CN113743819B - Crop yield estimation method, device, electronic equipment and storage medium - Google Patents

Crop yield estimation method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113743819B
CN113743819B CN202111078078.1A CN202111078078A CN113743819B CN 113743819 B CN113743819 B CN 113743819B CN 202111078078 A CN202111078078 A CN 202111078078A CN 113743819 B CN113743819 B CN 113743819B
Authority
CN
China
Prior art keywords
yield
crop
vegetation
remote sensing
time phase
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
Application number
CN202111078078.1A
Other languages
Chinese (zh)
Other versions
CN113743819A (en
Inventor
关盛勇
周会珍
朱菊蕊
陈晨
李冬冬
谌华
何建军
文强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Twenty First Century Aerospace Technology Co ltd
Original Assignee
Twenty First Century Aerospace Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Twenty First Century Aerospace Technology Co ltd filed Critical Twenty First Century Aerospace Technology Co ltd
Priority to CN202111078078.1A priority Critical patent/CN113743819B/en
Publication of CN113743819A publication Critical patent/CN113743819A/en
Application granted granted Critical
Publication of CN113743819B publication Critical patent/CN113743819B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q10/067—Enterprise or organisation modelling
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Image Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a method, a device, electronic equipment and a storage medium for estimating crop yield, wherein the method comprises the following steps: determining a key time phase of the remote sensing image based on a key climatic period of crops to be estimated; acquiring a remote sensing image of the key time phase, and calculating a plurality of vegetation indexes; respectively constructing regression models of each vegetation index and the measured yield data; sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period, and screening out the optimal vegetation indexes of the key time phases; and constructing an estimated yield model based on the optimal vegetation index and the actually measured yield data of the key time phase, and estimating the yield of crops. The method is based on remote sensing data, combines with crop growth characteristics, constructs an estimation model of regional crop yield by analyzing crop key periods and combining with optimal vegetation indexes and measured data, can be used for estimating the regional yield rapidly, and improves the reliability of yield estimation results.

Description

Crop yield estimation method, device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of crop production, in particular to a method and a device for estimating crop yield, electronic equipment and a storage medium.
Background
The dynamic monitoring and the output of the crop growth condition are timely and accurately predicted, and the method has important significance for the formulation of national grain policies, the development of rural economy and external grain trade. Along with the development of remote sensing technology, remote sensing data with high time resolution, high spatial resolution and high spectrum resolution are continuously emerging, so that the fineness and accuracy of the remote sensing data in crop estimation are continuously improved, and the use of the combination of the remote sensing data and statistical data for predicting crop yield has become a trend in the field of remote sensing estimation. The remote sensing yield estimation research is also developed from single crops to multiple crops, from small-area application to large-area application, from single information sources to comprehensive application of multiple remote sensing information sources, and the monitoring precision is also continuously improved.
However, there are also the following disadvantages in the existing methods of crop estimation:
(1) The principle of an empirical statistical model using single parameter modeling is simple, but the stability is not high;
(2) The light energy utilization rate model has insufficient consideration on the difference of the physiological processes of crops in different growth periods and is highly interfered by human factors;
(3) The crop growth model has excessive parameters, high running cost and longer parameter localization period, and can only simulate the single-point crop yield to be interpolated into a regional range, and the regional yield result is inaccurate.
(4) The coupling model construction process is complex, the parameter acquisition paths of different areas are unstable, and the coupling principle and the coupling method are still to be further researched and perfected.
The modeling image has single time phase, single modeling index, simple and easy realization of the model, poor model stability and non-ideal estimated result; or modeling parameters are too many, parameters are difficult to obtain, cost is too high, models are complex and difficult to realize, the estimated production period is long, and the large-scale popularization is difficult, so that the factors limit the further application and development of the regional remote sensing estimated production technology.
Disclosure of Invention
The invention mainly aims to provide a method, a device, electronic equipment and a storage medium for estimating crop yield, and aims to solve the technical problem of enabling crop yield estimation to be faster and more accurate.
The aim and the technical problems of the invention are realized by adopting the following technical proposal. The method for estimating crop yield provided by the invention comprises the following steps:
determining a key time phase of a remote sensing image for estimating the crop to be estimated based on the key waiting period of the crop to be estimated;
acquiring a remote sensing image of the key time phase, and calculating a plurality of vegetation indexes of the remote sensing image of the key time phase;
obtaining measured yield data, and respectively constructing regression models of each vegetation index and the measured yield data;
sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period, and screening out the optimal vegetation indexes of the key time phases;
and constructing an estimated yield model based on the optimal vegetation index and the actually measured yield data of the key time phase, and estimating the yield of crops.
The aim and the technical problems of the invention can be further realized by adopting the following technical measures.
Preferably, the method for estimating crop yield according to the foregoing aspect, wherein determining the key time phase of the remote sensing image for estimating crop yield based on the key season of the crop to be estimated, comprises:
selecting a research area of crops to be estimated, and determining the crop weathers and characteristics thereof by combining the weathers of the crops to be estimated in the research area;
based on different growth stages of crops, screening out periods in which crops grow vigorously and obvious vegetation information can be observed on remote sensing images, and determining key climatic periods for estimating crop yield;
and determining a key time phase of a remote sensing image for estimating the crop to be estimated based on the key climatic period of the crop yield estimation.
