CN109540811A - A method of black earth nutrient content precision of prediction is improved by spectrum transform - Google Patents
A method of black earth nutrient content precision of prediction is improved by spectrum transform Download PDFInfo
- Publication number
- CN109540811A CN109540811A CN201811589000.4A CN201811589000A CN109540811A CN 109540811 A CN109540811 A CN 109540811A CN 201811589000 A CN201811589000 A CN 201811589000A CN 109540811 A CN109540811 A CN 109540811A
- Authority
- CN
- China
- Prior art keywords
- black soil
- content
- spectrum
- prediction
- nutrient 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.)
- Pending
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 38
- 235000021049 nutrient content Nutrition 0.000 title claims abstract description 26
- 230000003595 spectral effect Effects 0.000 claims abstract description 27
- 238000002310 reflectometry Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000004044 response Effects 0.000 claims abstract description 7
- 230000001419 dependent effect Effects 0.000 claims abstract description 4
- 239000002689 soil Substances 0.000 claims description 96
- 235000015097 nutrients Nutrition 0.000 claims description 36
- 230000009466 transformation Effects 0.000 claims description 28
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 17
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 13
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 13
- 229910052757 nitrogen Inorganic materials 0.000 claims description 13
- 229910052698 phosphorus Inorganic materials 0.000 claims description 13
- 239000011574 phosphorus Substances 0.000 claims description 13
- 239000011591 potassium Substances 0.000 claims description 13
- 229910052700 potassium Inorganic materials 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 239000005416 organic matter Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 6
- 230000004069 differentiation Effects 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000004804 winding Methods 0.000 claims description 2
- 238000011426 transformation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000012417 linear regression Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000003556 assay Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010902 straw Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
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 belongs to spectral remote sensing technical fields, a kind of method improving black earth nutrient content precision of prediction by spectrum transform is specifically disclosed, and this method is specifically includes the following steps: step (1) seeks by wave band blackland surface sample point the related coefficient of reflectivity and nutrient content；Step (2) converts black earth spectrum；Step (3), using black earth nutrient content as independent variable, establishes response relation model using transformed black earth spectrum in above-mentioned steps (2) as dependent variable；Step (4) carries out root-mean-square error to forecast sample and the model coefficient of determination is evaluated, and selects optimal models, realizes the raising of black earth nutrient content precision of prediction.Method of the invention establishes the response relation model of spectrum and nutrient content, and optimal models are selected in precision evaluation, realizes the raising of black earth nutrient content precision of prediction.
Description
Technical Field
The invention belongs to the technical field of spectrum remote sensing, and particularly relates to a method for improving prediction accuracy of black soil nutrient content through spectrum transformation.
Background
With the intensive research of the hyperspectral remote sensing technology in the field of ecological evaluation, a rapid evaluation technology system for black soil nutrients is established, and scientific basis can be provided for management of black soil resources. The different jump energy level differences of different nutrients in the black soil are different, and the content of each component of the black soil is indirectly deduced by analyzing the absorption spectrum of nutrient substances. In practical research, due to the interference of soil moisture, straw interference and other climatic factors, the corresponding relation between the spectral characteristics and the component content is difficult to accurately establish. The existing solution idea is to search for a potential rule by collecting a large amount of spectral data and performing mathematical statistics calculation, and to solve the nutrient content under the support of actually measured sample point data.
The disadvantages of the existing method are reflected in two aspects: firstly, the overall reflectivity of the black soil spectrum is low, the original spectrum data is directly counted, and a remarkable characteristic wave band is difficult to obtain, so that the inversion accuracy has a bottleneck; and secondly, in order to enhance the characteristic wave band, different researchers select different spectrum transformation methods, although the inversion accuracy can be improved in a specific research area, the characteristic wave bands extracted by different researchers are inconsistent due to the lack of a normative and scientific evaluation process. Although the inversion accuracy is higher than that of the original spectrum, the result is not repeatable due to the non-specification selection of the transformation method.
Therefore, scientific evaluation on the precision of the existing spectrum transformation method is urgently needed to form a set of standard data processing flow, so that the precision of the hyperspectral black soil nutrient content inversion is further improved.
Disclosure of Invention
The invention aims to provide a method for improving the prediction accuracy of the content of nutrients in black soil through spectral transformation.
