CN110579186B - Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process - Google Patents

Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process Download PDF

Info

Publication number
CN110579186B
CN110579186B CN201910790564.2A CN201910790564A CN110579186B CN 110579186 B CN110579186 B CN 110579186B CN 201910790564 A CN201910790564 A CN 201910790564A CN 110579186 B CN110579186 B CN 110579186B
Authority
CN
China
Prior art keywords
pure
simulated
reflectivity
prosai
canopy
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
Application number
CN201910790564.2A
Other languages
Chinese (zh)
Other versions
CN110579186A (en
Inventor
黄健熙
尹峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN201910790564.2A priority Critical patent/CN110579186B/en
Publication of CN110579186A publication Critical patent/CN110579186A/en
Application granted granted Critical
Publication of CN110579186B publication Critical patent/CN110579186B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
    • G01B11/285—Measuring arrangements characterised by the use of optical techniques for measuring areas using photoelectric detection means
    • 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
    • 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)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention belongs to the field of agricultural remote sensing, and relates to a crop growth monitoring method based on inverse Gaussian process inversion leaf area index, which comprises the steps of obtaining the reflectivity of the No. 2 ground surface of a sentinel, extracting a crop space distribution diagram, obtaining the spectrum of a PROSAI L simulated crop under different backgrounds, converting the spectrum into a waveband spectrum, analyzing the main component of the simulated ground surface reflectivity under a black soil background to obtain the reflection characteristic of a pure canopy, analyzing the main component of the measured soil spectral reflectivity to obtain the reflection characteristic of the pure soil, linearly decomposing the simulated ground surface reflectivity containing soil information to obtain the reflection characteristic of the simulated pure canopy, simulating the mapping relation between the reflection characteristic of the pure canopy and L AI through Gaussian process simulation learning to obtain a trained Gaussian process model, linearly decomposing the No. 2 image of the sentinel to obtain the reflection characteristic of the pure canopy, selecting the simulated pure canopy reflectivity which is closest to the simulated pure canopy reflectivity to be input into the trained Gaussian process model to obtain L AI, and judging the current crop growth based on the average L AI track in the past.

