CN108985588B - Crop yield per unit remote sensing estimation method, device and system - Google Patents
Crop yield per unit remote sensing estimation method, device and system Download PDFInfo
- Publication number
- CN108985588B CN108985588B CN201810689070.0A CN201810689070A CN108985588B CN 108985588 B CN108985588 B CN 108985588B CN 201810689070 A CN201810689070 A CN 201810689070A CN 108985588 B CN108985588 B CN 108985588B
- Authority
- CN
- China
- Prior art keywords
- crop
- remote sensing
- model
- estimating
- yield
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention provides a crop yield remote sensing estimation method, a device and a system, wherein the method comprises the following steps: identifying a crop category based on the crop remote sensing data; estimating a first net crop productivity based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop; estimating the crop yield per unit based on the crop first net productivity by combining the crop growth environment information and the crop growth physiological and biochemical process parameters. The method can more effectively play the role of remote sensing data, fully utilize the growth mechanism of crops and ensure the accuracy, efficiency and stability of the estimation of the yield per unit of the crops on a larger scale.
Description
Technical Field
The invention relates to the technical field of agricultural production, in particular to a remote sensing estimation method, a device and a system for crop yield per unit.
Background
Crop yield is the ultimate goal of farm farming and is a direct index to assess farm productivity and the degree of benefit to farmers. The unit yield of crops is estimated in real time in an area or a larger scale, and guidance can be provided for grain storage, grain transaction and the like; the yield of different crops in a certain area is mastered, the regional planting suitability of the crops is favorably analyzed, and further, the food planting strategy is supported.
The formation of crop yield is a complex process, a great number of physiological and biochemical processes are involved in the middle, and meteorological conditions, soil conditions, field management, climatic information, farming time information and the like are all factors to be considered for yield estimation. Since the last 60 s, with the development of remote sensing technology, the estimate of single-crop yields has formally stepped into a rapid development phase, and over the next 50 s, crop yield estimation models have gone from simple parametric statistics to a physiological-ecological-mechanism-based yield estimation system.
The crop growth simulation model is also called as a physical model, namely the biomass accumulation of crops, the yield per unit of crops and the circulating flow of water, carbon, nitrogen and energy of a farmland ecosystem are obtained by simulating the growth process of the crops. At present, a crop growth simulation model becomes a powerful tool with world influence for calculating crop productivity and farmland ecological factors, and has wide application in aspects of crop yield estimation, crop breeding, field management and the like.
The crop yield estimation model based on the remote sensing technology can be simply summarized into a development process from an empirical model, a semi-empirical mechanism model to a mechanism model, and is two main implementation modes based on light energy utilization rate and crop growth as the mechanism model, and when the two modes are used for estimating the crop yield on a pixel scale, the problems of over-simplification of the physiological and biochemical process of crops and over-high parameter calibration cost respectively exist.
Disclosure of Invention
In order to overcome the problems or at least partially solve the problems, the invention provides a remote sensing estimation method, a device and a system for crop yield, which are used for more effectively playing the role of remote sensing data, fully utilizing the growth mechanism of crops and ensuring the accuracy, efficiency and stability of the estimation of the crop yield on a larger scale.
In a first aspect, the invention provides a crop yield remote sensing estimation method, which comprises the following steps: identifying a crop category based on the crop remote sensing data; estimating a first net crop productivity based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop; estimating the crop yield per unit based on the crop first net productivity by combining the crop growth environment information and the crop growth physiological and biochemical process parameters.
Wherein the step of estimating a first net productivity of the crop further comprises: and estimating the first net productivity of the crop by utilizing a light energy utilization rate model CASA.
Wherein the step of estimating a net first crop productivity based on the crop category, the solar parameter, the weather parameter, and the vegetation index time series of the crop further comprises: calculating the total solar radiation based on the sunshine duration information, the astronomical radiation information and the daily temperature difference information in the sunshine parameters, and calculating the photosynthetically active radiation absorption ratio based on the vegetation index time sequence of the crops; calculating photosynthetically active radiation based on the total solar radiation and the photosynthetically active radiation absorption ratio; determining a temperature/water stress factor based on the temperature information, rainfall information and solar radiation information of the meteorological parameters, and calculating the light energy utilization rate based on the temperature/water stress factor; estimating said first net crop productivity using a light energy utilisation model CASA based on said crop category, said photosynthetically active radiation and said light energy utilisation.
Wherein the step of estimating the crop yield per unit based on the first net crop productivity in combination with the crop growth environment information and the crop growth physiological biochemical process parameters further comprises: initializing and setting a crop growth environment based on the crop growth environment information, performing soil moisture simulation and crop evapotranspiration simulation of a crop growth process corresponding to the crop type, and acquiring crop growth physiological and biochemical process parameters including crop TSUM parameters and crop development stage DVS; estimating the crop single yield based on the crop first net productivity and the crop growth physiological biochemical process parameter.
Further, before the step of initializing a setting of a crop growth environment based on the crop growth environment information, the method further includes: constructing a WOFOST model corresponding to the crop category based on the crop category and the crop growth environment information; accordingly, the step of estimating the single crop yield based on the first net crop productivity in combination with the crop growth environment information and the crop growth physiological biochemical process parameters further comprises: model coupling is carried out on the light energy utilization rate model CASA and the WOFOST model respectively on three layers of dry matter distribution, water stress and nutrient stress to obtain a coupling model; estimating the crop single yield using the coupling model based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop.