The technical scheme for realizing the purpose of the invention is as follows: a method for improving the prediction accuracy of the content of nutrients in black soil through spectral transformation specifically comprises the following steps:
step (1) solving the correlation coefficient of the reflectivity and the nutrient content of the sampling point on the black soil ground wave band by wave band;
step (2) transforming the black soil spectrum;
step (3) establishing a response relation model by taking the spectrum of the black soil transformed in the step (2) as a dependent variable and the content of nutrients in the black soil as an independent variable;
and (4) evaluating the root mean square error and the model decision coefficient of the prediction sample, and selecting an optimal model to improve the prediction precision of the content of the black soil nutrients.
The specific steps of the step (1) are as follows: step (1.1) of solving the correlation r (X) between the reflectivity and the nutrient content band by bandi,Yi) (ii) a And (1.2) selecting a characteristic waveband of the black soil nutrient.
The correlation in the step (1.1)
And (3) in the step (1.2), the black soil nutrient comprises organic matters, nitrogen, phosphorus and potassium.
933.6, 914.5, 905, 866.8 and 943.1nm are selected as characteristic wave bands for predicting the organic matter content in the step (1.2); selecting 933.6, 866.8, 876.3, 847.7 and 914.5nm as characteristic bands for nitrogen content prediction; selecting 950.0, 933.6, 866.8, 857.3 and 914.5nm as characteristic bands for phosphorus content prediction; 523.7, 771.5, 571.4, 695.3 and 533.2nm were selected as characteristic bands for potassium content prediction.
The specific steps of the step (2) are as follows:
resampling the black soil spectrum, and determining the optimal extraction wavelength interval;
step (2.2) carrying out logarithmic reciprocal on the new value after the spectrum transformation of the black soil;
step (2.3) performing first order differentiation on the new value after the black soil spectrum transformation;
step (2.4) removing envelope lines of the black soil spectrum;
and (2.5) performing multivariate scattering correction on the new value after the black soil spectrum transformation.
The steps areThe formula for extracting the wavelength interval Δ i in (2.1) isThe logarithmic reciprocal formula in the step (2.2) is Rnew_i＝1/lgRi(ii) a The first order differential calculation formula in the step (2.3) is Rnew_i＝[Ri+Δi-Ri)]A,/Δ i; the step (2.4) of removing the winding line comprises the following steps: comparing all the convex peak points on the light black soil spectrum curve to obtain a maximum value point as an end point of the envelope curve, calculating the slope of a connecting line between the maximum value point and each maximum value point in the long wave direction, and taking the maximum slope point as the end point of the next envelope curve to carry out circulation until the last point; then taking the maximum value point as an envelope line end point, performing similar calculation in the short wave direction, and taking the slope minimum point as the next end point to perform circulation until the curve starting point; connecting the end points along the increasing direction of the wavelength, namely forming an envelope curve; the calculation formula of the multivariate scattering correction in the step (2.5) is Rnew_i＝(Ri-bi)/mi。
The specific steps of the step (3) are as follows: step (3.1) establishing a black soil nutrient organic matter neural network model; and (3.2) establishing a model of a nitrogen, phosphorus and potassium support vector machine for the black soil nutrient.
The specific steps of the step (4) are as follows: step (4.1) evaluation of prediction sample model root mean square XRMSAn error; and (4.2) predicting a sample model decision coefficient.
Root mean square in the step (4.1)
The invention has the beneficial technical effects that: the method provided by the invention carries out transformation such as resampling, logarithmic reciprocal, first-order differential, envelope removal, multivariate scattering correction and the like on the black soil spectrum, and establishes a quantitative extraction model of the contents of organic matters, nitrogen, phosphorus, potassium and other nutrients. According to the method, 5 typical spectrum transformation methods are processed on the basis of obtaining organic matter, nitrogen, phosphorus and potassium content characteristic wave bands by wave band nutrient content correlation relations, and the corresponding model precision is evaluated by establishing a response relation model, so that the spectrum transformation method is more scientific. In order to improve the spectrum inversion accuracy, the method processes the original spectrum reflectivity data into conversion values such as resampling, logarithmic reciprocal, first-order differentiation, envelope removal, multivariate scattering correction and the like. The method utilizes a neural network method to model the organic matter content of the sample, and utilizes a support vector machine to model the nitrogen, phosphorus and potassium content of the sample. The method can calculate the transformation method with the best extraction precision of each black soil nutrient, obtain the extraction precision difference of the five spectral transformation methods, and provide quantitative basis for mastering the response relation between the spectral transformation and the content of the black soil nutrients.
