CN117309780A - Method for determining content of germanium element in soil - Google Patents
Method for determining content of germanium element in soil Download PDFInfo
- Publication number
- CN117309780A CN117309780A CN202311595170.4A CN202311595170A CN117309780A CN 117309780 A CN117309780 A CN 117309780A CN 202311595170 A CN202311595170 A CN 202311595170A CN 117309780 A CN117309780 A CN 117309780A
- Authority
- CN
- China
- Prior art keywords
- soil
- germanium element
- determining
- element content
- content
- 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.)
- Granted
Links
- 239000002689 soil Substances 0.000 title claims abstract description 176
- 229910052732 germanium Inorganic materials 0.000 title claims abstract description 143
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical compound [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005070 sampling Methods 0.000 claims abstract description 64
- 238000001228 spectrum Methods 0.000 claims abstract description 51
- 230000003595 spectral effect Effects 0.000 claims abstract description 42
- 230000000875 corresponding effect Effects 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 14
- 238000002310 reflectometry Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 12
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000012937 correction Methods 0.000 description 15
- 238000011160 research Methods 0.000 description 14
- 238000007637 random forest analysis Methods 0.000 description 13
- 238000003066 decision tree Methods 0.000 description 8
- 230000005855 radiation Effects 0.000 description 7
- 238000010219 correlation analysis Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 229910018072 Al 2 O 3 Inorganic materials 0.000 description 3
- 229910004298 SiO 2 Inorganic materials 0.000 description 3
- 239000005416 organic matter Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005341 cation exchange Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 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
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Immunology (AREA)
- Mathematical Physics (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Medical Informatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Databases & Information Systems (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Food Science & Technology (AREA)
- Computational Linguistics (AREA)
- Medicinal Chemistry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The embodiment of the invention relates to the technical field of soil element content measurement, in particular to a method for determining the content of soil germanium element, which comprises the following steps: acquiring hyperspectral data of a region to be detected; acquiring spectrum data at a plurality of sampling points in a region to be detected, and the germanium element content of soil and a plurality of soil indexes; according to the spectrum data of the sampling points, a plurality of soil indexes and the content of germanium elements, determining soil index influence factors related to the content of the germanium elements in the soil indexes and characteristic wave bands related to the content of the germanium elements in the spectrum; and determining the germanium element content of the region to be detected according to the germanium element content of the sampling point, the soil index influence factor, the spectral data corresponding to the characteristic wave band and the hyperspectral data of the region to be detected. By using the method provided by the embodiment of the application, the hyperspectral inversion precision of the germanium element content of the soil can be effectively improved, the actual investigation requirements are met, and the investigation efficiency is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of soil element content measurement, in particular to a method for determining the content of soil germanium element.
Background
The traditional investigation method of the germanium element content in the soil is a geochemical investigation method, and specifically, the germanium element content in the soil is obtained by arranging sampling points with a certain degree of meshes in a region to be detected and carrying out sampling analysis. However, the method has the problems of long construction period, complicated working procedures, high cost of manpower and material resources and the like in practical application. The method for inverting the element content by utilizing the hyperspectrum, which is a research hotspot at present, has the advantages of strong timeliness, no damage and the like, but the research still belongs to experimental research properties, and the inversion precision is difficult to ensure in a large-scale practical investigation requirement.
Disclosure of Invention
In view of the above problems, the application provides a method for determining the content of germanium element in soil, which aims to stably improve the hyperspectral inversion precision of the content of germanium element, meet the actual investigation requirements and ensure the investigation effect.
The embodiment of the application provides a method for determining the content of germanium element in soil, which comprises the following steps: acquiring hyperspectral data of a region to be detected; acquiring spectrum data at a plurality of sampling points in a region to be detected, and the germanium element content of soil and a plurality of soil indexes; according to the spectrum data of the sampling points, a plurality of soil indexes and the content of germanium elements, determining soil index influence factors related to the content of the germanium elements in the soil indexes and characteristic wave bands related to the content of the germanium elements in the spectrum; and determining the germanium element content of the region to be detected according to the germanium element content of the sampling point, the soil index influence factor, the spectral data corresponding to the characteristic wave band and the hyperspectral data of the region to be detected.
