CN112666091A - Remote sensing inversion model and method for rice unit area overground part soluble sugar accumulation based on random gradient descent regression algorithm - Google Patents
Remote sensing inversion model and method for rice unit area overground part soluble sugar accumulation based on random gradient descent regression algorithm Download PDFInfo
- Publication number
- CN112666091A CN112666091A CN202011382698.XA CN202011382698A CN112666091A CN 112666091 A CN112666091 A CN 112666091A CN 202011382698 A CN202011382698 A CN 202011382698A CN 112666091 A CN112666091 A CN 112666091A
- Authority
- CN
- China
- Prior art keywords
- rice
- unit area
- soluble sugar
- overground part
- model
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a remote sensing inversion model of rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm, which is a random gradient descent regression model of Python language and further provides model parameters of the random gradient descent regression model. The remote sensing inversion method of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm is also provided. The remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm can quickly and accurately acquire the rice unit area overground part soluble sugar accumulation information, overcomes the difficulty that the characteristic wave band of the rice unit area overground part soluble sugar accumulation is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improves the accuracy of the rice unit area overground part soluble sugar accumulation inversion model, and is ingenious in design, simple and convenient to calculate, easy to implement, low in cost and suitable for large-scale popularization and application.
Description
Technical Field
The invention relates to the technical field of agricultural remote sensing, in particular to the technical field of measurement of the accumulation amount of soluble sugars on the overground part of a unit area of rice, and specifically relates to a remote sensing inversion model and method of the accumulation amount of the soluble sugars on the overground part of the unit area of rice based on a random gradient descent regression algorithm.
Background
The accumulation amount of soluble sugar in the upper part of the rice is the total accumulation amount of soluble sugar in the upper part of the rice. The content of soluble sugar is an important parameter for quantifying photosynthesis of rice to fix carbon dioxide and synthesize carbohydrates. Meanwhile, the soluble sugar has an important regulation effect in the life cycle of plants, provides energy and metabolic intermediates for the growth and development of rice, has an important signal function, is an important regulation factor for the growth and development of rice and gene expression, forms a complex signal network system with other signals, has an important regulation effect on important growth and development processes such as formation, growth and senescence of rice leaf and canopy structures, is an important index for physiological conditions of rice and growth vigor of rice, and reflects physiological, growth vigor and rich water conditions of rice (Zhoudouqin, Zhuyan, Yang, and the like.
The method has the advantages that the soluble sugar content of the overground part of the rice is monitored, the physiological state and the growth activity of the rice are effectively mastered, the yield and the quality of rice production can be ensured, meanwhile, the water and fertilizer control of the rice can be dynamically managed, and the production efficiency of the rice is improved, so that remarkable economic and social benefits are generated (Wangxuxizhen, Huangjing, plum, and the like; correlation analysis of biochemical parameters and hyperspectral remote sensing characteristic parameters of the rice [ J ]. agricultural engineering bulletin, 2003,19(002): 144-doped 148). The traditional method for monitoring the accumulation amount of soluble sugar on the overground part of rice mainly adopts a destructive sampling method, needs to be carried out indoors, needs to invest a large amount of manpower in the determination process, wastes time and labor, is poor in timeliness, cannot timely acquire the accumulation amount of soluble sugar on the overground part of rice, and is not beneficial to popularization and application.
In the physiological and biochemical processes of rice, the change of certain specific substances and cell structures in rice plants results in the change of rice reflectance spectra. Therefore, the change of the spectrum can be used for acquiring rice growth information such as the accumulation amount of soluble sugar on the overground part of the rice (Zhoudouqin. monitoring of rice nitrogen nutrition and grain quality based on the canopy reflection spectrum [ D ]. Nanjing agriculture university, 2007). Currently, hyperspectrum is used for monitoring the growth state of rice in crop growth monitoring. With the development and popularization of the spectrum technology, the hyperspectral data can quickly and rapidly acquire the accumulated amount information of the soluble sugar on the overground part of the rice, and the method becomes a consensus of more and more rice production practitioners and researchers. The most common mode is to use a portable full-waveband spectrometer to obtain growth information such as the accumulation amount of the soluble sugar in the overground part of the rice and select a characteristic waveband capable of reflecting the accumulation amount of the soluble sugar in the overground part to construct an inversion model. In the process of constructing the rice overground part soluble sugar accumulation inversion model, the spectral range measured by the full-waveband spectrometer covers 350-1100 nm, but because the components of the rice are complex, the characteristic wave bands of the component spectra are partially overlapped, the determination of the characteristic spectrum of the rice overground part soluble sugar accumulation is difficult, and meanwhile, the rapid processing of hyperspectral data becomes an urgent technical problem to be solved for estimating the rice overground part soluble sugar accumulation based on the hyperspectral data. In addition, when training data is added, the conventional model construction method needs to retrain all the training data or recalculate parameters of the model, is time-consuming and labor-consuming, and is not beneficial to popularization and application of the model.
Therefore, it is desirable to provide a remote sensing inversion model of the rice unit area overground part soluble sugar accumulation, which can quickly and accurately acquire the rice unit area overground part soluble sugar accumulation information, overcome the difficulty that the characteristic wave band of the rice unit area overground part soluble sugar accumulation is difficult to determine due to the spectrum superposition effect caused by complex rice components, and greatly improve the accuracy of the rice unit area overground part soluble sugar accumulation inversion model.
Disclosure of Invention
In order to overcome the defects in the prior art, one object of the present invention is to provide a remote sensing inversion model of the amount of accumulated soluble sugars in the upper part of a unit area of rice based on a stochastic gradient descent regression algorithm, which can quickly and accurately obtain the information of the amount of accumulated soluble sugars in the upper part of the unit area of rice, overcome the difficulty that the characteristic band of the amount of accumulated soluble sugars in the upper part of the unit area of rice is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improve the accuracy of the inversion model of the amount of accumulated soluble sugars in the upper part of the unit area of rice, and is suitable for large-scale popularization and application.