Drawings
FIG. 1 is a flow chart of a method for improving the prediction accuracy of the content of nutrients in black soil through spectral transformation.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in fig. 1, the method for improving the prediction accuracy of the content of nutrients in black soil by spectral transformation provided by the invention specifically comprises the following steps:
the method comprises the following steps of (1) solving the correlation coefficient of reflectivity and nutrient content of sampling points on the black soil ground wave band by wave band, and specifically comprises the following steps:
step (1.1) of solving the correlation r (X) between the reflectivity and the nutrient content band by bandi,Yi) The calculation formula is shown in the following formula (1):
in the formula, Cov (X)i,Yi) To assay the content XiWith hyperspectral reflectance data YiOf (4) covariance, Var [ X ]i]To assay the content XiVariance of (1), Var [ Y ]i]For hyperspectral reflectance data YiThe variance of (c).
Step (1.2) selecting characteristic wave bands of black soil nutrients
The black soil nutrient comprises organic matters, nitrogen, phosphorus and potassium.
On the hyperspectral image, 933.6, 914.5, 905, 866.8 and 943.1nm are selected as characteristic bands for organic matter content prediction.
On the hyperspectral image, 933.6, 866.8, 876.3, 847.7 and 914.5nm are selected as characteristic bands for nitrogen content prediction.
On a hyperspectral image, 950.0, 933.6, 866.8, 857.3 and 914.5nm are selected as characteristic bands for phosphorus content prediction.
On a hyperspectral image, 523.7, 771.5, 571.4, 695.3 and 533.2nm are selected as characteristic bands for potassium content prediction.
And (2) converting the black soil spectrum, which comprises the following specific steps:
step (2.1) resampling the black soil spectrum, and determining the optimal extraction wavelength interval delta i
Aiming at the scale uncertainty problem of the black soil spectrum and nutrient content extraction, the optimal black soil spectrum extraction wavelength interval delta i can be determined through resampling, and the calculation formula of the extraction wavelength interval delta i is shown as the following formula (2):
in the formula, Rnew_iAfter the spectrum of black soil is transformedA new value of (d); riThe spectral reflectivity of original black soil is obtained; Δ i is the extraction wavelength interval; when Δ i is an even number, n is Δ i, and when Δ i is an odd number, n is Δ i + 1.
Step (2.2) new value R after spectrum transformation of black soilnew_iAnd (3) performing logarithmic reciprocal calculation, wherein the logarithmic reciprocal calculation formula is shown as the following formula (3):
Rnew_i＝1/lgRi(3)
in the formula, Rnew_iThe new value is obtained after the spectrum of the black soil is transformed; riIs the original black soil spectral reflectance.
New value R after spectrum transformation of black soilnew_iAfter logarithmic calculation, the relative value can be approximate, and the data is prevented from being too large or too small. New value R after logarithmic calculation and black soil spectrum transformationnew_iAfter reciprocal calculation, the new value R of the black soil after spectrum transformation is obtainednew_iThe data are converted into the data with the same magnitude, so that the data are more comparable.
Step (2.3) new value R after black soil spectrum transformationnew_iFirst order differentiation is carried out, and a calculation formula of the first order differentiation is shown as the following formula (4):
Rnew_i＝[Ri+Δi-Ri)]/Δi (4)
in the formula, Rnew_iThe new value is obtained after the spectrum of the black soil is transformed; riThe spectral reflectivity of original black soil is obtained; ri+ΔiThe spectral reflectivity of the black soil is in a range spaced from the original wave band; Δ i is the extraction wavelength interval, depending on the conversion requirements.
And calculating differential values of different orders by performing data simulation on the black soil spectrum to quickly determine the change point of the black soil spectrum and the wavelength position of the maximum and minimum reflectivity. The first order differential enhances the effect of the spectral changes and compression of the black soil.
Step (2.4) of removing envelope curve of black soil spectrum
The specific steps of envelope removal are as follows: comparing all 'convex' peak points on the light black soil spectrum curve to obtain a maximum value point, using the maximum value point as an end point of the envelope curve, calculating the slope of a connecting line between the maximum value point and each maximum value point in the long wave direction, and using the maximum slope point as the end point of the next envelope curve to carry out circulation until the last point; then taking the maximum value point as an envelope line end point, performing similar calculation in the short wave direction, and taking the slope minimum point as the next end point to perform circulation until the curve starting point; these end points are connected in the wavelength increasing direction, i.e., an envelope is formed.