Wherein the step of identifying the crop category based on the crop remote sensing data further comprises: based on the crop remote sensing data, preprocessing of radiometric calibration, atmospheric correction, geometric correction, orthotropic correction, image mosaic and image cutting is sequentially carried out, and effective image data are obtained; based on the effective image data, sequentially performing image segmentation processing and artificial vectorization processing to obtain a target field boundary; and extracting spectral reflectivity characteristics, vegetation index characteristics and image texture signs of the image data in the boundary range of the target field block, and identifying the crop category by utilizing a classification algorithm based on supervision based on the spectral reflectivity characteristics, the vegetation index characteristics and the image texture signs.
Further, after the step of obtaining the coupling model, the method further comprises: and correspondingly calibrating parameters of farm scale, plot scale and pixel scale for the meteorological parameters, the crop growth physiological and biochemical process parameters and the soil parameters input into the model by adopting a literature data method, farm data collection, field observation and remote sensing inversion.
In a second aspect, the present invention provides a remote sensing estimation device for crop yield per unit, comprising: at least one memory, at least one processor, a communication interface, and a bus; the memory, the processor and the communication interface complete mutual communication through the bus, and the communication interface is used for information transmission between the estimation device and the model input parameter acquisition or storage equipment; the storage is stored with a computer program capable of running on the processor, and when the processor executes the computer program, the remote sensing estimation method for crop yield per unit is realized.
In a third aspect, the present invention provides a non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the method for remote sensing estimation of crop yield as described above. .
In a fourth aspect, the present invention provides a crop yield remote sensing estimation system, comprising: the crop yield remote sensing estimation device and the model input parameter acquisition or storage device are described above.
According to the crop yield remote sensing estimation method, the crop yield remote sensing estimation device and the crop yield remote sensing estimation system, the crop category is identified according to the crop remote sensing data, the crop growth light energy utilization rate and the crop growth physiological and biochemical process are comprehensively considered on the basis, the effect of the remote sensing data can be more effectively exerted, the growth mechanism of crops is fully utilized, and the accuracy, the efficiency and the stability of the crop yield estimation on a larger scale are ensured.
Drawings
FIG. 1 is a flow chart of a remote sensing estimation method for crop yield per unit according to an embodiment of the present invention;
FIG. 2 is a flow chart of crop remote sensing data preprocessing in a crop yield remote sensing estimation method according to an embodiment of the present invention;
FIG. 3 is a flow chart of another method for remote sensing estimation of crop yield per unit according to an embodiment of the present invention;
fig. 4 is a block diagram of a remote sensing estimation device for crop yield per unit according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As an aspect of the embodiment of the present invention, the embodiment provides a method for estimating a crop yield by remote sensing, and referring to fig. 1, a flowchart of the method for estimating a crop yield by remote sensing according to the embodiment of the present invention includes:
s1, identifying the crop type based on the crop remote sensing data;
s2, estimating first net productivity of the crops based on the crop category, the sunshine parameter, the meteorological parameter and the vegetation index time sequence of the crops;
and S3, estimating the single yield of the crop based on the first net productivity of the crop and the combination of the crop growth environment information and the physiological and biochemical process parameters of the crop growth.
It can be understood that, in the embodiment of the present invention, the remote sensing data is processed and analyzed based on the remote sensing data of the crop, and on the basis of obtaining the crop type in the remote sensing data, the first Net Primary Productivity (NPP) of the crop under the current various environmental parameter conditions is calculated, so as to finally accurately estimate the yield of the crop.
Specifically, in step S1, the obtained remote sensing data of the crop is preprocessed to obtain effective image data that can better express the characteristics of the crop, and the effective image data is classified and identified to obtain the crop category corresponding to the current remote sensing data. In one embodiment, the step of identifying the crop category based on the remote sensing data of the crop further includes:
based on the crop remote sensing data, preprocessing of radiometric calibration, atmospheric correction, geometric correction, orthorectification, image mosaic and image cutting is sequentially carried out, and effective image data are obtained;
based on the effective image data, sequentially performing image segmentation processing and artificial vectorization processing to obtain a target field boundary;
and extracting spectral reflectivity characteristics, vegetation index characteristics and image texture signs of the image data in the boundary range of the target field block, and identifying the crop category by using a classification algorithm based on supervision based on the spectral reflectivity characteristics, the vegetation index characteristics and the image texture signs.
It can be understood that, in the embodiment, remote sensing data of the land crops of the yield to be estimated, relevant environmental parameters and the like need to be collected in advance. For example, GF-1WFV remote sensing data of crops is obtained by accessing a data station of a high-grade first satellite (GF-1), meteorological parameters are obtained through a meteorological center database, and geospatial information of a land parcel, statistical yearbook data recorded according to historical data and the like are obtained at the same time.
The high-grade first satellite GF-1 runs by adopting a sun synchronous orbit, the height of the orbit is 645km, the inclination angle is 98.0506 degrees, and the camera can measure the pendulum angle to be 25 degrees. The GF-1WFV camera can acquire a 16 meter multispectral color image (4 bands of blue, green, red, near infrared). The GF-1 satellite is loaded with four WFV sensors, namely WFV1, WFV2, WFV3 and WFV4, and the imaging width can reach about 800 kilometers. The WFV camera parameters are shown in Table 1, and are GF-1WFV data parameter table.
