A method for establishing a comprehensive spectral monitoring model for winter wheat

Abstract

The present invention relates to the technical field of spectral analysis, and specifically discloses a method for establishing a comprehensive spectral monitoring model for winter wheat. The method includes: selecting six key growth indexes of winter wheat as the input of the model; obtaining the canopy spectral data of winter wheat through spectral remote sensing technology; introducing factor analysis technology to process and analyze the data of the six growth indexes of winter wheat; constructing a comprehensive growth index of winter wheat based on the results of factor analysis; combining the spectral data and the comprehensive growth index to establish a comprehensive growth spectral monitoring model of winter wheat based on support vector machine, so as to realize the real-time monitoring and evaluation of the comprehensive growth of winter wheat.

Description

Technical Field

[0001] The present invention relates to the technical field of spectral analysis, and more specifically, the present invention relates to a method for establishing a comprehensive spectral monitoring model for winter wheat. Background Art

[0002] In order to better implement refined management and quality control, the monitoring of winter wheat growth is particularly important. Spectral remote sensing technology has been widely used in the growth monitoring of winter wheat in the agricultural field due to its advantages such as rapidity, non-destructiveness, and wide coverage. The spectral data obtained by remote sensing can help evaluate the growth status of winter wheat, and thus provide a reference for agricultural management. However, the existing spectral monitoring models have low accuracy in practical applications and cannot accurately reflect the growth and health conditions of winter wheat, which is mainly restricted by the following factors:

[0003] 1. The ambiguity of spectral signals;

[0004] 2. The factors affecting the growth of winter wheat are very complex, such as climate change, soil quality, etc. A single growth parameter cannot accurately characterize the growth information of winter wheat;

[0005] Therefore, how to integrate the information of multiple growth indicators and accurately predict the growth and health conditions of winter wheat has become an urgent technical problem in this field.

[0006] In order to solve the above problems, a technical solution is provided now. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for establishing a comprehensive spectral monitoring model for winter wheat. By using six key growth indicators as the model input, obtaining the comprehensive spectral data of the winter wheat canopy by using spectral remote sensing technology, introducing factor analysis technology to process and analyze the growth indicator data to extract potential factors affecting crop growth, constructing comprehensive growth indicators, effectively integrating the information of multiple growth indicators, combining the spectral data and the comprehensive growth indicators, establishing a comprehensive growth spectral monitoring model for winter wheat based on support vector machines, realizing the problems of overcoming the ambiguity of spectral signals and complex influencing factors, improving the accuracy of the spectral remote sensing monitoring model, and accurately predicting the health value of winter wheat, so as to solve the problems proposed in the above background art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for establishing a comprehensive spectral monitoring model for winter wheat, comprising the following steps:

[0010] Step S1, selecting six key growth indicators of winter wheat as the input of the model;

[0011] Step S2, obtaining the canopy spectral data of winter wheat through spectral remote sensing technology;

[0012] Step S3, introducing factor analysis technology to process and analyze the data of six growth indicators;

[0013] Step S4, constructing a comprehensive growth index based on the results of factor analysis;

[0014] Step S5, combining the spectral data and the comprehensive growth index to establish a comprehensive spectral monitoring model of winter wheat growth based on support vector machine to accurately predict the health value of winter wheat. The health index of winter wheat is used for field management. The formula of the comprehensive spectral monitoring model is:

[0015] ;

[0016] In the formula, is the finally predicted health value of winter wheat, is the number of historical samples, is the influence degree of the th support vector on the finally predicted result, is the th sample's comprehensive growth index, is the current winter wheat's comprehensive growth index, is to adjust the influence degree of and on the finally predicted result, is the bias term, which is used to adjust the output to make the predicted value closer to the actual health value of winter wheat.

[0017] As a further solution of the present invention, six key winter wheat growth indicators are selected as the input of the model, including the following specific contents:

[0018] Six key growth indicators are selected to reflect the growth status and environmental adaptability of winter wheat. The six key growth indicators include leaf area index, above-ground dry biomass, above-ground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation; the leaf area index is an indicator that measures the ratio of the surface area of plant leaves to the surface area of the soil, reflects the photosynthetic capacity and overall growth status of the plant, and the leaf area index is obtained by inversion through spectral remote sensing data. A multispectral sensor is used to collect the canopy spectral information of winter wheat. By analyzing the reflectance data in different bands and combining vegetation indices, the leaf area index is calculated; the above-ground dry biomass reflects the dry matter weight of the above-ground part of winter wheat. The above-ground biomass is estimated through the reflectance spectrum of the plant canopy. Using the correlation between the vegetation index in remote sensing data and the above-ground biomass, a biomass estimation formula can be obtained through statistical regression analysis, so as to realize the non-destructive real-time monitoring of the above-ground dry biomass; the above-ground fresh biomass refers to the fresh weight of the above-ground part of winter wheat before drying treatment, reflects the growth vitality and nutritional status of the plant. Through remote sensing monitoring, the above-ground fresh biomass can be estimated from spectral data. The estimation of the above-ground fresh biomass usually combines other parameters such as water content for modeling. There is a strong relationship between the reflectance intensity in the green band of remote sensing data and the plant water content and biomass, and the spectral signal can be associated with the above-ground fresh biomass through data processing and inversion models; the plant water content is an important indicator to measure the water status of winter wheat, which directly affects the growth and yield of winter wheat. In spectral remote sensing, the monitoring of the plant water content mainly depends on the reflection characteristics of the water absorption band. There is a strong correlation between the band and the plant water content, and the corresponding water information can be obtained by inverting remote sensing data; the chlorophyll density directly affects the photosynthesis efficiency of plants. The chlorophyll absorption spectrum has obvious absorption peaks in the blue light region and the red light region, and there are significant changes in the red light region, which provides a basis for remote sensing monitoring. After obtaining the spectral reflectance data of the plant canopy using the multispectral sensor, the chlorophyll density can be estimated through an inversion model; nitrogen is an essential nutrient element for plant growth. In remote sensing monitoring, the nitrogen accumulation can be estimated through the relationship between the spectral characteristics of plants and the nitrogen content. The red light band and the near-infrared light band in the spectral reflectance are more sensitive to the plant nitrogen content. By analyzing the changes in these bands and combining the existing nitrogen content data, the nitrogen accumulation can be estimated.

[0019] As a further solution of the present invention, the canopy spectral data of winter wheat is obtained through spectral remote sensing technology, including the following specific contents:

[0020] For the growth cycle of winter wheat, the collected spectral data cover different time nodes to capture the dynamic changes in the growth of winter wheat. In ground monitoring, the spectrometers used usually have multiple bands that can cover the visible light, near-infrared, and short-wave infrared regions. These bands can capture the reflection spectral characteristics of the winter wheat canopy. In the application of unmanned aerial vehicle (UAV) or satellite remote sensing, through the multi-spectral sensors carried, data can be collected over a larger range and at different scales, further improving the spatial and temporal resolutions of the data. The multi-spectral sensors usually collect data of multiple bands according to the spectral reflection characteristics to form a spectral data set. Since the collected spectral data usually contain noise, outliers, or background interference, certain preprocessing is required to improve the data quality and the accuracy of the analysis results. The preprocessing includes: spectral smoothing and denoising, atmospheric correction, background noise removal, and standardization processing. The spectral smoothing and denoising remove high-frequency noise through a smoothing algorithm to ensure the smoothness and coherence of the spectral signal. When obtaining remote sensing data, it is often affected by water vapor and aerosols. The atmospheric correction inverses and calibrates the remote sensing data through ground-measured data. The background noise removal refers to removing background noise through the difference value method. Since remote sensing data is affected by external factors such as climate and light, directly using data from different time periods or environmental conditions for comparative analysis lacks consistency. Through the standardization processing, the spectral reflectance of different data sets is unified within the same standard range.

[0021] As a further aspect of the present invention, factor analysis technology is introduced to process and analyze the data of six winter wheat growth indicators, including the following specific contents:

[0022] Since the growth of winter wheat is comprehensively affected by multiple factors, the spectral data often contains complex information related to the growth of winter wheat and environmental conditions. The factor analysis method can effectively extract these potential factors that are difficult to directly observe. The potential factors extracted by factor analysis can not only reflect multiple aspects of the growth of winter wheat but also reveal the interaction and influence relationships among these aspects. The potential factors include soil fertility, climate temperature, and light environment, which will affect the growth of winter wheat, and the influence is manifested through the biophysical indicators of winter wheat.

[0023] As a further aspect of the present invention, based on the results of factor analysis, a comprehensive winter wheat growth indicator is constructed, including the following specific contents:

[0024] By extracting six biophysical indicators, namely leaf area index, above-ground dry biomass, above-ground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation, and combining factor analysis technology, potential factors that have an important impact on the growth of winter wheat are extracted, and a comprehensive growth indicator is constructed according to each indicator. The formula for the comprehensive growth indicator is:

[0025] ;

[0026] In the formula, is the leaf area index, is the above-ground dry biomass, is the above-ground fresh biomass, is the plant water content, is the chlorophyll density, is the nitrogen accumulation.

[0027] The technical effects and advantages of a method for establishing a comprehensive spectral monitoring model for winter wheat according to the present invention:

[0028] By selecting six key growth indicators, namely leaf area index, above-ground dry biomass, above-ground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation, as model inputs, the present invention uses spectral remote sensing technology to obtain multi-band and multi-time-node canopy spectral data of winter wheat and preprocesses it. The factor analysis technology is introduced to process and analyze the growth index data to extract potential factors affecting crop growth, and a comprehensive growth index is constructed. Combining the spectral data and the comprehensive growth index, a comprehensive growth spectral monitoring model for winter wheat based on support vector machines is established. Its advantage lies in being able to effectively integrate information on multiple growth indicators, overcome the problem of spectral signal ambiguity and complex influencing factors, improve the accuracy of the spectral remote sensing monitoring model, accurately predict the health value of winter wheat, and thus help farmers take timely field management measures to ensure the healthy and normal growth of winter wheat. Description of the Drawings

[0029] Figure 1 is a flow chart of a method for establishing a comprehensive spectral monitoring model for winter wheat according to the present invention. Detailed Embodiments

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] Example 1. Refer to Figure 1 The flow schematic diagram shown. An embodiment of the present invention provides a method for establishing a comprehensive spectral monitoring model for winter wheat, which includes the following steps:

[0032] Step S1, select six key winter wheat growth indicators as the input of the model;

[0033] Step S2: Obtain the canopy spectral data of winter wheat through spectral remote sensing technology;

[0034] Step S3: Introduce factor analysis technology to process and analyze the data of six winter wheat growth indexes;

[0035] Step S4: Based on the results of factor analysis, construct a comprehensive growth index of winter wheat;

[0036] Step S5: Combine the spectral data and the comprehensive growth index to establish a comprehensive growth spectral monitoring model of winter wheat based on support vector machine.

[0037] In this embodiment, before data collection, the multispectral sensor is strictly calibrated to ensure its measurement accuracy. At the same time, the stability of the multispectral sensor is checked, and the initial state of the multispectral sensor is recorded. During the collection process, the multispectral sensor is calibrated on-site regularly, and the parameters of the multispectral sensor are adjusted according to the standard light source or the reference plate with known reflectivity. For abnormal data, relevant environmental factors and measurement conditions are recorded on-site in a timely manner, and its rationality is preliminarily judged. After data collection, data cleaning is carried out to remove obvious error or missing data points. Then, statistical methods are used to identify and process outliers. For suspicious data, it is decided whether to retain or correct it according to the data distribution characteristics and actual situation. At the same time, a data review mechanism is established, and multiple people cross-check the data accuracy to ensure the reliability of the data.

[0038] Furthermore, six key winter wheat growth indexes are selected as the input of the model, including the following specific contents:

[0039] Six key growth indicators are selected to reflect the growth status and environmental adaptability of winter wheat. The six key growth indicators include leaf area index, aboveground dry biomass, aboveground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation. The leaf area index is an indicator that measures the ratio of the surface area of plant leaves to the surface area of the soil, reflecting the photosynthetic capacity and overall growth status of the plant. The leaf area index is retrieved through spectral remote sensing data. The canopy spectral information of winter wheat is collected using a multispectral sensor. By analyzing the reflectance data in different bands and combining vegetation indices, the leaf area index is calculated. The aboveground dry biomass reflects the dry matter weight of the aboveground part of winter wheat. The aboveground biomass is estimated through the reflectance spectrum of the plant canopy. Utilizing the correlation between the vegetation index in remote sensing data and the aboveground biomass, a biomass estimation formula can be obtained through statistical regression analysis, thereby realizing non-destructive real-time monitoring of the aboveground dry biomass. The aboveground fresh biomass refers to the fresh weight of the aboveground part of winter wheat before drying treatment, reflecting the growth vitality and nutritional status of the plant. Through remote sensing monitoring, the aboveground fresh biomass can be deduced from spectral data. The estimation of the aboveground fresh biomass usually involves modeling in combination with other parameters such as water content. There is a strong relationship between the reflectance intensity in the green band of remote sensing data and the plant water content and biomass, and the spectral signal can be associated with the aboveground fresh biomass through data processing and inversion models. The plant water content is an important indicator for measuring the water status of winter wheat, directly affecting the growth and yield of winter wheat. In spectral remote sensing, the monitoring of the plant water content mainly relies on the reflection characteristics of the water absorption band. There is a strong correlation between this band and the plant water content, and the corresponding water information can be retrieved through remote sensing data. The chlorophyll density directly affects the photosynthesis efficiency of plants. The chlorophyll absorption spectrum has obvious absorption peaks in the blue and red light regions, and there are significant changes in the red light region, providing a basis for remote sensing monitoring. After obtaining the spectral reflectance data of the plant canopy using the multispectral sensor, the chlorophyll density can be estimated through an inversion model. Nitrogen is an essential nutrient element for plant growth. In remote sensing monitoring, the nitrogen accumulation can be deduced through the relationship between the spectral characteristics of plants and the nitrogen content. The red light band and near-infrared light band in the spectral reflectance are relatively sensitive to the plant nitrogen content. By analyzing the changes in these bands and combining the existing nitrogen content data, the nitrogen accumulation can be estimated.

[0040] In this embodiment, the field test layout and sample selection method for winter wheat are specifically as follows: The field test layout adopts a completely randomized block design, with multiple small replicated areas set up to reduce errors caused by environmental factors such as soil fertility and topography. The area of the area is determined according to the test scale and the growth characteristics of winter wheat to ensure that the plants have sufficient growth space and are convenient for management operations. When selecting samples, first stratify according to factors such as winter wheat variety and planting time to ensure that the growth conditions of the plants within each layer are relatively consistent. Then, in each area, determine multiple sampling points according to the five-point sampling method or the checkerboard sampling method, etc. Select winter wheat plants with representative growth conditions from each sampling point, covering different growth trends, and avoid selecting extreme individuals to ensure that the samples can accurately reflect the growth of the entire field winter wheat population. At the same time, record in detail information such as the location and growth environment of the samples to provide a comprehensive and accurate basis for subsequent data analysis and model verification.

[0041] Furthermore, the canopy spectral data of winter wheat are obtained through spectral remote sensing technology, including the following specific contents:

[0042] For the growth cycle of winter wheat, the collected spectral data cover different time nodes to capture the dynamic changes in the growth of winter wheat. In ground monitoring, the spectrometers used usually have multiple bands that can cover the visible light, near-infrared, and short-wave infrared regions. These bands can capture the reflection spectral characteristics of the winter wheat canopy. In the visible light band, chlorophyll in the winter wheat leaves mainly absorbs blue and red light for photosynthesis and reflects more green light. Therefore, when growing normally, the reflectance in the green light band is high and the leaves are green. When the growth is poor, such as due to nitrogen deficiency resulting in reduced chlorophyll, the absorption of blue and red light decreases, the reflection increases, the green light reflection decreases, the spectral curve changes, and the leaf morphological structure affects light scattering and reflection. Thick and tightly structured leaves have a low reflectance. In the near-infrared band, its reflectance is mainly affected by the internal cell structure of the leaves. The close arrangement, many layers, and small gaps of mesophyll cells enhance multiple reflections and scattering, resulting in a high reflectance, which is closely related to the biomass of winter wheat. As the biomass increases, the reflectance rises. For example, during the vigorous growth period of winter wheat, the reflectance in this band is significantly higher than that in the seedling stage, and it can be used to estimate the leaf area index and above-ground dry biomass. In the short-wave infrared band, it is sensitive to the water content of the winter wheat plants, and the water absorption characteristics are obvious. When the water content is high, the absorption is strong and the reflectance is low in bands such as 1450 nm and 1950 nm, and the plant water content can be monitored based on this. In the application of unmanned aerial vehicle or satellite remote sensing, through the multi-spectral sensor carried, data can be collected over a larger range and at different scales, further improving the spatial and temporal resolutions of the data. The multi-spectral sensor usually collects data of multiple bands according to the characteristics of spectral reflection to form a spectral data set. Since the collected spectral data usually have noise, outliers, or background interference, certain preprocessing is required to improve the quality of the data and the accuracy of the analysis results. The preprocessing includes: spectral smoothing and denoising, atmospheric correction, removal of background noise, and standardization processing. The spectral smoothing and denoising remove high-frequency noise through a smoothing algorithm to ensure the smoothness and coherence of the spectral signal. When obtaining remote sensing data, it is often affected by water vapor and aerosols. The atmospheric correction inversely calculates and calibrates the remote sensing data through ground measured data. The removal of background noise refers to removing background noise through the difference value method. Since remote sensing data are affected by external factors such as climate and light, directly using data from different time periods or environmental conditions for comparative analysis lacks consistency. Through the standardization processing, the spectral reflectances of different data sets are unified into the same standard range.

[0043] Furthermore, factor analysis technology is introduced to process and analyze the data of six winter wheat growth indicators, including the following specific contents:

[0044] Due to the comprehensive influence of various factors on the growth of winter wheat, spectral data often contains complex information related to winter wheat growth, environmental conditions, etc. Factor analysis methods can effectively extract these potential and difficult-to-directly-observe factors. The potential factors extracted by factor analysis can not only reflect multiple aspects of winter wheat growth but also reveal the interaction and influence relationships among these aspects; the potential factors include soil fertility, climate temperature, and light environment, which will have an impact on the growth of winter wheat, and this impact is manifested through the biophysical indicators of winter wheat.

[0045] Furthermore, based on the results of factor analysis, a comprehensive growth index of winter wheat is constructed, including the following specific contents:

[0046] By extracting six biophysical indicators, namely leaf area index, aboveground dry biomass, aboveground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation, and combining factor analysis technology, potential factors that have an important impact on the growth of winter wheat are extracted, and a comprehensive growth index is constructed according to each indicator. The formula for the comprehensive growth index is:

[0047] ;

[0048] In the formula, is the leaf area index, is the aboveground dry biomass, is the aboveground fresh biomass, is the plant water content, is the chlorophyll density, is the nitrogen accumulation.

[0049] Furthermore, by combining the spectral data and the comprehensive growth index, a spectral monitoring model for the comprehensive growth of winter wheat based on support vector machines is established, including the following specific contents:

[0050] By combining the spectral data and the comprehensive growth index, a spectral monitoring model for the comprehensive index of winter wheat based on support vector machines is established to accurately predict the health value of winter wheat. The health index of winter wheat is used for field management. The formula for the spectral monitoring model for the comprehensive index of winter wheat based on support vector machines is:

[0051] ;

[0052] In the formula, is the finally predicted health value of winter wheat, is the number of historical samples, is the influence degree of the th support vector on the final prediction result, is the The comprehensive growth index of a sample is the comprehensive growth index of the current winter wheat is to adjust and the influence degree on the final prediction result is the bias term, which is used to adjust the output to make the predicted value closer to the actual health value of winter wheat; the finally predicted health value of winter wheat can help identify whether winter wheat is in a state of nutrient deficiency, and farmers can scientifically adjust the fertilization amount according to the degree of decrease in the health value; through the periodic monitoring of the finally predicted health value of winter wheat, farmers can understand the growth change trend of winter wheat in real time. If the health value rises steadily, it indicates that the growth of winter wheat is normal. If the health value drops, adjustment measures need to be taken; in addition, the finally predicted health value of winter wheat can also provide information on the best fertilization timing. If the finally predicted health value of winter wheat drops significantly during the jointing stage or booting stage, it indicates that the growth of winter wheat is weak during the critical growth period. At this time, timely field management is taken to effectively improve the growth vitality of winter wheat and ensure normal growth in the later stage.

[0053] In the present invention, six key growth indexes, namely leaf area index, above-ground dry biomass, above-ground fresh biomass, plant water content, chlorophyll density, and nitrogen accumulation, are selected as model inputs. The spectral remote sensing technology is used to obtain the canopy spectral data of winter wheat with multiple bands and multiple time nodes and preprocess it. The factor analysis technology is introduced to process and analyze the growth index data to extract the potential factors affecting crop growth, and a comprehensive growth index is constructed. Then, combined with the spectral data and the comprehensive growth index, a comprehensive growth spectral monitoring model of winter wheat based on support vector machine is established. Its advantage lies in that it can effectively integrate the information of multiple growth indexes, overcome the problems of spectral signal ambiguity and complex influencing factors, improve the accuracy of the spectral remote sensing monitoring model, accurately predict the health value of winter wheat, and thus help farmers take timely field management measures to ensure the healthy and normal growth of winter wheat.

