland lake water body is 0.022 to 0.028, and r is the value when the inland lake water body is on calm water surface sky Take the value of 0.022, r at the wind speed of 5m/s sky The value is 0.025, and the value is 0.026-0.028 at the wind speed of 10m/s, ρ p Is the reflectivity of the standard plate.
In the step (1), the measurement may be performed by using any suitable spectrometer, the measurement may be performed by using any suitable standard board, and more preferably, in the step (1), the measurement is performed by using a portable ground object spectrometer, the portable ground object spectrometer uses a lens with an angle of view of 25 °, the measurement is performed by using a measurement method above the water surface, and the observation geometry of the measurement method above the water surface is set as follows: phi (phi) v =135°, v=40°, the standard plate being a standard white plate with a reflectivity of 10%.
In the step (2), the pheophytin concentration C of the inland lake water body is measured Phaeo The step (2) of measuring pheophytin in the inland lake water body may specifically comprise any suitable method, preferablyConcentration C Phaeo The method specifically comprises the following steps:
collecting a water sample of the inland lake water body, filtering the water sample by adopting filter paper to obtain a filter paper sample, extracting the filter paper sample by adopting a pheophytin extraction solution, centrifuging, taking a supernatant, adding acid for treatment, and measuring absorbance A of the supernatant at 665nm and 750nm 665 And A 750 Calculating the pheophytin concentration C of the inland lake water body by using the following formula Phaeo :
C Phaeo =27.9*(A 665 -A 750 )*V 1 /V 2 ,
Wherein V is 1 Is the volume of the pheophytin extraction solution, V 2 Is the volume of the water sample.
In the step (2), the filter paper may be any suitable filter paper, the pheophytin extraction solution may be any suitable pheophytin extraction solution, the acid may be any suitable acid, more preferably, in the step (2), the filter paper is Whatman GF/F filter paper, the pheophytin extraction solution is 90% ethanol, the extraction is soaking and leaching for 8 hours at 4 ℃ in the dark, the acid is 1mol/L hydrochloric acid solution, the addition amount of the hydrochloric acid solution is 1 to 2 drops, and the acid adding treatment time is 1 minute.
In the step (3), the model parameter tuning rank order matrix is based on a decision coefficient R 2 Determining, preferably, in the step (3), the model parameter tuning rank matrix is:
Params={'min_samples_leaf','max_leaf_nodes','splitter','min_samples_split','min_weight_fraction_leaf','max_depth','ccp_alpha','min_impurity_decrease','criterion','min_impurity_split','max_features','presort'}。
in the step (4), the tuning values of the model parameters are sequentially determined according to the model parameter tuning rank matrix, and more preferably, in the step (4), the tuning values of the model parameters are:
'min_samples_leaf':1,'max_leaf_nodes':386,'splitter':'random','min_samples_split':2,'min_weight_fraction_leaf':0.005488135039273248,'max_depth':384,'ccp_alpha':0.0004695476192547066,'min_impurity_decrease':0.0002021839744032572,'criterion':'mse','min_impurity_split':0.0007103605819788694,'max_features':'auto','presort':'deprecated'。
in order to make the accuracy of the remote sensing inversion model of the inland lake water body pheophytin concentration based on the precision tree algorithm higher, a plurality of sample points of the inland lake water body can be selected, and the remote sensing reflectance of the water body of a plurality of characteristic wave bands and the pheophytin concentration of the plurality of sample points are measured, preferably, in the step (1), the step of measuring the remote sensing reflectance of the water body of the inland lake water body is specifically to measure the remote sensing reflectance of the water body of m sample points of the inland lake water body, and m sample points are uniformly distributed on the inland lake water body, and the remote sensing reflectance of the water body is the remote sensing reflectance of the water body of n characteristic wave bands; in the step (2), the pheophytin concentration C of the inland lake water body is measured Phaeo Specifically, the pheophytin concentration C of the m sample points is measured Phaeo 。
In the step (1), the m and the n are positive integers, which can be determined according to need, more preferably, in the step (1), the m is 32, the n characteristic wave bands are 751 characteristic wave bands, and the 751 characteristic wave bands are from 350nm wave bands to 1100nm wave bands.