Preferably, the method for estimating crop yield, wherein acquiring the remote sensing image of the key time phase, calculating a plurality of vegetation indexes of the remote sensing image of the key time phase, includes:
after acquiring a remote sensing image of a key time phase of a crop to be estimated, preprocessing the remote sensing image;
and calculating the preprocessed remote sensing image of the key time phase to obtain a plurality of vegetation indexes of the remote sensing image of the key time phase.
Preferably, the method for estimating crop yield, wherein the pretreatment comprises: radiometric calibration, atmospheric correction, geometric fine correction and image registration; the atmosphere correction is performed by using a FLAASH atmosphere correction model.
Preferably, the method for estimating crop yield, wherein the plurality of vegetation indexes comprises: the plant growth regulator comprises a green normalized plant index, a difference plant index, a crop nitrogen response index, a plant index for regulating soil brightness, a plant attenuation index, a ratio plant index, a soil regulating plant index and a structure reinforcing pigment plant index.
Preferably, the method for estimating crop yield, wherein obtaining measured yield data, respectively constructing regression models of each vegetation index and the measured yield data, includes:
checking the actually measured yield points one by one, and screening out error points of the actually measured yield to obtain actually measured yield data;
and respectively constructing regression models of each vegetation index of the key time phase and the measured yield data.
Preferably, the method for estimating crop yield in the foregoing method, wherein ranking the goodness of fit of regression models of each vegetation index and measured yield data in the same growth period, and screening out preferred vegetation indexes in a key time phase includes:
respectively evaluating regression models of each vegetation index and measured yield data of the key time phase of crops by adopting the fitting goodness of the models;
3-5 preferable vegetation indexes which can reflect the growth state of crops are screened out according to the fitting goodness.
The aim of the invention and the technical problems are also achieved by adopting the following technical proposal. According to the invention, a device for estimating crop yield is provided, which comprises:
the determining unit is used for determining a key time phase of a remote sensing image used for estimating the crop to be estimated based on the key waiting period of the crop to be estimated;
the acquisition unit is used for acquiring the remote sensing image of the key time phase and calculating a plurality of vegetation indexes of the remote sensing image of the key time phase;
the model construction unit is used for acquiring the actual measurement yield data and respectively constructing regression models of each vegetation index and the actual measurement yield data;
the screening unit is used for sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period and screening out the optimal vegetation indexes of the key time phases;
and the yield estimation unit is used for constructing a yield estimation model based on the optimal vegetation index and the actually measured yield data of the key time phase and estimating the yield of the crops.
The aim of the invention and the technical problems are also achieved by adopting the following technical proposal. According to the invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores computer program instructions, which when read and executed by the processor, perform the steps of the method according to any of the preceding claims.
The aim of the invention and the technical problems are also achieved by adopting the following technical proposal. According to the present invention, there is provided a storage medium having stored thereon computer program instructions which, when read and executed by a computer, perform the steps of the method of any of the preceding claims.
By means of the technical scheme, the crop estimated yield method, the device, the electronic equipment and the storage medium provided by the invention have at least the following advantages:
1. according to the method, regional crop yield estimation is realized by combining a preferable vegetation index and measured data modeling method through crop key climate period analysis. The invention aims to overcome the defects of poor stability of a single-parameter experience statistical model, insufficient consideration of differences of physiological processes of crops in different growth periods by a light energy utilization model, strong interference by human factors, excessive parameters of the crop growth model, high running cost and longer estimated production period, and the defects of complex construction process, difficult acquisition of parameters and limited local application of a coupling model, and aims to ensure that the estimation of the yield of crops in a region is more accurate, rapid and convenient, the wide-range popularization and use are easy, and the economic benefit is realized by fully considering the relation between the vegetation index and the crop growth state and the complementary relation of different vegetation index information.
2. The method is based on remote sensing data, combines with crop growth characteristics, constructs the regional crop yield estimation model by crop key weather analysis and combining with optimal vegetation indexes and actual measurement data, can be used for rapid regional yield estimation, ensures that regional crop yield estimation is quicker and more accurate, has wide development application range, high precision, low running cost and short estimated yield period, and is easy to popularize and use in a large scale.
The foregoing description is only an overview of the present invention, and is intended to provide a better understanding of the present invention, as it is embodied in the following description, with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and that other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for estimating crop yield according to one embodiment of the present application;
FIG. 3 is a detailed flow diagram of a method for estimating crop yield according to one embodiment of the present application;
FIG. 4 is a schematic structural view of an apparatus for estimating crop yield according to an embodiment of the present application;
FIG. 5a is a graph showing the spring corn yield distribution in Xinjiang according to the embodiment of the present application;
fig. 5b is a partial enlarged view at a of fig. 5 a.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of the method, device, electronic equipment and storage medium for estimating crop yield according to the invention, which are described in the following with reference to the accompanying drawings and preferred embodiments. In the following description, different "an embodiment" or "an embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Referring to fig. 1, an embodiment of the present application provides a schematic structural diagram of an electronic device 100, which may be a personal computer, a tablet computer, a smart phone, a personal digital assistant, and so on.
The electronic device 100 includes: a processor 101, a memory 102, a communication interface 103, and a communication bus for enabling connected communication of these components.
