CN108169162B - Rapid evaluation method for soil fertility level of tea garden - Google Patents
Rapid evaluation method for soil fertility level of tea garden Download PDFInfo
- Publication number
- CN108169162B CN108169162B CN201711329502.9A CN201711329502A CN108169162B CN 108169162 B CN108169162 B CN 108169162B CN 201711329502 A CN201711329502 A CN 201711329502A CN 108169162 B CN108169162 B CN 108169162B
- Authority
- CN
- China
- Prior art keywords
- tea garden
- sample
- spectrum
- soil
- fertility level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002689 soil Substances 0.000 title claims abstract description 88
- 241001122767 Theaceae Species 0.000 title claims abstract description 65
- 230000035558 fertility Effects 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 title claims abstract description 8
- 238000001228 spectrum Methods 0.000 claims abstract description 58
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000012937 correction Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 238000002203 pretreatment Methods 0.000 claims abstract description 6
- 230000000694 effects Effects 0.000 claims abstract description 5
- 238000012850 discrimination method Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 18
- 239000005416 organic matter Substances 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 11
- KMUONIBRACKNSN-UHFFFAOYSA-N potassium dichromate Chemical compound [K+].[K+].[O-][Cr](=O)(=O)O[Cr]([O-])(=O)=O KMUONIBRACKNSN-UHFFFAOYSA-N 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 235000015097 nutrients Nutrition 0.000 description 4
- 238000004497 NIR spectroscopy Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 235000009024 Ceanothus sanguineus Nutrition 0.000 description 2
- 240000003553 Leptospermum scoparium Species 0.000 description 2
- 235000015459 Lycium barbarum Nutrition 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000004016 soil organic matter Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000000184 acid digestion Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000003837 high-temperature calcination Methods 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000813 microbial effect Effects 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
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005527 soil sampling Methods 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- 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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- 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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N2021/3595—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using FTIR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a rapid evaluation method of soil fertility level of a tea garden, which comprises the steps of respectively selecting a plurality of soil samples of a barren tea garden, a good tea garden and a high-quality tea garden, and randomly dividing the soil samples into a correction set and a prediction set; determining a classification sample set according to the division range of the content; collecting near infrared spectrum information of a sample, continuously scanning for multiple times, and obtaining all average spectrum information of the sample under near infrared wavelength; carrying out different pretreatments on the original average spectrum of the sample, and determining the optimal pretreatment method of the spectrum according to the prediction effect of the tea garden soil fertility level judgment model; extracting characteristic spectrum information by adopting a continuous projection algorithm; and comparing the characteristic spectrum with the full spectrum by combining the three discrimination methods, and determining an optimal tea garden soil fertility level discrimination model according to the predicted classification accuracy, thereby realizing the prediction of the tea garden soil fertility level. The invention combines the near infrared spectrum technology to measure the soil fertility and can realize on-line, nondestructive and rapid detection.
Description
Technical Field
The invention relates to a soil fertility judging method, in particular to a rapid evaluation method for the soil fertility level of a tea garden.
Background
The soil provides nutrition and trace elements for the growth of the tea trees and keeps moisture, and is the natural foundation for the growth of the tea trees. Organic matters in soil are a key evaluation index of soil fertility, are important sources for tea to absorb inorganic elements such as nitrogen, phosphorus and potassium, and play an important role in increasing soil microbial communities and improving soil physicochemical properties. The production quality and the growth efficiency of the tea are determined by the level of the soil fertility level, and the rapid evaluation of the tea garden soil fertility level can provide important guidance for the management and construction of a high-quality tea garden. Frequent use of agricultural input (fertilizers) can damage soil properties and cause serious environmental pollution. Meanwhile, the destruction of soil fertility affects the yield and quality of tea. Therefore, the soil nutrient condition and the spatial variation are regularly monitored, and reasonable fertilization is very important according to the abundance degree of the soil nutrients in the tea garden. However, laboratory analysis of soil organic matter content typically requires strong acid digestion, high temperature calcination of samples for analysis, resulting in emission of acid gases to the environment. Not only increases heavy environmental burden, but also has complicated determination process, long time and higher input cost. Therefore, efficient and environment-friendly alternative technologies for analyzing the organic matter content of soil are needed to quickly evaluate the soil fertility level.