According to the method for determining the content of the germanium element in the soil, the hyperspectral inversion accuracy of the content of the germanium element in the soil can be effectively improved, inversion data full coverage is realized, and the requirement of large-scale practical investigation is met.
Drawings
Other objects and advantages of the present invention will become apparent from the following description of embodiments of the present invention, which is to be read in connection with the accompanying drawings, and may assist in a comprehensive understanding of the present invention.
Fig. 1 is a flowchart of a method for determining germanium element content in soil according to an embodiment of the present application.
Fig. 2 is a flowchart of determining a soil index influence factor influencing the content of germanium element in a plurality of soil indexes according to an embodiment of the present application.
Fig. 3 is a flow chart of determining characteristic bands in a spectrum that affect elemental germanium content according to an embodiment of the present application.
Fig. 4 is a flowchart for determining germanium element content in a region to be measured according to an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. It will be apparent that the described embodiments are one embodiment of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without the benefit of the present disclosure, are intended to be within the scope of the present application based on the described embodiments.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which this application belongs. If, throughout, reference is made to "first," "second," etc., the description of "first," "second," etc., is used merely for distinguishing between similar objects and not for understanding as indicating or implying a relative importance, order, or implicitly indicating the number of technical features indicated, it being understood that the data of "first," "second," etc., may be interchanged where appropriate. If "and/or" is present throughout, it is meant to include three side-by-side schemes, for example, "A and/or B" including the A scheme, or the B scheme, or the scheme where A and B are satisfied simultaneously. Furthermore, for ease of description, spatially relative terms, such as "above," "below," "top," "bottom," and the like, may be used herein merely to describe the spatial positional relationship of one device or feature to another device or feature as illustrated in the figures, and should be understood to encompass different orientations in use or operation in addition to the orientation depicted in the figures.
The inventor of the application finds that when the hyperspectral is utilized to determine the content of the germanium element, inversion is usually carried out based on spectral data of ground sampling points, and spatial interpolation is needed after inversion, so that the drawing precision of the germanium element is limited, the accuracy of the determination of the content of the germanium element is further affected, and the requirement of large-scale practical investigation is difficult to meet.
To this end, an embodiment of the present application provides a method for determining a germanium element content of soil, which includes the following steps S10 to S40, referring to fig. 1.
Step S10: and acquiring hyperspectral data of the region to be detected.
Step S20: and acquiring spectrum data at a plurality of sampling points in the region to be detected, and the germanium element content of the soil and a plurality of soil indexes.
Step S30: and determining a soil index influence factor related to the germanium element content in the soil indexes and a characteristic wave band related to the germanium element content in the spectrum according to the spectrum data of the sampling points, the soil indexes and the germanium element content.
Step S40: and determining the germanium element content of the region to be detected according to the germanium element content of the sampling point, the soil index influence factor, the spectral data corresponding to the characteristic wave band and the hyperspectral data of the region to be detected.
According to the determining method, spectrum data of a plurality of sampling points in the region to be detected, germanium element content of soil and a plurality of soil indexes are analyzed, soil indexes closely related to the germanium element content are screened out, characteristic wave bands related to the germanium element content in the spectrum are combined, the germanium element content of the whole region of the region to be detected is obtained based on inversion of acquired aviation hyperspectral data, spatial interpolation is not needed, and therefore accuracy of the measured germanium element content is effectively improved, investigation efficiency of the germanium element content of the soil is improved, and investigation effects are guaranteed.
In some embodiments, in step S10, when acquiring hyperspectral data of the area to be measured, the hyperspectral data may be acquired in the area to be measured by using an aviation hyperspectral sensor.
For example, when the germanium element content is measured in a certain research area, hyperspectral data can be acquired in the area, the type of sensor used can be a CASI/SASI aviation hyperspectral sensor, and the acquired spectral band range is 350-2450nm.
In some embodiments, in step S20, when obtaining spectral data at a plurality of sampling points in the area to be measured, and germanium element content of soil and a plurality of soil indexes, spectral measurement may be performed at a plurality of sampling points on the ground while obtaining hyperspectral data of the area to be measured in step S10, so as to obtain spectral data at a plurality of sampling points; and collecting soil at a plurality of sampling points on the ground, and analyzing the collected soil samples to obtain the germanium element content and a plurality of soil indexes of the soil at the plurality of sampling points.