Description

Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process
Technical Field
The invention belongs to the field of agricultural remote sensing, and particularly relates to a crop growth monitoring method for inverting a leaf area index based on an inverse Gaussian process.
Background
In current practical application, growth monitoring is generally carried out based on NDVI, and is less based on the leaf area index L AI, because the inversion of L AI is more difficult than that of NDVI obtained by only calculating the wave band, however, NDVI only reflects the spectral information of the crops in the red wave band and the near red wave band, and L AI reflects the sum of the single-sided green leaf area on the unit surface area, and the sum is more closely related to important biophysical processes of crops such as canopy interception, evapotranspiration, photosynthesis and the like, and the growth of the crops can be reflected more comprehensively.
At present, L AI is obtained mainly by using a remote sensing technology, one method is a statistical empirical relationship between canopy light radiation information and L AI, the other method is inversion L AI from the canopy light radiation information through a radiation transmission model, the first method is lack of universality, the empirical relationship established in a certain place is difficult to popularize in another place, the second method is very complex in calculation and has a plurality of input parameters, different-parameter same effects are easy to occur in inversion, and the inversion accuracy of L AI is reduced.
Disclosure of Invention
In order to solve the problem of multi-parameter simultaneous effect of the traditional method for obtaining L AI by inverting the canopy light radiation information through a radiation transmission model, the invention simulates the radiation transmission model based on the inverse Gaussian process, can quickly invert L AI, does not need ground actual measurement data in inversion, and can avoid different-parameter simultaneous effect, and by comparing L AI tracks of the growth of crops in the past, people can monitor the growth vigor of the current crops in time.
The invention provides a crop growth monitoring method based on inverse Gaussian process inversion leaf area index, which comprises the following specific steps:
s1, obtaining the consistent ground surface reflectivity of the sentinel No. 2 by using a sensor indifference atmospheric correction method SIAC;
s2, extracting each key growth period of the crop to be detected by using the time sequence data of the sentinel No. 2 surface reflectivity corresponding to the sample point, and performing supervision and classification to obtain a crop space distribution map in a research area;
s3, carrying out extensive sampling aiming at a PROSAI L model parameter set corresponding to crops to obtain crop spectrums simulated by PROSAI L under the background of black soil and crop spectrums simulated by PROSAI L under the background containing soil information;
s4, converting the crop spectrum simulated in S3 into a wave band spectrum corresponding to the sentinel No. 2 by using the spectrum response function of the sentinel No. 2, namely obtaining the surface reflectivity simulated by the PROSAI L under the background of black soil and the surface reflectivity simulated by the PROSAI L under the background containing soil information;
s5, performing principal component analysis on the surface reflectivity simulated by PROSAI L under the background of the black soil obtained in S4, and selecting the first 4 principal components as the spectral reflection characteristics of the pure canopy, and simultaneously performing principal component analysis on the reflectivity of the sentinel No. 2 corresponding to the actually measured soil spectral curve, and selecting the first 2 principal components as the spectral reflection characteristics of the pure soil;
s6, performing linear decomposition on the earth surface reflectivity simulated by the PROSAI L under the background containing the soil information obtained in S4 based on the spectral reflection characteristics of the pure canopy and the spectral reflection characteristics of the pure soil obtained in S5 to obtain the pure canopy reflectivity simulated by the PROSAI L;
s7, using the Gaussian process to simulate and learn the mapping relation between the PROSAI L simulated earth surface reflectivity and L AI under the black soil background obtained in S4, realizing the prediction from the pure canopy spectral reflectivity to L AI, and obtaining a well-trained Gaussian process model;
s8, based on the result of the principal component analysis of S5, carrying out linear decomposition on the original sentinel No. 2 image to obtain the corresponding pure canopy reflectivity, then comparing the pure canopy reflectivity simulated by the PROSAI L obtained in S6 with the pure canopy reflectivity, selecting the pure canopy reflectivity simulated by the PROSAI L closest to the pure canopy reflectivity, inputting the pure canopy reflectivity into a Gaussian process model trained by S7 to obtain L AI, and comparing the L AI track of the current year with the average L AI track of the plot of the last 3 years as a reference, thereby judging the growth vigor of the current crop.
In step S1, the SIAC is a method of the invention, the code of which is disclosed in the GitHub platform, and the website is https: com/MarcYin/SIAC.