The invention also aims to provide a remote sensing inversion model of the accumulation amount of the soluble sugar on the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm, which has the advantages of ingenious design, simple and convenient calculation, easy realization and low cost, and is suitable for large-scale popularization and application.
The invention also aims to provide a remote sensing inversion method of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm, which can quickly and accurately acquire the rice unit area overground part soluble sugar accumulation information, overcome the difficulty that the characteristic wave band of the rice unit area overground part soluble sugar accumulation is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improve the inversion precision of the rice unit area overground part soluble sugar accumulation, and is suitable for large-scale popularization and application.
The invention also aims to provide a remote sensing inversion method of the accumulation amount of the soluble sugar on the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm, which has the advantages of ingenious design, simple and convenient operation and low cost, and is suitable for large-scale popularization and application.
In order to achieve the above object, in a first aspect of the present invention, there is provided a remote sensing inversion model of rice unit area upper part soluble sugar accumulation based on a stochastic gradient descent regression algorithm, which is characterized in that the remote sensing inversion model of rice unit area upper part soluble sugar accumulation based on the stochastic gradient descent regression algorithm is a Python language stochastic gradient descent regression model, and the model parameters of the stochastic gradient descent regression model are: 'n _ iter _ no _ change' 29, 'epsilon' 0.014648521430621595, 'l1_ ratio' 0.15, 'leaving _ rate' invscaling '1000,' validity _ fraction '0.1,' dependency 'l2', 'loss' huber ', power _ t' 0.7938077877018379, 'fit _ interrupt' True, 'tol' 2.744072031501585, 'alpha' 0.7167750035123579, 'eta0' 0.0056907807163545186, 'average' False, 'early _ storing' False 'True'.
Preferably, the stochastic gradient descent regression model is trained by using a rice data set, the data set includes canopy reflectances of m sample points of the rice and an overground soluble sugar accumulation amount per unit area, the m sample points are uniformly distributed in a rice planting area, and the canopy reflectivity is a canopy reflectivity of n characteristic bands.
More preferably, m is 36, n characteristic bands are 2151 characteristic bands, and the 2151 characteristic bands are from 350nm band to 2500nm band.
In a second aspect of the invention, the invention provides a remote sensing inversion method of the amount of accumulated soluble sugar in the overground part of a unit area of rice based on a random gradient descent regression algorithm, which is characterized by comprising the following steps:
(1) measuring the canopy reflectance of the rice;
(2) measuring the amount of the accumulated soluble sugar in the upper part of the unit area of the rice;
(3) calculating by using the canopy reflectivity as input data and adopting a random gradient descent regression model of Python language to obtain an inversion value,calculating a decision coefficient R according to the inversion value and the unit area overground part soluble sugar accumulation amount2Changing the value of the model parameter, R, of the stochastic gradient descent regression model2The larger the change of the model parameter is, the greater the importance of the model parameter is, the model parameter is arranged from large to small according to the importance to construct a model parameter tuning rank matrix;
(4) training the stochastic gradient descent regression model by taking the canopy reflectivity as the input data and the overground part soluble sugar accumulation amount in unit area as an output result, and sequentially tuning the model parameters according to the model parameter tuning order matrix to obtain tuning values of the model parameters;
(5) using the canopy reflectivity as the input data, using the above-ground soluble sugar accumulation amount per unit area as the output result, using the adjusted values of the model parameters to train the stochastic gradient descent regression model, after the training of the stochastic gradient descent regression model is finished, obtaining a remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm, storing the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm by using a save method, if the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm needs to be used, the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm is loaded by using a load method for use.
Preferably, in the step (1), the measurement is performed by using a hyperspectral radiometer, the measurement time is 10: 00-14: 00, the hyperspectral radiometer adopts a lens with a 25-degree field angle, a sensor probe of the portable field hyperspectral radiometer vertically points to the canopy of the rice and has a vertical height of 1 m from the top layer of the canopy, the ground field range diameter of the sensor probe is 0.44 m, the sensor probe faces the sunlight, the measurement is corrected by using a standard board, and the standard board is a standard white board with a reflectivity of 95% -99%.
Preferably, in the step (2), the step of measuring the amount of the soluble sugar accumulated in the upper part of the unit area of the rice specifically includes:
collecting the overground part plants of the rice, deactivating enzyme, drying to constant weight to obtain dry plants, measuring the weight of the dry plants to obtain the overground part dry weight, and converting the overground part dry weight into the unit area overground part dry weight according to the sampling coverage area;
and crushing the dry plants, measuring the soluble sugar content of the overground part, and multiplying the weight of the overground part dry matter per unit area by the soluble sugar content of the overground part to obtain the accumulated amount of the overground part soluble sugar per unit area.
More preferably, in the step (2), the water-removing temperature is 105 ℃, the water-removing time is 20-30 minutes, the drying temperature is 80-90 ℃, and the anthrone colorimetric method is adopted for measuring the soluble sugar content in the overground part.
Preferably, in the step (3), the model parameter tuning rank matrix is:
Params＝{'n_iter_no_change','epsilon','l1_ratio','learning_rate','max_iter','validation_fraction','penalty','loss','power_t','fit_intercept','tol','alpha','eta0','average','early_stopping','shuffle'}。
preferably, in the step (4), the optimized values of the model parameters are:
'n_iter_no_change':29,'epsilon':0.014648521430621595,'l1_ratio':0.15,'learning_rate':'invscaling','max_iter':1000,'validation_fraction':0.1,'penalty':'l2','loss':'huber','power_t':0.7938077877018379,'fit_intercept':True,'tol':2.744072031501585,'alpha':0.7167750035123579,'eta0':0.0056907807163545186,'average':False,'early_stopping':False,'shuffle':True。
preferably, in the step (1), the step of measuring the canopy reflectance of the rice is specifically to measure the canopy reflectance of m sampling points of a rice planting area, the m sampling points are uniformly distributed in the rice planting area, and the canopy reflectance is the canopy reflectance of n characteristic bands; in the step (2), the step of measuring the amount of the soluble sugar accumulated in the upper part of the unit area of the rice is to measure the amount of the soluble sugar accumulated in the upper part of the unit area of the m spots.