In this embodiment, the obtaining of hyperspectral data, the obtaining of spectral data of each sampling point, and soil parameters (for example, germanium element content and soil index) may be performed synchronously, so as to ensure that the timeliness of the hyperspectral data, the ground spectral data and the soil parameters is consistent, and ensure the precision of the subsequent inversion.
Alternatively, when performing spectral measurements at a plurality of sampling points on the ground, the spectral measurement instrument may employ an ASD ground object spectrometer; the soil samples collected at the sampling points can be chemically analyzed to obtain the germanium element content and a plurality of soil indexes of the soil at a plurality of sampling points in the region to be measured.
In some embodiments, when performing spectral measurement and collecting soil samples, sampling grids can be arranged in an area to be measured according to a certain sampling interval, each sampling grid is internally provided with a sampling point, spectral measurement is performed at each sampling point, and soil at the sampling points is collected to obtain soil samples at different positions in the area to be measured.
In some embodiments, the plurality of soil metrics may include a plurality of soil constituent levels and a plurality of soil physicochemical metrics.
In some embodiments, the soil component content comprises a content of at least one of the following: organic matter N, P, K 2 O、SiO 2 、Al 2 O 3 、Fe 2 O 3 、CaO、MgO、Na 2 O. The soil physical and chemical indexes comprise at least one of the following: cation exchange amount, salt content, pH, conductivity, texture.
Fig. 2 shows an embodiment of determining a soil index influence factor that influences the content of germanium element in a plurality of soil indexes, referring to fig. 2, in step S30, including: step S301, determining relevant soil indexes in a plurality of soil indexes according to the spectrum data of each sampling point and the plurality of soil indexes; step S302, determining a soil index influence factor in the relevant soil index according to the relevant soil index and the germanium element content of each sampling point.
In some embodiments, in step S301, determining the associated soil index of the plurality of soil indexes comprises: respectively constructing a change relation model of the spectrum data and each soil index according to the spectrum data of each sampling point and the soil indexes; and screening relevant soil indexes in the plurality of soil indexes according to each change relation model. In the embodiment, by establishing a relation model of each soil index and spectrum data, the soil index related to the spectrum data is primarily screened out, so that the content of germanium element is conveniently analyzed according to the hyperspectral data and the screened soil index.
In some embodiments, when the change relation model of the spectrum data and each soil index is constructed, the spectrum data of each sampling point acquired in step S20 may be taken as an independent variable, and a plurality of soil indexes are taken as dependent variables, so as to respectively construct the change relation model of the spectrum data and each soil index.
Optionally, a random forest method can be utilized to construct a change relation model, and spectrum data and hyperspectral inversion models of various soil indexes are respectively constructed. The random forest belongs to an integrated learning method in machine learning, is an algorithm for integrating a plurality of decision trees based on an integrated learning idea, and is characterized in that a basic unit of the random forest is a decision tree, and a constructed random forest is the integration of the decision tree. Each decision tree is a classifier, for one input sample, N decision trees generate N classification voting results, all classification voting results are integrated by a random forest, and the class with the largest voting frequency is designated as the final output, namely the final model prediction result.
In the embodiment, when a hyperspectral inversion model of spectrum data and each soil index is respectively constructed by using a random forest method, the soil index and the spectrum data at each sampling point are taken as samples, selected training data are randomly put back in the samples, then a classifier is constructed, and finally the classifier obtained by combined training is combined to obtain the random forest model, so that the overall classification effect is improved, the prediction result is reliable, and the prediction speed is high. Only 2 parameters need to be determined when constructing the random forest model: i.e. the number of decision trees and the number of variables needed to create the branches. Wherein the number of decision trees can be set to 10000 and the number of variables needed to create decision branches can be set to 4.
In some embodiments, the decision coefficients of each of the plurality of variation relationship models may be determined when screening relevant soil indicators of the plurality of soil indicators according to each of the variation relationship models; and screening relevant soil indexes in the plurality of soil indexes according to the determining coefficients of the change relation model. The determination coefficients are used for judging the fitting effect and the accuracy of the change relation model, the value of the determination coefficients is between 0 and 1, and the larger the determination coefficients are, the better the fitting effect and the higher the accuracy of the model are.