The invention will be further illustrated with reference to specific examples. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention.
Examples
The remote sensing inversion method of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm of the embodiment is based on actual measurement hyperspectral data, adopts the water body optical characteristics and the water body component information collected by the Hongze lake, and has 43 sampling points which are uniformly distributed and completely cover the whole lake area of the Hongze lake. The Hongze lake is one of five large freshwater lakes in China, the average water depth is 5.62m, the re-suspension of the lake bottom sediment is greatly influenced by the wind and the wave on the lake surface, belongs to a high-turbidity water body, and is a typical inland second-class water body. The 43 sampling point data are divided into two parts by adopting a random method, wherein the 32 sampling point data are used for model construction, and the 11 sampling point data are used for model inspection. The flow of the remote sensing inversion method of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is shown in a figure 1, and the method comprises the following steps:
1. and (5) measuring the spectrum of the water body.
And measuring the spectrum of the water body by using a portable ground object spectrometer and a standard plate, and obtaining the remote sensing reflectance Rrs. The observation geometry is shown in fig. 2 by adopting a measurement method above the water surface, and the typical observation geometry is adopted at present: Φv=135°, v=40°. In measuring the spectrum of a body of water, a single integral value of the spectrum is recorded, without taking an average value, and a plurality of spectral values, for example 15 tests, are recorded, the measurement time spanning the wave period (measurement time 2-5 minutes). The spectrometer uses a lens with a field angle of 25 deg. and a standard white board with a reflectivity of 10%. And respectively measuring water spectrum data of 350nm wave bands to 1100nm wave bands, sky diffuse scattered light and reflected light of a standard plate, and calculating a water remote sensing reflectance Rrs:
Rrs=(L sw -r sky *L sky )/(L p *π/ρ p )
wherein Rrs is water remote sensing reflectance, L sw For the water spectrum data measured by the spectrometer, r sky For the reflectivity of the air-water surface, the value of the present case is 0.0245L sky Is diffuse scattered light of sky L p Is the reflection light of the standard plate, ρ p The reflectance of the standard plate used in this example was 10%.
2. And (5) measuring the concentration of pheophytin in the water body.
When the spectral data of the water body are measured, the water sample is synchronously collected, whatman GF/F filter paper is used for filtering, the filter paper after the filtering is folded in half, and the filter paper is put into aluminum foil paper for packaging, and is frozen and stored in a refrigerator at the temperature of minus 20 ℃. Extracting a filter paper sample by using a 90% hot ethanol solution at 75 ℃, soaking and leaching for 8 hours at 4 ℃ in a dark place, centrifuging, taking supernatant, adding 1-2 drops of 1mol/L hydrochloric acid solution by using a common rubber head suction pipe, and using 722 spectrophotometry after 1 minuteMeter measurements, recording absorbance A at 665nm and 750nm 665 And A 750 The pheophytin concentration was calculated using the formula:
C Phaeo =27.9*(A 665 -A 750 )*V 1 /V 2 ,
wherein C is Phaeo Concentration of pheophytin (ug/L), A 665 、A 750 Absorbance at 665 and 750nm after acid addition, V 1 Is the volume (ml) of 90% hot ethanol solution, V 2 Is the volume (L) of the water sample.
3. Model construction
The model construction is performed by adopting a Decission Tree model of Python language, and please refer to FIG. 3, the model construction mainly comprises the following steps:
3.1 data verification
And checking the acquired water remote sensing reflectance data, and eliminating abnormal whole spectrum curve data. The abnormal spectrum in the invention refers to a spectrum value with a variation of more than 100% between adjacent spectrums and comprises a null value and a negative value.
3.2 preprocessing of data
And preprocessing the checked water body remote sensing reflectance data and the pheophytin concentration data, wherein the preprocessing comprises removing the paired water body remote sensing reflectance data and the pheophytin concentration data containing the missing value and the null value.
3.3 partitioning of data sets
To ensure reasonable evaluation of the model training and inversion results, a random method was used to divide the entire dataset into two parts, 75% of the data was used for model training and 25% of the data was used for effect evaluation after training. In this embodiment, data of 32 sampling points are used for model training, and data of 11 sampling points are used for model effect evaluation.