The S3 specific method comprises the steps of obtaining the minimum value and the maximum value of main biophysical parameters of a PROSAI L model corresponding to crops according to a large number of actually measured sample points, randomly and uniformly sampling by using a Latin hypercube sampling method in the range, inputting a large number of sampled parameters into the PROSAI L model, and simulating the spectrum of the crops under different growth conditions to obtain the spectrum of the crops simulated by the PROSAI L under the black soil background and the spectrum of the crops simulated by the PROSAI L under the background containing soil information.
The black soil background in S3 means that the simulated spectrum does not include soil information, and the spectrum in the black soil background is the spectrum of the pure canopy.
In step S7, the prediction of the pure canopy spectral feature to L AI is implemented by the following formula:
f*and the training sample point y with Gaussian noise has a multivariate Gaussian distribution:
Figure BDA0002179425300000031
the mean value of the multivariate Gaussian distribution is 0 and the covariance matrix is
Figure BDA0002179425300000032
Wherein: f. of*Y is L AI for the predicted sample point and the training sample point, respectively, X*X is respectively the reflectivity data of the prediction sample point and the training sample point;
Figure BDA0002179425300000033
is the covariance of the training samples and,
Figure BDA0002179425300000034
is the variance of Gaussian noise, K (X), artificially added to the training sample*，X*) Is the covariance of the prediction sample, K (X, X)*) Is the covariance of the training sample and the prediction sample, representing obedience, N represents the Gaussian distribution;
thus, the conditional distribution probability of the prediction sample is:
Figure BDA0002179425300000035
calculated according to the equations (3), (4), wherein the meaning of E is desired,
Figure BDA0002179425300000036
is defined in the sense that it is defined as,-1represents the inverse of the matrix, | represents the condition:
Figure BDA0002179425300000037
Figure BDA0002179425300000041
let K be K (X, X), K*＝K(X，X*) Then predict the predicted mean of the sample
Figure BDA0002179425300000042
And prediction covariance cov (f)*) See formula (5), formula (6):
Figure BDA0002179425300000043
training of Gaussian processThe optimization process is an optimization process, which obtains the hyper-parameters that determine the covariance matrix in equation (1), so that the mean of the predicted samples can be calculated using equations (5), (6)
Figure BDA0002179425300000045
And uncertainty prediction covariance cov (f)*) (ii) a The meaning of T is transposed;
in the Gaussian process, the radial basis function kernel is as follows:
Figure BDA0002179425300000046
where σ is the hyper-parameter of the kernel function.
The crop is a staple grain crop selected from any one of wheat, rice, corn and the like.
The invention also provides an application of the crop growth monitoring method for inverting the leaf area index based on the inverse Gaussian process, which is used for guiding agricultural measures such as field irrigation, fertilization, plant protection and the like according to the growth monitoring result.
Compared with the prior art, the invention has the beneficial effects that:
1. the mapping from the input parameters to the output of the Prosail model is realized through the inverse Gaussian process, the problem of multi-parameter synchronization is avoided, and the inversion accuracy of L AI is improved.
2. The method overcomes the locality of the traditional machine learning, and the mapping of the inverse Gaussian process can be widely applied to various crops and various growing environments.
3. The biophysical and chemical parameters obtained by using all available wave bands and based on a physical radiation transmission model can more effectively and accurately reflect the growth condition of surface crops, and are greatly superior to the traditional plant index such as NDVI.
Drawings
FIG. 1 is a flow chart of a crop growth monitoring method based on inverse Gaussian process inversion leaf area index.
FIG. 2 is a graph of the L AI output obtained from the inversion in example 1.
FIG. 3 is a graph showing the results of judging the growth vigor of wheat in example 1.
Detailed Description
The following describes in further detail specific embodiments of the present invention with reference to examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Example 1
And (3) selecting balanced water as a research area, and monitoring the growth vigor of the wheat in the research area from 1 month in 2018 to 6 months in 2018.
S1, obtaining the consistent ground surface reflectivity of the sentinel No. 2 by using a sensor indifference atmospheric correction method SIAC; in step S1, the SIAC is the method invented by Yi in peak, the code of the SIAC is disclosed in a GitHub platform, and the website is https:// GitHub.
S2, extracting each key growth period of the wheat by using the time sequence data of the sentinel No. 2 surface reflectivity corresponding to the sample points, and carrying out supervision and classification to obtain a crop space distribution map in a research area.
S3, extensive sampling is performed on the crop-corresponding PROSAI L model parameter set to obtain crop spectra simulated by PROSAI L in a black soil background and crop spectra simulated by PROSAI L in a background containing soil information.
The method comprises the steps of obtaining the minimum value and the maximum value of main biophysical parameters of a PROSAI L model corresponding to the wheat according to a large number of actually measured sample points, randomly and uniformly sampling by using a Latin hypercube sampling method in the range, inputting a large number of sampled parameters into a PROSAI L model, and simulating the spectrum of the wheat under different growth conditions to obtain the spectrum of the wheat simulated by the PROSAI L under the black soil background and the spectrum of the wheat simulated by the PROSAI L under the background containing soil information.