In the present embodiment, the determination of the change relation model can be based onAnd (3) screening out soil indexes corresponding to the model with higher precision by using the coefficients so as to be used for constructing a determining model of the content of germanium element later. Alternatively, the decision coefficient R of the random forest model corresponding to each soil index can be determined 2 Screening a model with higher precision according to the determination coefficient, and screening a determination coefficient R which can be the model according to the screening basis 2 Greater than or equal to 0.6, i.e. R 2 And (3) screening out soil indexes corresponding to the model with the value of more than or equal to 0.6 to serve as related soil indexes.
For example, for the above-mentioned research area, a random forest model of each soil index and spectral data can be respectively constructed according to the spectral data of sampling points obtained in the research area and a plurality of soil indexes, and the decision coefficient R can be determined according to the decision coefficient of each random forest model 2 Screening out soil indexes corresponding to the model with the value of more than or equal to 0.6, wherein the screened out relevant soil indexes comprise: organic matter N, K 2 O、SiO 2 、Al 2 O 3 、Fe 2 O 3 、CaO、MgO、Na 2 O, cation exchange capacity, salt content, pH.
In some embodiments, in step S302, determining a soil index influence factor in the relevant soil index according to the relevant soil index and the germanium element content of the sampling point includes: according to the related soil indexes and the germanium element content of the sampling points, determining the related coefficient of each related soil index and the germanium element content respectively; carrying out significance test on the correlation coefficient of each correlated soil index and the content of germanium element; and screening soil index influence factors in the relevant soil indexes according to the relevant coefficients and the significance test results corresponding to the relevant soil indexes. In the embodiment, the soil index and the content of germanium element are subjected to correlation analysis, so that the soil index related to the content of germanium element is screened out; meanwhile, the correlation coefficient obtained by the correlation analysis is subjected to significance test to remove the soil index of the correlation generated by accidental factors or errors.
In some embodiments, when determining the correlation coefficient between each of the relevant soil indexes and the content of germanium element, the content of germanium element at the plurality of sampling points obtained in step S20 and the relevant soil indexes screened in step S301 may be subjected to correlation analysis, and the correlation coefficient between each of the soil indexes and the content of germanium element is determined, so as to determine the correlation strength between the content of germanium element and each of the soil indexes. The expression for determining the correlation coefficient is as follows:
wherein r represents a correlation coefficient,represents the germanium element content of the ith sample point, < >>Mean value of germanium element content representing all sampling points, +.>Relevant soil index selected in step S301 representing the ith sampling point, ++>The average of the relevant soil index for all sampling points is represented.
In some embodiments, when the correlation coefficient is subjected to the significance test, the obtained correlation coefficient between each of the related soil indexes and the content of germanium element can be subjected to the significance test, so that the soil indexes which are related to the content of germanium element due to accidental factors are eliminated.
In some embodiments, when determining the soil index influence factor in the related soil indexes, the soil index corresponding to the correlation coefficient with the correlation coefficient meeting the requirement and passing the saliency test can be screened out as the soil index influence factor according to the value of the correlation coefficient and the saliency test result thereof. In some embodiments, the soil index corresponding to the correlation coefficient satisfying the condition may be determined as the soil index influence factor by taking the correlation coefficient with the correlation number being greater than or equal to 0.3 and the correlation coefficient passing the significance test as a basis.
Illustratively, for a certain one of the aboveIn the research area, when determining the soil index influence factors, the correlation coefficient of each of the relevant soil index and the germanium element content can be determined according to the relevant soil index and the germanium element content of the sampling point obtained in the research area, the correlation coefficient is subjected to saliency test, the soil index is screened by taking the correlation coefficient with the correlation number being more than or equal to 0.3 as a basis, and finally the screened soil index influence factors comprise: organic matter N, K 2 O、SiO 2 、Al 2 O 3 、Fe 2 O 3 、MgO、pH。
It should be noted that, the soil component content and the soil physicochemical index closely related to the germanium element are screened, because these soil indexes generally have more obvious spectral characteristics, and can provide more abundant information when the germanium element content of the whole region is finally determined according to hyperspectral data, so as to improve the accuracy of determining the germanium element content.