3.4 partitioning of training data sets
To ensure the model training effect, a random method is used, and the training data set is divided into 5 parts during each model training iteration, so that the model is trained.
3.5 construction of parameter tuning rank order matrix of model
In the invention, the tuning of model parameters in the model training process is very important, and in order to ensure that the best model tuning is obtained as much as possible, a trial-and-error method is used for model parameter tuning. The invention uses the decision coefficient R 2 (R 2 The closer to 1 the better) as a test parameter, a parameter rank matrix for evaluating the model parameter weights is constructed. Firstly, calculating by using a default value of a model parameter according to a training data set to obtain an inversion value, and calculating a decision coefficient R according to the inversion value and the pheophytin concentration 2 Then changing the value of the model parameters, R 2 The larger the variation of the model parameters is, the larger the importance of the model parameters is, and the model parameters are arranged according to the importance from large to small to construct a model parameter tuning rank order matrix for subsequent calculation.
According to the water remote sensing reflectance data and the corresponding pheophytin concentration data in the training data set, the calculated model parameter tuning rank order matrix is as follows:
Params={'min_samples_leaf','max_leaf_nodes','splitter','min_samples_split','min_weight_fraction_leaf','max_depth','ccp_alpha','min_impurity_decrease','criterion','min_impurity_split','max_features','presort'}。
wherein presort changes do not cause changes in the accuracy of the model.
3.6 model construction
According to the obtained model parameter tuning rank matrix, modeling data comprising actually measured water remote sensing reflectance data and corresponding actually measured pheophytin concentration data, taking the actually measured water remote sensing reflectance data as input data, taking the actually measured pheophytin concentration data as output result, training a precision model, and sequentially tuning model parameters according to the model parameter tuning rank matrix to obtain complete parameters and values of the model, wherein the method comprises the following steps:
'min_samples_leaf':1,'max_leaf_nodes':386,'splitter':'random','min_samples_split':2,'min_weight_fraction_leaf':0.005488135039273248,'max_depth':384,'ccp_alpha':0.0004695476192547066,'min_impurity_decrease':0.0002021839744032572,'criterion':'mse','min_impurity_split':0.0007103605819788694,'max_features':'auto','presort':'deprecated'。
after model training is finished, the save method is used for storing the model, and if the model is needed, the load method is operated for loading and using.
3.7 model inspection
Inputting hyperspectral data of 11 sampling points outside the constructed model into the model, calculating by using the model parameters after tuning to obtain a predicted value, analyzing the relation between the predicted value and an actual measured value (pheophytin concentration), and obtaining the R of the model as shown in figure 4 2 = 0.9095, using the default parameters of the model, R 2 Only 0.2807.
The random partitioning of the training data and the test data and the construction, training and testing of the model used Matlab software (version: R2020a 9.8.0.1380330) and Python (version: 3.7.0) developed by MathWorks corporation, U.S. and called the Python's Decission Tree model by Matlab software.
Therefore, the invention provides a novel remote sensing inversion model of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm based on the measured hyperspectral remote sensing data, which can overcome the phenomenon of drift caused by the influence of factors such as complex optical characteristics of the inland turbid water body, complex components such as suspended matters, colored soluble organic matters and the like in the water body on the characteristic wave band of the pheophytin concentration based on the measured water body spectrum data and the pheophytin concentration data acquired in the field, fully utilizes the pheophytin concentration information contained in the wave band data, and improves the inversion model precision of the pheophytin concentration of the inland lake.
Compared with the prior art, the invention has the following advantages:
(1) The invention is based on the measured full-band data of the hyperspectral remote sensing data of the water body, fully utilizes the complete pheophytin concentration information contained in the hyperspectral data, and avoids the influence on the characteristic wave band of the pheophytin concentration caused by complex water body components of inland lakes, such as the phenomenon of drift of the pheophytin characteristic wave band caused by superposition of the respective characteristic wave bands of the complex water body components;
(2) The invention fully considers various effects between the pheophytin concentration and the characteristic wave band thereof, uses a Decision Tree (DT) model, avoids the limitation of using a linear or exponential model in the previous research work, comprehensively considers the linear effect and the nonlinear effect between the remote sensing reflectivity and the pheophytin concentration of the water body, and improves the precision of the inversion of the pheophytin concentration.