More preferably, in the step (1), the m is 36, the n characteristic bands are 2151 characteristic bands, and the 2151 characteristic bands are from 350nm to 2500 nm.
The invention has the following beneficial effects:
1. the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation amount based on the stochastic gradient descent regression algorithm is a stochastic gradient descent regression model of Python language, and the model parameters of the stochastic gradient descent regression model are as follows: ' n _ iter _ no _ change ' 29, ' epsilon ' 0.014648521430621595, ' l1_ ratio ' 0.15, ' left _ rate ' invscaling ' 1000, ' validity _ fraction ' 0.1, ' dependency ' l2', ' loss ' huber ', ' power _ t ' 0.7938077877018379, ' fit _ interrupt ' True, ' tol ' 2.744072031501585, ' alpha ' 0.7167750035123579, ' eta0' 0.0056907807163545186, ' amplitude ' False, ' early _ storing ' False ' True ', the model is verified, R is verified, and R is verified2Above 0.85, therefore, the method can quickly and accurately acquire the information of the amount of the soluble sugar accumulated on the upper part of the unit area of the rice, overcomes the difficulty that the characteristic wave band of the amount of the soluble sugar accumulated on the upper part of the unit area of the rice is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improves the accuracy of an inversion model of the amount of the soluble sugar accumulated on the upper part of the unit area of the rice, and is suitable for large-scale popularization and application.
2. The remote sensing inversion model of the rice unit area overground part soluble sugar accumulation amount based on the stochastic gradient descent regression algorithm is a stochastic gradient descent regression model of Python language, and the model parameters of the stochastic gradient descent regression model are as follows: 'n _ iter _ no _ change' 29, 'epsilon' 0.014648521430621595, 'l1_ ratio' 0.15, 'left _ rate' invscaling '1000,' validity _ fraction '0.1,' dependency 'l2,' loss 'hub' power _ t '0.7938077877018379,' fit _ interrupt '0.7938077877018379'True, 'tol' 2.744072031501585, 'alpha' 0.7167750035123579, 'eta0' 0.0056907807163545186, 'average' False, 'early _ stopping' False, 'shuffle' True, 'True', the model is examined, R2Above 0.85, therefore, the method has the advantages of ingenious design, simple and convenient calculation, easy realization and low cost, and is suitable for large-scale popularization and application.
3. The invention discloses a remote sensing inversion method of the accumulation amount of soluble sugar on the overground part of a unit area of rice based on a random gradient descent regression algorithm, which comprises the following steps: measuring the canopy reflectance of the rice; measuring the accumulation amount of soluble sugar on the overground part of a unit area of rice: calculating by taking the reflectivity of the canopy as input data and adopting a random gradient descent regression model of Python language to determine a coefficient R2Constructing a model parameter tuning order matrix; training a random gradient descent regression model by taking the reflectivity of the canopy as input data and the accumulation amount of the soluble sugar on the overground part of the unit area as an output result, and sequentially tuning model parameters according to a model parameter tuning order matrix to obtain tuning values of the model parameters; training a random gradient descent regression model by using the canopy reflectivity as input data and the overground part soluble sugar accumulation amount of a unit area as an output result and adopting an adjusted value of model parameters to obtain a rice unit area overground part soluble sugar accumulation amount remote sensing inversion model based on a random gradient descent regression algorithm, inspecting the model, and performing R2Above 0.85, therefore, the method can quickly and accurately acquire the information of the amount of the accumulated soluble sugar on the upper part of the unit area of the rice, overcomes the difficulty that the characteristic wave band of the amount of the accumulated soluble sugar on the upper part of the unit area of the rice is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improves the inversion precision of the amount of the accumulated soluble sugar on the upper part of the unit area of the rice, and is suitable for large-scale popularization and application.
4. The invention discloses a remote sensing inversion method of the accumulation amount of soluble sugar on the overground part of a unit area of rice based on a random gradient descent regression algorithm, which comprises the following steps: measuring the canopy reflectance of the rice; measuring the accumulation amount of soluble sugar on the overground part of a unit area of rice: calculating by taking the reflectivity of the canopy as input data and adopting a random gradient descent regression model of Python language to determine a coefficient R2Constructing a model parameter tuning order matrix; training a random gradient descent regression model by taking the reflectivity of the canopy as input data and the accumulation amount of the soluble sugar on the overground part of the unit area as an output result, and sequentially tuning model parameters according to a model parameter tuning order matrix to obtain tuning values of the model parameters; training a random gradient descent regression model by using the canopy reflectivity as input data and the overground part soluble sugar accumulation amount of a unit area as an output result and adopting an adjusted value of model parameters to obtain a rice unit area overground part soluble sugar accumulation amount remote sensing inversion model based on a random gradient descent regression algorithm, inspecting the model, and performing R2Above 0.85, therefore, the design is ingenious, the operation is simple and convenient, the cost is low, and the method is suitable for large-scale popularization and application.
These and other objects, features and advantages of the present invention will become more fully apparent from the following detailed description, the accompanying drawings and the claims, and may be realized by means of the instrumentalities, devices and combinations particularly pointed out in the appended claims.
Drawings
FIG. 1 is a schematic flow chart of a specific embodiment of the remote sensing inversion method of the accumulation amount of soluble sugars in the overground part of a unit area of rice based on a random gradient descent regression algorithm.
FIG. 2 is a schematic diagram of a model building process of the embodiment shown in FIG. 1.