Fig. 3 shows an embodiment of determining characteristic bands affecting the content of germanium element in a spectrum, referring to fig. 3, in step S30, further including: step S303, according to the spectrum data of the sampling points and the content of germanium elements, respectively determining the correlation coefficients of each wave band in the spectrum and the content of germanium elements; step S304, carrying out significance test on the correlation coefficient of each wave band and the content of germanium element; step S305, determining characteristic wave bands in the spectrum according to the correlation coefficient and the significance test result corresponding to each wave band. In the embodiment, through carrying out correlation analysis on each wave band of the spectrum and the content of germanium element, the characteristic wave band related to the content of germanium element is screened out; meanwhile, the correlation coefficient obtained by correlation analysis is subjected to significance test to eliminate the wave band generating correlation due to accidental factors or errors.
In some embodiments, in step S303, in determining the correlation coefficient between each band in the spectrum and the content of germanium element, the spectral features of the spectral data of the sampling points acquired in step S20 may be enhanced, so that the spectral features are more easily identified. And performing correlation analysis on the processed spectrum data and the germanium element content of the sampling points acquired in the step S20, and respectively determining correlation coefficients of each wave band in the spectrum and the germanium element content. Optionally, the obtained spectral data of the sampling point may be subjected to envelope removal transformation to enhance the spectral characteristics of the spectral data of the sampling point.
The expression for determining the correlation coefficient between a certain wave band and the content of germanium element is as follows:
wherein r represents a correlation coefficient,represents the germanium element content of the ith sample point, < >>Mean value of germanium element content representing all sampling points, +.>Spectral data corresponding to the band representing the ith sample point, for example>Representing the average value of the spectral data corresponding to the band for all the sample points.
In some embodiments, in step S304, when the determined correlation coefficient is subjected to the saliency test, the correlation coefficient between each band and the content of germanium element in the spectrum obtained in step S303 may be subjected to the saliency test, so as to reject the band that generates the correlation due to the accidental factor.
In some embodiments, in step S305, when determining the characteristic band in the spectrum, a band that has a correlation coefficient that meets the requirement and passes the saliency test may be selected as the characteristic band of the spectrum according to the value of the correlation coefficient and the saliency test result thereof. In some embodiments, the wavelength band satisfying this condition may be determined to be a characteristic wavelength band of the spectrum based on the correlation number being greater than or equal to 0.3 and the correlation coefficient passing the saliency test.
For example, for the above-mentioned certain research area, when screening the characteristic wave band, according to the spectrum data and the germanium element content of the sampling point obtained in the research area, the correlation coefficient between each wave band in the spectrum and the germanium element content can be respectively determined, the correlation coefficient is subjected to saliency test, the wave band is screened according to the correlation coefficient with the correlation number being greater than or equal to 0.3, and the characteristic wave band in the finally screened spectrum is: 660nm, 1540nm, 2010nm, 2210nm, 2260nm and 2350nm.
The spectrum data corresponding to the characteristic wave band and the soil index closely related to the germanium element are determined and used as the basis for determining the germanium element content of the whole area according to the hyperspectral data, so that the accuracy of the determined germanium element content can be effectively improved.
Fig. 4 shows an embodiment of determining the germanium element content of the region to be measured, referring to fig. 4, in step S40, including: step S401, constructing a determining model of the content of germanium element according to the content of germanium element at the sampling point, the soil index influence factor and the spectral data corresponding to the characteristic wave band; step S402, based on the determination model of the germanium element content, determining the germanium element content of the region to be detected according to the hyperspectral data of the region to be detected. In the embodiment, the germanium element content of the region to be detected is obtained by constructing a determination model of the germanium element content and inverting according to hyperspectral data of the region to be detected, so that the investigation efficiency and accuracy of the germanium element content are improved.
In some embodiments, in step S401, when the determination model of the germanium element content is constructed, the soil index influence factor determined in step S302 and the spectral data corresponding to the characteristic band determined in step S305 may be used together as independent variables, and the germanium element content of the sampling point obtained in step S20 is used as the dependent variable to construct the determination model of the germanium element content. The spectral data corresponding to the soil index influence factors and the characteristic wave bands are used as independent variables to construct a model for determining the content of the germanium element, so that modeling accuracy can be effectively improved, and accuracy of determining the content of the germanium element is improved.