TABLE 1 GF-1WFV data parameter Table
The obtained GF-1WFV data is a level 1 product, and the level 1 data needs to be subjected to preprocessing processes such as radiometric calibration, geometric correction and the like to obtain effective image data which can express crop characteristics better. Specifically, as shown in fig. 2, a flowchart for preprocessing the remote sensing data of the crop in the remote sensing estimation method for the specific yield of the crop according to the embodiment of the present invention includes: radiometric calibration, atmospheric correction, geometric correction, orthometric correction, image mosaicing, image cropping, and the like.
The radiometric calibration is to establish a quantitative relation between a digital quantization output value DN value of the remote sensing sensor and a radiance value in a corresponding view field. The GF-1 scaling factor is downloaded from a website of a China resource satellite application center, and channel observed values (DN values) of loads of GF-1WFV are converted into apparent radiance values by the following formula:
Lε(λε)＝Gain·DN+Bias
in the formula, Lε(λε) Indicating the converted apparent radiance, Gain indicating the scaling slope, DN indicating the satellite load observation, and Bias indicating the scaling intercept.
In the atmospheric correction process, considering that all radiant energy for remote sensing passes through the atmosphere of the earth and interacts with the atmosphere (scattering, absorption and the like), the attenuation of the atmosphere is selective to light with different wavelengths, and in order to obtain the real reflectivity of ground objects, the processing process of weakening the influence of atmospheric conditions on remote sensing data is called atmospheric correction. For example, the FLAASH (Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes) module in the ENVI software is used for Atmospheric correction. FLAASH is an atmospheric correction module developed under the support of an aerodynamic laboratory of the United states of America of the institute of optical imaging-spectral science research, and a MODTRAN4+ radiation transmission model is adopted, so that a surface reflectivity meter can be carried out according to a standard atmospheric model and aerosol types of a research area.
The original remote sensing image usually has geometric deformity, which is caused by external factors such as the attitude and orbit of the satellite and the movement and shape of the earth, and internal factors such as the structural performance of a remote sensor, the irregular movement of a scanning mirror, the sampling delay of a detector, the configuration of a detector, the misregistration between wave bands and the like. The purpose of geometric correction is to correct image distortion caused by these factors, and geometric correction includes general geometric correction and orthometric correction. The ortho-rectification is to carry out the rectification of image deformation on each pixel of the image by means of a terrain elevation model (DEM), so that the remote sensing image is more in line with the requirements of ortho-projection.
On the basis of the data processing, geometric fine correction is performed, for example, geometric fine correction is performed by using a quadratic polynomial method with reference to an OLI image corrected by actually measuring control points, so that the images used for research have geometric consistency.
And finally, carrying out re-projection and clipping. In order to ensure that all images used in the embodiment of the present invention have the same projection information, it is necessary to perform a re-projection process on the images, and then crop the images according to the research area range to obtain effective image data.
On the basis of obtaining effective image data according to the processing, due to the existence of crop rotation, the annual crop planting type needs to be identified, GF-2 data is mainly used for crop identification, and a field-oriented classification method is adopted on the basis of basic data such as land utilization types, so that the effective identification of cotton planting fields in a research area is realized.
Specifically, on the basis of the effective image data, field boundary data of the research area, that is, the target field boundary, is obtained through image segmentation and artificial vectorization. Then, extracting classification features such as spectral reflectivity features, vegetation index features and image texture signs of image data in the boundary range of the target field, selecting a monitoring classification method such as MLC (maximum likelihood), SVM (support vector machine) or NN (neural network), classifying the field-level feature images, researching the influence of each classification feature and classification method on the remote sensing identification result of the crops, and identifying the crop category.
Specifically, in step S2, a first net productivity NPP of the crop is calculated. Particularly, the yield obtained under the same condition may be different for different crop categories, so the first net productivity of the crops is calculated by comprehensively considering the factors of the crops, including the crop categories, the vegetation index time sequence of the crops, and the environmental condition factors of the crop growth, including sunlight parameters, meteorological parameters and the like. It is understood that the vegetation index time series can be obtained by analyzing and processing a plurality of frames of crop remote sensing data acquired according to time sequence.
Specifically, in step S3, on the premise of obtaining the first net productivity of the crop by calculation according to the above steps, further calculation is required according to the first net productivity of the crop to obtain the yield of the crop corresponding to the crop category. Firstly, initializing and setting soil moisture information, crop evapotranspiration information and crop growth information in the growth environment information of crop growth, determining physiological and biochemical process parameters of crop growth on the basis, and then carrying out comprehensive evaluation calculation based on the first net productivity of crops and the physiological and biochemical process parameters of crop growth to obtain an estimation result of crop yield.
According to the crop yield remote sensing estimation method provided by the embodiment of the invention, the crop category is identified according to the crop remote sensing data, and the crop growth light energy utilization rate and the crop growth physiological and biochemical process are comprehensively considered on the basis, so that the effect of the remote sensing data can be more effectively exerted, the growth mechanism of the crop is fully utilized, and the accuracy, the efficiency and the stability of the crop yield estimation on a larger scale are ensured.