And S4, converting the wheat spectrum simulated in the S3 into a wave band spectrum corresponding to the sentinel No. 2 by using the spectrum response function of the sentinel No. 2, namely obtaining the surface reflectivity simulated by the PROSAI L under the background of black soil and the surface reflectivity simulated by the PROSAI L under the background containing soil information.
S5, performing principal component analysis on the surface reflectivity simulated by PROSAI L under the background of the black soil obtained in S4, selecting the first 4 principal components as the spectral reflection characteristics of the pure canopy, and simultaneously performing principal component analysis on the reflectivity of sentinel No. 2 corresponding to the actually measured soil spectral curve, and selecting the first 2 principal components as the spectral reflection characteristics of the pure soil.
And S6, performing linear decomposition on the ground surface reflectivity simulated by the PROSAI L under the background containing the soil information obtained in S4 based on the spectral reflection characteristics of the pure canopy obtained in S5 and the spectral reflection characteristics of the pure soil, and obtaining the pure canopy reflectivity simulated by the PROSAI L.
S7, using the Gaussian process to simulate and learn the mapping relation between the PROSAI L simulated earth surface reflectivity and L AI under the black soil background obtained in S4, realizing the prediction from the pure canopy spectral reflectivity to L AI, and obtaining a well-trained Gaussian process model;
the prediction from pure canopy spectral features to L AI is realized by the following formula:
f*and the training sample point y with Gaussian noise has a multivariate Gaussian distribution:
Figure BDA0002179425300000061
the mean value of the multivariate Gaussian distribution is 0 and the covariance matrix is
Figure BDA0002179425300000062
Wherein: f. of*Y is L AI for the predicted sample point and the training sample point, respectively, X*X is respectively the reflectivity data of the prediction sample point and the training sample point;
Figure BDA0002179425300000063
is the covariance of the training samples and,
Figure BDA0002179425300000064
is the variance of Gaussian noise, K (X), artificially added to the training sample*，X*) Is the covariance of the prediction sample, K (X, X)*) Is the covariance of the training sample and the prediction sample, representing obedience, N represents the Gaussian distribution;
thus, the conditional distribution probability of the prediction sample is:
Figure BDA0002179425300000065
calculated according to the equations (3), (4), wherein the meaning of E is desired,
Figure BDA0002179425300000066
is defined in the sense that it is defined as,-1represents the inverse of the matrix, | represents the condition:
Figure BDA0002179425300000067
Figure BDA0002179425300000071
let K be K (X, X), K*＝K(X，X*) Then predict the predicted mean of the sample
Figure BDA0002179425300000072
And prediction covariance cov (f)*) See formula (5), formula (6):
Figure BDA0002179425300000073
Figure BDA0002179425300000074
the Gaussian process training is an optimization process to obtain the hyper-parameters that determine the covariance matrix in equation (1), so that the mean of the predicted samples can be calculated using equations (5), (6)
Figure BDA0002179425300000075
And uncertainty prediction covariance cov (f)*) (ii) a The meaning of T is transposed;
in the Gaussian process, the radial basis function kernel is as follows:
Figure BDA0002179425300000076
where σ is the hyper-parameter of the kernel function.
S8, based on the result obtained by the principal component analysis of S5, carrying out linear decomposition on the original sentinel No. 2 image to obtain a corresponding pure canopy reflectivity, then comparing the pure canopy reflectivity obtained by the PROSAI L simulation obtained by S6 with the pure canopy reflectivity, selecting the pure canopy reflectivity closest to the PROSAI L simulation and inputting the pure canopy reflectivity into a Gaussian process model trained by S7 to obtain L AI, specifically, the obtained L AI picture is shown in figure 2, and comparing the current year L AI track with the current year L AI track by taking the last 3 years plot average L AI track as a reference, thereby judging the difference of the growth vigor of the current wheat, wherein the judgment result is shown in figure 3.
According to the method, mapping from input parameters to output of the Prosail model is achieved through the inverse Gaussian process, the problem of multi-parameter synchronization is avoided, the L AI inversion precision is improved, the locality of traditional machine learning is overcome, and the mapping of the inverse Gaussian process can be widely applied to various types of wheat and various growing environments.
According to the monitoring result of the embodiment, the agricultural measures such as field irrigation, fertilization, plant protection and the like on weak growth conditions are performed according to the growth conditions of specific plots, and the effect is good.
Although the invention has been described in detail hereinabove with respect to a general description and specific embodiments thereof, it will be apparent to those skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.

Claims (3)

1. A crop growth monitoring method based on inverse Gaussian process inversion leaf area index is characterized by comprising the following specific steps:
s1, obtaining the consistent ground surface reflectivity of the sentinel No. 2 by using a sensor indifference atmospheric correction method SIAC;
s2, extracting each key growth period of the crop to be detected by using the time sequence data of the sentinel No. 2 surface reflectivity corresponding to the sample point, and performing supervision and classification to obtain a crop space distribution map in a research area;
s3, carrying out extensive sampling aiming at a PROSAI L model parameter set corresponding to crops to obtain a crop spectrum simulated by PROSAI L under the background of black soil and a crop spectrum simulated by PROSAI L under the background containing soil information, wherein the S3 specific method comprises the steps of obtaining the minimum value and the maximum value of main biophysical parameters of a PROSAI L model corresponding to the crops according to a large number of actual measurement sample points, carrying out random uniform sampling by using a Latin hypercube sampling method in the range of the minimum value and the maximum value, inputting a large number of parameters obtained by sampling into a PROSAI L model, simulating the spectrum of the crops under different growth conditions, and obtaining the crop spectrum simulated by PROSAI L under the background of black soil and the crop spectrum simulated by PROSAI L under the background containing soil information;
s4, converting the crop spectrum simulated in S3 into a wave band spectrum corresponding to the sentinel No. 2 by using the spectrum response function of the sentinel No. 2, namely obtaining the surface reflectivity simulated by the PROSAI L under the background of black soil and the surface reflectivity simulated by the PROSAI L under the background containing soil information;
s5, performing principal component analysis on the surface reflectivity simulated by PROSAI L under the background of the black soil obtained in S4, and selecting the first 4 principal components as the spectral reflection characteristics of the pure canopy, and simultaneously performing principal component analysis on the surface reflectivity of the sentinel No. 2 corresponding to the actually measured soil spectral curve, and selecting the first 2 principal components as the spectral reflection characteristics of the pure soil;
s6, performing linear decomposition on the earth surface reflectivity simulated by the PROSAI L under the background containing the soil information obtained in S4 based on the spectral reflection characteristics of the pure canopy and the spectral reflection characteristics of the pure soil obtained in S5 to obtain the pure canopy reflectivity simulated by the PROSAI L;
s7, using the mapping relation between the PROSAI L simulated earth surface reflectivity and L AI under the black soil background obtained by Gaussian process simulation learning S4 to realize the prediction from pure canopy spectral reflectivity to L AI and obtain a trained Gaussian process model, and the prediction from pure canopy spectral characteristics to L AI in the step S7, wherein the adopted formula is as follows:
f*and the training sample point y with Gaussian noise has a multivariate Gaussian distribution:
Figure FDA0002478383920000021
the mean value of the multivariate Gaussian distribution is 0 and the covariance matrix is
Figure FDA0002478383920000022
Wherein: f. of*Y is L AI for the predicted sample point and the training sample point, respectively, X*X is respectively the reflectivity data of the prediction sample point and the training sample point;
Figure FDA0002478383920000023
is the covariance of the training samples and,
Figure FDA0002478383920000024
is the variance of Gaussian noise, K (X), artificially added to the training sample*,X*) Is the covariance of the prediction sample, K (X, X)*) Is the covariance of the training sample and the prediction sample, representing obedience, N represents the Gaussian distribution;
thus, the conditional distribution probability of the prediction sample is:
Figure FDA0002478383920000025
calculated according to the equations (3), (4), wherein the meaning of E is desired,
Figure FDA0002478383920000026
is defined in the sense that it is defined as,－1representation matrixThe inverse of (c), represents the condition:
Figure FDA0002478383920000027
Figure FDA0002478383920000028
let K be K (X, X), K*＝K(X,X*) Then predict the predicted mean f of the sample
Figure FDA00024783839200000211
And prediction covariance cov (f)*) See formula (5), formula (6):
Figure FDA0002478383920000029
Figure FDA00024783839200000210
the Gaussian process training is an optimization process to obtain the hyper-parameters that determine the covariance matrix in equation (1), so that the mean of the predicted samples can be calculated using equations (5), (6)
Figure FDA0002478383920000031
And uncertainty prediction covariance cov (f)*) (ii) a The meaning of T is transposed;
in the Gaussian process, the radial basis function kernel is as follows:
Figure FDA0002478383920000032
wherein σ is a hyper-parameter of the kernel function;
s8, based on the result of the principal component analysis of S5, carrying out linear decomposition on the original sentinel No. 2 image to obtain the corresponding pure canopy reflectivity, then comparing the pure canopy reflectivity simulated by the PROSAI L obtained in S6 with the pure canopy reflectivity, selecting the pure canopy reflectivity simulated by the PROSAI L closest to the pure canopy reflectivity, inputting the pure canopy reflectivity into a Gaussian process model trained by S7 to obtain L AI, and comparing the L AI track of the current year with the average L AI track of the plot of the last 3 years as a reference, thereby judging the growth vigor of the current crop.
2. The inverse gaussian process-based inversion leaf area index crop growth monitoring method of claim 1, wherein said crop is a staple grain crop.
3. The use of the method for monitoring the growth of crops based on inversion of leaf area index by inverse Gaussian process as claimed in claim 1 or 2, which is to guide field irrigation, fertilization and plant protection according to the growth monitoring result.
CN201910790564.2A 2019-08-26 2019-08-26 Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process Active CN110579186B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910790564.2A CN110579186B (en) 2019-08-26 2019-08-26 Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910790564.2A CN110579186B (en) 2019-08-26 2019-08-26 Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process

Publications (2)

Publication Number Publication Date
CN110579186A CN110579186A (en) 2019-12-17
CN110579186B true CN110579186B (en) 2020-07-21

