CN117907248A - Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat - Google Patents
Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat Download PDFInfo
- Publication number
- CN117907248A CN117907248A CN202410310229.9A CN202410310229A CN117907248A CN 117907248 A CN117907248 A CN 117907248A CN 202410310229 A CN202410310229 A CN 202410310229A CN 117907248 A CN117907248 A CN 117907248A
- Authority
- CN
- China
- Prior art keywords
- growth period
- winter wheat
- soil
- data
- root system
- 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.)
- Granted
Links
- 239000002689 soil Substances 0.000 title claims abstract description 163
- 241000209140 Triticum Species 0.000 title claims abstract description 152
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 152
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 230000002262 irrigation Effects 0.000 claims abstract description 88
- 238000003973 irrigation Methods 0.000 claims abstract description 88
- 238000012706 support-vector machine Methods 0.000 claims abstract description 44
- 230000003595 spectral effect Effects 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000001228 spectrum Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000002310 reflectometry Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012952 Resampling Methods 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims 1
- 238000010606 normalization Methods 0.000 abstract description 6
- 238000010276 construction Methods 0.000 abstract description 5
- 239000010410 layer Substances 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000013499 data model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 101000794020 Homo sapiens Bromodomain-containing protein 8 Proteins 0.000 description 1
- 101001006782 Homo sapiens Kinesin-associated protein 3 Proteins 0.000 description 1
- 101000615355 Homo sapiens Small acidic protein Proteins 0.000 description 1
- WGKGADVPRVLHHZ-ZHRMCQFGSA-N N-[(1R,2R,3S)-2-hydroxy-3-phenoxazin-10-ylcyclohexyl]-4-(trifluoromethoxy)benzenesulfonamide Chemical compound O[C@H]1[C@@H](CCC[C@@H]1N1C2=CC=CC=C2OC2=C1C=CC=C2)NS(=O)(=O)C1=CC=C(OC(F)(F)F)C=C1 WGKGADVPRVLHHZ-ZHRMCQFGSA-N 0.000 description 1
- 102100021255 Small acidic protein Human genes 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a remote sensing monitoring method and a remote sensing monitoring system for the water content of root system soil in a key growth period of winter wheat, wherein the method comprises the steps of extracting spectral images in the whole growth period of winter wheat and preprocessing, and further comprises the following steps: acquiring irrigation area sample data; acquiring satellite remote sensing sample data; constructing winter wheat growth period classification characteristics; constructing a deep soil water content prediction model based on support vector machine regression and training; and (5) evaluating the accuracy of inversion results of the water content of the deep soil in the key growth period. According to the remote sensing monitoring method and system for the root system soil moisture content of the winter wheat in the key growth period, which are provided by the invention, the accurate identification of the growth period of the winter wheat is realized by setting the spectral threshold and calculating a plurality of normalization indexes, the accurate prediction of the root system soil moisture of the winter wheat is realized by a support vector machine regression model, the soil moisture content monitoring of the winter wheat in the key growth period is ensured, and effective technical support is provided for the construction of digital irrigation areas.
Description
Technical Field
The invention relates to the technical field of soil moisture remote sensing monitoring, in particular to a remote sensing monitoring method and system for the moisture content of root system soil in a key growth period of winter wheat.
Background
There have been studies to distinguish the growth period of crops by spectral curve thresholds of different growth periods of crops, and finally to determine the growth period of winter wheat by Sentinel-2 Level-2A data and a plurality of normalized indices.
At present, the deep soil moisture content is difficult to monitor by a remote sensing technology, the shallow soil moisture content and the root system deep soil moisture content are connected through a mathematical method such as multiple regression fitting for solving the problem of deep soil moisture content prediction, along with the development of a computer technology, more and more regression methods are realized through machine learning, and finally, the prediction of the shallow soil moisture content to the deep soil moisture content is realized through regression based on a support vector machine.
These studies only use small amounts of data to predict the relationship between surface soil water content and deep soil water content and identify different growth periods of crops, with large errors in predicting deep soil water content, particularly in the presence of rainfall or irrigation effects.
The invention patent application with publication number of CN111721714A discloses a soil moisture content estimation method based on multi-source optical remote sensing data, which integrates the spectral characteristics of hyperspectral data and the high spatial resolution characteristics of high spatial resolution images, constructs high spatial resolution hyperspectral data through data compounding and splitting, and completes the estimation of soil moisture by using a model. The method has the defects that the use data are optical remote sensing data which are easily affected by weather and cloud layer thickness images, the data are easily interfered, the capability of penetrating through soil in a visible light wave band is weak, and the deep soil water content data are not easy to monitor.
The invention patent application with publication number CN 107505265A discloses a soil water content remote sensing monitoring method, which comprises the steps of acquiring optical remote sensing image data of vegetation distribution in a monitoring area, extracting characteristics of the optical remote sensing image data, and determining vegetation coverage degree data of areas where different types of vegetation are monitored by dividing the monitoring area according to vegetation types and positions; introducing growth periods of different vegetation types, and establishing a vegetation coverage degree data model of a monitoring area with respect to time and position; acquiring the ground surface temperature and evaporation capacity of a monitoring area through satellite remote sensing, and synchronously processing a vegetation coverage degree data model, the ground surface temperature and the evaporation capacity of the monitoring area with respect to time and position; determining a temperature vegetation drought index of a monitoring area; determining a surface soil moisture content for the monitored parameter; determining a surface soil moisture verification value for the monitored parameter; and determining the water content of the surface soil. The method has the defects that only a single optical remote sensing data is used as a data source, the data is easily affected by weather and cannot be used, the optical remote sensing data has a longer reentry period and cannot be monitored in real time, and the monitoring of the water content of deep soil is not considered, and only the water content of a surface layer is monitored.
Disclosure of Invention
In order to solve the technical problems, the remote sensing monitoring method and system for the root system soil moisture content of the winter wheat in the key growth period provided by the invention realize the accurate identification of the growth period of the winter wheat by setting a spectrum threshold value and calculating a plurality of normalization indexes, realize the accurate prediction of the root system soil moisture of the winter wheat by a support vector machine regression model, ensure the soil moisture content monitoring of the winter wheat in the key growth period and provide effective technical support for digital irrigation district construction.