Step (2.5) new value R after black soil spectrum transformationnew_iPerforming multivariate scatter correction
Firstly, the average spectrum of all the spectra is taken as a standard spectrum, unitary linear regression operation is carried out on each sample spectrum and the standard spectrum, the regression constant and coefficient of each spectrum relative to the standard spectrum are calculated, the linear translation amount is subtracted, and simultaneously the regression coefficient is divided to correct the relative inclination of the baseline of the spectrum, so that the purpose of correcting the baseline translation and the offset of each spectrum under the reference of the standard spectrum is achieved, and the signal-to-noise ratio of the spectrum is improved on the premise of not losing the spectral absorption information.
New value R after spectrum transformation of black soilnew_iThe calculation formula for the multiple scattering correction is shown in the following formula (5):
Rnew_i＝(Ri-bi)/mi(5)
wherein,
in the formula, Rnew_iThe new value is obtained after the spectrum of the black soil is transformed; riThe spectral reflectivity of original black soil is obtained; m isiAnd biRespectively carrying out unary linear regression on each black soil spectrum and the average spectrum to obtain a relative offset coefficient and a translation quantity;the average value of each wave band of each black soil spectrum is shown.
Step (3) establishing a response relation model by taking the spectrum of the black soil transformed in the step (2) as a dependent variable and the content of nutrients in the black soil as an independent variable
Wherein, the organic matter in the black soil nutrient adopts a neural network model, and the nitrogen, phosphorus and potassium in the black soil nutrient adopt a support vector machine model.
Step (3.1) of establishing a black soil nutrient organic matter neural network model
The neuron learning rate is 4, a training error function is set by adopting a minimum root mean square error method, a hidden layer neuron excitation function is a transfer function tansig, an output layer neuron excitation function is a linear function purelin, and a training weight value updating method is an adaptive gradient descent method ADAPTTgdwm with momentum.
Step (3.2) establishing a model of a support vector machine for nitrogen, phosphorus and potassium in black soil nutrients
Supporting the model class selection of the vector machine for eps-regression, selecting linear of the kernel function, calculating the optimal gamma and penalty factor by adopting a trial-and-error method, wherein the gamma is set to be 10-5～10-1The penalty factors were selected from 10, 50 and 100, and the error bias for each combination was evaluated according to a 20-pass cross-check approach.
And (4) evaluating the root mean square error and the model decision coefficient of the prediction sample, and selecting an optimal model to improve the prediction precision of the content of the black soil nutrients.
Step (4.1) evaluation of prediction sample model root mean square XRMSError, root mean square XRMSThe formula is shown in the following formula (6):
xicalculate the nutrient content for each soil sample, XRMSThe root mean square value of the calculated value of the content.
Prediction sample root mean square XRMSThe smaller the error is, the better the model is, and the higher the prediction precision of the content of the black soil nutrients of the model is; root mean square error XRMSThe larger the model, the better the stability of the model, but the lower the accuracy of the model for predicting the content of black soil nutrients.
Step (4.2) predicting sample model decision coefficients
And after the prediction sample model is subjected to linear regression, evaluating the regression model to determine the goodness of fit of the coefficient.
The present invention has been described in detail with reference to the drawings and examples, but the present invention is not limited to the examples, and various changes can be made within the knowledge of those skilled in the art without departing from the spirit of the present invention. The prior art can be adopted in the content which is not described in detail in the invention.
Claims (10)
1. A method for improving the prediction accuracy of the content of nutrients in black soil through spectral transformation is characterized by comprising the following steps:
step (1) solving the correlation coefficient of the reflectivity and the nutrient content of the sampling point on the black soil ground wave band by wave band;
step (2) transforming the black soil spectrum;
step (3) establishing a response relation model by taking the spectrum of the black soil transformed in the step (2) as a dependent variable and the content of nutrients in the black soil as an independent variable;
and (4) evaluating the root mean square error and the model decision coefficient of the prediction sample, and selecting an optimal model to improve the prediction precision of the content of the black soil nutrients.
2. The method for improving the prediction accuracy of the content of the nutrients in the black soil through the spectral transformation as claimed in claim 1, wherein the specific steps of the step (1) are as follows: step (1.1) of solving the correlation r (X) between the reflectivity and the nutrient content band by bandi,Yi) (ii) a And (1.2) selecting a characteristic waveband of the black soil nutrient.
3. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 2, wherein the method comprises the following steps: the correlation in the step (1.1)
4. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 3, wherein the method comprises the following steps: and (3) in the step (1.2), the black soil nutrient comprises organic matters, nitrogen, phosphorus and potassium.
5. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 4, wherein the method comprises the following steps: 933.6, 914.5, 905, 866.8 and 943.1nm are selected as characteristic wave bands for predicting the organic matter content in the step (1.2); selecting 933.6, 866.8, 876.3, 847.7 and 914.5nm as characteristic bands for nitrogen content prediction; selecting 950.0, 933.6, 866.8, 857.3 and 914.5nm as characteristic bands for phosphorus content prediction; 523.7, 771.5, 571.4, 695.3 and 533.2nm were selected as characteristic bands for potassium content prediction.
6. The method for improving the prediction accuracy of the content of the nutrients in the black soil through the spectral transformation as claimed in claim 5, wherein the specific steps of the step (2) are as follows:
resampling the black soil spectrum, and determining the optimal extraction wavelength interval;
step (2.2) carrying out logarithmic reciprocal on the new value after the spectrum transformation of the black soil;
step (2.3) performing first order differentiation on the new value after the black soil spectrum transformation;
step (2.4) removing envelope lines of the black soil spectrum;
and (2.5) performing multivariate scattering correction on the new value after the black soil spectrum transformation.
7. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 6, wherein the method comprises the following steps: the formula for extracting the wavelength interval delta i in the step (2.1) isThe logarithmic reciprocal formula in the step (2.2) is Rnew_i＝1/lgRi(ii) a The first order differential calculation formula in the step (2.3) is Rnew_i＝[Ri+Δi-Ri)]A,/Δ i; the step (2.4) of removing the winding line comprises the following steps: comparing all the convex peak points on the light black soil spectrum curve to obtain a maximum value point as an end point of the envelope curve, calculating the slope of a connecting line between the maximum value point and each maximum value point in the long wave direction, and taking the maximum slope point as the end point of the next envelope curve to carry out circulation until the last point; then taking the maximum value point as an envelope line end point, performing similar calculation in the short wave direction, and taking the slope minimum point as the next end point to perform circulation until the curve starting point; connecting the end points along the increasing direction of the wavelength, namely forming an envelope curve; the calculation formula of the multivariate scattering correction in the step (2.5) is Rnew_i＝(Ri-bi)/mi。
8. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 7, wherein the method comprises the following steps: the specific steps of the step (3) are as follows: step (3.1) establishing a black soil nutrient organic matter neural network model; and (3.2) establishing a model of a nitrogen, phosphorus and potassium support vector machine for the black soil nutrient.
9. The method for improving the prediction accuracy of the content of the nutrients in the black soil through the spectral transformation as claimed in claim 8, wherein the specific steps of the step (4) are as follows: step (4.1) evaluation of prediction sample model root mean square XRMSAn error; and (4.2) predicting a sample model decision coefficient.
10. The method for improving the prediction accuracy of the nutrient content in the black soil by the spectral transformation according to claim 9, wherein the method comprises the following steps: root mean square in the step (4.1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589000.4A CN109540811A (en) | 2018-12-25 | 2018-12-25 | A method of black earth nutrient content precision of prediction is improved by spectrum transform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589000.4A CN109540811A (en) | 2018-12-25 | 2018-12-25 | A method of black earth nutrient content precision of prediction is improved by spectrum transform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109540811A true CN109540811A (en) | 2019-03-29 |
Family
ID=65857956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811589000.4A Pending CN109540811A (en) | 2018-12-25 | 2018-12-25 | A method of black earth nutrient content precision of prediction is improved by spectrum transform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109540811A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110687053A (en) * | 2019-10-08 | 2020-01-14 | 中国科学院地理科学与资源研究所 | Regional organic matter content estimation method and device based on hyperspectral image |
