CN111507312A - Soil moisture extraction method based on hyperspectral data - Google Patents
Soil moisture extraction method based on hyperspectral data Download PDFInfo
- Publication number
- CN111507312A CN111507312A CN202010457335.1A CN202010457335A CN111507312A CN 111507312 A CN111507312 A CN 111507312A CN 202010457335 A CN202010457335 A CN 202010457335A CN 111507312 A CN111507312 A CN 111507312A
- Authority
- CN
- China
- Prior art keywords
- wave band
- soil moisture
- sensitive
- absorption rate
- hyperspectral
- 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
- 239000002689 soil Substances 0.000 title claims abstract description 43
- 238000000605 extraction Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000010521 absorption reaction Methods 0.000 claims abstract description 25
- 238000002310 reflectometry Methods 0.000 claims abstract description 21
- 238000012216 screening Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 8
- 230000035945 sensitivity Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract 1
- 238000000513 principal component analysis Methods 0.000 description 9
- 230000003595 spectral effect Effects 0.000 description 9
- 239000013598 vector Substances 0.000 description 7
- 238000001228 spectrum Methods 0.000 description 6
- 238000002835 absorbance Methods 0.000 description 5
- 238000012952 Resampling Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000004927 clay Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005669 field effect Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 229910017135 Fe—O Inorganic materials 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000005090 crystal field Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- UQSXHKLRYXJYBZ-UHFFFAOYSA-N iron oxide Inorganic materials [Fe]=O UQSXHKLRYXJYBZ-UHFFFAOYSA-N 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- NDLPOXTZKUMGOV-UHFFFAOYSA-N oxo(oxoferriooxy)iron hydrate Chemical compound O.O=[Fe]O[Fe]=O NDLPOXTZKUMGOV-UHFFFAOYSA-N 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a soil moisture extraction method based on hyperspectral data. It comprises the following steps: preliminarily processing remote sensing hyperspectral reflectivity data, and solving an apparent absorption rate and a first derivative of the apparent absorption rate according to the reflectivity; extracting a wave band screening coefficient by using a principal component analysis method, and selecting a sensitive wave band; establishing an optimal exponential method based on the standard deviation of the wave band and the correlation coefficient, and further optimizing the sensitive wave band by combining the physical significance of the wave band; and establishing an inversion model of the soil moisture by utilizing the sensitive wave band and using a stepwise regression method. The invention overcomes the defects of excessive variables, lower efficiency, poorer model stability and the like of the existing method model; has the advantage of improving the extraction precision of soil moisture.
Description
Technical Field
The invention relates to the fields of hyperspectral remote sensing and irrigation and water conservancy, in particular to a soil moisture extraction method based on hyperspectral data.
Background
The accurate acquisition of soil moisture plays an important role in agricultural development, ecological protection and the like in arid and semiarid regions; the traditional method for extracting soil moisture is to collect a sample in the field and bring the sample back to a laboratory for testing, and the method has high precision, but has high labor cost and long time consumption; the method for extracting the large-area soil moisture information by utilizing the hyperspectral remote sensing data is an important scientific and technological support.
The currently used satellite hyperspectral data or the hyperspectral data acquired by a ground object spectrometer are mostly expressed as reflectivity data; the reflectivity data of visible light, near infrared and short-wave infrared spectrums are closely related to various properties such as soil moisture, salt, organic matters, color, ferric oxide, texture and the like; however, the amount of information provided by the reflectivity data is limited, and the reflectivity data cannot be directly reflected due to other spectral characteristics such as absorption characteristics of a spectral curve, such as absorption peaks and absorption valleys, shape characteristics of the spectral curve, such as inflection points, convex points and concave points, and the influence of a baseline effect on the spectral curve; therefore, a transform process, such as an absorptance transform, a derivative transform, etc., is required on the hyperspectral reflectance data.
The existing regression methods for hyperspectral inversion of soil moisture models comprise a partial least square method, a neural network method, a stepwise regression method, a multiple linear regression method and the like; the linear partial least square method and the nonlinear neural network method can overcome the problem of multiple collinearity of high spectral variables and establish a high-dimensional regression model; however, because the variables of the model are too many, the efficiency of model calibration is low, the stability of the model is poor, and the popularization is not strong; the stepwise regression method, the multiple linear regression method and the like have high requirements on the number of variables, and high-dimensional hyperspectral data are difficult to directly use.
Therefore, it is very important to develop a soil moisture extraction method of hyperspectral data with good model stability and high model calibration efficiency.