FIG. 3 is a diagram illustrating the results of model testing in the embodiment shown in FIG. 1, wherein the measured values and the predicted values are both in g/m units2。
Detailed Description
The invention provides a remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm aiming at the requirements of hyperspectral estimation of the rice unit area overground part soluble sugar accumulation based on hyperspectrum, overcoming the difficulties that the characteristic wave band of the rice unit area overground part soluble sugar accumulation is difficult to determine and the characteristic wave band of hyperspectral data is time-consuming and labor-consuming in screening caused by complex rice components, the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm is a random gradient descent regression model of Python language, and the model parameters of the random gradient descent regression model are as follows: 'n _ iter _ no _ change' 29, 'epsilon' 0.014648521430621595, 'l1_ ratio' 0.15, 'leaving _ rate' invscaling '1000,' validity _ fraction '0.1,' dependency 'l2', 'loss' huber ', power _ t' 0.7938077877018379, 'fit _ interrupt' True, 'tol' 2.744072031501585, 'alpha' 0.7167750035123579, 'eta0' 0.0056907807163545186, 'average' False, 'early _ storing' False 'True'.
The stochastic gradient descent regression model may be trained using any suitable data set, and preferably, the stochastic gradient descent regression model is trained using a data set of rice, the data set includes canopy reflectances of m sample points of the rice and an amount of accumulated soluble sugar in an upper part of a unit area, the m sample points are uniformly distributed in a rice planting area, and the canopy reflectance is a canopy reflectance of n characteristic bands. The rice planting area can be a plurality of ecological points and a plurality of varieties of rice planting areas.
M and n are positive integers, which can be determined according to needs, and more preferably, m is 36, n characteristic bands are 2151 characteristic bands, and the 2151 characteristic bands are from 350nm to 2500 nm.
The invention also provides a remote sensing inversion method of the accumulation amount of the soluble sugar on the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm, which comprises the following steps:
(1) measuring the canopy reflectance of the rice;
(2) measuring the amount of the accumulated soluble sugar in the upper part of the unit area of the rice;
(3) calculating by using the canopy reflectivity as input data and adopting a random gradient descent regression model of Python language to obtain an inversion value, and calculating a decision coefficient R according to the inversion value and the unit area overground part soluble sugar accumulation2Changing the value of the model parameter, R, of the stochastic gradient descent regression model2The greater the variation of (a), the greater the significance of the model parameters, the moreArranging the model parameters according to the importance from large to small to construct a model parameter tuning rank matrix;
(4) training the stochastic gradient descent regression model by taking the canopy reflectivity as the input data and the overground part soluble sugar accumulation amount in unit area as an output result, and sequentially tuning the model parameters according to the model parameter tuning order matrix to obtain tuning values of the model parameters;
(5) using the canopy reflectivity as the input data, using the above-ground soluble sugar accumulation amount per unit area as the output result, using the adjusted values of the model parameters to train the stochastic gradient descent regression model, after the training of the stochastic gradient descent regression model is finished, obtaining a remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm, storing the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm by using a save method, if the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm needs to be used, the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm is loaded by using a load method for use.
In the step (1), the measurement may be performed by any suitable spectrometer and method, preferably, in the step (1), the measurement is performed by using a hyperspectral radiometer, the measurement time is 10:00 to 14:00, the hyperspectral radiometer uses a lens with a field angle of 25 degrees, a sensor probe of the portable field hyperspectral radiometer vertically points to the canopy of the rice and has a vertical height of 1 meter from the top layer of the canopy, the ground field range diameter of the sensor probe is 0.44 meter, the sensor probe faces the sun, the measurement is corrected by using a standard board, and the standard board is a standard white board with a reflectivity of 95% to 99%.
In the step (2), the step of measuring the amount of soluble sugar accumulated in the upper part of the unit area of the rice may specifically include any suitable method, and preferably, in the step (2), the step of measuring the amount of soluble sugar accumulated in the upper part of the unit area of the rice specifically includes:
collecting the overground part plants of the rice, deactivating enzyme, drying to constant weight to obtain dry plants, measuring the weight of the dry plants to obtain the overground part dry weight, and converting the overground part dry weight into the unit area overground part dry weight according to the sampling coverage area;
and crushing the dry plants, measuring the soluble sugar content of the overground part, and multiplying the weight of the overground part dry matter per unit area by the soluble sugar content of the overground part to obtain the accumulated amount of the overground part soluble sugar per unit area.
In the step (2), the water-removing and the drying can adopt any suitable conditions, and the determination of the soluble sugar content in the overground part can adopt any suitable method, and more preferably, in the step (2), the water-removing temperature is 105 ℃, the water-removing time is 20-30 minutes, the drying temperature is 80-90 ℃, and the determination of the soluble sugar content in the overground part adopts an anthrone colorimetric method.
In the step (3), the model parameter tuning rank matrix is based on a decision coefficient R2Determining, preferably, in the step (3), that the model parameter tuning rank matrix is:
Params＝{'n_iter_no_change','epsilon','l1_ratio','learning_rate','max_iter','validation_fraction','penalty','loss','power_t','fit_intercept','tol','alpha','eta0','average','early_stopping','shuffle'}。
in the step (4), the tuning values of the model parameters are sequentially determined according to the model parameter tuning rank matrix, and more preferably, in the step (4), the tuning values of the model parameters are:
'n_iter_no_change':29,'epsilon':0.014648521430621595,'l1_ratio':0.15,'learning_rate':'invscaling','max_iter':1000,'validation_fraction':0.1,'penalty':'l2','loss':'huber','power_t':0.7938077877018379,'fit_intercept':True,'tol':2.744072031501585,'alpha':0.7167750035123579,'eta0':0.0056907807163545186,'average':False,'early_stopping':False,'shuffle':True。
in order to make the precision of the remote sensing inversion model of the overground part soluble sugar accumulation amount of the rice unit area based on the stochastic gradient descent regression algorithm higher, a plurality of sampling points of a rice planting area can be selected, and the canopy reflectivity of a plurality of characteristic wave bands of the plurality of sampling points and the overground part soluble sugar accumulation amount of the unit area of the plurality of sampling points are measured, preferably, in the step (1), the step of measuring the canopy reflectivity of the rice is specifically to measure the canopy reflectivity of m sampling points of the rice planting area, the m sampling points are uniformly distributed in the rice planting area, and the canopy reflectivity is the canopy reflectivity of n characteristic wave bands; in the step (2), the step of measuring the amount of the soluble sugar accumulated in the upper part of the unit area of the rice is to measure the amount of the soluble sugar accumulated in the upper part of the unit area of the m spots.
In the step (1), m and n are positive integers, which can be determined as required, and more preferably, in the step (1), m is 36, the n characteristic bands are 2151 characteristic bands, and the 2151 characteristic bands are from 350nm to 2500 nm.
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention.
Examples
The remote sensing inversion method of the amount of accumulated soluble sugar in the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm is based on actually measured hyperspectral data, and adopts rice canopy reflectivity spectrum data and the amount of accumulated soluble sugar in the overground part of the unit area of the rice, which are collected by a rice planting area (a rice and wheat planting base in Huai 'an area of agricultural science research institute of Huai' an, Jiangsu province, Huai rice 5, and a sampling period is a rice jointing period), wherein the total number of sampling points is 48, and the sampling points are uniformly distributed and completely cover the whole area of the rice planting area. The data of 48 sampling points are divided into two parts by a random method, wherein the data of 36 sampling points is used for model construction, and the data of 12 sampling points is used for model inspection. The flow of the remote sensing inversion method of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm is shown in figure 1, and the method comprises the following steps:
1. and (4) performing spectral measurement.
The rice canopy spectrum measurement is carried out by using a field Spec Pro portable field hyperspectral radiometer produced by American ASD in clear weather, no wind or small wind speed within the time range of 10: 00-14: 00, and the sampling testers wear dark clothes to reduce the influence or interference on the spectrometer. During sampling, a lens with a 25-degree field angle is selected, a sensor probe vertically points to a measurement target, namely a canopy, the vertical height of the sensor probe is about 1 meter from the top layer of the canopy, the diameter of the ground field range is 0.44 meter, the average value of reflection spectra measured for 10 times is taken as the spectral data of the sampling point. And in the measurement process, the standard white board is corrected before and after the measurement of each sampling point. If the distribution of the environmental light field changes in the test process, the standard white board is also corrected, and the reflectivity of the standard white board used in the embodiment is 99%. The measured spectrum data is checked by using field Spec Pro portable field hyperspectral radiometer random software RS3 or ViewSpec Pro software, abnormal spectrum files are removed, interpolation calculation is carried out on the spectrum data to obtain spectrum data with the range of 350 nm-2500 nm and the resolution of 1nm, the average value of parallel sampling spectra of the spectrum is calculated, and finally, the spectrum data is exported and stored as ASCII files.
2. Determination of amount of soluble sugar accumulated in the overground part of unit area of rice
Collecting 6 rice overground part plants uniformly distributed in a spectral measurement view field of each sampling point, wrapping the plants by absorbent paper, bringing the plants back to a laboratory, deactivating enzyme at 105 ℃ for 20 minutes, drying the plants at 85 ℃ until the plants have constant weight, obtaining dry plants, measuring the weight of the dry plants, wherein the obtained data is the dry weight of the rice overground part, converting the dry weight of the rice overground part into the dry weight (PD) of the rice overground part in unit area in g/m according to the sampling coverage area2。
Pulverizing the dried plant, adoptingAnthracene ketone colorimetric method for measuring Soluble Sugar Content (SSC) (% by weight) (Leyou Kai. general analysis method for soil agricultural chemistry [ M)]Beijing scientific Press, 1983,79-272), the accumulation amount SSA of soluble sugars in the aerial part per unit area is calculated by the following formula to obtain the accumulation amount of soluble sugars in the aerial part per unit area in g/m2。
SSA＝PD×SSC。
3. Model construction
The model construction is implemented by adopting a random gradient descent regression model of Python language, please refer to FIG. 2, and the model construction mainly comprises the following steps:
3.1 data verification
And checking the acquired rice canopy reflectivity data, and rejecting abnormal whole spectral curve data. The abnormal spectrum in the invention means that adjacent spectrum changes by more than 100%, and spectrum values including null values and negative values are included.
3.2 preprocessing of data
And preprocessing the verified rice canopy reflectivity data and the rice unit area overground part soluble sugar accumulation data, wherein the preprocessing comprises removing the paired rice canopy reflectivity data and the rice unit area overground part soluble sugar accumulation data containing the missing value and the null value.
3.3 partitioning of data sets
To ensure a reasonable evaluation of the model training and inversion results, a stochastic approach was used to divide the entire data set (48 groups) into two parts, with 75% (36 groups) of data used for model training and 25% (12 groups) for post-training effectiveness evaluation.
3.4 partitioning of training data sets
In order to ensure the effect of model training, a random method is used, and a training data set is divided into 5 parts to train the model when the model is trained and iterated every time.
3.5 construction of model parameter tuning rank matrix
In the invention, the tuning of the model parameters in the model training process is very important, and in order to ensure that the best model tuning is obtained as much as possible, a trial-and-error method is used for tuning the model parameters. The inventionUsing a decision coefficient R2(R2The closer to 1, the better) as the test parameter, a parameter rank matrix for evaluating the weight of the model parameter is constructed. According to a training data set, firstly, a default value of a model parameter is used for calculation to obtain an inversion value, and a decision coefficient R is calculated according to the inversion value and the accumulation amount of the above-ground soluble sugar in unit area2Then changing the value of the model parameter, R2The larger the change of the model parameter is, the greater the importance of the model parameter is, the model parameter is arranged from large to small according to the importance to construct a model parameter tuning rank matrix for subsequent calculation.
According to the canopy reflectivity data in the training data set and the corresponding unit area overground part soluble sugar accumulation data, the model parameter tuning order matrix obtained by calculation is as follows:
Params＝{'n_iter_no_change','epsilon','l1_ratio','learning_rate','max_iter','validation_fraction','penalty','loss','power_t','fit_intercept','tol','alpha','eta0','average','early_stopping','shuffle'}。
wherein, the change of the model parameters 'average', 'early _ stopping' and 'shuffle' of the stochastic gradient descent regression model does not cause the precision change of the stochastic gradient descent regression model.
3.6 model construction
Adjusting an order matrix according to the obtained model parameters, training a random gradient descent regression model by using data used for modeling, including actually measured crown layer reflectivity data and corresponding actually measured unit area overground part soluble sugar accumulation data, taking the actually measured crown layer reflectivity data as input data and the actually measured unit area overground part soluble sugar accumulation data as output results, and sequentially adjusting the model parameters according to the model parameter adjustment order matrix to obtain complete parameters and values of the model, wherein the data comprises the following data:
'n_iter_no_change':29,'epsilon':0.014648521430621595,'l1_ratio':0.15,'learning_rate':'invscaling','max_iter':1000,'validation_fraction':0.1,'penalty':'l2','loss':'huber','power_t':0.7938077877018379,'fit_intercept':True,'tol':2.744072031501585,'alpha':0.7167750035123579,'eta0':0.0056907807163545186,'average':False,'early_stopping':False,'shuffle':True。
after the model training is finished, the save method is used for saving the model, and if the model is required to be used, the load method is operated for loading and using.
3.7 model test
Using 12 sampling points except for the constructed model to input the hyperspectral data into the model, using the adjusted model parameters to calculate to obtain a predicted value, analyzing the relationship between the predicted value and an actual measured value (the accumulation amount of soluble sugar in the overground part of a unit area), and obtaining a result shown in figure 3, wherein R of the model is2Is 0.9026. Model R using default parameters2Is 0.2933.
In the embodiment, Matlab software (version: R2020a 9.8.0.1380330) and Python (version:3.7.0) developed by MathWorks company in the United states are used for random division of training data and test data and construction, training and test of models, and the random gradient descent regression model of Python is called through the Matlab software.
Therefore, the invention provides a novel rice unit area overground part soluble sugar accumulation remote sensing inversion model based on a random gradient descent regression algorithm based on actual measurement hyperspectral remote sensing data, the information of the rice unit area overground part soluble sugar accumulation can be quickly and accurately obtained based on the actual measurement rice canopy reflectivity data and the rice unit area overground part soluble sugar accumulation data collected on site, the difficulty that the characteristic wave band of the rice unit area overground part soluble sugar accumulation caused by the spectrum superposition effect caused by complex rice components is difficult to determine is overcome, model parameters are optimized by a trial-and-error method by constructing a model parameter optimization rank matrix, the phenomenon of linear model overfitting is effectively reduced, the rice unit area overground part soluble sugar accumulation inversion accuracy is greatly improved, and the rice unit area overground part soluble sugar accumulation inversion model is suitable for different ecological regions, Quantitative inversion of the accumulated amount of the soluble sugar on the overground part of the unit area of the rice of different varieties and main growth periods is carried out, so that the physiological state of the rice and the state of water and fertilizer supply are obtained, the growth information acquisition efficiency in the rice cultivation and planting process is improved, and basic scientific data are provided for the water and fertilizer operation in the rice production.
Compared with the prior art, the invention has the following advantages:
(1) the method is characterized in that a Stochastic Gradient Regression Model (SGDRM) used by the method is suitable for the inversion of the overground part soluble sugar accumulation amount of the rice unit area based on the hyperspectrum, on the basis of comprehensively considering the information of the wave band range of 350-2500 nm of the hyperspectrum, the influence and the superposition effect of various substance compositions and cell structures in the rice body, particularly the influence and the superposition effect of complex components on the characteristic wave band of the overground part soluble sugar accumulation amount of the rice unit area are considered, and the overground part soluble sugar accumulation amount information of the rice unit area contained in different wave bands in remote sensing data is fully utilized to invert the overground part soluble sugar accumulation amount of the rice unit area.
(2) A model of the reflectivity of 350-2500 nm and the rice unit area overground part soluble sugar accumulation amount is constructed by using a random gradient descent regression algorithm in machine learning, the relation between a large amount of spectrum band information and the rice unit area overground part soluble sugar accumulation amount is effectively solved, and an inversion model of the rice unit area overground part soluble sugar accumulation amount is constructed. In addition, the algorithm can be used for continuously training by directly using new data on the basis of a trained model, a new model is established, the speed and the efficiency of the inversion of the accumulation amount of the soluble sugars on the overground part of the unit area of the rice based on the hyperspectral information are improved, and the method is convenient to apply and popularize.
(3) The independence of model training and model inspection is fully considered, the training data set and the inspection data set are divided by a random segmentation method, the training data set is only used for model training, and the inspection data set is only used for model inspection, so that the reasonability of model effect inspection is ensured.
(4) Since the parameter tuning of the model is very important to the calculation accuracy of the model, the invention constructs a model parameter rank matrix to determine the coefficient R2In order to evaluate the parameters, a trial and error method is used for model parameter tuning, and on the basis of ensuring the parameter tuning effect, the speed of model training and parameter tuning is greatly improved.
(5) The inversion method for the overground part soluble sugar accumulation amount of the rice unit area is simple and convenient to calculate, is suitable for remote sensing quantitative inversion of the overground part soluble sugar accumulation amount of the rice unit area in different ecological regions, different varieties and different growth periods, can accurately invert the overground part soluble sugar accumulation amount of the rice unit area, can quickly acquire information such as physiological conditions and growth vigor of the rice, and meanwhile provides scientific data for water and fertilizer planning management of rice planting and cultivation.