According to the above embodiments, the first net crop productivity is estimated, in particular by using the light energy utilisation model CASA. Specifically, the step of estimating a net first crop productivity based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop further comprises:
calculating the total solar radiation based on the sunshine duration information, astronomical radiation information and daily temperature difference information in the sunshine parameters, and calculating the photosynthetically active radiation absorption ratio based on the vegetation index time sequence of crops;
calculating photosynthetically active radiation based on the total solar radiation and the photosynthetically active radiation absorption ratio;
determining a temperature/water stress factor based on temperature information, rainfall information and solar radiation information of meteorological parameters, and calculating the light energy utilization rate based on the temperature/water stress factor;
estimating a first net crop productivity using a light energy utilisation model CASA based on crop category, photosynthetically active radiation and light energy utilisation.
It will be appreciated that in using the CASA model to estimate the net first productivity of a crop, the photosynthetically active radiation APAR and the light energy efficiency during the growth of the crop need to be calculated separately. And specifically, the sunshine parameter, the meteorological parameter and the crop vegetation index time sequence are comprehensively considered, and the two indexes are respectively solved.
When the photosynthetically active radiation is calculated, on one hand, the total solar radiation SQL is calculated by utilizing a light energy utilization rate model CASA based on sunlight duration information, astronomical radiation information and daily temperature difference information, on the other hand, the photosynthetically active radiation absorption ratio FRAR is calculated according to a crop vegetation index time sequence, and then, the photosynthetically active radiation APAR in the crop growth process is calculated on the basis.
Wherein the calculation of the light energy utilization rate is performed based on the acquired meteorological data. For example, one embodiment of the present invention uses temperature data, rainfall data, and solar radiation data, which are downloaded in the China Meteorological data network. And arranging the downloaded data in a text document to be used as input data. And comprehensively analyzing and processing the meteorological parameter data, determining the temperature/water stress factor of the crop growth, and calculating the light energy utilization rate on the basis.
And then, after determining the photosynthetic active radiation and the light energy utilization rate of the crop growth according to the steps, comprehensively analyzing and calculating the crop category, the photosynthetic active radiation and the light energy utilization rate by using a light energy utilization rate model CASA to obtain the first net productivity of the crop.
According to the above embodiment, the step of estimating the single crop yield based on the first net crop productivity in combination with the crop growth environment information and the crop growth physiological biochemical process parameters further comprises: initializing and setting a crop growth environment based on the crop growth environment information, performing soil moisture simulation and crop evapotranspiration simulation of a crop growth process corresponding to a crop type, and acquiring crop growth physiological and biochemical process parameters including crop TSUM parameters and crop development stage DVS; estimating the crop yield per unit based on the crop first net productivity and the crop growth physiological biochemical process parameters.
It will be appreciated that the yield of the crop is closely related to the crop itself and the growing environment of the crop, wherein the initial information of the soil moisture for the crop to grow, the crop transpiration, etc. is also taken into account on the basis of the first net productivity of the crop calculated according to the above embodiment. Specifically, the method comprises the steps of simulating the growth process of crops by initializing soil moisture of the growth environment of the crops, crop transpiration and the growth state of the crops, obtaining TSUM (total dissolved flux) parameters of the crops in a plot and physiological and biochemical process parameters of the crop growth including DVS (dynamic voltage scaling) parameters of the crop development stage, and estimating the corresponding crop yield by combining the first net productivity of the crops obtained according to the embodiment on the basis.
On the basis of the above embodiment, the estimation method further includes:
constructing a WOFOST model corresponding to the crop type based on the crop type and the crop growth environment information;
performing model coupling on a light energy utilization rate model CASA and a WOFOST model on three levels of dry matter distribution, water stress and nutrient stress respectively to obtain a coupling model;
and estimating the single yield of the crops by using a coupling model based on the crop category, the sunlight parameter, the meteorological parameter and the vegetation index time sequence of the crops.
It can be understood that the present embodiment solves the problems of the prior art by coupling a sunlight-Ames-Stanford Approach (CASA) and a crop model (World Food studios). The CASA model and the WOFOST model are coupled to obtain a CASA-WOFOST single-yield estimation model, the operation speed of the CASA model and the mechanism advantage of the WOFOST model can be considered at the same time, the function of remote sensing data can be effectively played, the precision and the stability of single-yield estimation on a large scale are ensured, and the estimation precision of main grain crops can reach 85-90%.
Specifically, the CASA model is a main framework of a coupling model, the accumulated quantity (biomass) of dry matters is obtained through daily simulation of first net productivity of crops, the yield of the crops is obtained through a harvest index, and meanwhile, a related module of the WOFOST model is added to improve the capacity of the CASA model in the aspect of single-yield estimation.
The method mainly couples three processes of dry matter distribution, transpiration (soil water circulation) and nutrient stress (nutrient absorption and utilization). The coupling is divided into three stages, the first stage is to couple the dry matter distribution process, and the simulation capability of the CASA model on the distribution of the dry matter to the storage organs in different growth periods is increased, so that the harvest index is replaced, and unnecessary errors are avoided; the second level is the coupling to the water stress, the capability of the CASA model for coping with extreme weather conditions is improved, the third level is the coupling to the nutrient stress, and the nutrient module is added to enable the CASA model to have the capability of simulating the absorption and utilization of quick-acting nitrogen, phosphorus and potassium by the simulated crops. And finally, simulating the crop growth on the basis of CASA-WOFOST yield per unit estimation coupling model parameter calibration and remote sensing data assimilation realization, and obtaining a final yield per unit estimation result by considering the nutrient stress effect.