Alternatively, a hyperspectral inversion model of germanium element content can be constructed by adopting a random forest method, wherein the number of decision trees in model parameters can be 10000, and the number of variables required for creating branches is 4.
In some embodiments, in step S402, when determining the germanium element content of the region to be measured, hyperspectral data corresponding to the characteristic band of the region to be measured may be determined according to the hyperspectral data of the region to be measured. And determining the germanium element content of the region to be detected according to hyperspectral data corresponding to the characteristic wave band based on the determination model of the germanium element content.
In some embodiments, when determining the germanium element content of the region to be measured, correction processing may be performed on the hyperspectral data to obtain the ground object spectral reflectance of the region to be measured. And determining the content of germanium element in the region to be detected according to the spectral reflectivity of the ground object.
In some embodiments, when determining the germanium element content of the region to be measured, the hyperspectral data of the region to be measured obtained in step S10 may be corrected, so as to obtain an accurate ground object spectral reflectance of the region to be measured. Optionally, radiation correction, geometric correction, and atmospheric correction processing may be performed on the hyperspectral data of the region to be measured. The radiation correction aims to eliminate or correct the image brightness distortion caused by radiation errors; the purpose of geometric correction is to eliminate or correct geometric errors of remote sensing images; the atmospheric correction aims to eliminate the influence of factors such as atmosphere, illumination and the like on the ground reflection.
For the above-mentioned certain research area, when determining the germanium element content of the research area, firstly, performing radiation correction, geometric correction and atmospheric correction on hyperspectral data obtained in the research area, and then inputting the corrected ground object spectral reflectivity data into a constructed random forest model for determining the germanium element content to obtain the germanium element content of the whole research area. Specifically, radiation correction and geometric correction are performed on hyperspectral data first. And carrying out atmospheric correction and spectrum reconstruction on the hyperspectral data by utilizing a mode of combining an atmospheric radiation transmission model and ground-air return, wherein the FLAASH atmospheric radiation transmission model is firstly utilized for carrying out preliminary atmospheric correction, and then the spectral data of the ground black and white calibration cloth are utilized for further carrying out atmospheric correction, so that the ground feature spectral reflectivity data of the region to be detected is finally obtained.
It should also be noted that, in the embodiments of the present invention, the features of the embodiments of the present invention and the features of the embodiments of the present invention may be combined with each other to obtain new embodiments without conflict.
The present invention is not limited to the above embodiments, but the scope of the invention is defined by the claims.
Claims (12)
1. The method for determining the content of the germanium element in the soil is characterized by comprising the following steps of:
acquiring hyperspectral data of a region to be detected;
acquiring spectrum data at a plurality of sampling points in the region to be detected, and the germanium element content of soil and a plurality of soil indexes;
according to the spectrum data of the sampling points, a plurality of soil indexes and germanium element content, determining soil index influence factors related to the germanium element content in the soil indexes and characteristic wave bands related to the germanium element content in a spectrum;
and determining the germanium element content of the region to be detected according to the germanium element content of the sampling point, the soil index influence factor, the spectral data corresponding to the characteristic wave band and the hyperspectral data of the region to be detected.
2. The method according to claim 1, wherein determining a soil index influence factor that influences the germanium element content in the plurality of soil indexes and a characteristic band that influences the germanium element content in a spectrum according to the spectral data of the sampling points, a plurality of soil indexes, and germanium element content, comprises:
determining relevant soil indexes in the soil indexes according to the spectrum data of each sampling point and the soil indexes;
and determining a soil index influence factor in the relevant soil index according to the relevant soil index and the germanium element content of each sampling point.
3. The method of claim 2, wherein the determining a relevant soil index of the plurality of soil indexes from the spectral data of the sampling points and the plurality of soil indexes comprises:
respectively constructing a change relation model of the spectrum data and each soil index according to the spectrum data of the sampling points and the soil indexes;
and screening relevant soil indexes in the plurality of soil indexes according to each change relation model.
4. The method of claim 3, wherein the step of,
determining a decision coefficient of the change relation model;
and screening relevant soil indexes in the soil indexes according to the determining coefficients of the change relation model.