The first object of the invention is to provide a remote sensing monitoring method for the root system soil moisture content in the key growth period of winter wheat, which comprises the steps of extracting spectral images in the whole growth period of winter wheat and preprocessing, and is characterized by further comprising the following steps:
step 1: acquiring irrigation area sample data;
step 2: acquiring satellite remote sensing sample data;
step 3: constructing winter wheat growth period classification characteristics;
step 4: constructing a deep soil water content prediction model based on support vector machine regression and training;
step 5: and (5) evaluating the accuracy of inversion results of the water content of the deep soil in the key growth period.
Preferably, the extracting and preprocessing of the spectral image of the winter wheat in the whole growth period comprises obtaining a Sentinel-2 Level-2A surface reflectivity product of the winter wheat in the whole growth period of the irrigation area, and preprocessing the data to obtain an image set of the winter wheat in the growth period.
In any of the above schemes, preferably, the obtaining the Sentinel-2 Level-2A surface reflectivity product of the winter wheat in the irrigation area in the whole growth period includes visually interpreting and inquiring weather data of the irrigation area to screen out remote sensing images where the snowfall and the heavy fog are located, selecting images without clouds or with less clouds, and cutting out remote sensing images in the irrigation area through a vector diagram of the irrigation area.
In any of the above schemes, preferably, the method for obtaining the winter wheat growth period image set includes obtaining a 10m resolution spectrum image set of 12 spectrum bands of winter wheat in the irrigation area after performing band fusion resampling on the 12 spectrum bands of the image in the irrigation area.
In any of the above schemes, preferably, the step 1 includes the following substeps:
Step 11: collecting soil moisture content data of soil moisture content stations of irrigation areas, and obtaining soil moisture content data samples of soil layers with different depths;
Step 12: acquiring rainfall data of rainfall stations around the irrigation area, and determining the rainfall date and the rainfall;
step 13: acquiring soil texture data of a irrigated area, and determining soil texture distribution conditions of the irrigated area;
step 14: and acquiring the DEM data of the irrigation area to calculate the gradient and the slope direction.
In any of the above schemes, preferably, the step 2 includes obtaining SMAP-developed 1-km surface soil moisture content, daily surface temperature data and solar reflectance data of the winter wheat in the irrigation area.
In any of the above schemes, preferably, the step 3 includes generating a plurality of vegetation indexes by using the image set of the growth period of the winter wheat, fusing the vegetation indexes with the image set of the growth period of the winter wheat to form a synthetic image set, and determining spectral features of different growth periods of the winter wheat according to the synthetic image set to form a spectral feature set of the growth period of the winter wheat.
In any of the above schemes, preferably, the step 3 includes the following substeps:
Step 31: selecting corresponding spectrum bands from 12 spectrum bands to perform band calculation to obtain 5 vegetation indexes;
step 32: and carrying out band fusion on the 5 vegetation indexes serving as independent bands and 12 spectrum bands to obtain a second fusion image set of 17 bands in the whole growth period of winter wheat, and distinguishing characteristic spectrum curves of different growth periods of winter wheat by analyzing images of the second fusion image set.
In any of the above schemes, preferably, the 5 vegetation indexes include normalized difference vegetation index NDVI, difference vegetation index DVI, normalized difference water index NDWI, enhanced vegetation index EVI and normalized building index NDBI, and the calculation formula is
NDVI=(NIR- RED)/(NIR+ RED)
DVI= NIR- RED
NDWI= (Green-NIR)/(Green+NIR)
EVI= 2.5 * ((NIR – RED) / ((NIR) + (6 * RED) – (7.5 * BLUE) + 1))
NDBI= (SWIR - NIR) / (SWIR + NIR)
Wherein, NIR is near infrared band reflection value, RED is RED light band reflection value, green is Green light band reflection value, BLUE is BLUE light band reflection value, SWIR is short wave infrared band reflection value.
In any of the above solutions, preferably, the step 4 includes applying the irrigation area sample data and the satellite remote sensing sample data as inputs of a support vector machine regression model, and training the support vector machine regression model.
In any of the above schemes, preferably, the step 4 includes the following substeps:
Step 41: constructing a regression model formula f (x) =w T x+b;
step 42: constructing an input data matrix X= [ X1, X2, … xn ] and a tag matrix Y= [ Y1, Y2, … yn ] T,
Step 43: constructing Lagrangian and Japanese equations L, and solving by using an SMO method to obtain a * and a minimum LThe formula is
；
Step 44: the bias of w is derived by the Lagrangian equation:
，
Step 45: the bias of b is derived by the Lagrangian equation:
，
step 46: the bias is calculated by the Lagrangian equation pair:
，
step 47: the three equations are obtained by meeting the KKT condition:
，
，
Step 48: calculating the minimum L value by SMO method as a * and Obtaining a training equation f (x) =w T x+b;
Wherein w is the hyperplane normal vector, w T is the transpose of the hyperplane normal vector, x is the input matrix, b is the hyperplane distance from the origin, For the relaxation variable to be used to handle the inseparable case, a is the Lagrangian multiplier used to weight the constraint in the loss function, μ is the Lagrangian multiplier used to weight the constraint of the relaxation variable, C is the penalty parameter used to balance the interval size and the misclassification weight, n is the number of samples, a i is the Lagrangian multiplier of the ith equation, x i is the ith input variable, y i is the ith output, a * and/>Is the two optimal lagrange multipliers.
In any of the above schemes, preferably, the step 5 includes obtaining root system soil moisture data of the winter wheat in the full growth period of the irrigation area through a deep soil moisture prediction model based on regression of a support vector machine, classifying the root system soil moisture data according to spectral characteristics of the winter wheat in the growth period to obtain root system soil moisture data of the winter wheat in the key growth period, and performing precision assessment.
In any of the above schemes, preferably, the step 5 includes selecting root system soil moisture content data of winter wheat in a key growth period, and performing accuracy assessment by Root Mean Square Error (RMSE), wherein the calculation formula is as follows
，
The calculation formula of the correlation coefficient R is
，
SM P is the actual measurement of the soil water content of the key growth period of different depths, SM i is the regression model for predicting the soil water content of the corresponding key growth period, and m is the effective number of samples.
The second object of the invention is to provide a remote sensing monitoring system for the root system soil moisture content in winter wheat in a key growth period, which comprises a remote sensing data processing module and further comprises the following modules:
the winter wheat growth period distinguishing module is used for constructing winter wheat growth period classification characteristics;
regression root system soil water content prediction module based on support vector machine: constructing a deep soil water content prediction model based on support vector machine regression and training;
and the precision detection module is used for: evaluating the accuracy of inversion results of the water content of the deep soil in the key growth period;
The system adopts the method described in the first object to remotely monitor the water content of root system soil in the key growth period of winter wheat.
Preferably, the remote sensing data processing module is used for extracting and preprocessing the spectrum image of the winter wheat in the whole growth period.
In any of the above schemes, preferably, the extracting and preprocessing the spectral image of the winter wheat in the whole growth period comprises obtaining a Sentinel-2 Level-2A surface reflectivity product of the winter wheat in the whole growth period in the irrigation area, and preprocessing the data to obtain an image set of the winter wheat in the growth period.
In any of the above schemes, preferably, the method for obtaining the winter wheat growth period image set includes obtaining a 10m resolution spectrum image set of 12 spectrum bands of winter wheat in the irrigation area after performing band fusion resampling on the 12 spectrum bands of the image in the irrigation area.
In any of the above schemes, preferably, the remote sensing data processing module is further configured to obtain the irrigation area sample data and satellite remote sensing sample data.
In any of the above schemes, preferably, the method for acquiring the irrigation area sample data includes the following substeps:
Step 11: collecting soil moisture content data of soil moisture content stations of irrigation areas, and obtaining soil moisture content data samples of soil layers with different depths;
Step 12: acquiring rainfall data of rainfall stations around the irrigation area, and determining the rainfall date and the rainfall;
step 13: acquiring soil texture data of a irrigated area, and determining soil texture distribution conditions of the irrigated area;
step 14: and acquiring the DEM data of the irrigation area to calculate the gradient and the slope direction.
In any of the above schemes, preferably, the satellite remote sensing sample data comprises SMAP-developed 1-km surface soil moisture content, daily surface temperature data and solar reflectance data of the winter wheat in the irrigation area.
In any of the above schemes, preferably, the construction method of the winter wheat growth period classification feature comprises the following substeps:
Step 31: selecting corresponding spectrum bands from 12 spectrum bands to perform band calculation to obtain 5 vegetation indexes;
step 32: and carrying out band fusion on the 5 vegetation indexes serving as independent bands and 12 spectrum bands to obtain a second fusion image set of 17 bands in the whole growth period of winter wheat, and distinguishing characteristic spectrum curves of different growth periods of winter wheat by analyzing images of the second fusion image set.
In any of the above schemes, preferably, the vegetation index comprises a normalized difference vegetation index NDVI, a difference vegetation index DVI, a normalized difference water index NDWI, an enhanced vegetation index EVI and a normalized building index NDBI, and the calculation formula is
NDVI=(NIR- RED)/(NIR+ RED)
DVI= NIR- RED
NDWI= (Green-NIR)/(Green+NIR)
EVI= 2.5 * ((NIR – RED) / ((NIR) + (6 * RED) – (7.5 * BLUE) + 1))
NDBI= (SWIR - NIR) / (SWIR + NIR)
Wherein, NIR is near infrared band reflection value, RED is RED light band reflection value, green is Green light band reflection value, BLUE is BLUE light band reflection value, SWIR is short wave infrared band reflection value.
In any of the above schemes, preferably, the support vector machine regression root system based soil water content prediction module is used for applying the irrigation area sample data and the satellite remote sensing sample data as inputs of a support vector machine regression model, and training the support vector machine regression model.
In any of the above schemes, preferably, the construction method of the support vector machine regression model includes the following sub-steps:
Step 41: constructing a regression model formula f (x) =w T x+b;
step 42: constructing an input data matrix X= [ X1, X2, … xn ] and a tag matrix Y= [ Y1, Y2, … yn ] T,
Step 43: constructing Lagrangian and Japanese equations L, and solving by using an SMO method to obtain a * and a minimum LThe formula is
；
Step 44: the bias of w is derived by the Lagrangian equation:
，
Step 45: the bias of b is derived by the Lagrangian equation:
，
step 46: the bias is calculated by the Lagrangian equation pair:
，
step 47: the three equations are obtained by meeting the KKT condition:
，
，
，
Step 48: calculating the minimum L value by SMO method as a * and Obtaining a training equation f (x) =w T x+b;
Wherein w is the hyperplane normal vector, w T is the transpose of the hyperplane normal vector, x is the input matrix, b is the hyperplane distance from the origin, For the relaxation variable to be used to handle the inseparable case, a is the Lagrangian multiplier used to weight the constraint in the loss function, μ is the Lagrangian multiplier used to weight the constraint of the relaxation variable, C is the penalty parameter used to balance the interval size and the misclassification weight, n is the number of samples, a i is the Lagrangian multiplier of the ith equation, x i is the ith input variable, y i is the ith output, a * and/>Is the two optimal lagrange multipliers.
In any of the above schemes, preferably, the precision detection module is used for obtaining root system soil moisture data of the winter wheat in the irrigation area in the whole growth period through a deep soil moisture prediction model based on regression of a support vector machine, classifying the root system soil moisture data according to spectral characteristics of the winter wheat in the growth period to obtain root system soil moisture data of the winter wheat in the key growth period, and performing precision assessment.
In any of the above schemes, preferably, the precision detection module is further configured to select root system soil moisture content data of winter wheat in a key growth period to perform precision assessment through root mean square error RMSE, where a calculation formula is as follows
，
The calculation formula of the correlation coefficient R is
，
SM P is the actual measurement of the soil water content of the key growth period of different depths, SM i is the regression model for predicting the soil water content of the corresponding key growth period, and m is the effective number of samples.
The invention provides a remote sensing monitoring method and a remote sensing monitoring system for the water content of the root system soil in the key growth period of winter wheat, which realize the accurate identification of the growth period of winter wheat, and the accuracy of the water content of the root system soil in the key growth period of winter wheat based on the regression prediction of a support vector machine is high, so that the accurate prediction of the water content of the root system soil in the key growth period of winter wheat is realized.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of a remote sensing monitoring method for root system soil moisture content during key growth period of winter wheat according to the present invention.
Fig. 2 is a block diagram of a preferred embodiment of a remote sensing monitoring system for root system soil moisture content during key growth period of winter wheat according to the present invention.
Fig. 3 is a flow chart of another preferred embodiment of a remote sensing monitoring method for root system soil moisture content in winter wheat during key growth period according to the present invention.
Fig. 4 is a schematic diagram of regression principle of a support vector machine according to another preferred embodiment of the remote sensing monitoring method of root system soil moisture content in winter wheat during key growth period.
Detailed Description
The invention is further illustrated by the following figures and specific examples.
Example 1
As shown in fig. 1 and 2, step 100 is performed, and the remote sensing data processing module 200 extracts and pre-processes spectral images of winter wheat in the whole growth period, obtains sentel-2 Level-2A surface reflectivity products of winter wheat in the whole growth period in the irrigation area, and pre-processes data to obtain an image set of winter wheat in the growth period;
The method for obtaining the Sentinel-2 Level-2A surface reflectivity product of winter wheat in the irrigation area in the whole growth period comprises the steps of utilizing visual interpretation and inquiring weather data of the irrigation area to screen out remote sensing images where snowfall and heavy fog are located, selecting images without clouds or with less clouds, and cutting out remote sensing images in the irrigation area through a vector image of the irrigation area;
The method for acquiring the winter wheat growth period image set comprises the steps of carrying out band fusion resampling on 12 spectral bands of the shrub region image to obtain a 10-meter resolution spectral image set of the 12 spectral bands of the winter wheat in the shrub region.
Executing step 110, the remote sensing data processing module 200 obtains the irrigation area sample data, including the following sub-steps:
Step 111 is executed, soil moisture content data of soil moisture content sites of irrigation areas are collected, and soil moisture content data samples of soil layers with different depths are obtained;
step 112 is executed, rainfall data of rainfall stations around the irrigation area are obtained, and the rainfall date and the rainfall are determined;
Step 113 is executed to acquire soil texture data of the irrigation area and determine the distribution condition of the soil texture of the irrigation area;
step 114 is executed to obtain the DEM data of the irrigation area to calculate the gradient and the slope direction.
Step 120 is executed, where the remote sensing data processing module 200 obtains satellite remote sensing sample data, and obtains SMAP-developed 1-km surface soil moisture content, daily surface temperature data, and solar reflectance data of the winter wheat in the irrigation area.
Step 130 is executed, where the winter wheat growth period distinguishing module 210 constructs a winter wheat growth period classification feature, applies a winter wheat growth period image set to generate a plurality of vegetation indexes, and fuses the vegetation indexes and the winter wheat growth period image set to form a synthetic image set, and determines different growth period spectrum features of winter wheat according to the synthetic image set to form a winter wheat growth period spectrum feature set, including the following sub-steps:
Step 131 is executed, and corresponding spectral bands are selected from the 12 spectral bands, and band calculation is performed to obtain 5 vegetation indexes, wherein the vegetation indexes comprise normalized difference vegetation indexes NDVI, difference vegetation indexes DVI, normalized difference water indexes NDWI, enhanced vegetation indexes EVI and normalized building indexes NDBI, and the calculation formula is that
NDVI=(NIR- RED)/(NIR+ RED)
DVI= NIR- RED
NDWI= (Green-NIR)/(Green+NIR)
EVI= 2.5 * ((NIR – RED) / ((NIR) + (6 * RED) – (7.5 * BLUE) + 1))
NDBI= (SWIR - NIR) / (SWIR + NIR)
Wherein NIR is near infrared band reflection value, RED is RED light band reflection value, green is Green light band reflection value, BLUE is BLUE light band reflection value, SWIR is short wave infrared band reflection value;
step 132 is executed, in which the 5 vegetation indexes are used as independent wave bands and are subjected to wave band fusion with 12 spectrum wave bands to obtain a second fusion image set of 17 wave bands of the winter wheat in the whole growth period, and the images of the second fusion image set are analyzed to distinguish the characteristic spectrum curves of the winter wheat in different growth periods.
Step 140 is executed, wherein the deep soil water content prediction model based on support vector machine regression is constructed and trained based on the support vector machine regression root system soil water content prediction module 220, the support vector machine regression model is trained by applying the irrigation area sample data and the satellite remote sensing sample data as the input of the support vector machine regression model, and the support vector machine regression model is trained, and the method comprises the following substeps:
Step 141 is executed to construct a regression model equation f (x) =w T x+b;
Step 142 is performed to construct an input data matrix x= [ X1, X2, … xn ] and a tag matrix y= [ Y1, Y2, … yn ] T,
Step 143 is executed to construct Lagrangian and Japanese equations L, and the solution is performed by SMO method to obtain a * and a minimum LThe formula is
；
Step 144 is executed, where the bias of w is derived by the lagrangian equation:
，
Step 145 is performed, where b is derived by the lagrangian equation:
，
Step 146 is executed, where the bias is derived by the lagrangian equation pair:
，
Executing step 147, the above three equations satisfy the KKT condition to obtain:
，
，
，
step 148 is executed to calculate the minimum L value a * and the minimum L value by the SMO method Obtaining a training equation f (x) =w T x+b;
Wherein w is the hyperplane normal vector, w T is the transpose of the hyperplane normal vector, x is the input matrix, b is the hyperplane distance from the origin, For the relaxation variable to be used to handle the inseparable case, a is the Lagrangian multiplier used to weight the constraint in the loss function, μ is the Lagrangian multiplier used to weight the constraint of the relaxation variable, C is the penalty parameter used to balance the interval size and the misclassification weight, n is the number of samples, a i is the Lagrangian multiplier of the ith equation, x i is the ith input variable, y i is the ith output, a * and/>Is the two optimal lagrange multipliers.
Executing step 150, the precision detection module 230 evaluates the precision of the inversion result of the deep soil moisture content in the key growth period, selects root system soil moisture content data in the key growth period of winter wheat, and evaluates the precision by root mean square error RMSE, wherein the calculation formula is as follows
，
The calculation formula of the correlation coefficient R is
，
SM P is the actual measurement of the soil water content of the key growth period of different depths, SM i is the regression model for predicting the soil water content of the corresponding key growth period, and m is the effective number of samples.
Example two
The invention aims to provide a technical scheme of a winter wheat key growth period root system soil water content remote sensing monitoring system based on support vector machine regression, which comprises the following steps:
s1, extracting and preprocessing spectral images of winter wheat in the whole growth period: obtaining a Sentinel-2 Level-2A surface reflectivity product of winter wheat in the irrigation area in the whole growth period, and preprocessing data to obtain an image set of winter wheat in the growth period.