Near Infrared Spectroscopy (NIRS) is an electromagnetic wave with a wavelength of 780-2526 nm between a visible light region and a middle Infrared region, and a spectrum region of the NIRS almost comprises the resultant frequency of vibration of all hydrogen-containing groups (C-H, N-H and O-H) in organic matters and characteristic absorption information of frequency doubling of each stage. The near infrared spectrum is used as a basis for analyzing the composition and property information of the organic matters. The modern near infrared spectrum analysis is combined with a chemometrics method to perform qualitative or quantitative analysis by using full-band or multi-wavelength spectrum information, and the method is scientific and accurate. The technology can simultaneously measure various chemical components and has the characteristics of high detection speed, low cost, no damage and real-time monitoring. The method is very suitable for rapid discrimination and analysis of tea garden soil, and has been widely applied to determination of soil nutrient information in recent years. However, no relevant article report about the judgment of fertility level based on the near infrared spectrum analysis technology combined with the tea garden soil organic matter is found at home and abroad.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a rapid evaluation method for the soil fertility level of a tea garden, and can realize accurate and rapid online detection.
The invention is realized by the following technical scheme, and the method comprises the following steps:
(1) selecting and pretreating a sample:
respectively selecting a plurality of soil samples of a barren tea garden with the organic matter content of less than or equal to 1.5%, a good tea garden with the organic matter content of 1.5-2.0% and a high-quality tea garden with the organic matter content of more than or equal to 2.0%, and randomly dividing the soil samples into a correction set and a prediction set;
(2) detecting the chemical value of the soil sample:
measuring the organic matter content of the sample, and determining a classification sample set according to the division range of the content;
(3) acquisition and pretreatment of near infrared spectra
(31) Collecting near infrared spectrum information of a sample, continuously scanning for multiple times, and obtaining all average spectrum information of the sample under near infrared wavelength;
(32) carrying out different pretreatments on the original average spectrum of the sample, and determining the optimal pretreatment method of the spectrum according to the prediction effect of the tea garden soil fertility level judgment model;
(4) establishment of prediction model
(41) Acquiring a near infrared spectrum of a sample, and screening characteristic spectrum information by using a continuous projection algorithm by taking a fertility level classification standard as an index;
(42) then, establishing a classification discrimination model of the soil fertility level of the tea garden based on a linear discrimination analysis method, a support vector machine algorithm and an extreme learning machine algorithm;
(43) and comparing the characteristic spectrum with the full spectrum by combining the three discrimination methods, and determining an optimal tea garden soil fertility level discrimination model according to the predicted classification accuracy, thereby realizing the prediction of the tea garden soil fertility level.
In the step (1), representative tea garden soil samples with large organic matter content difference are selected from tea garden soil with different soil types and soil layer thickness of 0-45 cm in six areas. The soil sample with larger difference is more beneficial to measuring accuracy.
In a preferred embodiment of the present invention, in step (1), the sample is divided into the calibration set and the prediction set at a ratio of 2: 1.
The content of organic matters in the sample is determined by adopting a potassium dichromate volumetric method according to GB 9834-1988, and characteristic spectrum variables are screened by utilizing a continuous projection algorithm according to the high-low distribution range of the content of the organic matters in the soil as a division index.