It should be understood that, because the last two-stage coupling still involves more parameters to be calibrated, the corresponding module is called only when an abnormal duress occurs, so as to ensure the running speed and the cost of the model.
According to the remote sensing estimation method for the crop yield per unit, the CASA-WOFOST yield per unit estimation model obtained through coupling can simultaneously take account of the operation speed of the CASA model and the mechanism advantages of the WOFOST model, the effect of remote sensing data can be more effectively exerted, the growth mechanism of crops is fully utilized, and the accuracy, the efficiency and the stability of the estimation of the crop yield per unit on a larger scale are ensured.
Further, after the step of obtaining the coupling model, the method further comprises: and correspondingly calibrating parameters of farm scale, plot scale and pixel scale for meteorological parameters, crop growth physiological and biochemical process parameters and soil parameters of the input model by adopting a literature data method, farm data collection, field observation and remote sensing inversion.
It will be appreciated that calibration of the coupling model parameters is performed on the basis of the parameter sensitivity analysis and the acquisition of the ground observation data set according to the above-described embodiment. The model calibration is mainly performed in four ways: literature data methods, farm data collection, field observation and remote sensing inversion.
Specifically, when the model parameter calibration is performed, the calibration is mainly performed according to the following scales: weather data except temperature, most crop parameters and soil parameters are calibrated on a farm scale; calibrating partial soil nutrient parameters on a plot scale; and calibrating part of core parameters (crop growth period, leaf area index and the like) on a pixel scale. The main calibration parameters include meteorological parameters, crop parameters, soil parameters and the like.
To further illustrate the technical solution of the present invention, the following preferred processing flow is provided, but the scope of the present invention is not limited thereto.
Referring to fig. 3, a flow chart of another crop specific yield remote sensing estimation method according to an embodiment of the present invention is shown, wherein the operation of the method can be considered as an operation process including several process flows of data acquisition and preprocessing, crop category identification based on crop time series remote sensing data, crop NPP estimation by CASA model, and crop yield estimation by fusion of wobest model.
In the data acquisition stage, data including crop time sequence remote sensing data, geographic space data, unified yearbook data, meteorological data, solar parameters and the like are collected. And then, in a data preprocessing stage, preprocessing such as radiometric calibration, atmospheric correction, geometric correction, orthometric correction, image mosaic, image cutting and the like is sequentially carried out on the crop time sequence remote sensing data to obtain effective crop image data.
And then, in a crop category remote sensing identification stage, based on effective crop image data, classification feature extraction, crop information extraction and precision evaluation/statistics are carried out. Namely, based on the effective crop image data, the time sequence NDVI is obtained by extracting the image NDVI and performing the time sequence NDVI smooth reconstruction. And selecting partial data in the time sequence NDVI as training sample input, and acquiring the real category of the crop through visual interpretation based on effective crop image data. And (3) taking the real category of the crop as a sample label, inputting the training sample and the sample label into the crop category identification model together, training the crop category identification model, and obtaining the ideal crop category identification model through precision evaluation statistics. And then carrying out crop category identification on the image features to be identified by utilizing the ideal crop category identification model.
And at the stage of estimating crop NPP by the CASA model, acquiring total solar radiation by using the CASA model according to sunshine parameters including sunshine duration, astronomical radiation, namely solar temperature difference and the like, acquiring photosynthetic effective radiation absorption ratio according to the vegetation index time sequence, and determining photosynthetic effective radiation APAR under the sunshine condition according to the total solar radiation and the photosynthetic effective radiation absorption ratio. On the other hand, according to meteorological data, including temperature, rainfall, solar radiation and the like, a temperature/water stress factor is obtained, and the light energy utilization rate is determined based on the temperature/water stress factor. And finally, acquiring a first net productivity NPP corresponding to the crop based on the photosynthetically active radiation APAR and the light energy utilization rate.
And finally, in the stage of estimating the crop yield by fusing the WOFOST model, firstly, initializing parameter settings of a soil moisture simulation module, a crop growth module and a crop evapotranspiration module of the model respectively. On this basis, crop TSUM information, crop developmental stage DVS parameters and memory organ distribution coefficients are determined using the wofors model. Finally, based on these information parameters and the first net productivity NPP of the crop, crop yield is estimated.
As another aspect of the embodiment of the present invention, the present embodiment provides a remote sensing estimation device for crop yield, and referring to fig. 4, the present invention is a block diagram of a remote sensing estimation device for crop yield, including: at least one memory 1, at least one processor 2, a communication interface 3 and a bus 4.
The memory 1, the processor 2 and the communication interface 3 complete mutual communication through a bus 4, and the communication interface 3 is used for acquiring parameters related to model input of an estimation device or transmitting information between storage devices; the memory 1 stores a computer program operable on the processor 2, and the processor 2 executes the computer program to implement the remote sensing estimation method for crop yield per unit as described in the above embodiments.
It can be understood that the crop yield remote sensing estimation device at least comprises a memory 1, a processor 2, a communication interface 3 and a bus 4, and the memory 1, the processor 2 and the communication interface 3 are in communication connection with each other through the bus 4 and can complete communication with each other.