In conclusion, the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm can quickly and accurately acquire the rice unit area overground part soluble sugar accumulation information, overcomes the difficulty that the characteristic wave band of the rice unit area overground part soluble sugar accumulation is difficult to determine due to the spectrum superposition effect caused by complex rice components, greatly improves the accuracy of the rice unit area overground part soluble sugar accumulation inversion model, and is ingenious in design, simple and convenient to calculate, easy to implement, low in cost and suitable for large-scale popularization and application.
It will thus be seen that the objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the embodiments, and the embodiments may be modified without departing from the principles. Therefore, this invention includes all modifications encompassed within the spirit and scope of the claims.
Claims (11)
1. A remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm is characterized in that the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm is a random gradient descent regression model of Python language, and model parameters of the random gradient descent regression model are as follows: 'n _ iter _ no _ change' 29, 'epsilon' 0.014648521430621595, 'l1_ ratio' 0.15, 'leaving _ rate' invscaling '1000,' validity _ fraction '0.1,' dependency 'l2', 'loss' huber ', power _ t' 0.7938077877018379, 'fit _ interrupt' True, 'tol' 2.744072031501585, 'alpha' 0.7167750035123579, 'eta0' 0.0056907807163545186, 'average' False, 'early _ storing' False 'True'.
2. The remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm as claimed in claim 1, wherein the stochastic gradient descent regression model is trained by adopting a rice data set, the data set comprises canopy reflectivities of m sample points of the rice and the unit area overground part soluble sugar accumulation, the m sample points are uniformly distributed in a rice planting area, and the canopy reflectivity is the canopy reflectivity of n characteristic wave bands.
3. The remote sensing inversion model of the soluble sugar accumulation amount of the overground part of a unit area of rice based on the stochastic gradient descent regression algorithm as claimed in claim 2, wherein m is 36, the n characteristic wave bands are 2151 characteristic wave bands, and the 2151 characteristic wave bands are from 350nm wave band to 2500nm wave band.
4. A remote sensing inversion method of the accumulation amount of soluble sugar on the overground part of a unit area of rice based on a random gradient descent regression algorithm is characterized by comprising the following steps:
(1) measuring the canopy reflectance of the rice;
(2) measuring the amount of the accumulated soluble sugar in the upper part of the unit area of the rice;
(3) calculating by using the canopy reflectivity as input data and adopting a random gradient descent regression model of Python language to obtain an inversion value, and calculating a decision coefficient R according to the inversion value and the unit area overground part soluble sugar accumulation2Changing the value of the model parameter, R, of the stochastic gradient descent regression model2The larger the change of the model parameter is, the greater the importance of the model parameter is, the model parameter is arranged from large to small according to the importance to construct a model parameter tuning rank matrix;
(4) training the stochastic gradient descent regression model by taking the canopy reflectivity as the input data and the overground part soluble sugar accumulation amount in unit area as an output result, and sequentially tuning the model parameters according to the model parameter tuning order matrix to obtain tuning values of the model parameters;
(5) using the canopy reflectivity as the input data, using the above-ground soluble sugar accumulation amount per unit area as the output result, using the adjusted values of the model parameters to train the stochastic gradient descent regression model, after the training of the stochastic gradient descent regression model is finished, obtaining a remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on a random gradient descent regression algorithm, storing the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the random gradient descent regression algorithm by using a save method, if the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm needs to be used, the remote sensing inversion model of the rice unit area overground part soluble sugar accumulation based on the stochastic gradient descent regression algorithm is loaded by using a load method for use.
5. The remote sensing inversion method of the amount of the accumulated soluble sugar in the overground part of the rice unit area based on the stochastic gradient descent regression algorithm according to claim 4, wherein in the step (1), the measurement is performed by using a hyperspectral radiometer, the measurement time is 10: 00-14: 00, the hyperspectral radiometer uses a lens with a field angle of 25 degrees, a sensor probe of the portable field hyperspectral radiometer vertically points to the canopy of the rice and has a vertical height of 1 meter from the top layer of the canopy, the diameter of the ground field range of the sensor probe is 0.44 meter, the sensor probe faces the sun, the measurement is corrected by using a standard board, and the standard board is a standard white board with a reflectivity of 95-99%.
6. The remote sensing inversion method of the rice unit area upper part soluble sugar accumulation based on the stochastic gradient descent regression algorithm as claimed in claim 4, wherein in the step (2), the step of measuring the rice unit area upper part soluble sugar accumulation specifically comprises:
collecting the overground part plants of the rice, deactivating enzyme, drying to constant weight to obtain dry plants, measuring the weight of the dry plants to obtain the overground part dry weight, and converting the overground part dry weight into the unit area overground part dry weight according to the sampling coverage area;
and crushing the dry plants, measuring the soluble sugar content of the overground part, and multiplying the weight of the overground part dry matter per unit area by the soluble sugar content of the overground part to obtain the accumulated amount of the overground part soluble sugar per unit area.
7. The remote sensing inversion method of the amount of the accumulated soluble sugar in the overground part of a unit area of rice based on the stochastic gradient descent regression algorithm according to claim 6, wherein in the step (2), the water-removing temperature is 105 ℃, the water-removing time is 20-30 minutes, the drying temperature is 80-90 ℃, and the anthrone colorimetry is adopted for measuring the content of the soluble sugar in the overground part.