In the step (31), the acquisition of the near infrared spectrum data information is specifically as follows: spectrum collection is carried out by using an MPA type Fourier transform near infrared spectrometer, and the spectrum range of the near infrared spectrum is as follows: 12500cm-1～4000cm-1Resolution of 8cm-1The method comprises the steps of putting a sample into a sample cup, scanning the soil sample three times by converting the position of the sample cup from three different angles of 0 degrees, 120 degrees and 240 degrees respectively by using a near-infrared diffuse reflection spectrum technology to obtain three parallel spectrums, collecting the three parallel spectrums, and taking the average spectrum as a near-infrared original spectrum value of the sample. To reduce experimental error, constant room temperature (25. + -. 1 ℃) and humidity (45%. + -. 1%) were maintained throughout the experiment. Three parallel spectrums are selected, and the average spectrum is taken as the near infrared spectrum value of the sample, so that the error can be further reduced.
In the step (42), the preprocessed spectrum is combined with a continuous projection algorithm to preferably select 23 characteristic spectrum variables.
In the step (42), a classification variable is set, the classification variable of the soil sample of the barren tea garden is set to be 1, the classification variable of the soil sample of the good tea garden is set to be 2, the classification variable of the soil sample of the good tea garden is set to be 3, qualitative judgment is carried out on 23 screened characteristic spectrum variables and the corresponding classification variables, and a judgment model of the tea garden soil fertility level is respectively established by utilizing a linear discriminant analysis LDA, a support vector machine SVM and an extreme learning machine ELM.
And qualitatively distinguishing the characteristic spectrum variables obtained by screening the full spectrum variables and the continuous projection algorithm with prediction models established by corresponding classification variables, respectively comparing the predicted classification accuracy rates, and finally determining an optimal tea garden soil fertility level distinguishing model.
In agricultural production, soil fertility can change along with the influence of factors such as moisture, nutrients, air, heat and the like, and near infrared spectrum information can represent internal information of soil. In the process, the content change degree of the organic matters is small, but the change in the fertility grade classification is obvious, so that the characteristic spectrum variable related to the content of the organic matters is screened out through a continuous projection algorithm, and a discrimination model of the fertility level of the tea garden soil is established.
Compared with the prior art, the invention has the following advantages: the invention replaces the defects of the traditional analysis method, measures the soil fertility by combining the near infrared spectrum technology, provides a scientific and accurate qualitative judgment method for judging the soil fertility level, and can realize online, nondestructive and rapid detection.
Drawings
FIG. 1 is a schematic view showing the distribution of sampling points in a soil sampling area according to the present invention;
FIG. 2 shows the wavenumber range of 3999.81cm for different samples in different regions-1～12493.12cm-1Original spectrogram.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
The specific determination process of this embodiment is as follows:
(1) selecting and pretreating a sample:
selecting representative tea garden soil samples with large organic matter content difference from tea garden soil with different soil types and soil layer thickness of 0-45 cm in different areas.
As shown in fig. 1, 34 samples are taken from Yunnan, 25 samples are taken from Fujian, 35 samples are taken from Guizhou, 9 samples are taken from Sichuan, 26 samples are taken from Shandong and 64 samples are taken from Hubei, 75 parts of barren tea gardens with the organic matter content of less than or equal to 1.5%, 43 parts of good tea gardens with the organic matter content of 1.5-2.0% and 75 parts of soil samples with the organic matter content of high-quality tea gardens of more than or equal to 2.0% are respectively selected and randomly divided into correction sets and prediction sets according to the proportion of 2:1, 129 parts of the samples are obtained as the correction sets and used for establishing prediction models, and the remaining 64 parts are used as the prediction sets and used for checking the reliability and the prediction capability of the models;
(2) detecting the chemical value of the soil sample:
the content of organic matters in the sample is determined by adopting a potassium dichromate volumetric method according to GB 9834-1988, the content distribution range of the organic matters in the soil is used as a division index, and the specific results are shown in Table 1:
TABLE 1 statistics of organic matter content in tea garden soil samples
| Parameter(s) | Number of samples n | Minimum value (%) | Maximum value (%) | Mean value (%) | Standard deviation (%) |
| Barren | 75 | 0.406 | 1.466 | 1.022 | 0.256 |
| Good effect | 43 | 1.515 | 1.986 | 1.740 | 0.131 |
| High quality | 75 | 3.045 | 7.618 | 4.596 | 1.270 |
(3) Acquisition and pretreatment of near infrared spectra
As shown in fig. 2, the spectra were collected using MPA type fourier transform near infrared spectrometer (with Pbs detector). To reduce experimental error, constant room temperature (25. + -. 1 ℃) and humidity (45%. + -. 1%) were maintained throughout the experiment. The spectral range of the near infrared spectrum is 12500cm-1～4000cm-1(every 3.86cm-1) Resolution of 8cm-1. A sample (20 +/-0.01 g) is put into a sample cup (9.7cm), each sample spectrum and background are scanned 32 times by a concentration sphere by applying a near infrared diffuse reflection spectrum technology, the position of the sample cup is converted along one direction from three different angles of 0 degrees, 120 degrees and 240 degrees respectively, and a soil sample is scanned 3 times to obtain 3 parallel spectra.
The raw spectra of each sample were obtained by averaging the data from 3 parallel spectral scans by running the spectrometer's own OPUS 6.5 software.
(4) Establishment of prediction model
Respectively establishing a prediction model of the content of organic matters in the soil of the tea garden by using a Linear Discriminant Analysis (LDA), a Support Vector Machine (SVM) algorithm and an Extreme Learning Machine (ELM) algorithm on the correction set samples by using the spectral information of all wave bands;
the preprocessed spectrum is combined with a continuous projection algorithm (SPA) to preferably select 23 characteristic spectrum variables, wherein the characteristic spectrum variables are 12485.41cm respectively-1、12477.69cm-1、12462.27cm-1、12446.8cm-1、12435.3cm-1、12423.7cm-1、12408.3cm-1、12381.3cm-1、12346.6cm-1、12246.3cm-1、12230.8cm-1、12207.7cm-1、12130.6cm-1、12080.4cm-1、12034.1cm-1、11343.7cm-1、10067.0cm-1、5897.5cm-1、4956.4cm-1、4408.7cm-1、4370.1cm-1、4308.4cm-1、4262.1cm-1。
Three classification discrimination methods of SPA combined LDA (SPA-LDA), SPA combined SVM (SPA-SVM) and SPA combined ELM (SPA-ELM) are adopted for the correction set samples, and prediction discrimination models of the tea garden soil fertility level are respectively established;
establishing a discrimination model based on a Linear Discriminant Analysis (LDA), an Extreme Learning Machine (ELM) and a Support Vector Machine (SVM) to set classification variables, setting the classification variable of the poor tea garden soil sample as 1, setting the classification variable of the good tea garden soil sample as 2, setting the classification variable of the high-quality tea garden soil sample as 3, qualitatively discriminating 23 characteristic spectrum variables obtained by screening the full spectrum variable and a continuous projection algorithm with the corresponding classification variables respectively, and establishing a LDA, SVM and ELM classification discrimination model of the tea garden soil fertility level. Through comparison of the fertility level prediction accuracy rates, the discrimination results of the models are shown in table 2, the classification effect of SPA-ELM is good, the total discrimination rate of the prediction set can reach 84.38%, the tea garden soil fertility level can be discriminated, and the classification results of each type at three levels are shown in table 3.