The communication interface 3 realizes the communication connection between the crop single-yield remote sensing estimation device and the model input related parameters or the storage device, and can complete the mutual information transmission, such as the acquisition of crop remote sensing data, sunshine parameters, meteorological parameters and the like through the communication interface 3.
When the crop yield remote sensing estimation device runs, the processor 2 calls the program instructions in the memory 1 to execute the methods provided by the above-mentioned embodiments of the methods, for example, the methods include: based on the crop remote sensing data, preprocessing of radiometric calibration, atmospheric correction, geometric correction, orthorectification, image mosaic and image cutting is sequentially carried out, and effective image data are obtained; and estimating a first net crop productivity based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop, and the like.
In another embodiment of the present invention, a non-transitory computer-readable storage medium is provided, which stores computer instructions that cause the computer to perform the method for remote sensing estimation of crop yield as described in the above embodiments.
It will be appreciated that the logic instructions in the memory 1 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Alternatively, all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, where the program may be stored in a computer-readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The embodiments of the remote sensing estimation device for crop yield described above are merely illustrative, and the units illustrated as separate components may or may not be physically separate, and may be located in one place or distributed on different network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the technical solutions mentioned above may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a usb disk, a removable hard disk, a ROM, a RAM, a magnetic or optical disk, etc., and includes several instructions for causing a computer device (such as a personal computer, a server, or a network device, etc.) to execute the methods described in the method embodiments or some parts of the method embodiments.
According to the crop yield remote sensing estimation device and the non-transitory computer readable storage medium provided by the embodiment of the invention, the crop type is identified according to the crop remote sensing data, and the crop growth light energy utilization rate and the crop growth physiological and biochemical process are comprehensively considered on the basis, so that the effect of the remote sensing data can be more effectively exerted, the growth mechanism of the crop is fully utilized, and the accuracy, the efficiency and the stability of the estimation of the crop yield on a larger scale are ensured.
As a further aspect of the embodiments of the present invention, the present embodiment provides a crop yield remote sensing estimation system, which includes the crop yield remote sensing estimation apparatus according to the above embodiments and a device for acquiring or storing the parameters related to the model input, which is connected in communication with the crop yield remote sensing estimation apparatus. The relevant parameters input by the model comprise crop remote sensing data, sunlight parameters, meteorological parameters, crop growth environment information and the like.
The system is used for realizing the estimation of the single yield of the crops by utilizing the fusion of the light energy utilization rate and the growth process of the crops based on the remote sensing images of the crops in the embodiments. Therefore, the description and definition in the remote sensing estimation of crop yield per unit can be used for understanding the execution modules in the embodiments of the present invention.
It is understood that, in the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).
According to the remote sensing estimation system for the crop yield per unit, the estimation device and the corresponding parameter acquisition or storage equipment are arranged, the crop type is identified according to the crop remote sensing data, the crop growth light energy utilization rate and the crop growth physiological and biochemical process are comprehensively considered on the basis, the effect of the remote sensing data can be more effectively exerted, the growth mechanism of crops is fully utilized, and the accuracy, the efficiency and the stability of the estimation for the crop yield per unit on a larger scale are ensured.
In addition, it should be understood by those skilled in the art that the terms "comprises," "comprising," or any other variation thereof, in the specification of the present invention, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the description of the present invention, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects.
However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A crop yield remote sensing estimation method is characterized by comprising the following steps:
identifying a crop category based on the crop remote sensing data;
estimating a first net crop productivity based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop; the vegetation index time sequence of the crops is obtained by analyzing and processing multi-frame crop remote sensing data acquired according to a time sequence;
estimating the single yield of the crop based on the first net productivity of the crop by combining the crop growth environment information and the physiological and biochemical process parameters of the crop growth;
wherein the step of estimating a net first crop productivity based on the crop category, the solar parameter, the weather parameter, and the vegetation index time series of the crop further comprises:
calculating the total solar radiation based on the sunshine duration information, the astronomical radiation information and the daily temperature difference information in the sunshine parameters, and calculating the photosynthetically active radiation absorption ratio based on the vegetation index time sequence of the crops;
calculating photosynthetically active radiation based on the total solar radiation and the photosynthetically active radiation absorption ratio;
determining a temperature/water stress factor based on the temperature information, rainfall information and solar radiation information of the meteorological parameters, and calculating the light energy utilization rate based on the temperature/water stress factor;
estimating said first net crop productivity using a light energy utilisation model CASA based on said crop category, said photosynthetically active radiation and said light energy utilisation.
2. The method of claim 1, wherein the step of estimating a first net productivity of the crop further comprises: and estimating the first net productivity of the crop by utilizing a light energy utilization rate model CASA.
3. The method of claim 2, wherein the step of estimating the crop yield per unit based on the first net crop productivity in combination with the crop growth environment information and the crop growth physiological biochemical process parameters further comprises:
initializing and setting a crop growth environment based on the crop growth environment information, performing soil moisture simulation and crop evapotranspiration simulation of a crop growth process corresponding to the crop type, and acquiring crop growth physiological and biochemical process parameters including crop TSUM parameters and crop development stage DVS;
estimating the crop single yield based on the crop first net productivity and the crop growth physiological biochemical process parameter.