5. The method of claim 2, wherein determining a soil index influence factor in the relevant soil index based on the relevant soil index and germanium element content of the sampling point comprises:
according to the related soil indexes and the germanium element content of the sampling points, determining the related coefficient of each related soil index and the germanium element content respectively;
performing significance test on the correlation coefficient of each correlated soil index and the germanium element content;
and screening soil index influence factors in the relevant soil indexes according to the relevant coefficients and the significance test results corresponding to the relevant soil indexes.
6. The method of claim 5, wherein the step of determining the position of the probe is performed,
and determining the relevant soil index corresponding to the relevant coefficient as the soil index influence factor according to the fact that the relevant coefficient is larger than or equal to 0.3 and the relevant coefficient passes through the significance test.
7. The method of any one of claims 1-6, wherein the soil index comprises a plurality of soil composition levels and a plurality of soil physicochemical indices.
8. The method of claim 1, wherein determining a soil index influence factor in the plurality of soil indices that influences the germanium element content and a characteristic band in a spectrum that influences the germanium element content from the spectral data of the sampling points, a plurality of soil indices, and a germanium element content, further comprises:
according to the spectrum data of the sampling points and the content of germanium elements, respectively determining correlation coefficients of each wave band in a spectrum and the content of germanium elements;
performing significance test on correlation coefficients of the wave bands and the germanium element content;
and determining characteristic wave bands in the spectrum according to the correlation coefficient and the significance test result corresponding to each wave band.
9. The method of claim 8, wherein the step of determining the position of the first electrode is performed,
and determining a wave band corresponding to the correlation coefficient as the characteristic wave band according to the correlation coefficient being greater than or equal to 0.3 and the correlation coefficient passing the significance test.
10. The method according to claim 1, wherein the determining the germanium element content of the region to be measured according to the germanium element content of the sampling point, the soil index influence factor, the spectral data corresponding to the characteristic band, and the hyperspectral data of the region to be measured includes:
constructing a determining model of the germanium element content according to the germanium element content of the sampling points, the soil index influence factors and the spectral data corresponding to the characteristic wave bands;
and determining the germanium element content of the region to be detected according to the hyperspectral data of the region to be detected based on the determination model of the germanium element content.
11. The method of claim 10, wherein the step of determining the position of the first electrode is performed,
according to the hyperspectral data of the region to be detected, hyperspectral data corresponding to the characteristic wave band of the region to be detected is determined;
and determining the germanium element content of the region to be detected according to hyperspectral data corresponding to the characteristic wave band based on the determination model of the germanium element content.
12. The method as recited in claim 10, further comprising:
correcting the hyperspectral data to obtain the ground object spectral reflectance of the region to be detected;
and determining the content of germanium element in the region to be detected according to the ground object spectral reflectivity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311595170.4A CN117309780B (en) | 2023-11-27 | 2023-11-27 | Method for determining content of germanium element in soil |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311595170.4A CN117309780B (en) | 2023-11-27 | 2023-11-27 | Method for determining content of germanium element in soil |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117309780A true CN117309780A (en) | 2023-12-29 |
CN117309780B CN117309780B (en) | 2024-02-06 |
Family
ID=89255516
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311595170.4A Active CN117309780B (en) | 2023-11-27 | 2023-11-27 | Method for determining content of germanium element in soil |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117309780B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095562A (en) * | 2015-05-29 | 2015-11-25 | 中国石油天然气股份有限公司 | Method and device for predicting soil light hydrocarbon index |