In the step S1, the specific method for obtaining the Sentinel-2 Level-2A surface reflectivity product of the winter wheat in the irrigation area in the whole growth period comprises the following steps:
Screening out remote sensing images with snowfall and heavy fog by utilizing visual interpretation and inquiring meteorological data of the irrigation area, selecting out images without clouds or with less clouds, and cutting out remote sensing images in the irrigation area through a vector image of the irrigation area;
the specific method for synthesizing the growth period images and obtaining the growth period image set comprises the following steps:
And carrying out band fusion resampling on 12 spectral bands of the irrigated area image to obtain a 10-meter resolution spectral image set of 12 bands of winter wheat in the irrigated area.
Step S2, acquiring irrigation area sample data: and collecting soil moisture content data of soil moisture content stations of irrigation areas, and obtaining soil moisture content data samples of soil layers with different depths. And acquiring rainfall data of rainfall stations around the irrigation area, and determining the rainfall date and the rainfall. And accessing a national Qinghai-Tibet plateau data center to acquire soil texture data of the irrigation area, and determining the soil texture distribution condition of the irrigation area. And accessing the geospatial data cloud to acquire the irrigation area DEM data for slope and slope direction calculation.
In the step S2, three raster data sets are generated for subsequent calculation by calculating the gradient and slope directions of the acquired DEM data.
Step S3, satellite remote sensing sample data acquisition: and obtaining SMAP-developed 1-km surface soil moisture content data of the winter wheat in the irrigation area in the whole growth period for subsequent inversion of root system soil moisture content. Solar surface temperature data, solar reflectance data, and the like.
S4, constructing winter wheat growth period classification characteristics: and generating a plurality of vegetation indexes by using the image set, fusing the vegetation indexes with the image set to form a synthetic image set, and determining the spectral characteristics of winter wheat in different growth periods according to the image set to form a winter wheat growth period spectral characteristic set.
In the step S4, the specific method for generating a plurality of vegetation indexes by using the spectral image set of winter wheat in the irrigation area includes:
selecting corresponding wave bands from the 12 wave bands of the image set, and performing wave band calculation to obtain 5 vegetation index data: normalized Differential Vegetation Index (NDVI), differential Vegetation Index (DVI), normalized Differential Water Index (NDWI), enhanced Vegetation Index (EVI), normalized building index (NDBI):
DVI=(NIR- RED)/(NIR+ RED) ；
DVI= NIR- RED；
NDWI= (Green-NIR)/(Green+NIR) ；
EVI= 2.5 * ((NIR – RED) / ((NIR) + (6 * RED) – (7.5 * BLUE) + 1)) ；
NDBI= (SWIR - NIR) / (SWIR + NIR)；
and carrying out band fusion on the 5 index features serving as independent bands and 12 bands of the image set to obtain a second fused image set of 17 bands of the winter wheat in the whole growth period, and distinguishing characteristic spectrum curves of different growth periods of the winter wheat by analyzing images of the second fused image set.
S5, constructing and training a deep soil water content prediction model based on support vector machine regression: and training the support vector machine regression model by using the irrigation area sample data and the satellite remote sensing sample data as the input of the support vector machine regression model.
S6, evaluating the precision of inversion results of the deep soil water content in the key growth period: obtaining root system soil moisture data of winter wheat in the whole growth period of the irrigation area through a deep soil moisture prediction model based on support vector machine regression, classifying the root system soil moisture data according to spectral characteristics of the winter wheat in the growth period to obtain root system soil moisture data of winter wheat in the key growth period, and carrying out precision assessment.
In the step S6, the specific method includes:
the root system soil water content data of the winter wheat in the key growth period is selected to carry out precision assessment through Root Mean Square Error (RMSE), and the calculation formula is as follows:
，
SM P: measuring the water content of soil in key growth periods at different depths;
SM: predicting the water content of the soil in the corresponding key growth period by using a regression model;
m: the effective number of samples;
the invention discloses a remote sensing monitoring system for root system soil moisture content in winter wheat in key growth period based on support vector machine regression, which comprises:
The remote sensing data processing module is configured to acquire data products of the Sentinel-2 satellite, the SMAP satellite and the MODIS satellite, perform preprocessing such as atmospheric correction and radiation correction to obtain an image set, and perform band fusion to obtain a first synthetic image set.
The winter wheat growth period distinguishing module is configured to calculate each index characteristic by using the synthesized image set, and fuse each calculated index characteristic with the first synthesized image set, so as to distinguish the growth period of winter wheat according to the spectrum characteristic and each index difference.
The root system soil water content prediction module based on support vector machine regression is configured to divide sample data into a training set and a test set through hierarchical sampling, apply the training set and the remote sensing data product as support vector machine regression model inputs, and train the support vector machine regression model.
The precision detection module is configured to detect the prediction precision of the root system soil water content in the key growth period by applying a root mean square error formula.
A third aspect of the invention discloses an electronic device. The electronic equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps in the remote sensing monitoring method of the root system soil moisture content of the winter wheat in the key growth period based on the regression of the support vector machine in any one of the first aspect of the disclosure when executing the computer program.
A fourth aspect of the present invention discloses a storage medium. The computer readable storage medium stores a computer program which, when executed by a processor, implements the steps in the remote sensing monitoring method for root system soil moisture content in winter wheat key growth period based on support vector machine regression in any one of the first aspects of the disclosure.
Example III
As shown in fig. 3, the remote sensing monitoring method for the root system soil moisture content in the winter wheat during the key growth period based on support vector machine regression comprises the following steps:
s1, extracting and preprocessing spectral images of winter wheat in the whole growth period: obtaining a Sentinel-2 Level-2A surface reflectivity product of winter wheat in the irrigation area in the whole growth period, and preprocessing data to obtain an image set of winter wheat in the growth period.
In step S1, the extracting and preprocessing of the spectral image of winter wheat in the whole growth period includes:
(1) And (5) performing atmospheric correction to eliminate the influence of cloud.
(2) The radiation correction is performed to eliminate or correct image distortion caused by radiation errors.
(3) And cutting according to the irrigation area range, and determining an acquisition spectrum range.
Step S2, acquiring irrigation area sample data: and collecting soil moisture content data of soil moisture content stations of irrigation areas, and obtaining soil moisture content data samples of soil layers with different depths. And acquiring rainfall data of rainfall stations around the irrigation area, and determining the rainfall date and the rainfall. And accessing a national Qinghai-Tibet plateau data center to acquire soil texture data of the irrigation area, and determining the soil texture distribution condition of the irrigation area. And accessing the geospatial data cloud to acquire the irrigation area DEM data for slope and slope direction calculation.
In step S2, the irrigated area sample data acquisition includes:
(1) Determining the range of the irrigation area, and downloading soil texture distribution data in the range of the irrigation area through the national Qinghai-Tibet plateau data center
(2) And downloading the distribution map of the irrigation area DEM, and calculating the gradient and the slope direction through the downloaded data of the irrigation area DEM to obtain three irrigation area information raster data graphs.
Step S3, satellite remote sensing sample data acquisition: and obtaining SMAP-developed 1-km surface soil moisture content data of the winter wheat in the irrigation area in the whole growth period for subsequent inversion of root system soil moisture content. Solar surface temperature data, solar reflectance data, and the like.
S4, constructing winter wheat growth period classification characteristics: and generating a plurality of vegetation indexes by using the image set, fusing the vegetation indexes with the image set to form a synthetic image set, and determining the spectral characteristics of winter wheat in different growth periods according to the image set to form a winter wheat growth period spectral characteristic set.
In step S4, the winter wheat spectral feature set is constructed:
(1) And (3) carrying out band fusion on 12 bands of the Sentinel-2 data collected in the step (S1) to obtain 12 band winter wheat spectral images in the irrigation area.
(2) And carrying out normalization index calculation by using a wave band in the winter wheat spectral image of the irrigation area to obtain a normalization index grid data graph of the irrigation area, and combining the normalization index grid data graph with the winter wheat spectral image to distinguish different growth periods of the winter wheat.
S5, constructing and training a deep soil water content prediction model based on support vector machine regression: and training the support vector machine regression model by using the irrigation area sample data and the satellite remote sensing sample data as the input of the support vector machine regression model.
In step S5, as shown in fig. 4, a deep soil moisture content prediction model based on support vector machine regression is constructed and trained:
(1) Regression model formula f (x) =w T x+b;
(2) Constructing an input data matrix x= [ X1, X2, … xn ], and a tag matrix y= [ Y1, Y2, … yn ] T;
(3) Constructing Lagrangian and Japanese equations L, and solving by using an SMO method to obtain a * and a minimum L ；
，
And solving bias derivative on w by using the Lagrangian equation, wherein the bias derivative is 0:
，
Obtaining the product ；
B is biased by the Lagrangian equation, and the value of b is 0:
，
Simultaneously satisfies the KKT condition:
，
，
，
，
Deriving ；
Calculating the minimum L value by SMO method as a * andAnd then b and w expressions are obtained, thereby obtaining a training equation f (x) =w T x+b.
S6, evaluating the precision of inversion results of the deep soil water content in the key growth period: obtaining root system soil moisture data of winter wheat in the whole growth period of the irrigation area through a deep soil moisture prediction model based on support vector machine regression, classifying the root system soil moisture data according to spectral characteristics of the winter wheat in the growth period to obtain root system soil moisture data of winter wheat in the key growth period, and carrying out precision assessment.
The root system soil moisture content prediction precision assessment in the key growth period of the winter wheat in the step S6 comprises the following steps:
(1) Root Mean Square Error (RMSE), calculated as:
，
(2) The correlation coefficient (R) is calculated by the following formula:
，
SM P: measuring the water content of soil in key growth periods at different depths;
SM i: predicting the water content of the soil in the corresponding key growth period by using a regression model;
m: the effective number of samples;
According to the invention, the accurate identification of the growth period of winter wheat is realized by setting the spectrum threshold value and calculating a plurality of normalization indexes, the accurate prediction of the soil moisture of the winter wheat root system is realized by a support vector machine regression model, the soil moisture content monitoring of the winter wheat in the key growth period is ensured, and an effective technical support is provided for the construction of digital irrigation areas.
The foregoing description of the invention has been presented for purposes of illustration and description, but is not intended to be limiting. Any simple modification of the above embodiments according to the technical substance of the present invention still falls within the scope of the technical solution of the present invention. In this specification, each embodiment is mainly described in the specification as a difference from other embodiments, and the same or similar parts between the embodiments need to be referred to each other. For system embodiments, the description is relatively simple as it essentially corresponds to method embodiments, and reference should be made to the description of method embodiments for relevant points.
Claims (10)
1. The remote sensing monitoring method for the root system soil water content in the key growth period of winter wheat comprises the steps of extracting spectral images in the whole growth period of winter wheat and preprocessing, and is characterized by further comprising the following steps:
step 1: acquiring irrigation area sample data;
step 2: acquiring satellite remote sensing sample data;
step 3: constructing winter wheat growth period classification characteristics, generating a plurality of vegetation indexes by applying a winter wheat growth period image set, fusing the vegetation indexes with the winter wheat growth period image set to form a synthetic image set, determining different growth period spectrum characteristics of winter wheat according to the synthetic image set, and forming a winter wheat growth period spectrum characteristic set, wherein the method comprises the following sub-steps:
Step 31: selecting corresponding spectrum bands in 12 spectrum bands to perform band calculation to obtain 5 vegetation indexes, wherein the 5 vegetation indexes comprise normalized difference vegetation index NDVI, difference vegetation index DVI, normalized difference water index NDWI, enhanced vegetation index EVI and normalized building index NDBI, and the calculation formula is that
NDVI=(NIR- RED)/(NIR+ RED)
DVI= NIR- RED
NDWI= (Green-NIR)/(Green+NIR)
EVI= 2.5 * ((NIR – RED) / ((NIR) + (6 * RED) – (7.5 * BLUE) + 1))
NDBI= (SWIR - NIR) / (SWIR + NIR)
Wherein NIR is near infrared band reflection value, RED is RED light band reflection value, green is Green light band reflection value, BLUE is BLUE light band reflection value, SWIR is short wave infrared band reflection value;
Step 32: the 5 vegetation indexes are used as independent wave bands and are subjected to wave band fusion with 12 spectrum wave bands to obtain a second fusion image set of 17 wave bands in the whole growth period of winter wheat, and the characteristic spectrum curves of different growth periods of winter wheat are distinguished by analyzing the images of the second fusion image set;
step 4: constructing a deep soil water content prediction model based on support vector machine regression and training;
step 5: and (5) evaluating the accuracy of inversion results of the water content of the deep soil in the key growth period.
2. The remote sensing monitoring method for the moisture content of root system soil in the key growth period of winter wheat according to claim 1, wherein the steps of extracting and preprocessing the spectral images of the winter wheat in the whole growth period comprise obtaining Sentinel-2 Level-2A surface reflectivity products of the winter wheat in the whole growth period of the shrub area, and preprocessing the data to obtain an image set of the winter wheat in the growth period.
3. The method for remotely sensing and monitoring the moisture content of root system soil in the key growth period of winter wheat according to claim 2, wherein the step of obtaining the Sentinel-2 Level-2A surface reflectivity product in the whole growth period of winter wheat in the irrigation area comprises the steps of utilizing visual interpretation and inquiring weather data in the irrigation area to screen out remote sensing images where snowfall and heavy fog are located, selecting images without clouds or with less clouds, and cutting out remote sensing images in the range of the irrigation area through a vector diagram in the irrigation area.
4. The remote sensing monitoring method for the water content of root system soil in the key growth period of winter wheat as set forth in claim 3, wherein the method for acquiring the image set in the growth period of winter wheat comprises the step of obtaining a 10-meter resolution spectrum image set of 12 spectrum bands of winter wheat in an irrigation area after carrying out band fusion resampling on the 12 spectrum bands of the image in the irrigation area.
5. The remote sensing monitoring method for the moisture content of root system soil in the key growth period of winter wheat as set forth in claim 4, wherein the step 1 comprises the following substeps:
Step 11: collecting soil moisture content data of soil moisture content stations of irrigation areas, and obtaining soil moisture content data samples of soil layers with different depths;
Step 12: acquiring rainfall data of rainfall stations around the irrigation area, and determining the rainfall date and the rainfall;
step 13: acquiring soil texture data of a irrigated area, and determining soil texture distribution conditions of the irrigated area;
step 14: and acquiring the DEM data of the irrigation area to calculate the gradient and the slope direction.
6. The remote sensing method for monitoring the moisture content of root system soil in winter wheat in critical growth period as set forth in claim 5, wherein the step 2 comprises obtaining the SMAP-advanced 1-km surface soil moisture content, daily surface temperature data and solar reflectance data in the winter wheat in the full growth period of the irrigation area.
7. The remote sensing monitoring method for the moisture content of root system soil in winter wheat during key growth period as set forth in claim 6, wherein the step 4 includes the following substeps:
Step 41: constructing a regression model formula f (x) =w T x+b;
step 42: constructing an input data matrix X= [ X1, X2, … xn ] and a tag matrix Y= [ Y1, Y2, … yn ] T,
Step 43: constructing Lagrangian and Japanese equations L, and solving by using an SMO method to obtain a * and a minimum LThe formula is
；
Step 44: the bias of w is derived by the Lagrangian equation:
，
Step 45: the bias of b is derived by the Lagrangian equation:
，
step 46: the bias is calculated by the Lagrangian equation pair:
，
step 47: the three equations are obtained by meeting the KKT condition:
，
，
，
Step 48: calculating the minimum L value by SMO method as a * and Obtaining a training equation f (x) =w T x+b;
Wherein w is the hyperplane normal vector, w T is the transpose of the hyperplane normal vector, x is the input matrix, b is the hyperplane distance from the origin, For the relaxation variable to be used to handle the inseparable case, a is the Lagrangian multiplier used to weight the constraint in the loss function, μ is the Lagrangian multiplier used to weight the constraint of the relaxation variable, C is the penalty parameter used to balance the interval size and the misclassification weight, n is the number of samples, a i is the Lagrangian multiplier of the ith equation, x i is the ith input variable, y i is the ith output, a * and/>Is the two optimal lagrange multipliers.
8. The remote sensing monitoring method for root system soil moisture content in winter wheat in critical growth period as set forth in claim 7, wherein the step 5 comprises obtaining root system soil moisture content data in winter wheat in full growth period of the shrub area through a deep soil moisture content prediction model based on support vector machine regression, and classifying the root system soil moisture content data according to spectral characteristics of winter wheat in growth period to obtain root system soil moisture content data in winter wheat in critical growth period for precision evaluation.
9. The method for remotely sensing and monitoring the moisture content of root system soil in the key growth period of winter wheat as set forth in claim 8, wherein the step 5 comprises selecting the moisture content data of the root system soil in the key growth period of winter wheat to evaluate the accuracy by means of root mean square error RMSE, and the calculation formula is
，
The calculation formula of the correlation coefficient R is
，
SM P is the actual measurement of the soil water content of the key growth period of different depths, SM i is the regression model for predicting the soil water content of the corresponding key growth period, and m is the effective number of samples.