4. The method of claim 3, further comprising, prior to the step of initializing a setting of a crop growing environment based on the crop growing environment information:
constructing a WOFOST model corresponding to the crop category based on the crop category and the crop growth environment information;
accordingly, the step of estimating the single crop yield based on the first net crop productivity in combination with the crop growth environment information and the crop growth physiological biochemical process parameters further comprises:
model coupling is carried out on the light energy utilization rate model CASA and the WOFOST model respectively on three layers of dry matter distribution, water stress and nutrient stress to obtain a coupling model;
estimating the crop single yield using the coupling model based on the crop category, the solar parameter, the meteorological parameter, and the vegetation index time series of the crop.
5. The method of claim 1, wherein the step of identifying a crop category based on the remote crop sensing data further comprises:
based on the crop remote sensing data, preprocessing of radiometric calibration, atmospheric correction, geometric correction, orthotropic correction, image mosaic and image cutting is sequentially carried out, and effective image data are obtained;
based on the effective image data, sequentially performing image segmentation processing and artificial vectorization processing to obtain a target field boundary;
and extracting spectral reflectivity characteristics, vegetation index characteristics and image texture signs of the image data in the boundary range of the target field block, and identifying the crop category by utilizing a classification algorithm based on supervision based on the spectral reflectivity characteristics, the vegetation index characteristics and the image texture signs.
6. The method of claim 4, further comprising, after the step of obtaining a coupling model:
and correspondingly calibrating parameters of farm scale, plot scale and pixel scale for the meteorological parameters, the crop growth physiological and biochemical process parameters and the soil parameters input into the model by adopting a literature data method, farm data collection, field observation and remote sensing inversion.
7. A crop yield remote sensing estimation device, comprising: at least one memory, at least one processor, a communication interface, and a bus;
the memory, the processor and the communication interface complete mutual communication through the bus, and the communication interface is used for information transmission between the estimation device and the model input parameter acquisition or storage equipment;
the memory has stored therein a computer program operable on the processor, which when executed by the processor, implements the method of any of claims 1 to 6.
8. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1-6.
9. A crop yield remote sensing estimation system, comprising: the estimation apparatus of claim 7 and said model input parameter acquisition or storage device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689070.0A CN108985588B (en) | 2018-06-28 | 2018-06-28 | Crop yield per unit remote sensing estimation method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689070.0A CN108985588B (en) | 2018-06-28 | 2018-06-28 | Crop yield per unit remote sensing estimation method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108985588A CN108985588A (en) | 2018-12-11 |
| CN108985588B true CN108985588B (en) | 2021-09-03 |
Family
ID=64539419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810689070.0A Active CN108985588B (en) | 2018-06-28 | 2018-06-28 | Crop yield per unit remote sensing estimation method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985588B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109614763B (en) * | 2019-01-30 | 2019-09-06 | 北京师范大学 | A kind of area crops yield estimation method correcting crop modeling based on multi-source information substep |
| CN109919395A (en) * | 2019-04-01 | 2019-06-21 | 安徽大学 | A kind of winter wheat yield monitoring method based on short cycle remote sensing area data |
| CN110243406B (en) * | 2019-06-21 | 2021-06-15 | 武汉思众空间信息科技有限公司 | Crop yield estimation method and device, electronic equipment and storage medium |
| CN110276304A (en) * | 2019-06-25 | 2019-09-24 | 北京师范大学 | High-resolution vegetation productivity remote sensing estimation method based on NO emissions reduction |
| CN110176067A (en) * | 2019-07-03 | 2019-08-27 | 中国水利水电科学研究院 | A kind of WOFOST-PAR coupling model method for building up |
| CN110458618A (en) * | 2019-08-09 | 2019-11-15 | 天津市测绘院 | Agricultural land value calculation method, device, server and storage medium |
| CN110930002A (en) * | 2019-11-12 | 2020-03-27 | 秒针信息技术有限公司 | Method and device for realizing material management and control, computer storage medium and terminal |
| CN113033262B (en) * | 2019-12-25 | 2022-08-05 | 中移(成都)信息通信科技有限公司 | Model training method and crop yield estimation method |
| US11935242B2 (en) | 2020-03-09 | 2024-03-19 | International Business Machines Corporation | Crop yield estimation |
| US11500876B2 (en) | 2020-04-29 | 2022-11-15 | International Business Machines Corporation | Method for duplicate determination in a graph |
| US11941056B2 (en) | 2020-04-29 | 2024-03-26 | International Business Machines Corporation | Method for weighting a graph |
| CN113052433B (en) * | 2021-02-22 | 2024-02-06 | 中国科学院空天信息创新研究院 | Crop unit yield estimation method based on key time phase and farmland landscape characteristic parameters |
| US11823448B2 (en) | 2021-04-29 | 2023-11-21 | International Business Machines Corporation | Agricultural crop identification using satellite and crop rotation |
| US11531656B1 (en) | 2021-06-08 | 2022-12-20 | International Business Machines Corporation | Duplicate determination in a graph |