TABLE 2 comparison of classification results of different classification algorithms under full spectrum and characteristic wavelength conditions
TABLE 3 discrimination results of different fertility levels of ELM model under characteristic spectrum conditions
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. A rapid evaluation method for the soil fertility level of a tea garden is characterized by comprising the following steps:
(1) selecting and pretreating a sample:
respectively selecting a plurality of soil samples of a barren tea garden with the organic matter content of less than or equal to 1.5%, a good tea garden with the organic matter content of 1.5-2.0% and a high-quality tea garden with the organic matter content of more than or equal to 2.0%, and randomly dividing the soil samples into a correction set and a prediction set;
(2) detecting the chemical value of the soil sample:
measuring the organic matter content of the sample, and determining a classification sample set according to the division range of the content;
(3) acquisition and pretreatment of near infrared spectra
(31) Collecting near infrared spectrum information of a sample, continuously scanning for multiple times, and obtaining all average spectrum information of the sample under near infrared wavelength;
in the step (31), the acquisition of the near infrared spectrum data information is specifically as follows: spectrum collection is carried out by using an MPA type Fourier transform near infrared spectrometer, and the spectrum range of the near infrared spectrum is as follows: 12500cm-1～4000cm-1Resolution of 8cm-1The method comprises the following steps of putting a sample into a sample cup, scanning the soil sample three times by converting the position of the sample cup from three different angles of 0 degrees, 120 degrees and 240 degrees respectively by using a near-infrared diffuse reflection spectrum technology to obtain three parallel spectrums, collecting the three parallel spectrums, and taking the average spectrum as a near-infrared original spectrum value of the sample;
(32) carrying out different pretreatments on the original average spectrum of the sample, and determining the optimal pretreatment method of the spectrum according to the prediction effect of the tea garden soil fertility level judgment model;
(4) establishment of prediction model
(41) Acquiring a near infrared spectrum of a sample, and screening characteristic spectrum information by using a continuous projection algorithm by taking a fertility level classification standard as an index;
(42) then, establishing a classification discrimination model of the soil fertility level of the tea garden based on a linear discrimination analysis method, a support vector machine algorithm and an extreme learning machine algorithm;
in the step (42), classification variables are set, the classification variable of the soil sample of the barren tea garden is set to be 1, the classification variable of the soil sample of the good tea garden is set to be 2, the classification variable of the soil sample of the good tea garden is set to be 3, qualitative judgment is carried out on 23 screened characteristic spectrum variables and the corresponding classification variables, and a judgment model of the tea garden soil fertility level is respectively established by utilizing a linear discriminant analysis LDA, a support vector machine SVM and an extreme learning machine ELM;
(43) comparing the characteristic spectrum with the full spectrum by combining the three discrimination methods, and determining an optimal tea garden soil fertility level discrimination model according to the predicted classification accuracy, so as to predict the tea garden soil fertility level;
in the step (1), representative tea garden soil samples with large organic matter content difference are selected from tea garden soil with different soil types and soil layer thickness of 0-45 cm in six areas;
the optimal tea garden soil fertility level distinguishing model is established according to a classification distinguishing method combining a continuous projection algorithm and an extreme learning machine algorithm.
2. The method for rapidly evaluating the soil fertility level of a tea garden as claimed in claim 1, wherein in the step (1), the samples are divided into the correction set and the prediction set according to a ratio of 2: 1.
3. The method for rapidly evaluating the soil fertility level of a tea garden as claimed in claim 1, wherein the content of organic matters in the sample is determined by a potassium dichromate volumetric method according to GB 9834-.