CN105547366A (en) * | 2015-12-30 | 2016-05-04 | 东北农业大学 | Miniaturized unmanned aerial vehicle crop information obtaining and fertilization irrigation guiding apparatus |
CN108593606A (en) * | 2017-12-20 | 2018-09-28 | 江苏地质矿产设计研究院 | A method of testing Ge content in coal using atomic fluorescence spectrophotometry |
CN112683813A (en) * | 2020-12-31 | 2021-04-20 | 核工业北京地质研究院 | Hyperspectral extraction method for soil pollution information of hard rock type uranium mine |
CN113866102A (en) * | 2021-09-24 | 2021-12-31 | 中国地质调查局西安地质调查中心(西北地质科技创新中心) | Soil health investigation monitoring method based on spectrum |
CN114660105A (en) * | 2022-04-08 | 2022-06-24 | 成都理工大学 | Soil heavy metal Cd content inversion method, system, medium and computer equipment |
WO2023097399A1 (en) * | 2021-12-03 | 2023-06-08 | Terramera, Inc. | Systems and methods for predicting soil carbon content |
-
2023
- 2023-11-27 CN CN202311595170.4A patent/CN117309780B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095562A (en) * | 2015-05-29 | 2015-11-25 | 中国石油天然气股份有限公司 | Method and device for predicting soil light hydrocarbon index |
CN105547366A (en) * | 2015-12-30 | 2016-05-04 | 东北农业大学 | Miniaturized unmanned aerial vehicle crop information obtaining and fertilization irrigation guiding apparatus |
CN108593606A (en) * | 2017-12-20 | 2018-09-28 | 江苏地质矿产设计研究院 | A method of testing Ge content in coal using atomic fluorescence spectrophotometry |
CN112683813A (en) * | 2020-12-31 | 2021-04-20 | 核工业北京地质研究院 | Hyperspectral extraction method for soil pollution information of hard rock type uranium mine |
CN113866102A (en) * | 2021-09-24 | 2021-12-31 | 中国地质调查局西安地质调查中心(西北地质科技创新中心) | Soil health investigation monitoring method based on spectrum |
WO2023097399A1 (en) * | 2021-12-03 | 2023-06-08 | Terramera, Inc. | Systems and methods for predicting soil carbon content |
CN114660105A (en) * | 2022-04-08 | 2022-06-24 | 成都理工大学 | Soil heavy metal Cd content inversion method, system, medium and computer equipment |
Non-Patent Citations (2)
Title |
---|
张恒 等: "基于高光谱成像的区域尺度植烟土壤有机质 含量和 pH 值估测", 烟草科技, pages 1 - 15 * |
赵宁博 等: "黑土地硒含量的航空高光谱综合反演模型", 测绘科学, vol. 46, no. 6, pages 128 - 135 * |
Also Published As
Publication number | Publication date |
---|---|
CN117309780B (en) | 2024-02-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lehnert et al. | Hyperspectral data analysis in R: The hsdar package | |
CN110132862B (en) | Construction method and application of disease index special for wheat scab detection | |
CN112634212B (en) | Disease latent tree detection method and system based on hyperspectral unmanned aerial vehicle | |
CN107796764B (en) | Method for constructing wheat leaf area index estimation model based on three-band vegetation index | |
CN104198396B (en) | The method that polarization-hyperspectral technique diagnosis crop N P and K wanes | |
CN110455722A (en) | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system | |
CN106815643A (en) | Infrared spectrum Model Transfer method based on random forest transfer learning | |
CN113866102B (en) | Soil health investigation monitoring method based on spectrum | |
Shu et al. | Improving the estimation accuracy of SPAD values for maize leaves by removing UAV hyperspectral image backgrounds | |
CN103854305A (en) | Module transfer method based on multiscale modeling | |
CN115372282B (en) | Farmland soil water content monitoring method based on hyperspectral image of unmanned aerial vehicle | |
CN114120132A (en) | Crop yield estimation method and device combining meteorological remote sensing and red-edge wave band remote sensing | |
KR20210063187A (en) | A method and system for measuring biochemical information using color space conversion | |
CN114676636A (en) | Grassland area soil moisture rapid inversion method integrating vegetation and habitat characteristics | |
CN103186893A (en) | Universal high-resolution remote sensing image fusion method | |
US20110150290A1 (en) | Method and apparatus for predicting information about trees in images | |
US20240099179A1 (en) | Machine learning-based hyperspectral detection and visualization method of nitrogen content in soil profile | |
CN117309780B (en) | Method for determining content of germanium element in soil | |
CN116818687B (en) | Soil organic carbon spectrum prediction method and device based on spectrum guide integrated learning | |
CN104198397A (en) | Method for detecting nutrient content of greenhouse crops under nitrogen, phosphorus and potassium interaction | |
CN115855860A (en) | Method for predicting moisture content in tea drying process and processing terminal | |
Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves | |
CN115266720A (en) | Multi-scale spectral imaging corn growth period nutrient information detection method | |
CN117269078B (en) | Method for determining cation exchange capacity of soil | |
CN117630000B (en) | Soil salt content evaluation method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |