CN115170969A - Method and system for constructing overground biomass model of vertically-grown crop - Google Patents
Method and system for constructing overground biomass model of vertically-grown crop Download PDFInfo
- Publication number
- CN115170969A CN115170969A CN202210892720.8A CN202210892720A CN115170969A CN 115170969 A CN115170969 A CN 115170969A CN 202210892720 A CN202210892720 A CN 202210892720A CN 115170969 A CN115170969 A CN 115170969A
- Authority
- CN
- China
- Prior art keywords
- crop
- biomass
- model
- constructing
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for constructing a ground biomass model of a vertically-grown crop, and relates to the technical field of crop planting. The invention comprises the following steps: obtaining crop biomass related parameters by using a remote sensing biomass monitoring method; calculating the crop planting density based on the remote sensing image of the initial crop stage; and constructing a crop biomass model according to the crop biomass related parameters and the crop planting density. The method can accurately acquire crop biomass information in time in a large area, and has important significance for agricultural departments to master crop growth information and yield prediction in various parts of the country and make scheduling and decision in time.
Description
Technical Field
The invention relates to the technical field of crop planting, in particular to a method and a system for constructing a overground biomass model of a vertically-grown crop.
Background
Wheat and corn are important reserve grain crops in China, the high and stable yield of the wheat and corn are the keys for guaranteeing national grain safety, and the timely and accurate growth quantitative evaluation technology of the wheat and the corn becomes an important scientific decision basis for agricultural condition scheduling of agricultural departments and adjustment of field management measures by vast farmers. Aboveground biomass (AGB) is an important physiological parameter reflecting the growth condition of crops, is closely related to crop yield, and is one of the important indicators for monitoring the growth of crops and predicting the yield. At present, in order to master crop biomass information in actual production, agricultural technicians are required to select representative sampling points for destructive sampling, and then the samples are sent back to a laboratory for pretreatment, drying and weighing. This method is destructive, hysteretic, and non-dynamic, and is costly. And the point and the strip surfaces are easy to deviate, so that the method is not suitable for acquiring the crop biomass information of a large area. In addition, the selected representative sampling points are greatly influenced by the subjectivity of investigators, and the problem that the given results are inconsistent due to the fact that different investigators exist in the same area is solved. The remote sensing technology is the only means which can rapidly acquire space continuous earth surface information in a large range at present, and the importance of developing high-yield, high-efficiency and environment-friendly modern agriculture is generally accepted. However, the existing optical remote sensing vegetation index tends to be saturated under medium-to-high-degree crop coverage, and the optical remote sensing cannot well detect biomass distributed in crop stalks and reproductive organs (such as ears), so that the crop biomass cannot be estimated more accurately, and the method is one of the main bottlenecks in monitoring the crop biomass by the optical remote sensing at present. Although the combination of the existing remote sensing technology and the advanced statistical regression model can improve the biomass estimation precision to a certain extent, the data-driven biomass model lacks the explanation of the photosynthetic product transfer of crops in the vegetative growth and reproductive growth stages, so that the contribution change of leaf biomass, stem and ear biomass to the total biomass in different growth periods cannot be reflected, and therefore, the simple and effective crop biomass model capable of reflecting the change is constructed, the crop biomass information can be timely and accurately acquired in a large area, and the method has important significance for the agricultural department to master the crop growth information and yield prediction in all parts of the country and to timely make scheduling and decision.
Disclosure of Invention
In view of the above, the invention provides a method and a system for constructing an aboveground biomass model of a vertically growing crop.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for constructing a ground biomass model of a vertically growing crop comprises the following steps:
obtaining crop biomass related parameters by using a remote sensing biomass monitoring method;
calculating the crop planting density based on the remote sensing image of the initial crop stage;
constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB is the total biomass, LAI is the leaf area index, C m To average leaf dry matter content, C d To plant density, C h For plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
Optionally, the calculation formula of the leaf area index is as follows:
Optionally, the average dry matter content of the stalks or reproductive organs is defined by the formula:
C sm =A as ×D as ;
A as average cross-sectional area of the stem or reproductive organ, D as Mean dry matter density of the stalks or reproductive organs.
Optionally, the remote sensing data-based leaf area index inversion method adopts a spectral vegetation index method, a machine learning method and an inversion method based on a radiation transmission model.
Optionally, the plant height is obtained based on a crop surface model generated by digital, multispectral or hyperspectral images acquired by the unmanned aerial vehicle remote sensing platform.
An aboveground biomass model construction system for vertically grown crops, comprising:
a crop biomass related parameter acquisition module: the method is used for acquiring crop biomass related parameters by using a remote sensing biomass monitoring method;
the crop planting density calculation module: the method is used for calculating the crop planting density based on the remote sensing image of the initial crop;
a crop biomass construction module: the method is used for constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB is the total biomass, LAI is the leaf area index, C m To average leaf dry matter content, C d To plant density, C h For plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
According to the technical scheme, compared with the prior art, the invention discloses and provides a method and a system for constructing the overground biomass model of the vertically-grown crops, and the method and the system have the following beneficial effects: by respectively establishing models for the biomass of leaves and the biomass of stalks or reproductive organs of crops, the transfer process of photosynthetic products of the crops in vegetative growth and reproductive growth stages is well described. Compared with the existing biomass model based on optical remote sensing, the biomass estimated by the model has higher precision, stronger universality and stability, and can greatly improve the efficiency of acquiring crop biomass information.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a method for constructing a ground biomass model of a vertically growing crop, which comprises the following steps as shown in figure 1:
obtaining crop biomass related parameters by using a remote sensing biomass monitoring method;
calculating the crop planting density based on the remote sensing image of the initial crop stage;
constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB is the total biomass, LAI is the leaf area index, C m Average leaf Dry matter content, C d To plant density, C h Is plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
The invention constructs a new crop biomass model, and the model is suitable for vertically growing crops such as wheat and corn. The model can reflect the transfer of photosynthetic products of crops in vegetative growth and reproductive growth stages, thereby better explaining the change of contribution of leaf biomass, stalk biomass and ear biomass to the total biomass in different growth periods. In the early vegetative stages, such as wheat emergence and tillering, the photosynthetic products are mainly stored in the leaves of the crop. During the mid-late vegetative growth stages, such as the jointing and flag-picking stages of wheat, the photosynthetic products are stored in the leaves and stalks of the crop. In the reproductive growth stage, such as flowering and filling stages of wheat, the photosynthetic products are mainly stored in crop stalks and ears. To reflect the transfer of photosynthetic products during different periods of fertility, the newly constructed crop biomass model consists of two parts, namely: a leaf biomass model and a stalk biomass model, wherein the stalk biomass comprises the biomass of stalks or ears as the growth process of the crop progresses. Leaf biomass (AGB) l ) Straw biomass (AGB) s ) And the overall biomass (AGB) is calculated as follows:
AGB=AGB l +AGBs (1)
wherein C is d Is the planting density, and the unit is m -2 ;C m Is the average dry matter content of the leaves, in g/m 2 ;L a,i Is the area of the ith leaf of a representative plant, and the unit is m 2 ,The area sum of all leaves of a representative plant is shown, and the area sum can be replaced by the average value of the leaf areas of a plurality of plants in practice, so that the deviation caused by sampling is relieved. Due to the fact thatLAI (Leaf area index) is the Leaf area index in m 2 /m 2 Therefore, equation (2) can be rewritten as:
AGB l =LAI×C m (3)
the crop stem biomass model can be described by formula (4),
wherein C is h The height is the height from the ground to the top of the crop (top leaf, ear of wheat or tassel of corn), and is expressed in m; a (h) is the cross-sectional area of the crop stem in m 2 (ii) a D (h) is dry matter density of crop stem or reproductive organ, and the unit is g/m 3 . For practical purposes, two parameters are introduced, one being the average dry matter density D of the stalks or reproductive organs as In units of g/m 3 (ii) a Second, the average cross-sectional area A of the stem or reproductive organ as In the unit of m 2 Thus, therefore, it is
The formula (4) can be rewritten as the formula (5),
AGB s =C d D as C h A as (5)
in the stem biomass model, a new parameter C is defined sm =A as ×D as It represents the average dry matter content of the stalks in g/m. Therefore, the formula (5) can be rewritten as the formula (6),
AGB s =C d C h C sm (6)
thus the crop biomass model equation (1) can be expanded to equation (7),
AGB=[LAI]C m +C d C h C sm (7)
the newly constructed crop biomass model is suitable for field actual investigation and large-area remote sensing biomass monitoring.
In the field actual survey, LAI, C in the model d And C h All three parameters can be directly measured in a non-destructive manner; and C m And C sm For the same crop in the same growth period, the fluctuation of the value is small, so that the different growth periods C of the wheat and the corn can be given according to the accumulated data of actual field measurement m And C sm The lookup tables of the two parameters can directly estimate the biomass of the crops, so that destructive sampling, post sample pretreatment, drying, weighing and other operations are omitted, and the timeliness of biomass information acquisition is greatly improved.
In remote biomass monitoring over large areas, C d ,LAI,C m ,C h And C sm Can be obtained indirectly from telemetric data. Based on the remote sensing image of the crop growth initial stage, the C can be estimated by combining the digital image processing method and the machine learning method d . The LAI inversion method based on remote sensing data comprises (1) a spectrum vegetation index method, commonly used vegetation indexes comprise a Normalized vegetation index NDVI (Normalized difference vegetation index), an Enhanced vegetation index EVI (Enhanced vegetation index), an Optimized soil adjusted vegetation index OSAVI (Optimized soil adjusted vegetation index) and the like, and large-area LAI information can be obtained through a linear or nonlinear model between the existing vegetation index and the LAI; (2) Compared with a vegetation index method, the method is relatively complex, but the estimation accuracy of the LAI is relatively high, and common machine learning methods comprise an artificial neural network, a support vector machine, a random forest, deep learning and the like; (3) A radiation transmission model inversion method based on a radiation transmission model comprises a PROSECT blade optical model and an SAIL canopy reflectivity model, which are commonly used for crop LAI inversion. Plant height C h The method can be obtained based on a crop surface model generated by digital, multispectral or hyperspectral images acquired by an unmanned aerial vehicle remote sensing platform. C m And C sm Height of the plant C h There is a certain relationship that as the plant height of the crop increases, the stalks will gradually thicken to support the vertical growth structure,thus C m And C sm Can be estimated by a machine learning model built based on a crop surface model and spectral indices or spectral reflectivities.
The analysis is carried out based on experimental data of winter wheat in a certain year, and the result shows that the leaf biomass and the LAI have stronger linear correlation in different growth periods. As the growth process of crops advances, the proportion of the biomass of the stalks or the reproductive organs in the total biomass gradually increases until the biomass is dominant. This is consistent with the transfer of the photosynthetic products, which are primarily stored in the leaves during the early stages of crop growth, then primarily in the leaves and stalks, and finally in the stalks and reproductive organs (e.g., ear). C h ,C h ×C d ,C h ×C d ×C sm The analysis result related to the biomass of the stem or the reproductive organ shows that C h ×C d ×C sm The correlation with the biomass of the stalks or reproductive organs is the highest, and reaches a very significant level. The conclusion shows that the proposed crop biomass model can better depict the biomass of different parts of crops and can reflect the process of transferring the photosynthetic products.
Based on the accumulated field sampling data of winter wheat and summer corn, a part of the growth period C is formed initially m And C sm The lookup table can be corrected later along with the increase of data, including field data collected by different varieties and different regions.
TABLE 1 preliminary C derived based on existing winter wheat and summer maize data m And C sm Lookup table
A specific application example is that the biomass of winter wheat is estimated based on a constructed biomass model and by combining hyperspectral data of an unmanned aerial vehicle. Firstly, a crop surface model can be generated in the process of splicing hyperspectral data of the unmanned aerial vehicle, and the plant height of the crop can be estimated based on the model. Obtaining LAI, C by adopting a multi-input multi-output artificial neural network model m And C sm Three parameters, the modeThe input of the model is a crop surface model, a spectral index and a spectral reflectivity, and the output is LAI, C m And C sm . The planting density is obtained by field investigation.
Table 2 presents the comparison of the method and the estimation results of the optimal exponential model
Note: the optimal exponential model is y = a × x 1 x 2 + b, a and b are model coefficients; x is the number of 1 Extracting crop surface model parameters for hyperspectral data of the unmanned aerial vehicle; x is the number of 2 The red-border chlorophyll index CIRE = R 782 /R 702 -1, wherein R 782 And R 702 Reflectivity at bands 782nm and 702nm, respectively.
The embodiment also discloses a system for constructing the aboveground biomass model of the vertically grown crop, which is characterized by comprising the following steps:
a crop biomass related parameter acquisition module: the method is used for acquiring crop biomass related parameters by using a remote sensing biomass monitoring method;
the crop planting density calculation module: the method is used for calculating the crop planting density based on the remote sensing image of the initial crop;
a crop biomass construction module: the method is used for constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB is total biomass, LAI is leaf area index, C m To average leaf dry matter content, C d To plant density, C h For plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A method for constructing a ground biomass model of a vertically grown crop is characterized by comprising the following steps of:
acquiring crop biomass related parameters by using a remote sensing biomass monitoring method;
calculating the crop planting density based on the remote sensing image of the initial crop stage;
constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB is the total biomass, LAI is the leaf area index, C m To average leaf dry matter content, C d To plant density, C h For plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
3. The method for constructing the aboveground biomass model of a vertically grown crop as claimed in claim 1, wherein the average dry matter content of the stalks or reproductive organs is defined as follows:
C sm =A as ×D as ;
A as average cross-sectional area of the stem or reproductive organ, D as Mean dry matter density of the stalks or reproductive organs.
4. The method for constructing the aboveground biomass model of the vertically grown crop according to claim 1, further comprising a leaf area index inversion method based on remote sensing data, wherein the leaf area index inversion method adopts a spectral vegetation index method, a machine learning method and an inversion method based on a radiation transmission model.
5. The method for constructing the aboveground biomass model of the vertically grown crop according to claim 1, wherein the plant height is obtained based on a crop surface model generated by digital, multispectral or hyperspectral images acquired by an unmanned aerial vehicle remote sensing platform.
6. An aboveground biomass model construction system for vertically grown crops, comprising:
a crop biomass related parameter acquisition module: the method is used for acquiring crop biomass related parameters by using a remote sensing biomass monitoring method;
the crop planting density calculation module: the method is used for calculating the crop planting density based on the remote sensing image of the initial crop;
a crop biomass construction module: the method is used for constructing a crop biomass model according to the crop biomass related parameters and the crop planting density:
AGB=[LAI]C m +C d C h C sm ;
wherein AGB isTotal biomass, LAI is leaf area index, C m To average leaf dry matter content, C d To plant density, C h For plant height, C sm Is the average dry matter content of the stalks or reproductive organs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210892720.8A CN115170969A (en) | 2022-07-27 | 2022-07-27 | Method and system for constructing overground biomass model of vertically-grown crop |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210892720.8A CN115170969A (en) | 2022-07-27 | 2022-07-27 | Method and system for constructing overground biomass model of vertically-grown crop |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115170969A true CN115170969A (en) | 2022-10-11 |
Family
ID=83497014
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210892720.8A Pending CN115170969A (en) | 2022-07-27 | 2022-07-27 | Method and system for constructing overground biomass model of vertically-grown crop |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115170969A (en) |
-
2022
- 2022-07-27 CN CN202210892720.8A patent/CN115170969A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108985588B (en) | Crop yield per unit remote sensing estimation method, device and system | |
CN109711102B (en) | Method for rapidly evaluating crop disaster loss | |
CN113268923B (en) | Summer corn yield estimation method based on simulated multispectral | |
CN111104858A (en) | Large-scale crop phenological extraction method based on morphological model method | |
CN111008733B (en) | Crop growth control method and system | |
CN109754125A (en) | Crop yield forecast method based on crop modeling, history and meteorological forecast data | |
CN115577866A (en) | Method and device for predicting waiting period, electronic equipment and storage medium | |
CN115018105A (en) | Winter wheat meteorological yield prediction method and system | |
CN108537679B (en) | Remote sensing and crop model fused region scale crop emergence date estimation method | |
CN108106676A (en) | A kind of monitoring method and device of the crops Spring frost based on remotely-sensed data | |
CN111275567B (en) | SENP cotton yield estimation method based on unmanned aerial vehicle image and estimation model construction method | |
CN112819227A (en) | County scale winter wheat yield per unit prediction method and system | |
CN115439402A (en) | Sugar cane yield-per-unit remote sensing estimation method and device based on SAFY-Sugar model | |
CN116415704A (en) | Regional precision irrigation method and system based on multi-data fusion and assimilation | |
US11864552B2 (en) | Digital detection method and system for predicting drug resistance of transgenic maize | |
Pandey et al. | Discrimination of sugarcane crop and cane yield estimation using Landsat and IRS resourcesat satellite data | |
Mutanga et al. | Determining the best optimum time for predicting sugarcane yield using hyper-temporal satellite imagery | |
Hashimoto et al. | Feasibility of yield estimation based on leaf area dynamics measurements in rice paddy fields of farmers | |
CN116308866A (en) | Rice ear biomass estimation method and system based on canopy reflection spectrum | |
CN109615150B (en) | Method and system for determining rice meteorological output | |
CN116797950A (en) | Tea tree water stress monitoring method based on unmanned aerial vehicle multispectral remote sensing | |
CN115170969A (en) | Method and system for constructing overground biomass model of vertically-grown crop | |
CN116151454A (en) | Method and system for predicting yield of short-forest linalool essential oil by multispectral unmanned aerial vehicle | |
CN115496999A (en) | Method and device for estimating field straw yield | |
CN115661641A (en) | Method and system for evaluating important phenotype parameters of tea garden in different growth stages based on multi-source unmanned aerial vehicle remote sensing |
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 |