[0054] As mentioned above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0055] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for establishing a comprehensive spectral monitoring model for winter wheat, characterized in that: The steps include: Step S1, selecting six key winter wheat growth indicators as inputs of the model; Step S2, obtaining winter wheat canopy spectral data by spectral remote sensing technology; Step S3, introducing factor analysis technology to process and analyze the data of six winter wheat growth indicators; Step S4, constructing a comprehensive growth index of winter wheat based on the results of factor analysis; Step S5, combining the spectral data and the comprehensive growth index, establishing a winter wheat comprehensive growth spectral monitoring model based on a support vector machine to accurately predict the health value of winter wheat. The health index of winter wheat is used for field management. The formula of the winter wheat comprehensive growth spectral monitoring model based on a support vector machine is: ， In the formula, is the final predicted health value of winter wheat, is the number of historical samples, For the The influence of the support vector on the final prediction result. For the The comprehensive growth index of samples, It is the comprehensive growth index of winter wheat at present. To adjust and The degree of influence on the final prediction results. is a bias term, which is used to adjust the output to make the predicted value closer to the actual winter wheat health value; In step S4, by extracting the six biophysical indices of leaf area index, aboveground dry biomass, aboveground fresh biomass, plant water content, chlorophyll density and nitrogen accumulation, combined with factor analysis technology, potential factors that have an important impact on the growth of winter wheat are extracted, and a comprehensive growth index is constructed based on each index. The formula of the comprehensive growth index is: ， In the formula, It is a comprehensive growth indicator. is the leaf area index, is the aboveground dry biomass, is the aboveground fresh biomass, is the water content of the plant, is the chlorophyll density, is the nitrogen accumulation.

2. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 1, characterized in that: In step S1, six key winter wheat growth indicators are selected as inputs of the model. The six key winter wheat growth indicators include leaf area index, aboveground dry biomass, aboveground fresh biomass, plant water content, chlorophyll density and nitrogen accumulation, which are used as indicators reflecting the growth status of winter wheat and its environmental adaptability.

3. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The leaf area index is obtained by inverting spectral remote sensing data, using a multispectral sensor to collect spectral information of the winter wheat canopy, analyzing reflectance data of different bands and calculating it in combination with the vegetation index.

4. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The aboveground dry biomass is estimated by using the plant canopy reflectance spectrum, and the correlation between vegetation index and aboveground biomass in remote sensing data is used to obtain a biomass estimation formula through statistical regression analysis to achieve non-destructive real-time monitoring.

5. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The aboveground fresh biomass is estimated by remote sensing monitoring, combined with water content parameter modeling, using the relationship between the green band reflection intensity of remote sensing data and the water content and biomass of the plants, and linking the data processing and inversion model with the spectral signal.

6. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The plant water content is monitored by the reflectance characteristics of the water absorption band in spectral remote sensing, and the corresponding water information is obtained by inverting the remote sensing data through the correlation between the band and the plant water content.

7. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The chlorophyll density is estimated by using an inversion model after obtaining the plant canopy spectral reflectance data using a multispectral sensor. Its absorption spectrum has obvious absorption peaks in the blue light region and the red light region. The significant changes in the red light region provide a basis for remote sensing monitoring.

8. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 2, characterized in that: The nitrogen accumulation amount is estimated by analyzing the relationship between the plant spectral characteristics and the nitrogen content, analyzing the changes in the red light band and the near-infrared light band in the spectral reflectance, and combining with the existing nitrogen content data for estimation.

9. The method for establishing a comprehensive spectral monitoring model for winter wheat according to claim 1, characterized in that: In step S2, comprehensive spectral data of the winter wheat canopy is obtained by spectral remote sensing technology, and the collected data covers different time nodes in the winter wheat growth cycle. Ground monitoring uses a spectrometer covering visible light, near infrared and short-wave infrared regional bands, and unmanned aerial vehicles or satellite remote sensing collect multi-band data by carrying multi-spectral sensors to form a spectral data set.

Images