Disclosure of Invention
The invention aims to provide a soil moisture extraction method based on hyperspectral data, which improves the extraction efficiency of soil moisture and has good model stability.
In order to achieve the purpose, the technical scheme of the invention is as follows: the soil moisture extraction method based on hyperspectral data is characterized by comprising the following steps of: the method comprises the following steps:
step 1: the method comprises the following steps of (1) preliminarily processing hyperspectral remote sensing reflectivity data of soil, and solving an apparent absorption rate and a first derivative of the apparent absorption rate according to the reflectivity;
step 2: extracting a wave band screening coefficient by using a principal component analysis method, and primarily selecting a sensitive wave band;
on the basis of the hyperspectral data of the apparent absorption rate and the first-order derivative of the apparent absorption rate obtained in the step 1, solving a wave band screening coefficient by using a principal component analysis method, and selecting a sensitive wave band;
and step 3: extracting the optimal index of each wave band based on the standard deviation and the correlation coefficient of the selected wave band, and further optimizing the sensitive wave band by combining the physical significance of the wave band;
and 4, step 4: and establishing an inversion model of the soil moisture content by using a stepwise regression method.
The invention has the following advantages: (1) carrying out absorption rate transformation and derivative transformation on the hyperspectral reflectivity data, extracting apparent absorption rates and first-order derivatives of the apparent absorption rates, and highlighting soil spectral characteristics to carry out soil moisture inversion; (2) solving a wave band screening coefficient by using a principal component analysis method, and extracting sensitive wave bands distributed in visible light, near infrared and short wave infrared ranges; the sensitive wave bands comprise 435, 520, 575, 1400, 1890, 1930, 1955, 1995 and 2410 nm; the sensitive wave band covers effective information in the hyperspectral data, the variable number of spectral analysis is reduced, the complexity in a soil moisture extraction equation is reduced, and the calculation efficiency and precision are improved; (3) on the basis of selecting 9 sensitive wave bands, based on standard deviation and correlation coefficient, an optimal index of the wave band is established, and four sensitive wave bands of 435nm, 1400nm, 1930 nm and 2410nm are further optimized by combining the physical significance of the wave bands; (4) the extraction efficiency of soil moisture is improved, the stability of the model is good, and the adaptability of the selected sensitive wave band is strong (the method is not only suitable for the area of the embodiment of the invention, but also suitable for other areas).
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
FIG. 2 is an apparent absorbance of an embodiment of the invention.
FIG. 3 is a first derivative plot of the apparent absorbance of an embodiment of the invention.
FIG. 4 is a graph of band-pass filter coefficients as a function of band in accordance with an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail with reference to the accompanying drawings, which are not intended to limit the present invention, but are merely exemplary. While the advantages of the invention will be clear and readily understood by the description.
The soil moisture extraction method based on hyperspectral data is characterized by comprising the following steps of: the method comprises the following steps:
step 1: the method comprises the following steps of (1) preliminarily processing hyperspectral remote sensing reflectivity data of soil, and solving an apparent absorption rate and a first derivative of the apparent absorption rate according to the reflectivity;
step 2: extracting a wave band screening coefficient by using a principal component analysis method, and primarily selecting a sensitive wave band;
extracting a wave band screening coefficient by using a principal component analysis method on the basis of the hyperspectral data of the apparent absorption rate and the first-order derivative of the apparent absorption rate obtained in the step 1, and selecting a sensitive wave band;
and step 3: extracting the optimal index of each wave band based on the standard deviation and the correlation coefficient of the selected wave band, and further optimizing the sensitive wave band by combining the physical significance of the wave band;
and 4, step 4: establishing an inversion model of the soil moisture content by using a stepwise regression method;
in the step 2, the selected sensitive wave bands are distributed in the visible light, near infrared and short wave infrared ranges, and the sensitive wave bands comprise 435, 520, 575, 1400, 1890, 1930, 1955, 1995 and 2410 nm;
in step 3, the selected sensitive wave bands are distributed in the visible light, near infrared and short wave infrared ranges, and the sensitive wave bands comprise 435, 1400,1930 and 2410 nm; these bands are important for soil moisture inversion, and their physical significance lies in: 435nm is a representative band of 400-600nm, and Fe3+、Fe2+The crystal field effect caused by plasma is related to charge transfer of Fe-O, B-O and the like; 1400nm is a 1300-1550nm representative band associated with the field effect of the crystal and OH-Fe, H2Molecular vibrational correlation of O; 1930,2410nm is a representative waveband of 1810-2、H2O, etc. are involved in molecular vibrations.