(3) The pheophytin concentration inversion method provided by the invention is simple and convenient to calculate, and is suitable for remote sensing quantitative inversion of pheophytin concentrations of inland lakes in different areas and different seasons.
(4) The invention fully considers the independence of model training and model checking, uses a random segmentation method to divide the training data set and the checking data set, wherein the training data set is only used for model training, and the checking data set is only used for model checking, so as to ensure the rationality of model effect checking.
(5) Since the parameter tuning of the model is very important to the calculation accuracy of the model, a model parameter rank order matrix is constructed in the invention to determine the coefficient R 2 In order to evaluate parameters, a trial-and-error method is used for model parameter tuning, and on the basis of guaranteeing the parameter tuning effect, the speed of model training and parameter tuning is greatly improved.
In conclusion, the remote sensing inversion model of the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm can reduce the error of the calculation result, improve the accuracy of the inversion model of the pheophytin concentration of the water body, has ingenious design, simple and convenient calculation, is easy to realize, has low cost and is suitable for large-scale popularization and application.
It will thus be seen that the objects of the present invention have been fully and effectively attained. The functional and structural principles of the present invention have been shown and described in the examples and embodiments may be modified at will without departing from such principles. Therefore, this invention includes all modifications encompassed within the spirit of the following claims and the scope of the following claims.
Claims (12)
1. The remote sensing inversion model for the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is characterized in that the remote sensing inversion model for the pheophytin concentration of the inland lake water body based on the Decission Tree algorithm is a Decission Tree model of Python language, and model parameters of the Decission Tree model are as follows: ' min_samples_leaf ' 1, ' max_leaf_nodes ' 386, ' split ', ' min_samples_split ' 2, ' min_weight_fraction_leaf ' 0.005488135039273248, ' max_depth ' 384, ' ccp_alpha ' 0.0004695476192547066, ' min_input_degradation ' 0.0002021839744032572, ' criterion ' mse ' and ' min_input_split ' 0.0007103605819788694, ' max_features ' auto ' and ' presort ' decrepitation '.
2. The inland lake water body pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm of claim 1, wherein the Decission Tree model is trained by adopting a data set of inland lake water bodies, the data set comprises water body remote sensing reflectance and pheophytin concentration of m sample points of the inland lake water bodies, the m sample points are uniformly distributed on the inland lake water bodies, and the water body remote sensing reflectance is of water body remote sensing reflectance of n characteristic wave bands.
3. The inland lake water body pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm as claimed in claim 2, wherein m is 32, n characteristic wave bands are 751 characteristic wave bands, and 751 characteristic wave bands are from 350nm wave bands to 1100nm wave bands.
4. An inland lake water body pheophytin concentration remote sensing inversion method based on a Decission Tree algorithm is characterized by comprising the following steps of:
(1) Measuring the water body remote sensing reflectance of the inland lake water body;
(2) Measuring the pheophytin concentration C of the inland lake water body Phaeo :
(3) Taking the water remote sensing reflectance as input data, calculating by adopting a precision tree model of Python language to obtain an inversion value, and according to the inversion value and the inversion valueThe pheophytin concentration calculating and determining coefficient R 2 Changing the value of the model parameters of the Decission Tree model, R 2 The larger the change of the model parameters is, the larger the importance of the model parameters is, and the model parameters are arranged from big to small according to the importance to construct a model parameter tuning rank matrix;
(4) Training the Decission Tree model by taking the water remote sensing reflectance as the input data and the pheophytin concentration as the output result, and sequentially tuning the model parameters according to the model parameter tuning rank order matrix to obtain tuning values of the model parameters;
(5) And training the Decission Tree model by taking the water body remote sensing reflectance as the input data and the pheophytin concentration as the output result and adopting the optimal value of the model parameter, obtaining an inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm after the Decission Tree model is trained, storing the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a save method, and loading the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm by using a load method if the inland lake water pheophytin concentration remote sensing inversion model based on the Decission Tree algorithm is needed.
5. The remote sensing inversion method of the pheophytin concentration of inland lake water based on the Decission Tree algorithm as set forth in claim 4, wherein in the step (1), the step of measuring the remote sensing reflectance of the inland lake water specifically includes:
measuring water spectrum data L of inland lake water sw Sky diffuse scattered light L of inland lake water body sky Reflected light L of standard plate p Calculating the remote sensing reflectance of the water body:
Rrs=(L sw -r sky *L sky )/(L p *π/ρ p ),
wherein Rrs is the water remote sensing reflectance; r is (r) sky The reflectivity of the air surface of the inland lake water body is 0.022 to 0.028, and r is the value when the inland lake water body is on calm water surface sky Take the value of 0.022, r at the wind speed of 5m/s sky The value is 0.025, and the value is 0.026-0.028 at the wind speed of 10m/s, ρ p Is the reflectivity of the standard plate.
6. The remote sensing inversion method of the pheophytin concentration of inland lake water body based on the Decission Tree algorithm according to claim 5, wherein in the step (1), the measurement is performed by using a portable ground object spectrometer, the portable ground object spectrometer uses a lens with a field angle of 25 degrees, the measurement uses a measurement method above the water surface, and the observation geometry of the measurement method above the water surface is set as follows: phi (phi) v =135°, v=40°, the standard plate being a standard white plate with a reflectivity of 10%.
7. The remote sensing inversion method of pheophytin concentration in inland lake water based on Decission Tree algorithm as claimed in claim 4, wherein in said step (2), said pheophytin concentration C in said inland lake water is measured Phaeo The method specifically comprises the following steps:
collecting a water sample of the inland lake water body, filtering the water sample by adopting filter paper to obtain a filter paper sample, extracting the filter paper sample by adopting a pheophytin extraction solution, centrifuging, taking a supernatant, adding acid for treatment, and measuring absorbance A of the supernatant at 665nm and 750nm 665 And A 750 Calculating the pheophytin concentration C of the inland lake water body by using the following formula Phaeo :
C Phaeo =27.9*(A 665 -A 750 )*V 1 /V 2 ,
Wherein V is 1 Is the volume of the pheophytin extraction solution, V 2 Is the volume of the water sample.
8. The remote sensing inversion method of the pheophytin concentration of inland lake water body based on the Decission Tree algorithm according to claim 7, wherein in the step (2), the filter paper is Whatman GF/F filter paper, the pheophytin extraction solution is 90% ethanol, the extraction is light-shielding soaking and leaching at 4 ℃ for 8 hours, the acid is 1mol/L hydrochloric acid solution, the adding amount of the hydrochloric acid solution is 1-2 drops, and the acid adding treatment time is 1 minute.
9. The remote sensing inversion method of the pheophytin concentration of inland lake water based on the Decission Tree algorithm as claimed in claim 4, wherein in the step (3), the model parameter tuning rank order matrix is:
Params={'min_samples_leaf','max_leaf_nodes','splitter','min_samples_split','min_weight_fraction_leaf','max_depth','ccp_alpha','min_impurity_decrease','criterion','min_impurity_split','max_features','presort'}。
10. the remote sensing inversion method of the pheophytin concentration of inland lake water based on the Decission Tree algorithm as claimed in claim 9, wherein in the step (4), the optimal values of the model parameters are:
'min_samples_leaf':1,'max_leaf_nodes':386,'splitter':'random','min_samples_split':2,'min_weight_fraction_leaf':0.005488135039273248,'max_depth':384,'ccp_alpha':0.0004695476192547066,'min_impurity_decrease':0.0002021839744032572,'criterion':'mse','min_impurity_split':0.0007103605819788694,'max_features':'auto','presort':'deprecated'。
11. the remote sensing inversion method for pheophytin concentration in inland lake water based on Decission Tree algorithm as claimed in claim 4, wherein in said step (1), said step of measuring water remote sensing reflectance of inland lake water is specifically to measure said water remote sensing reflectance of m samples of said inland lake water, m samples are uniformly distributed on said inland lake water, said water remote sensing reflectance is a water remote sensing reflectance of n characteristic wave bandsReflectance; in the step (2), the pheophytin concentration C of the inland lake water body is measured Phaeo Specifically, the pheophytin concentration C of the m sample points is measured Phaeo 。
12. The remote sensing inversion method of the pheophytin concentration of inland lake water body based on the Decission Tree algorithm as claimed in claim 11, wherein in the step (1), m is 32, the n characteristic wave bands are 751 characteristic wave bands, and the 751 characteristic wave bands are from 350nm wave bands to 1100nm wave bands.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011163340.8A CN117434010A (en) | 2020-10-27 | 2020-10-27 | Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011163340.8A CN117434010A (en) | 2020-10-27 | 2020-10-27 | Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117434010A true CN117434010A (en) | 2024-01-23 |
Family
ID=89552126
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011163340.8A Pending CN117434010A (en) | 2020-10-27 | 2020-10-27 | Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117434010A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409441A (en) * | 2018-11-16 | 2019-03-01 | 福州大学 | Based on the coastal waters chlorophyll-a concentration remote sensing inversion method for improving random forest |
CN110598251A (en) * | 2019-08-05 | 2019-12-20 | 中国科学院南京地理与湖泊研究所 | Lake chlorophyll a concentration inversion method based on Landsat-8 data and machine learning |
-
2020
- 2020-10-27 CN CN202011163340.8A patent/CN117434010A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409441A (en) * | 2018-11-16 | 2019-03-01 | 福州大学 | Based on the coastal waters chlorophyll-a concentration remote sensing inversion method for improving random forest |
CN110598251A (en) * | 2019-08-05 | 2019-12-20 | 中国科学院南京地理与湖泊研究所 | Lake chlorophyll a concentration inversion method based on Landsat-8 data and machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111855600A (en) | Remote sensing inversion model and method for CDOM (spectral absorption coefficient) of inland lake water body | |
CN112070234B (en) | Water chlorophyll and phycocyanin land-based remote sensing machine learning algorithm under complex scene | |
Gallego et al. | Rapid measurement of phenolics compounds in red wine using Raman spectroscopy | |
CN105445218B (en) | The method for building up of middle infrared spectrum rapeseed protein content detection adaptive model | |
Yue et al. | A smart data-driven rapid method to recognize the strawberry maturity | |
CN105486655A (en) | Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model | |
CN111239071A (en) | Method for detecting concentration of nitrate in seawater by spectrometry | |
CN109324000A (en) | Kuerle delicious pear soluble solids content prediction technique based on CARS-MIV-SVR | |
CN111781147A (en) | Remote sensing inversion model and method for chlorophyll a concentration of inland lake water body based on two wave bands | |
CN111855608A (en) | Near-infrared nondestructive detection method for apple acidity based on fusion characteristic wavelength selection algorithm | |
CN114216877B (en) | Automatic detection and reconstruction method and system for spectral peak in tea near infrared spectral analysis | |
CN115420726A (en) | Method for rapidly identifying target object by using reconstructed SERS spectrum | |
CN117434010A (en) | Inland lake water body pheophytin concentration remote sensing inversion model and method based on Decission Tree algorithm | |
CN108007917B (en) | Method for establishing Raman spectrum measurement model of nitrogen content in rice plant by Hilbert method | |
CN112362812A (en) | Remote sensing inversion model and method for rice leaf chlorophyll carotenoid content ratio based on Lars algorithm | |
CN115950871B (en) | Method, device, system and equipment for detecting content of polyhydroxyalkanoate | |
CN116310788A (en) | Plant leaf nitrogen content hyperspectral modeling method based on map fusion | |
Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves | |
CN117434011A (en) | Inland lake water chlorophyll a concentration remote sensing inversion model and method based on linear SVR algorithm | |
CN115656063A (en) | Target pollutant content analysis method and device based on hyperspectral data | |
CN112949038B (en) | Method for calculating specific absorption coefficients of different phytoplankton populations in ocean water | |
CN111855601A (en) | Remote sensing inversion model and method for chlorophyll a concentration of inland lake water body | |
CN117434009A (en) | Inland lake water body phycocyanin concentration remote sensing inversion model and method based on gradient lifting algorithm | |
CN105651727B (en) | The method that near-infrared spectrum analysis based on JADE and ELM differentiates apple shelf life | |
CN113933247A (en) | Construction method of fruit maturity detection model |
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 |