10. The remote sensing monitoring system for the root system soil moisture content in the winter wheat in the key growth period comprises a remote sensing data processing module and is characterized by further comprising the following modules:
the winter wheat growth period distinguishing module is used for constructing winter wheat growth period classification characteristics;
regression root system soil water content prediction module based on support vector machine: constructing a deep soil water content prediction model based on support vector machine regression and training;
and the precision detection module is used for: evaluating the accuracy of inversion results of the water content of the deep soil in the key growth period;
The system adopts the method as claimed in claim 1 to remotely monitor the water content of root system soil in the key growth period of winter wheat.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410310229.9A CN117907248B (en) | 2024-03-19 | 2024-03-19 | Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410310229.9A CN117907248B (en) | 2024-03-19 | 2024-03-19 | Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117907248A true CN117907248A (en) | 2024-04-19 |
| CN117907248B CN117907248B (en) | 2024-05-28 |
Family
ID=90685484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410310229.9A Active CN117907248B (en) | 2024-03-19 | 2024-03-19 | Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117907248B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090024038A1 (en) * | 2007-07-16 | 2009-01-22 | Arnold Stephen C | Acoustic imaging probe incorporating photoacoustic excitation |
| US20110047867A1 (en) * | 2003-11-07 | 2011-03-03 | Holland Kyle H | Plant treatment based on a water invariant chlorophyll index |
| WO2013183247A1 (en) * | 2012-06-04 | 2013-12-12 | パナソニック株式会社 | Acoustooptic imaging device |
| CN108830249A (en) * | 2018-06-26 | 2018-11-16 | 安徽大学 | Winter wheat powdery mildew remote sensing monitoring method based on ASD hyperspectral data |
| US20190150749A1 (en) * | 2017-11-22 | 2019-05-23 | Seno Medical Instruments, Inc. | Optoacoustic probe |
| CN113361191A (en) * | 2021-05-24 | 2021-09-07 | 中国科学院空天信息创新研究院 | Pixel scale winter wheat yield remote sensing estimation method based on multi-scenario simulation |
| CN115015132A (en) * | 2022-06-01 | 2022-09-06 | 南京农业大学 | Winter wheat moisture condition monitoring method based on data fusion |
| CN116124709A (en) * | 2022-09-20 | 2023-05-16 | 中国水利水电科学研究院 | Winter wheat drought unmanned aerial vehicle rapid monitoring and distinguishing method based on chlorophyll relative content |
| CN116310840A (en) * | 2023-05-11 | 2023-06-23 | 天地信息网络研究院(安徽)有限公司 | Winter wheat remote sensing identification method integrating multiple key weather period spectral features |
-
2024
- 2024-03-19 CN CN202410310229.9A patent/CN117907248B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110047867A1 (en) * | 2003-11-07 | 2011-03-03 | Holland Kyle H | Plant treatment based on a water invariant chlorophyll index |
| US20090024038A1 (en) * | 2007-07-16 | 2009-01-22 | Arnold Stephen C | Acoustic imaging probe incorporating photoacoustic excitation |
| WO2013183247A1 (en) * | 2012-06-04 | 2013-12-12 | パナソニック株式会社 | Acoustooptic imaging device |
| US20190150749A1 (en) * | 2017-11-22 | 2019-05-23 | Seno Medical Instruments, Inc. | Optoacoustic probe |
| CN108830249A (en) * | 2018-06-26 | 2018-11-16 | 安徽大学 | Winter wheat powdery mildew remote sensing monitoring method based on ASD hyperspectral data |
| CN113361191A (en) * | 2021-05-24 | 2021-09-07 | 中国科学院空天信息创新研究院 | Pixel scale winter wheat yield remote sensing estimation method based on multi-scenario simulation |
| CN115015132A (en) * | 2022-06-01 | 2022-09-06 | 南京农业大学 | Winter wheat moisture condition monitoring method based on data fusion |
| CN116124709A (en) * | 2022-09-20 | 2023-05-16 | 中国水利水电科学研究院 | Winter wheat drought unmanned aerial vehicle rapid monitoring and distinguishing method based on chlorophyll relative content |
| CN116310840A (en) * | 2023-05-11 | 2023-06-23 | 天地信息网络研究院(安徽)有限公司 | Winter wheat remote sensing identification method integrating multiple key weather period spectral features |
Non-Patent Citations (5)
| Title |
|---|
| 刘帅;李琦;: "组合核支持向量回归提取高光谱影像不透水面", 遥感学报, no. 03, 25 May 2016 (2016-05-25) * |
| 常迪;黄仲冬;韩洋;梁志杰;齐学斌;: "人民胜利渠灌区冬小麦灌溉需水量模拟与时空特征研究", 灌溉排水学报, no. 11, 13 November 2018 (2018-11-13) * |
| 李小涛;黄诗峰;郭怀轩;: "基于纹理特征的SPOT 5影像水体提取方法研究", 人民黄河, no. 12, 31 December 2020 (2020-12-31) * |
| 梁栋;管青松;黄文江;黄林生;杨贵军;: "基于支持向量机回归的冬小麦叶面积指数遥感反演", 农业工程学报, no. 07, 1 April 2013 (2013-04-01) * |
| 陈智芳;宋妮;王景雷;孙景生;: "基于高光谱遥感的冬小麦叶水势估算模型", 中国农业科学, no. 05, 31 December 2017 (2017-12-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117907248B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Rapid identification of soil organic matter level via visible and near-infrared spectroscopy: Effects of two-dimensional correlation coefficient and extreme learning machine | |
| Li et al. | Satellite-derived land surface temperature: Current status and perspectives | |
| Quegan et al. | Multitemporal ERS SAR analysis applied to forest mapping | |
| Yue et al. | Method for accurate multi-growth-stage estimation of fractional vegetation cover using unmanned aerial vehicle remote sensing | |
| CN113505635A (en) | Method and device for identifying winter wheat and garlic mixed planting area based on optics and radar | |
| CN102298150A (en) | Global land cover broadband emissivity inversion method and system | |
| Yi et al. | Evaluation of MODIS surface reflectance products for wheat leaf area index (LAI) retrieval | |
| Yin et al. | Calculation of land surface emissivity and retrieval of land surface temperature based on a spectral mixing model | |
| CN113252583B (en) | Method for calculating alpine hay coverage based on hay vegetation index | |
| Bayat et al. | Retrieval of land surface properties from an annual time series of Landsat TOA radiances during a drought episode using coupled radiative transfer models | |
| Xiang et al. | Integration of tillage indices and textural features of Sentinel-2A multispectral images for maize residue cover estimation | |
| CN112577906A (en) | Method for detecting water content of urban green land soil | |
| Fortes Gallego et al. | Using NDVI and guided sampling to develop yield prediction maps of processing tomato crop | |
| CN114819737B (en) | Method, system and storage medium for estimating carbon reserves of highway road vegetation | |
| Sabzchi-Dehkharghani et al. | Recognition of different yield potentials among rain-fed wheat fields before harvest using remote sensing | |
| Lou et al. | An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data | |
| CN113534083B (en) | SAR-based corn stubble mode identification method, device and medium | |
| Jiang et al. | Desertification in the south Junggar Basin, 2000–2009: Part I. Spatial analysis and indicator retrieval | |
| Das et al. | Ensemble surface soil moisture estimates at farm-scale combining satellite-based optical-thermal-microwave remote sensing observations | |
| Liu et al. | Research on generic optical remote sensing products: A review of scientific exploration, technology research, and engineering application | |
| CN113343783A (en) | Intelligent crop identification and growth prediction method and system | |
| CN117907248B (en) | Remote sensing monitoring method and system for root system soil water content in key growth period of winter wheat | |
| Huang et al. | A 3D approach to reconstruct continuous optical images using lidar and MODIS | |
| Liu et al. | Assessment of generalized allometric models for aboveground biomass estimation: A case study in Australia | |
| Liao et al. | Continuous woody vegetation biomass estimation based on temporal modeling of Landsat data |
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 |