Example 1
The invention takes the moisture information extracted based on the hyperspectral soil data (soil samples mainly comprising clay and silty clay) in the northwest region as an embodiment for detailed description, and has guiding significance for other region soil moisture extraction methods based on the hyperspectral data.
Step 1: preliminarily processing remote sensing hyperspectral reflectivity data, and solving an apparent absorption rate and a first derivative of the apparent absorption rate according to the reflectivity;
primarily processing remote sensing hyperspectral data by utilizing a basic image processing method for resampling and a common data statistical method; resampling is a process of interpolating information of one type of pixel according to the information of another type of pixel; in remote sensing, resampling is a process of extracting a low-resolution image from a high-resolution remote sensing image;
measuring a soil sample spectrum signal by using an AgriSpec spectrometer manufactured by American ASD (analytical spectral device), wherein the spectrum range provided by the instrument is 350-2500 nm, and the resolution is 1 nm; in order to reduce the data volume and enhance the generalization of the model, the model can be conveniently applied to hyperspectral data (the resolution is 5nm) provided by the existing high-resolution five-satellite AHSI sensor, and the average value of the reflectivity of 5 continuous wave bands is calculated to replace the original reflectivity value through a spectrum smoothing technology; therefore, the reflectivity data in the range of 400-2450 nm is processed, and the spectral resolution of 1nm is resampled to 5 nm; most of the resampled information is still stored;
the soil hyperspectral data represent the reflectivity spectrum of the soil, the soil sample hyperspectral data after resampling still represent the reflectivity spectrum R of the soil, and the information content of the reflectivity data is highlighted by utilizing two spectrum pretreatment technologies:
the first spectral pretreatment method is to determine the apparent absorbance a (as shown in fig. 2):
A＝log(1/R)
the second is to find the first derivative (a') of the apparent absorbance based on the apparent absorbance (as shown in fig. 3);
normalizing the two groups of data A and A 'to normalized data with the mean value of 0 and the variance of 1, so as to enhance the contrast of different forms of hyperspectral data and obtain the normalized apparent absorption rate A and the first derivative A' thereof;
step 2: on the basis of the apparent absorption rate (A) obtained in the step 1, a first derivative (A') of the apparent absorption rate and hyperspectral data, solving a wave band screening coefficient by using a Principal Component Analysis (PCA) method, and selecting a sensitive wave band; 9 sensitive bands sensitive to the moisture of the soil sample are selected, wherein the bands are 435, 520, 575, 1400, 1890, 1930, 1955, 1995 and 2410nm (the selected sensitive bands are not only suitable for the embodiment of the invention, but also suitable for other regions);
the method for solving the band screening coefficient is obtained according to a load vector and a principal component characteristic value of a Principal Component Analysis (PCA); when a Principal Component Analysis (PCA) method is used for processing data, a plurality of principal components can be extracted, and the principal components represent most of information of original measured hyperspectral data; in the PCA processing process, each principal component can obtain two groups of output variables, and the first group of variables are load vectors of the principal components; the second set of variables are eigenvalues of the principal components; it is generally considered that the greater the absolute value of the coefficient (positive or negative) of a band in the load vector, the more important the band is; the characteristic value influences the importance of the load vector, the load vector can be corrected by utilizing the characteristic value, the first three main components of A are respectively subjected to load vector square multiplication operation and the characteristic value, the load vector square multiplication operation and the characteristic value multiplication operation are added to obtain a wave band screening coefficient of A, the wave band screening coefficient of A 'is solved in the same way, and finally the wave band screening coefficient of A and the wave band screening coefficient of A' are added to obtain a final wave band screening coefficient; in the embodiment, a sensitive waveband is extracted through a waveband screening coefficient, and the waveband screening coefficient shows continuous fluctuation characteristics in an interval (generally more than 20 nm), which indicates that the waveband in the interval is relatively important;
in specific implementation, firstly, the hyperspectral data are processed by using principal component analysis, and for A, A' two groups of hyperspectral data, after PCA processing, the explained variance of the first three principal components of the data (the sum of the characteristic values of the first three principal components in each group of data) reaches 90%, and information is contained in the first three principal components; calculating A, A' two groups of hyperspectral data, adding the wave band screening coefficients, and displaying the wave band screening coefficients along with the change graph of the wave band screening coefficients along with the wavelength (as shown in figure 4); 435, 520, 575, 1400, 1890, 1930, 1955, 1995 and 2410nm 9 sensitive wavebands are selected according to the waveband screening coefficient change diagram;
and step 3: extracting the optimal index OI (the standard deviation of a certain waveband is divided by the sum of the absolute values of the correlation coefficients of the waveband and other wavebands) of each waveband based on the standard deviation and the correlation coefficient of the selected waveband, preferentially extracting wavebands with large optimal indexes and representative physical meanings of the wavebands, and further preferentially selecting sensitive wavebands; the final selected sensitive band comprises 435, 1400,1930,2410 nm;
Siis the standard deviation of the ith band, rijIs the correlation coefficient of the ith band and the jth band, which is k bands, in this case k is 18, i.e. the 9 sensitive bands of a plus the 9 sensitive bands of a'.