4. The method for rapidly evaluating the soil fertility level of a tea garden as claimed in claim 1, wherein in the step (42), the preprocessed spectrum is combined with a continuous projection algorithm to preferably select 23 characteristic spectrum variables.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711329502.9A CN108169162B (en) | 2017-12-13 | 2017-12-13 | Rapid evaluation method for soil fertility level of tea garden |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711329502.9A CN108169162B (en) | 2017-12-13 | 2017-12-13 | Rapid evaluation method for soil fertility level of tea garden |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108169162A CN108169162A (en) | 2018-06-15 |
| CN108169162B true CN108169162B (en) | 2021-01-19 |
Family
ID=62525810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711329502.9A Active CN108169162B (en) | 2017-12-13 | 2017-12-13 | Rapid evaluation method for soil fertility level of tea garden |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108169162B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109696407B (en) * | 2019-01-22 | 2020-11-03 | 中国农业大学 | Coconut husk matrix available nitrogen spectrum detection method based on characteristic wavelength |
| CN114931004B (en) * | 2022-06-28 | 2023-03-10 | 湖南省土壤肥料研究所 | Improvement method for red soil dry land acidification barrenness |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234922A (en) * | 2013-03-29 | 2013-08-07 | 浙江大学 | Rapid soil organic matter detection method based on large sample soil visible-near infrared spectrum classification |
| CN104297203B (en) * | 2014-09-28 | 2016-08-17 | 安徽农业大学 | A kind of Quick method of congou tea fermented quality based on near-infrared spectral analysis technology |
| CN106126879B (en) * | 2016-06-07 | 2018-09-28 | 中国科学院合肥物质科学研究院 | A kind of soil near-infrared spectrum analysis prediction technique based on rarefaction representation technology |
| CN106096656A (en) * | 2016-06-07 | 2016-11-09 | 中国科学院合肥物质科学研究院 | A kind of soil near-infrared spectral analytical method based on rarefaction representation and BP nerual network technique |
-
2017
- 2017-12-13 CN CN201711329502.9A patent/CN108169162B/en active Active
Non-Patent Citations (3)
| Title |
|---|
| SPA-LS-SVW检测土壤有机质和速效钾研究;章海亮 等;《光谱学与光谱分析》;20140531;第1348-1351页 * |
| 基于光谱和高光谱成像技术的土壤养分及类型检测与仪器开发;章海亮;《中国博士学位论文全文数据库 农业科技辑》;20150515;第1-7页 * |
| 基于多源辅助变量和极限学习机的蔬菜土壤有机质预测研究;宋英强 等;《土壤通报》;20170228;第118-126页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108169162A (en) | 2018-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101915744B (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
| Lu et al. | Quantitative determination and characteristic wavelength selection of available nitrogen in coco-peat by NIR spectroscopy | |
| CN104020127A (en) | Method for rapidly measuring inorganic element in tobacco by near infrared spectrum | |
| CN103353446A (en) | Method of near-infrared rapid detection of physicochemical indexes in wine | |
| CN110596028B (en) | High-spectrum inversion method for content of deposited rare earth La element | |
| CN105784628A (en) | Method for detecting chemical composition of soil organic matter with mid-infrared spectra | |
| CN101762569A (en) | Non-destructive monitoring method of livestock excrement industrialized composting fermentation process | |
| CN108169162B (en) | Rapid evaluation method for soil fertility level of tea garden | |
| CN105758819A (en) | Method for detecting organic components of soil by utilizing near infrared spectrum | |
| CN105486663B (en) | A method of detecting the stable carbon isotope ratio of soil using near infrared spectrum | |
| Lu et al. | A feasibility quantitative analysis of NIR spectroscopy coupled Si-PLS to predict coco-peat available nitrogen from rapid measurements | |
| Ning et al. | Rapid evaluation of soil fertility in tea plantation based on near-infrared spectroscopy | |
| Ning et al. | Rapid identification and quantitative pit mud by near infrared Spectroscopy with chemometrics | |
| Wang et al. | Predicting organic matter content, total nitrogen and ph value of lime concretion black soil based on visible and near infrared spectroscopy | |
| CN114112983A (en) | Python data fusion-based Tibetan medicine all-leaf artemisia rupestris L producing area distinguishing method | |
| CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
| CN105784629B (en) | The method that the stable carbon isotope ratio of soil is quickly detected using middle infrared spectrum | |
| CN113310943A (en) | Lotus root starch adulteration identification method based on machine learning | |
| CN105699314B (en) | A method of detecting soil stabilization carbon isotope ratio using middle infrared spectrum | |
| Liu et al. | Research on the online rapid sensing method of moisture content in famous green tea spreading | |
| CN115586159A (en) | Method for evaluating aging association degree of white spirit based on mid-infrared spectrum detection technology | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection | |
| CN108007916B (en) | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method | |
| Lu et al. | Prediction performance optimization of different resolution and spectral band ranges for characterizing coco-peat substrate available nitrogen | |
| CN111487219A (en) | Method for rapidly detecting content of bergamot pear lignin based on near infrared spectrum technology |
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 |