8. The remote sensing inversion method of the amount of the accumulated soluble sugar in the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm as claimed in claim 4, wherein in the step (3), the model parameter tuning rank matrix is:
Params＝{'n_iter_no_change','epsilon','l1_ratio','learning_rate','max_iter','validation_fraction','penalty','loss','power_t','fit_intercept','tol','alpha','eta0','average','early_stopping','shuffle'}。
9. the remote sensing inversion method of the amount of the accumulated soluble sugar in the overground part of the unit area of the rice based on the stochastic gradient descent regression algorithm as claimed in claim 8, wherein in the step (4), the optimized values of the model parameters are as follows:
'n_iter_no_change':29,'epsilon':0.014648521430621595,'l1_ratio':0.15,'learning_rate':'invscaling','max_iter':1000,'validation_fraction':0.1,'penalty':'l2','loss':'huber','power_t':0.7938077877018379,'fit_intercept':True,'tol':2.744072031501585,'alpha':0.7167750035123579,'eta0':0.0056907807163545186,'average':False,'early_stopping':False,'shuffle':True。
10. the remote sensing inversion method of the amount of the accumulated soluble sugar in the overground part of the rice unit area based on the stochastic gradient descent regression algorithm according to claim 4, wherein in the step (1), the step of measuring the reflectivity of the canopy of the rice is specifically to measure the reflectivity of the canopy of m sampling points in a rice planting area, the m sampling points are uniformly distributed in the rice planting area, and the reflectivity of the canopy is the reflectivity of the canopy of n characteristic bands; in the step (2), the step of measuring the amount of the soluble sugar accumulated in the upper part of the unit area of the rice is to measure the amount of the soluble sugar accumulated in the upper part of the unit area of the m spots.
11. The remote sensing inversion method of the amount of the soluble sugar accumulation in the overground part of a unit area of rice based on the stochastic gradient descent regression algorithm as claimed in claim 10, wherein in the step (1), the m is 36, the n characteristic bands are 2151 characteristic bands, and the 2151 characteristic bands are from 350nm to 2500 nm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382698.XA CN112666091A (en) | 2020-12-01 | 2020-12-01 | Remote sensing inversion model and method for rice unit area overground part soluble sugar accumulation based on random gradient descent regression algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382698.XA CN112666091A (en) | 2020-12-01 | 2020-12-01 | Remote sensing inversion model and method for rice unit area overground part soluble sugar accumulation based on random gradient descent regression algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112666091A true CN112666091A (en) | 2021-04-16 |
Family
ID=75403904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011382698.XA Pending CN112666091A (en) | 2020-12-01 | 2020-12-01 | Remote sensing inversion model and method for rice unit area overground part soluble sugar accumulation based on random gradient descent regression algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112666091A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111829965A (en) * | 2020-08-04 | 2020-10-27 | 淮阴师范学院 | Remote sensing inversion model and method for starch accumulation amount of rice overground part |
| CN111855589A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for rice leaf nitrogen accumulation |
| CN111855592A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for upper dry matter weight in unit area of rice |
| CN111855590A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for rice leaf starch accumulation |
-
2020
- 2020-12-01 CN CN202011382698.XA patent/CN112666091A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111829965A (en) * | 2020-08-04 | 2020-10-27 | 淮阴师范学院 | Remote sensing inversion model and method for starch accumulation amount of rice overground part |
| CN111855589A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for rice leaf nitrogen accumulation |
| CN111855592A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for upper dry matter weight in unit area of rice |
| CN111855590A (en) * | 2020-08-04 | 2020-10-30 | 淮阴师范学院 | Remote sensing inversion model and method for rice leaf starch accumulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111855589A (en) | Remote sensing inversion model and method for rice leaf nitrogen accumulation | |
| CN111855591A (en) | Rice overground part carbon-nitrogen ratio remote sensing inversion model and method | |
| CN111855590A (en) | Remote sensing inversion model and method for rice leaf starch accumulation | |
| CN113268923B (en) | Summer corn yield estimation method based on simulated multispectral | |
| CN111829965A (en) | Remote sensing inversion model and method for starch accumulation amount of rice overground part | |
| CN102788752B (en) | Non-destructive detection device and method of internal information of crops based on spectrum technology | |
| CN107505271B (en) | Plant nitrogen estimation method and system based on nitrogen component radiation transmission model | |
| CN110567892B (en) | Summer corn nitrogen hyperspectral prediction method based on critical nitrogen concentration | |
| CN111855593A (en) | Remote sensing inversion model and method for starch content of rice leaf | |
| CN112270131A (en) | Remote sensing inversion model and method for rice leaf area index based on ARD regression algorithm | |
| CN101210875A (en) | Damage-free measurement method for soil nutrient content based on near infrared spectra technology | |
| CN104502283A (en) | Two-band hyperspectral index and prediction model for estimating yield and shoot dry weight of soybean | |
| CN111855592A (en) | Remote sensing inversion model and method for upper dry matter weight in unit area of rice | |
| CN111044516B (en) | Remote sensing estimation method for chlorophyll content of rice | |
| CN112816618A (en) | Method for screening nitrogen-efficient wheat varieties | |
| CN201503392U (en) | Handheld soil nutrient nondestructive measurement device based on near infrared spectrum | |
| CN113049499A (en) | Indirect remote sensing inversion method for water total nitrogen concentration, storage medium and terminal equipment | |
| CN1900695A (en) | Field quick monitoring method for wheat nitrogen content and seed protein quality based on high light spectrum | |
| CN112362812A (en) | Remote sensing inversion model and method for rice leaf chlorophyll carotenoid content ratio based on Lars algorithm | |
| CN113670913B (en) | Construction method for inversion hyperspectral vegetation index of nitrogen content of rice | |
| CN113552096A (en) | Spectrum-based pineapple leaf nitrogen content estimation method | |
| CN105158177A (en) | Method for quantitatively detecting solid fermentation moisture distribution uniformity through hyper-spectral image technology | |
| CN112632847A (en) | XGboost regression algorithm-based rice leaf starch content remote sensing inversion model and method | |
| CN112525831A (en) | Remote sensing inversion model and method for protein nitrogen accumulation of rice overground part based on Catboost regression algorithm | |
| CN112630167A (en) | Rice leaf carbon-nitrogen ratio remote sensing inversion model and method based on support vector machine regression algorithm |
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 |