And 4, step 4: establishing an inversion model of the water content of 99 soil samples by using the sensitive wave bands in the step 3 and a stepwise regression method;
Y＝-0.1837·A435+0.8016·A1930-0.6157·A2410+0.0833·A’1400-0.0424
using the decision coefficient r2The accuracy of the decision model, and the relative root mean square error rmse.
m is the soil moisture test value, y is the soil moisture prediction value, and n is the soil sample number.
Coefficient of determination r of model20.932, relative root mean square error rmse of 0.115; the model was verified using 99 actual measurement samples (model verification samples and calibration samples were selected alternately for water content), and the coefficient of determination r of the model was determined20.935 and a relative root mean square error rmse of 0.112;
other details not described are prior art.
Claims (3)
1. The soil moisture extraction method based on hyperspectral data is characterized by comprising the following steps of: the method comprises the following steps:
step 1: the method comprises the following steps of (1) preliminarily processing hyperspectral remote sensing reflectivity data of soil, and solving apparent absorption rate and first-order reciprocal of the apparent absorption rate according to the reflectivity;
step 2: extracting a wave band screening coefficient by using a principal component analysis method, and primarily selecting a sensitive wave band;
extracting a wave band screening coefficient by using a principal component analysis method on the basis of the hyperspectral data of the apparent absorption rate and the first-order derivative of the apparent absorption rate obtained in the step 1, and selecting a sensitive wave band;
and step 3: extracting the optimal index of each wave band based on the standard deviation and the correlation coefficient of the selected wave band, and further optimizing the sensitive wave band by combining the physical significance of the wave band;
and 4, step 4: and establishing an inversion model of the soil moisture content by using a stepwise regression method.
2. The hyperspectral data based soil moisture extraction method according to claim 1, characterized in that: in step 2, the selected sensitive wave bands are distributed in the visible light, near infrared and short wave infrared ranges, and the sensitive wave bands comprise 435, 520, 575, 1400, 1890, 1930, 1955, 1995 and 2410 nm.
3. The hyperspectral data based soil moisture extraction method according to claim 2, characterized in that: in step 3, the sensitivity wave bands finally selected by using the optimal exponential method comprise 435, 1400,1930 and 2410 nm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010457335.1A CN111507312A (en) | 2020-05-26 | 2020-05-26 | Soil moisture extraction method based on hyperspectral data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010457335.1A CN111507312A (en) | 2020-05-26 | 2020-05-26 | Soil moisture extraction method based on hyperspectral data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111507312A true CN111507312A (en) | 2020-08-07 |
Family
ID=71876984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010457335.1A Pending CN111507312A (en) | 2020-05-26 | 2020-05-26 | Soil moisture extraction method based on hyperspectral data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507312A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104122210A (en) * | 2014-07-02 | 2014-10-29 | 中国林业科学研究院林业研究所 | Hyperspectral waveband extraction method based on optimum index factor-correlation coefficient method |
| CN106918566A (en) * | 2017-03-09 | 2017-07-04 | 长江勘测规划设计研究有限责任公司 | Soil moisture based on high-spectral data, salinity information consolidation extracting method |
| US10154624B2 (en) * | 2016-08-08 | 2018-12-18 | The Climate Corporation | Estimating nitrogen content using hyperspectral and multispectral images |
| CN109344536A (en) * | 2018-10-30 | 2019-02-15 | 中国科学院、水利部成都山地灾害与环境研究所 | A kind of multi-level passive microwave soil moisture verification method coupling multi-source data |
| CN109460789A (en) * | 2018-11-07 | 2019-03-12 | 中国农业科学院农田灌溉研究所 | A kind of soil moisture fusion method based on Bayes's maximum entropy |
| CN110795895A (en) * | 2020-01-06 | 2020-02-14 | 南京邮电大学 | Method for predicting soil moisture by using earth surface reflection signals and random forest regression algorithm |
-
2020
- 2020-05-26 CN CN202010457335.1A patent/CN111507312A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104122210A (en) * | 2014-07-02 | 2014-10-29 | 中国林业科学研究院林业研究所 | Hyperspectral waveband extraction method based on optimum index factor-correlation coefficient method |
| US10154624B2 (en) * | 2016-08-08 | 2018-12-18 | The Climate Corporation | Estimating nitrogen content using hyperspectral and multispectral images |
| CN106918566A (en) * | 2017-03-09 | 2017-07-04 | 长江勘测规划设计研究有限责任公司 | Soil moisture based on high-spectral data, salinity information consolidation extracting method |
| CN109344536A (en) * | 2018-10-30 | 2019-02-15 | 中国科学院、水利部成都山地灾害与环境研究所 | A kind of multi-level passive microwave soil moisture verification method coupling multi-source data |
| CN109460789A (en) * | 2018-11-07 | 2019-03-12 | 中国农业科学院农田灌溉研究所 | A kind of soil moisture fusion method based on Bayes's maximum entropy |
| CN110795895A (en) * | 2020-01-06 | 2020-02-14 | 南京邮电大学 | Method for predicting soil moisture by using earth surface reflection signals and random forest regression algorithm |
Non-Patent Citations (2)
| Title |
|---|
| CHI XU 等: "Prediction of Soil Moisture Content and Soil Salt Concentration from Hyperspectral Laboratory and Field Data", 《REMOTE SENSING》 * |
| 王李娟等: "《设施作物遥感监测原理与方法》", 31 October 2017, 中国矿业大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107219188B (en) | A method of based on the near-infrared spectrum analysis textile cotton content for improving DBN | |
| CN108956505B (en) | Method and device for detecting concentration of chlorophyll a in small water body based on Sentinel-2 image | |
| CN106918566A (en) | Soil moisture based on high-spectral data, salinity information consolidation extracting method | |
| Tiwari et al. | Prediction modeling and mapping of soil carbon content using artificial neural network, hyperspectral satellite data and field spectroscopy | |
| CN113866102B (en) | Soil health investigation monitoring method based on spectrum | |
| CN112991288A (en) | Hyperspectral remote sensing image fusion method based on abundance image sharpening reconstruction | |
| CN113252583B (en) | Method for calculating alpine hay coverage based on hay vegetation index | |
| CN114199800B (en) | Rice sheath blight disease identification method, system, equipment and medium | |
| CN114676636A (en) | Grassland area soil moisture rapid inversion method integrating vegetation and habitat characteristics | |
| CN115372282A (en) | Farmland soil water content monitoring method based on hyperspectral image of unmanned aerial vehicle | |
| CN114216877B (en) | Automatic detection and reconstruction method and system for spectral peak in tea near infrared spectral analysis | |
| Liu et al. | Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method | |
| CN106525729A (en) | Substance element content information detection method based on spectral analysis technology | |
| Wan et al. | MAE-NIR: A masked autoencoder that enhances near-infrared spectral data to predict soil properties | |
| CN111507312A (en) | Soil moisture extraction method based on hyperspectral data | |
| CN116312860A (en) | Agricultural product soluble solid matter prediction method based on supervised transfer learning | |
| CN115984715A (en) | Hyperspectral satellite adaptive atmosphere correction method based on prior ground object spectrum matching | |
| CN113496218B (en) | Evaluation method and system for hyperspectral remote sensing sensitive wave band selection mode | |
| CN115392305A (en) | Soil organic matter content high spectrum modeling method based on improved time convolution network | |
| CN114942233A (en) | Near infrared spectrum characteristic wavelength selection method, device, equipment and storage medium | |
| CN113177488A (en) | Hyperspectral image waveband selection method based on optimal index waveband combination | |
| Mejia-Cabrera et al. | Soil salinity estimation of sparse vegetation based on multispectral image processing and machine learning | |
| Yu et al. | Influence of light intensity distribution characteristics of light source on measurement results of canopy reflectance spectrometers | |
| CN112697724A (en) | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle | |
| CN118225711B (en) | Intelligent soil water potential detection method based on spectral analysis |
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: 20200807 |