The Memory 102 is used for storing various data such as remote sensing images of crops to be estimated in each weathered period and corresponding computer program instructions of the method and apparatus for estimating crops provided in the embodiments of the present application, where the Memory 102 may be, but is not limited to, a Random access Memory (Random AccessMemory, RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an erasable Read Only Memory (Erasable Programmable Read-OnlyMemory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-OnlyMemory, EEPROM), and the like.
The processor 101 is configured to execute the steps of the method for estimating crop yield provided in the embodiment of the present application when reading and running the computer program instructions stored in the memory, so as to obtain a key time phase remote sensing image of the crop to be estimated from the memory, calculate a plurality of vegetation indexes of the key time phase based on the key time phase remote sensing image, and then construct regression models of each vegetation index of the key time phase and the measured yield data based on the measured yield data; sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period, and screening out a key time phase optimal vegetation index; and finally, constructing an estimated yield model based on the critical time phase optimal vegetation index and the actual measured yield data, and estimating the yield of crops.
Further, the processor 101 may be an integrated circuit chip with signal processing capability. The processor 101 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The communication interface 103 may use any transceiver-like device to send the crop yield estimate to a user terminal communicatively coupled to the electronic device 100 for display.
Referring to fig. 2, fig. 2 is a flowchart of a method for estimating crop yield according to an embodiment of the present application, where the method is applied to the electronic device 100 shown in fig. 1, and the flow shown in fig. 2 will be described in detail, and the method includes the following steps:
s100, determining a key time phase of a remote sensing image used for estimating the crop to be estimated based on a key waiting period of the crop to be estimated;
the step S100 specifically includes:
s101, selecting a research area of crops to be estimated, and determining the crop weathers and characteristics thereof by combining the weathers of the crops to be estimated in the research area;
s102, screening out periods of vigorous growth of crops and obvious vegetation information can be observed on a remote sensing image based on different growth stages of the crops, and determining key climatic periods of crop yield estimation;
and S103, determining a key time phase of a remote sensing image for estimating the crop to be estimated based on the key period of crop yield estimation.
In this step S100, the waiting period is a waiting period when the change of the law of growth, development, activity, etc. of animals and plants and organisms reflects the climate. And analyzing the weather period of the crop suitable for estimating the yield by remote sensing, namely the key weather period, wherein the growth vigorous stage of the plant with typical vegetation spectral characteristics can be used as the key weather period of the crop to be estimated.
The critical weather period in S100 refers to a weather period that is closely related to the crop species and has a large influence on the yield of the crop. There may be multiple key climatic periods for the crop, different crops having different key climatic periods. According to the embodiment of the application, the key waiting period is adopted, so that a more accurate estimated production result can be obtained, and the calculation complexity is low.
Specifically, in order to reduce the computational complexity of the yield estimation method on the basis of ensuring the accuracy of the yield estimation result, for each crop to be estimated, accurate estimation of the yield of the crop is realized only by the remote sensing image of the crop in the key climatic stage, for example, rice, and the estimation of the yield of the rice can be realized only by acquiring the data of the rice in the gestation stage, the heading stage or the breast-maturing stage, without acquiring the data of the rice in the seedling stage, the tillering stage, the waxing stage and the maturing stage. For another example, the wheat can be estimated by only acquiring the data of the wheat in the booting stage, the heading stage and the grouting stage, and the data of the wheat in the sowing stage, the seedling stage, the jointing stage, the overwintering stage, the turning green stage, the lifting stage (biological jointing), the blooming stage and the maturing stage are not required to be acquired.
In one possible implementation, S100 may be implemented as follows: the electronic device 100 receives the remote sensing image of the crop to be estimated in the critical weathered period, stores the remote sensing image of the weathered period in the memory 102, and obtains the remote sensing image of the crop to be estimated in the critical weathered period from the memory 102 when the yield of the crop to be estimated is required to be estimated. In this embodiment, the crop to be estimated may be, but is not limited to, rice, wheat, corn, soybean, etc.
In another possible embodiment, the remote sensing image of the crop to be estimated during the critical weather period may be a remote sensing image photographed by a satellite.
Because the resolution ratio of the remote sensing image obtained through the unmanned aerial vehicle is higher than that of the remote sensing image obtained through the satellite, the image data of crops can also be obtained through the unmanned aerial vehicle in the embodiment of the application.
S200, acquiring a remote sensing image of the key time phase, and calculating a plurality of vegetation indexes of the remote sensing image of the key time phase;
the step S200 specifically includes:
s201, preprocessing a remote sensing image of a key time phase of a crop to be estimated after acquiring the remote sensing image;
wherein the preprocessing comprises: radiometric calibration, atmospheric correction, geometric fine correction, and image registration.
Furthermore, the atmospheric correction is performed by selecting a FLAASH atmospheric correction model, the FLAASH is generated based on an MODTRAN4+ radiation transmission model, so that the scattering effect of water vapor and aerosol in remote sensing imaging is effectively removed, and meanwhile, the proximity effect of cross radiation of a target pixel and a neighboring pixel is corrected based on pixel-level correction.
S202, calculating the preprocessed remote sensing image of the key time phase to obtain a plurality of vegetation indexes of the remote sensing image of the key time phase.