Family

ID=68812077

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910790564.2A Active CN110579186B (en) 2019-08-26 2019-08-26 Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process

Country Status (1)

Country Link
CN (1) CN110579186B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330672B (en) * 2020-11-28 2022-07-29 华中农业大学 Crop leaf area index inversion method based on PROSAIL model and canopy coverage optimization
CN112633374A (en) * 2020-12-22 2021-04-09 江苏海洋大学 Supervision and classification method combined with multispectral mixed pixel linear decomposition
CN112804304B (en) * 2020-12-31 2022-04-19 平安科技（深圳）有限公司 Task node distribution method and device based on multi-point output model and related equipment
CN116503747B (en) * 2023-06-30 2023-09-15 华中农业大学 Heterogeneous earth surface leaf area index inversion method based on multi-scale remote sensing
CN117890184B (en) * 2024-03-14 2024-05-28 中国科学院地质与地球物理研究所 Mars-simulated soil and preparation method thereof

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0808340D0 (en) * 2008-05-08 2008-06-18 Univ Edinburgh Remote sensing system
CN107437267B (en) * 2016-05-26 2019-01-04 中国科学院遥感与数字地球研究所 Vegetation region high spectrum image analogy method
CN109886962B (en) * 2019-03-27 2022-08-09 南京林业大学 Vegetation coverage and management measure factor remote sensing inversion method based on LAI and multi-angle data
CN109975250B (en) * 2019-04-24 2020-03-24 中国科学院遥感与数字地球研究所 Leaf area index inversion method and device

Also Published As

Publication number Publication date
CN110579186A (en) 2019-12-17

Similar Documents

Publication Publication Date Title
CN110579186B (en) Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process
CN110287944B (en) Crop pest monitoring method based on multispectral remote sensing image of deep learning
CN109711102A (en) A kind of crop casualty loss fast evaluation method
Sonobe et al. Hyperspectral reflectance sensing for quantifying leaf chlorophyll content in wasabi leaves using spectral pre-processing techniques and machine learning algorithms
Chen et al. Comparison between back propagation neural network and regression models for the estimation of pigment content in rice leaves and panicles using hyperspectral data
CN110082309B (en) Method for establishing SPAD value comprehensive spectrum monitoring model of winter wheat canopy
Im et al. Hyperspectral remote sensing analysis of short rotation woody crops grown with controlled nutrient and irrigation treatments
CN112836725A (en) Weak supervision LSTM recurrent neural network rice field identification method based on time sequence remote sensing data
Wang et al. Digital image processing technology under backpropagation neural network and K-Means Clustering algorithm on nitrogen utilization rate of Chinese cabbages
Yi et al. Evaluating the performance of PC-ANN for the estimation of rice nitrogen concentration from canopy hyperspectral reflectance
Yuan et al. Research on rice leaf area index estimation based on fusion of texture and spectral information
Dinh et al. Nested leave-two-out cross-validation for the optimal crop yield model selection
Mangalraj et al. Recent trends and advances in hyperspectral imaging techniques to estimate solar induced fluorescence for plant phenotyping
Zhai et al. CatBoost algorithm for estimating maize above-ground biomass using unmanned aerial vehicle-based multi-source sensor data and SPAD values
US20230108422A1 (en) Methods and systems for use in processing images related to crops
CN116151454A (en) Method and system for predicting yield of short-forest linalool essential oil by multispectral unmanned aerial vehicle
Lu et al. Improving the spatial and temporal estimation of ecosystem respiration using multi-source data and machine learning methods in a rainfed winter wheat cropland
Masemola et al. Estimating leaf nitrogen concentration from similarities in fresh and dry leaf spectral bands using a model population analysis framework
CN113343783A (en) Intelligent crop identification and growth prediction method and system
CN112595267A (en) Summer corn LAI inversion method fusing factor analysis and ant colony wavelet neural network model
Wang et al. Predicting maize leaf area index by partial least square combined with wavelet transform
Sun et al. Potential of multi-seasonal vegetation indices to predict rice yield from UAV multispectral observations
Reyes-Muñoz et al. Inferring global terrestrial carbon fluxes from the synergy of Sentinel 3 & 5P with Gaussian process hybrid models
CN113761790B (en) Fruit tree leaf nitrogen content estimation method based on Stacking integrated learning
Bonneu et al. Machine learning based on functional principal component analysis to identify major influential factors of wheat yield

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