| CN116935227A (en) * | 2023-08-03 | 2023-10-24 | 沃杰(北京)科技有限公司 | Crop yield analysis method, system and medium based on satellite remote sensing image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704758A (en) * | 2004-05-28 | 2005-12-07 | 北京农业信息技术研究中心 | Method for realizing wheat behavior monitoring and forecasting by utilizing remote sensing and geographical information system technology |
| CN1731216A (en) * | 2005-08-19 | 2006-02-08 | 广州地理研究所 | A remote sensing detection and evaluation method for the area and production of large-area crop raising |
| CN106446564A (en) * | 2016-09-29 | 2017-02-22 | 华南农业大学 | Method for remote sensing estimation of net primary productivity of plants |
| US9953241B2 (en) * | 2014-12-16 | 2018-04-24 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for satellite image processing to estimate crop yield |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10096073B2 (en) * | 2011-05-13 | 2018-10-09 | The Climate Corporation | Systems to prescribe and deliver fertilizer over agricultural fields and related methods |
| CN103886213B (en) * | 2014-04-03 | 2017-01-25 | 北京大学 | Remote sensing estimation method and system of crop gross primary productivity |
| US10275731B2 (en) * | 2016-07-06 | 2019-04-30 | Agrian, Inc. | Multi-year crop yield analysis using remotely-sensed imagery for missing or incomplete yield events for site-specific variable rate applications |
| CN106355143A (en) * | 2016-08-25 | 2017-01-25 | 中国农业大学 | Seed maize field identification method and system based on multi-source and multi-temporal high resolution remote sensing data |
-
2018
- 2018-06-28 CN CN201810689070.0A patent/CN108985588B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704758A (en) * | 2004-05-28 | 2005-12-07 | 北京农业信息技术研究中心 | Method for realizing wheat behavior monitoring and forecasting by utilizing remote sensing and geographical information system technology |
| CN1731216A (en) * | 2005-08-19 | 2006-02-08 | 广州地理研究所 | A remote sensing detection and evaluation method for the area and production of large-area crop raising |
| US9953241B2 (en) * | 2014-12-16 | 2018-04-24 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for satellite image processing to estimate crop yield |
| CN106446564A (en) * | 2016-09-29 | 2017-02-22 | 华南农业大学 | Method for remote sensing estimation of net primary productivity of plants |
Non-Patent Citations (2)
| Title |
|---|
| "基于遥感与作物生长模型的冬小麦生长模拟研究";郭建茂;《中国博士学位论文全文数据库 农业科技辑》;20071215;第1.2.4-2.4节、图2.2 * |
| "遥感在种植业保险估损中的应用";蒙继华等;《遥感技术与应用》;20170430;第32卷(第2期);第3.5节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108985588A (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985588B (en) | Crop yield per unit remote sensing estimation method, device and system | |
| Zheng et al. | Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery | |
| Zhang et al. | Estimating the maize biomass by crop height and narrowband vegetation indices derived from UAV-based hyperspectral images | |
| Peng et al. | Remote prediction of yield based on LAI estimation in oilseed rape under different planting methods and nitrogen fertilizer applications | |
| Battude et al. | Estimating maize biomass and yield over large areas using high spatial and temporal resolution Sentinel-2 like remote sensing data | |
| Fang et al. | Corn‐yield estimation through assimilation of remotely sensed data into the CSM‐CERES‐Maize model | |
| Fang et al. | Integration of MODIS LAI and vegetation index products with the CSM–CERES–Maize model for corn yield estimation | |
| Sun et al. | Retrieval of rapeseed leaf area index using the PROSAIL model with canopy coverage derived from UAV images as a correction parameter | |
| Sharifi | Estimation of biophysical parameters in wheat crops in Golestan province using ultra-high resolution images | |
| Dong et al. | Deriving maximum light use efficiency from crop growth model and satellite data to improve crop biomass estimation | |
| Mathews | Object-based spatiotemporal analysis of vine canopy vigor using an inexpensive unmanned aerial vehicle remote sensing system | |
| Meiyan et al. | Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images | |
| Singh et al. | UAV-based hyperspectral imaging technique to estimate canola (Brassica napus L.) seedpods maturity | |
| Jeong et al. | Application of an unmanned aerial system for monitoring paddy productivity using the GRAMI-rice model | |
| Li et al. | Estimating plant traits of alpine grasslands on the Qinghai-Tibetan Plateau using remote sensing | |
| Yang et al. | Leaf nitrogen spectral reflectance model of winter wheat (Triticum aestivum) based on PROSPECT: simulation and inversion | |
| Zhou et al. | Remote sensing of regional-scale maize lodging using multitemporal GF-1 images | |
| Song et al. | Estimating reed loss caused by Locusta migratoria manilensis using UAV-based hyperspectral data | |
| Chen et al. | LAI-NOS: An automatic network observation system for leaf area index based on hemispherical photography | |
| Tu et al. | A time-efficient fractional vegetation cover estimation method using the dynamic vegetation growth information from time series Glass FVC product | |
| Kawamura et al. | Mapping herbage biomass and nitrogen status in an Italian ryegrass (Lolium multiflorum L.) field using a digital video camera with balloon system | |
| Yuan et al. | Research on rice leaf area index estimation based on fusion of texture and spectral information | |
| Lyu et al. | UAV time-series imagery with novel machine learning to estimate heading dates of rice accessions for breeding | |
| Campos et al. | Analyzing the effect of shadow on the relationship between ground cover and vegetation indices by using spectral mixture and radiative transfer models | |
| Guillén-Climent et al. | Estimating radiation interception in heterogeneous orchards using high spatial resolution airborne imagery |
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 |