In this embodiment, the plurality of vegetation indexes of the remote sensing image of the key time phase include, but are not limited to: green normalized vegetation index (GNDVI), normalized vegetation index (NDVI), differential Vegetation Index (DVI), crop Nitrogen Response Index (NRI), soil brightness adjustment vegetation index (OSAVI), vegetation reduction index (PSRI), ratio Vegetation Index (RVI), soil Adjustment Vegetation Index (SAVI) and structure enhanced pigment vegetation index (SIPI), greenness Vegetation Index (GVI), vertical vegetation index (PVI), atmospheric Resistance Vegetation Index (ARVI), greenness sum index (SG).
In some preferred embodiments, the plurality of vegetation indices of the remote sensing image of the key time phase comprises: green normalized vegetation index (GNDVI), normalized vegetation index (NDVI), differential Vegetation Index (DVI), crop Nitrogen Response Index (NRI), soil brightness adjustment vegetation index (OSAVI), vegetation decay index (PSRI), ratio Vegetation Index (RVI), soil Adjustment Vegetation Index (SAVI), and structure-enhancing pigment vegetation index (SIPI).
These vegetation indices selected above can reflect the growth and development status of crops, and are typical and representative.
And calculating a plurality of vegetation indexes of the key time phase according to the blue wave band, the green wave band, the red wave band and the near infrared wave band of the remote sensing image of the key time phase.
The calculation formulas of the green normalized vegetation index (GNDVI), the normalized vegetation index (NDVI), the Differential Vegetation Index (DVI), the crop Nitrogen Reaction Index (NRI), the vegetation index for regulating the soil brightness (OSAVI), the vegetation attenuation index (PSRI), the Ratio Vegetation Index (RVI), the soil regulating vegetation index (SAVI) and the structure enhancing pigment vegetation index (SIPI) are respectively shown in the following formulas (1) to (9):
GNDVI＝(B4-B2)/(B4+B2) (1)
NDVI＝(B4-B2)/(B4+B2) (2)
DVI＝(B4-B3)/(B4+B3) (3)
NRI＝(B2-B3)/(B2+B3) (4)
OSAVI＝(1+0.16)×B4-B3)/(B4+B3+0.16) (5)
PSRI＝(B3-B1)/B4 (6)
RVI＝B4/B3 (7)
SAVI＝(B4-B3)/(B4+B3+0.5)×(1+0.5) (8)
SIPI＝(B4+B1)/(B4-B1) (9)
wherein, B1, B2, B3 and B4 respectively represent blue wave band, green wave band, red wave band and near infrared wave band of the remote sensing image.
S300, obtaining actual measurement yield data, and respectively constructing regression models of each vegetation index and the actual measurement yield data;
the step S300 specifically includes:
s301, checking actually measured yield points one by one, and screening out actually measured yield error points to obtain actually measured yield data;
in this step, the actual measurement yield refers to uniformly selecting a sampling plot of the crop to be estimated in the region to be estimated and performing actual measurement by actual cutting, thereby obtaining the actual yield of the sampling plot, i.e. the actual measurement yield. Because errors, such as yield recording errors, positioning longitude and latitude deviations and the like, exist in the actual measurement process of actual cutting, the actual measurement yield with abnormal numerical value and abnormal positioning is screened out. When the actually measured output points are checked one by one, the actual measurement points are overlapped with the remote sensing images and the space distribution data of the land parcels, and if the positions of the actual measurement points are not in the corn land parcels, such as on roads or other types of land parcels, the actual measurement points are screened out.
S302, respectively constructing regression models of each vegetation index of the key time phase and the measured yield data.
Regression models of various multi-vegetation indexes and measured yield data of key time phases of crops are as follows:
Y＝a gndvi X gndvi +Z gndvi (10)
Y＝a ndvi X ndvi +Z ndvi (11)
Y＝a dvi X dvi +Z dvi (12)
Y＝a nri X nri +Z nri (13)
Y＝a osavi X osavi +Z osavi (14)
Y＝a psri X psri +Z psri (15)
Y＝a rv X rvi +Z rvi (16)
Y＝a savi X savi +Z savi (17)
Y＝a sipi X sipi +Z sipi (18)
wherein Y represents real-test point yield data, a gndvi ,…,a sipi Representing regression equation coefficients, X gndvi ,…,X sipi Representing the index data of each vegetation, Z gndvi ,…,Z sipi Representing an error term.
S400, sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period, and screening out the optimal vegetation indexes of the key time phases;
using the goodness of fit of the model (R 2 ) Respectively evaluating regression models of crop key time phase vegetation indexes and yield;
wherein y is i Andthe measured yield and the estimated yield, respectively, n being the sample size,>is the average of the measured yields.
Further, 3-5 preferable vegetation indexes which can reflect the growth state of crops in a key time phase of the crops are screened out according to the fitting goodness;
considering that the estimated yield model of a single parameter is poor in stability, the vegetation indexes with small correlation with the measured yield may be introduced due to excessive parameters, so that 3-5 vegetation indexes are preferable as the preferable vegetation indexes in the embodiment.
Specifically, according to the goodness of fit (R 2 ) And arranging from the big order to the small order, and selecting the vegetation index corresponding to the first 3-5 bits as the preferable vegetation index of the key time phase. For example, when the first 5 bits are selected as the preferred vegetation Index, index1, index2, index3, index4, and Index5, respectively; when the first 4 bits are selected as the preferred vegetation Index, index1, index2, index3, and Index4, respectively; when the first 3 bits are selected as the preferred vegetation Index, index1, index2, and Index3, respectively.
Further, preferred vegetation indices for which the first 3 bits are selected as key phases are Index1, index2, and Index3, respectively.
The indexes have higher correlation with the yield, and can better reflect the growth state and yield change of crops, so Index1, index2 and Index3 are preferable vegetation indexes.
S500, constructing an estimated yield model based on the optimal vegetation index and the actually measured yield data of the key time phase, and estimating the yield of crops.
Specifically, an estimated yield model of a crop key time phase preferred vegetation Index is constructed by using the obtained Index1, index2 and Index3 and is represented by a formula (20);
Yield＝b 1 Index1+b 2 Index2+b 3 Index3+Z (20)
wherein Yield represents the final Yield of the model simulation, b 1 、b 2 、b 3 Represents the preferred vegetation Index contribution coefficient, index1, index2, index3 represent the preferred vegetation Index when the crop is critical, and Z represents the error term.
And (3) rapidly calculating the regional crop yield distribution result by using the obtained yield estimation model based on the key time phase optimal vegetation index, and drawing and outputting.
Referring to fig. 3, a detailed flowchart of a method for estimating crop yield according to an embodiment of the present application is provided, wherein an operation process of the method includes:
the first stage: determining a key time phase of a remote sensing image used for estimating crop to be estimated, and acquiring the remote sensing image of the key time phase; the key time phase remote sensing image needs to have a blue wave band, a green wave band, a red wave band and a near infrared wave band.
The second stage, based on the remote sensing image of the key time phase, calculating a plurality of vegetation indexes of the remote sensing image of the key time phase; the plant indexes are respectively green normalized plant index (GNDVI), normalized plant index (NDVI), differential plant index (DVI), crop Nitrogen Reaction Index (NRI), soil brightness adjusting plant index (OSAVI), plant attenuation index (PSRI), ratio plant index (RVI), soil adjusting plant index (SAVI) and structure enhancing pigment plant index (SIPI), and the calculation formulas are respectively shown in formulas (1) to (9);
step four, obtaining measured yield data, and respectively constructing regression models of each vegetation index and the measured yield data; and the goodness of fit (R) of regression models to the measured yield data and the individual vegetation indices during the same growth period 2 ) Sorting, and screening out a preferred vegetation index of a key time phase; preferred vegetation indices with the first 3 bits as key phases are Index1, index2, index3, respectively.
And a fifth stage, constructing an estimated yield model based on the critical time phase preferred vegetation index and the measured yield data, and estimating the yield of crops to be estimated in the area. And constructing an estimated yield model of the crop critical time phase preferred vegetation Index by using the obtained Index1, index2 and Index3, and determining the yield of the crop as shown in a formula (20).
Referring to fig. 4, fig. 4 is a block diagram illustrating an apparatus 400 for estimating crop yield according to an embodiment of the present application. The block diagram of fig. 4 will be described, and the apparatus includes:
a determining unit 410, configured to determine a key time phase of a remote sensing image for estimating the crop to be estimated based on the key season of the crop to be estimated;
an obtaining unit 420, configured to obtain a remote sensing image of the key time phase, and calculate a plurality of vegetation indexes of the remote sensing image of the key time phase;
the model building unit 430 is configured to obtain measured yield data, and build regression models of the vegetation indexes and the measured yield data respectively;
a screening unit 440, configured to sort the goodness of fit of regression models of the vegetation indexes and the measured yield data in the same growth period, and screen out the preferred vegetation indexes of the key time phase;
and an estimating unit 450 for constructing an estimating model based on the preferred vegetation index and the measured yield data of the key time phase, and estimating the yield of the crop.
For the process of implementing the respective functions of the functional units in this embodiment, please refer to the content described in the embodiment shown in fig. 2, which is not described herein again.
Furthermore, the embodiments of the present application also provide a storage medium in which a computer program is stored, which when run on a computer causes the computer to perform the method provided in any of the embodiments of the present application.
In summary, the method, the device, the electronic equipment and the storage medium for estimating crop yield according to the embodiments of the present application, where the method includes: determining a key time phase remote sensing image of the crop to be estimated based on the key waiting period of the crop to be estimated; acquiring the key time phase remote sensing image and determining a plurality of vegetation indexes of the key time phase; respectively constructing regression models of all vegetation indexes of the key time phases based on the measured yield data; sequencing the output in the same growing period and the fitting goodness of regression models of all vegetation indexes, and screening out the optimal vegetation indexes of the key time phase; and constructing an estimated yield model based on the critical time phase preferred vegetation index and the actual measured yield data, and estimating the yield of crops.
The method is based on remote sensing data, combines with crop growth characteristics, constructs the regional crop yield estimation model by crop key weather analysis and combining with optimal vegetation indexes and actual measurement data, can be used for rapid regional yield estimation, ensures that regional crop yield estimation is quicker and more accurate, has wide development application range, high precision, low running cost and short estimated yield period, and is easy to popularize and use in a large scale.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The invention will be further described with reference to specific examples, which are not to be construed as limiting the scope of the invention, but rather as falling within the scope of the invention, since numerous insubstantial modifications and adaptations of the invention will now occur to those skilled in the art in light of the foregoing disclosure.
The invention will be described in further detail below with reference to the accompanying drawings and detailed description.
Examples
A spring corn rapid yield estimation method based on a preferred vegetation index specifically comprises the following steps:
and step one, combining spectral feature analysis of the county spring corns to determine key climatic periods for estimating the yield of the spring corns, wherein the climatic periods are shown in table 1.
TABLE 1 spring maize waiting period
As can be seen from table 1, the county spring corn is sown in the late 4 months and emerges in the late 5 months, the spectrum characteristic is bare land information, and the 6 month jointing period begins to enter the vigorous growth stage, so that the spectral characteristic of vegetation is met; the flowering period and the maturing period from the middle ten days of 7 months to the late ten days of 7 months belong to the stage of vegetation growth exuberance, and have typical vegetation spectral characteristics; the vegetation enters the mature period from the milk mature period in the early period of 8 months to 9 months and also belongs to the vigorous growth period, and has typical vegetation spectral characteristics. In summary, the beginning of 7 to 9 months is the key climate period for estimating the yield of spring corn.
Therefore, the key time phase of the county spring corn estimated production remote sensing data is finally determined to be 7 months and 30 days by combining the spectral characteristic analysis and the regional climate analysis of the spring corn and the availability of the remote sensing data.
Step two, acquiring a key time phase remote sensing image and preprocessing the key time phase remote sensing image;
in this embodiment, the satellite image of county HJ-1 of day 7 and 30 is obtained for preprocessing, the multispectral image wave bands are near infrared, red, green and blue, the image is subjected to radiation calibration and FLAASH atmospheric correction preprocessing, and then the Landsat/TM 30 m orthographic image is used as a reference image for geometric fine correction, wherein the correction precision is 0.5-1 pixel in the plain area, so that the geometric position of the image is ensured to be accurate.
Step three, calculating a plurality of vegetation indexes capable of reflecting the growth and development states of crops for the preprocessed remote sensing images;
calculating vegetation indexes capable of reflecting the growth and development states of spring corns on the preprocessed images, wherein the vegetation indexes are respectively as follows: the calculation formulas of the green normalized vegetation index (GNDVI), the normalized vegetation index (NDVI), the Difference Vegetation Index (DVI), the crop Nitrogen Reaction Index (NRI), the vegetation index for adjusting the soil brightness (OSAVI), the vegetation attenuation index (PSRI), the Ratio Vegetation Index (RVI), the Soil Adjustment Vegetation Index (SAVI) and the structure-enhanced pigment vegetation index (SIPI) are shown in (1) to (9).
Step four, constructing a spring corn key time phase vegetation index optimization model;
(1) And (3) checking and screening yield data of actual measurement points, analyzing data distribution rationality, crop variety correctness and the like, and eliminating unreasonable data.
(2) And constructing a regression model of the spring corn key time phase vegetation index and the actual measurement yield.
And (5) establishing a regression model by respectively calculating 9 vegetation indexes and actual measurement yields of the key time phase images. Goodness of fit R to yield and index models in the same growth period 2 Ranking was performed when the goodness of fit (R 2 ) The model input vegetation index at the first 3 positions of the maximum value of the period is the optimal vegetation index of the key time phase of spring corn. The preferred vegetation index for this period is NRI, RVI, SIPI;
fifthly, constructing a regression model by utilizing the critical time phase optimal vegetation index and the actual measurement data, obtaining the whole-area crop yield data and drawing, and obtaining a final estimated yield model as follows:
Y＝863.7439NRI+372.645RVI+1398.564PSRI+779.231 (21)
the root mean square error of the model is 18.93, and the regression coefficient of the model is 0.74, which shows that the model has higher precision and higher reliability.
Obtaining a county spring corn yield area distribution diagram from the yield estimation model, wherein the specific yield distribution of the county spring corn is shown in fig. 5a and 5b, and obtaining the average estimated yield of the county 2019 spring corn as 861.39 kg/mu.
The crop yield estimation method can realize the estimation of the crop yield in a large area in a region by only using the remote sensing image and the actually measured yield data, and the data is easy to obtain, strong in operability and quick and convenient.
The present invention is not limited to the above-mentioned embodiments, but is intended to be limited to the following embodiments, and any modifications, equivalents and modifications can be made to the above-mentioned embodiments without departing from the scope of the invention.

Claims (9)

1. A method for estimating crop yield, comprising the steps of:
determining a key time phase of a remote sensing image for estimating the crop to be estimated based on the key waiting period of the crop to be estimated; comprising the following steps:
selecting a research area of crops to be estimated, and determining the crop weathers and characteristics thereof by combining the weathers of the crops to be estimated in the research area;
based on different growth stages of crops, screening out periods in which crops grow vigorously and obvious vegetation information can be observed on remote sensing images, and determining key climatic periods for estimating crop yield;
determining a key time phase of a remote sensing image for estimating crop yield to be estimated based on the key climatic period of crop yield estimation;
acquiring a remote sensing image of the key time phase, and calculating a plurality of vegetation indexes of the remote sensing image of the key time phase;
obtaining measured yield data, and respectively constructing regression models of each vegetation index and the measured yield data;
sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period, and screening out the optimal vegetation indexes of the key time phases;
and constructing an estimated yield model based on the optimal vegetation index and the actually measured yield data of the key time phase, and estimating the yield of crops.
2. The method of estimating crop yield according to claim 1 wherein obtaining the remote sensing image of the key time phase and calculating a plurality of vegetation indices of the remote sensing image of the key time phase comprises:
after acquiring a remote sensing image of a key time phase of a crop to be estimated, preprocessing the remote sensing image;
and calculating the preprocessed remote sensing image of the key time phase to obtain a plurality of vegetation indexes of the remote sensing image of the key time phase.
3. A method of assessing crop yield as claimed in claim 2 wherein the pre-treatment comprises: radiometric calibration, atmospheric correction, geometric fine correction and image registration; the atmosphere correction is performed by using a FLAASH atmosphere correction model.
4. The method of estimating crop yield according to claim 2 wherein said plurality of vegetation indices comprises: the plant growth regulator comprises a green normalized plant index, a difference plant index, a crop nitrogen response index, a plant index for regulating soil brightness, a plant attenuation index, a ratio plant index, a soil regulating plant index and a structure reinforcing pigment plant index.
5. The method of estimating crop yield according to claim 1, wherein obtaining measured yield data, constructing regression models of each vegetation index and the measured yield data, respectively, comprises:
checking the actually measured yield points one by one, and screening out error points of the actually measured yield to obtain actually measured yield data;
and respectively constructing regression models of each vegetation index of the key time phase and the measured yield data.
6. The method of estimating crop yield according to claim 1 wherein ranking the goodness of fit of regression models of individual vegetation indices and measured yield data over the same growth period, screening out preferred vegetation indices for key time phases comprises:
respectively evaluating regression models of each vegetation index and measured yield data of the key time phase of crops by adopting the fitting goodness of the models;
3-5 preferable vegetation indexes which can reflect the growth state of crops are screened out according to the fitting goodness.
7. An apparatus for estimating crop yield, the apparatus comprising:
the determining unit is used for determining a key time phase of a remote sensing image used for estimating the crop to be estimated based on the key waiting period of the crop to be estimated; the determining step comprises the following steps:
selecting a research area of crops to be estimated, and determining the crop weathers and characteristics thereof by combining the weathers of the crops to be estimated in the research area;
based on different growth stages of crops, screening out periods in which crops grow vigorously and obvious vegetation information can be observed on remote sensing images, and determining key climatic periods for estimating crop yield;
determining a key time phase of a remote sensing image for estimating crop yield to be estimated based on the key climatic period of crop yield estimation;
the acquisition unit is used for acquiring the remote sensing image of the key time phase and calculating a plurality of vegetation indexes of the remote sensing image of the key time phase;
the model construction unit is used for acquiring the actual measurement yield data and respectively constructing regression models of each vegetation index and the actual measurement yield data;
the screening unit is used for sequencing the fitting goodness of regression models of all vegetation indexes and measured yield data in the same growing period and screening out the optimal vegetation indexes of the key time phases;
and the yield estimation unit is used for constructing a yield estimation model based on the optimal vegetation index and the actually measured yield data of the key time phase and estimating the yield of the crops.
8. An electronic device comprising a memory and a processor, the memory having stored therein computer program instructions which, when read and executed by the processor, perform the steps of the method of any of claims 1-6.
9. A storage medium having stored thereon computer program instructions which, when read and executed by a computer, perform the steps of the method according to any of claims 1-6.
CN202111078078.1A 2021-09-15 2021-09-15 Crop yield estimation method, device, electronic equipment and storage medium Active CN113743819B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111078078.1A CN113743819B (en) 2021-09-15 2021-09-15 Crop yield estimation method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111078078.1A CN113743819B (en) 2021-09-15 2021-09-15 Crop yield estimation method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113743819A CN113743819A (en) 2021-12-03
CN113743819B true CN113743819B (en) 2024-03-26

Family

ID=78738888

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111078078.1A Active CN113743819B (en) 2021-09-15 2021-09-15 Crop yield estimation method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113743819B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510528B (en) * 2022-02-15 2023-11-17 平安科技（深圳）有限公司 Crop yield display method, device electronic equipment and storage medium
CN116579521B (en) * 2023-05-12 2024-01-19 中山大学 Yield prediction time window determining method, device, equipment and readable storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101480143A (en) * 2009-01-21 2009-07-15 华中科技大学 Method for predicating single yield of crops in irrigated area
CN104123409A (en) * 2014-07-09 2014-10-29 江苏省农业科学院 Field winter wheat florescence remote sensing and yield estimating method
KR101822410B1 (en) * 2016-07-22 2018-01-29 아인정보기술 주식회사 Apparatus for diagnosing growth state of crop organ using crop organ image
CN108363949A (en) * 2017-12-27 2018-08-03 二十世纪空间技术应用股份有限公司 A kind of cotton remote-sensing monitoring method based on phenology analysis
CN110243406A (en) * 2019-06-21 2019-09-17 武汉思众空间信息科技有限公司 Crop Estimation Method, device, electronic equipment and storage medium
CN111241912A (en) * 2019-12-18 2020-06-05 安徽易刚信息技术有限公司 Multi-vegetation index rice yield estimation method based on machine learning algorithm
CN111798327A (en) * 2020-06-24 2020-10-20 安徽大学 Construction method and application of wheat yield calculation model based on hyperspectral image
CN112345458A (en) * 2020-10-22 2021-02-09 南京农业大学 Wheat yield estimation method based on multispectral image of unmanned aerial vehicle
CN112881327A (en) * 2021-01-25 2021-06-01 安徽皖南烟叶有限责任公司 Tobacco leaf SPAD value estimation method based on novel vegetation index
CN113052433A (en) * 2021-02-22 2021-06-29 中国科学院空天信息创新研究院 Crop yield per unit estimation method based on key time phase and farmland landscape characteristic parameters
CN113223040A (en) * 2021-05-17 2021-08-06 中国农业大学 Remote sensing-based banana yield estimation method and device, electronic equipment and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11935242B2 (en) * 2020-03-09 2024-03-19 International Business Machines Corporation Crop yield estimation

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101480143A (en) * 2009-01-21 2009-07-15 华中科技大学 Method for predicating single yield of crops in irrigated area
CN104123409A (en) * 2014-07-09 2014-10-29 江苏省农业科学院 Field winter wheat florescence remote sensing and yield estimating method
KR101822410B1 (en) * 2016-07-22 2018-01-29 아인정보기술 주식회사 Apparatus for diagnosing growth state of crop organ using crop organ image
CN108363949A (en) * 2017-12-27 2018-08-03 二十世纪空间技术应用股份有限公司 A kind of cotton remote-sensing monitoring method based on phenology analysis
CN110243406A (en) * 2019-06-21 2019-09-17 武汉思众空间信息科技有限公司 Crop Estimation Method, device, electronic equipment and storage medium
CN111241912A (en) * 2019-12-18 2020-06-05 安徽易刚信息技术有限公司 Multi-vegetation index rice yield estimation method based on machine learning algorithm
CN111798327A (en) * 2020-06-24 2020-10-20 安徽大学 Construction method and application of wheat yield calculation model based on hyperspectral image
CN112345458A (en) * 2020-10-22 2021-02-09 南京农业大学 Wheat yield estimation method based on multispectral image of unmanned aerial vehicle
CN112881327A (en) * 2021-01-25 2021-06-01 安徽皖南烟叶有限责任公司 Tobacco leaf SPAD value estimation method based on novel vegetation index
CN113052433A (en) * 2021-02-22 2021-06-29 中国科学院空天信息创新研究院 Crop yield per unit estimation method based on key time phase and farmland landscape characteristic parameters
CN113223040A (en) * 2021-05-17 2021-08-06 中国农业大学 Remote sensing-based banana yield estimation method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN113743819A (en) 2021-12-03

Similar Documents

Publication Publication Date Title
Fang et al. Integration of MODIS LAI and vegetation index products with the CSM–CERES–Maize model for corn yield estimation
CN110309985B (en) Crop yield prediction method and system
CN113743819B (en) Crop yield estimation method, device, electronic equipment and storage medium
US10564316B2 (en) Forecasting national crop yield during the growing season
Li et al. Estimating winter wheat (Triticum aestivum) LAI and leaf chlorophyll content from canopy reflectance data by integrating agronomic prior knowledge with the PROSAIL model
CN109711102B (en) Method for rapidly evaluating crop disaster loss
CN111798327A (en) Construction method and application of wheat yield calculation model based on hyperspectral image
Liu et al. Quantitative analysis and hyperspectral remote sensing of the nitrogen nutrition index in winter wheat
Zhang et al. Estimating wheat yield by integrating the WheatGrow and PROSAIL models
EP3719722A1 (en) Forecasting national crop yield during the growing season
CN111044516B (en) Remote sensing estimation method for chlorophyll content of rice
CN114120132A (en) Crop yield estimation method and device combining meteorological remote sensing and red-edge wave band remote sensing
CN108520127A (en) A kind of EO-1 hyperion inversion method of seeds leaf area index
CN110647932B (en) Planting crop structure remote sensing image classification method and device
CN111829957A (en) System and method for inverting moisture content of winter wheat plants based on multispectral remote sensing of unmanned aerial vehicle
CN113553697B (en) Long-time-sequence multi-source data-based vegetation disturbance analysis method for coal mining
CN113591631A (en) Crop yield estimation method based on multi-source data
Warren et al. Agricultural applications of high-resolution digital multispectral imagery
Jeong et al. Application of an unmanned aerial system for monitoring paddy productivity using the GRAMI-rice model
CN115759524B (en) Soil productivity grade identification method based on remote sensing image vegetation index
CN115545311A (en) Crop yield estimation method and device, storage medium and electronic equipment
CN113298859A (en) Crop nitrogen fertilizer variable management method based on unmanned aerial vehicle image
US11762125B2 (en) Forecasting national crop yield during the growing season
Li et al. Monitoring of leaf nitrogen content of winter wheat using multi-angle hyperspectral data
CN110321774B (en) Crop disaster situation evaluation method, device, equipment and computer readable storage medium

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