| CN114486761A (en) * | 2022-01-24 | 2022-05-13 | 云南省热带作物科学研究所 | Method for rapidly estimating magnesium content of rubber tree leaves |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954567A (en) * | 2014-04-15 | 2014-07-30 | 塔里木大学 | Soil salinity determining method based on continuum removal method |
| CN106644978A (en) * | 2016-11-16 | 2017-05-10 | 山东省科学院海洋仪器仪表研究所 | Detection method capable of judging precision and used for analyzing content of soil nutrients based on spectral characteristic wavelength |
| CN108663330A (en) * | 2018-04-19 | 2018-10-16 | 中国国土资源航空物探遥感中心 | A kind of vegetation-covered area soil copper inversion method based on blade measured spectra |
-
2018
- 2018-12-25 CN CN201811589000.4A patent/CN109540811A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954567A (en) * | 2014-04-15 | 2014-07-30 | 塔里木大学 | Soil salinity determining method based on continuum removal method |
| CN106644978A (en) * | 2016-11-16 | 2017-05-10 | 山东省科学院海洋仪器仪表研究所 | Detection method capable of judging precision and used for analyzing content of soil nutrients based on spectral characteristic wavelength |
| CN108663330A (en) * | 2018-04-19 | 2018-10-16 | 中国国土资源航空物探遥感中心 | A kind of vegetation-covered area soil copper inversion method based on blade measured spectra |
Non-Patent Citations (3)
| Title |
|---|
| 张东辉 等: "光谱变换方法对黑土养分含量高光谱遥感反演精度的影响", 《农业工程学报》 * |
| 王雅丽 等: "《概率论与数理统计（经管类）》", 31 July 2018, 湖南师范大学出版社 * |
| 高灯州 等: "闽江口湿地土壤全氮含量的高光谱遥感估算", 《生态学杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110687053A (en) * | 2019-10-08 | 2020-01-14 | 中国科学院地理科学与资源研究所 | Regional organic matter content estimation method and device based on hyperspectral image |
| CN114486761A (en) * | 2022-01-24 | 2022-05-13 | 云南省热带作物科学研究所 | Method for rapidly estimating magnesium content of rubber tree leaves |
| CN114486761B (en) * | 2022-01-24 | 2024-04-12 | 云南省热带作物科学研究所 | Rapid estimation method for magnesium content of rubber tree blade |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110174359B (en) | Aviation hyperspectral image soil heavy metal concentration assessment method based on Gaussian process regression | |
| Banerjee et al. | High-throughput phenotyping using digital and hyperspectral imaging-derived biomarkers for genotypic nitrogen response | |
| CN108303044B (en) | Leaf area index obtaining method and system | |
| CN110531054B (en) | Soil organic carbon prediction uncertainty estimation method based on Bootstrap sampling | |
| CN111855589A (en) | Remote sensing inversion model and method for rice leaf nitrogen accumulation | |
| CN103196838B (en) | Hyperspectral remote sensing monitoring method for coastal estuary eutrophication | |
| CN108801934A (en) | A kind of modeling method of soil organic carbon EO-1 hyperion prediction model | |
| CN107607486B (en) | Soil total nitrogen detection method and device | |
| CN104502288A (en) | Soil lead content measurement method using visible and near-infrared spectroscopy technology | |
| CN111044516A (en) | Remote sensing estimation method for chlorophyll content of rice | |
| CN110779875B (en) | Method for detecting moisture content of winter wheat ear based on hyperspectral technology | |
| CN103344597B (en) | Anti-flavored-interference near infrared non-destructive testing method for internal components of lotus roots | |
| CN110503156A (en) | A kind of multivariate calibration characteristic wavelength selection method based on least correlativing coefficient | |
| CN104778349B (en) | One kind is used for rice table soil nitrogen application Classified Protection | |
| CN114676636A (en) | Grassland area soil moisture rapid inversion method integrating vegetation and habitat characteristics | |
| CN110569605A (en) | Non-glutinous rice leaf nitrogen content inversion model method based on NSGA2-ELM | |
| CN109540811A (en) | A method of black earth nutrient content precision of prediction is improved by spectrum transform | |
| CN105608296B (en) | A kind of blade potassium concn inversion method based on lichee canopy spectra | |
| CN111855608A (en) | Near-infrared nondestructive detection method for apple acidity based on fusion characteristic wavelength selection algorithm | |
| Chen et al. | Hyperspectral detection of sugar content for sugar-sweetened apples based on sample grouping and SPA feature selecting methods | |
| CN113686811A (en) | Spectral data processing method based on double sensors | |
| Xiao et al. | Rapid detection of maize seed germination rate based on Gaussian process regression with selection kernel function | |
| CN115951025B (en) | Inversion method for total phosphorus concentration of water body | |
| CN115358321A (en) | Hyperspectral soil quick-acting potassium content prediction method based on convolutional neural network | |
| CN114004147B (en) | Method for simultaneously predicting multiple soil attributes under soil wet state |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |