CN115600771A - Crop yield estimation method, device, equipment and storage medium - Google Patents
Crop yield estimation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115600771A CN115600771A CN202211576177.7A CN202211576177A CN115600771A CN 115600771 A CN115600771 A CN 115600771A CN 202211576177 A CN202211576177 A CN 202211576177A CN 115600771 A CN115600771 A CN 115600771A
- Authority
- CN
- China
- Prior art keywords
- index data
- leaf area
- area index
- model
- growth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000012010 growth Effects 0.000 claims abstract description 224
- 238000010168 coupling process Methods 0.000 claims abstract description 22
- 230000008878 coupling Effects 0.000 claims abstract description 18
- 238000005859 coupling reaction Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 69
- 238000012549 training Methods 0.000 claims description 56
- 238000005070 sampling Methods 0.000 claims description 40
- 238000012544 monitoring process Methods 0.000 claims description 28
- 238000004088 simulation Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000003698 anagen phase Effects 0.000 claims 2
- 230000001808 coupling effect Effects 0.000 abstract description 6
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000001914 filtration Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 13
- 230000035945 sensitivity Effects 0.000 description 8
- 230000035558 fertility Effects 0.000 description 7
- 238000005259 measurement Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000009395 breeding Methods 0.000 description 4
- 230000001488 breeding effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 240000007594 Oryza sativa Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 238000010206 sensitivity analysis Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 235000013339 cereals Nutrition 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- 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 method, a device, equipment and a storage medium for estimating crop yield, which relate to the technical field of agricultural remote sensing and comprise the following steps: acquiring multi-dimensional parameter information and remote sensing data of a region to be detected; inputting the multi-dimensional parameter information into a crop growth model to obtain simulated leaf area index data output by the crop growth model; carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on the weight of the growth period corresponding to different growth periods to obtain assimilation leaf area index data; and inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model. According to the method, the leaf area index data are used as the assimilation quantity in the assimilation coupling process, the divergence phenomenon is avoided, the assimilation coupling processing is performed on the remote sensing data and the simulated leaf area index data by combining the weight coefficient of each growth period, the assimilation coupling effect of the crop model and the remote sensing data is effectively improved, and the accuracy of crop yield evaluation is further improved.
Description
Technical Field
The invention relates to the technical field of agricultural remote sensing, in particular to a crop yield estimation method, a crop yield estimation device, crop yield estimation equipment and a storage medium.
Background
Assimilation of crop models with remote sensing data for crop growth monitoring and yield estimation has become a reliable method of crop growth research. The mechanism characteristics of the crop model can dynamically provide day-to-day growth information; the timeliness of the remote sensing data ensures that the crop model is consistent with the actual production process in the simulation process.
At present, an assimilation algorithm combining a coupled crop growth model and remote sensing data mainly comprises a variation algorithm and a filtering algorithm, wherein the variation method is used for assimilating observed values into a simulation process according to background errors and observation errors, however, the variation method cannot be embodied in the assimilation process, the influence of different key growth periods of crops corresponding to various assimilation nodes can possibly cause lower accuracy of assimilation results. The filtering algorithm calculates the probability distribution of the prediction result by integrating a plurality of groups of analog values and observation values, and finally obtains a good prediction value, but the filtering algorithm may have the problem of filter divergence, so that severe oscillation occurs in the simulation process, and the accuracy of crop yield estimation is low.
Disclosure of Invention
The invention provides a crop yield estimation method, a device, equipment and a storage medium, aiming at improving the accuracy of crop yield estimation.
The invention provides a crop yield estimation method, which comprises the following steps:
acquiring multi-dimensional parameter information and remote sensing data of a region to be detected;
inputting the multi-dimensional parameter information into a crop growth model to obtain simulated leaf area index data output by the crop growth model;
carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on the weight of the growth period corresponding to different growth periods to obtain assimilation leaf area index data;
the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period;
and inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
According to the crop yield estimation method provided by the invention, the growth period weights corresponding to different growth periods are determined based on the following steps:
obtaining historical crop yield of the crops in the area to be detected and historical monitoring data of different growth periods;
constructing a yield prediction model corresponding to each growth period based on the historical crop yield and the historical monitoring data of different growth periods;
and fusing the yield prediction models corresponding to the growth periods by using a preset weight optimization algorithm to obtain a growth period weight coefficient of each yield prediction model.
According to the crop yield estimation method provided by the invention, the assimilation coupling processing is performed on the remote sensing data and the simulated leaf area index data based on the growth period weights corresponding to different growth periods to obtain the assimilation leaf area index data, and the method comprises the following steps:
carrying out inversion processing on the remote sensing data to obtain inversion leaf area index data;
and calculating to obtain the assimilation leaf area index data by utilizing a preset assimilation algorithm based on the weight of each growth period, the inversion leaf area index data and the simulation leaf area index data.
According to the crop yield estimation method provided by the invention, the assimilation leaf area index data is calculated by using a preset assimilation algorithm based on the weight of each growth period, the inversion leaf area index data and the simulation leaf area index data, and the method comprises the following steps:
constructing an observation operator in the preset assimilation algorithm based on each growth period weight;
and utilizing a preset assimilation algorithm of a newly-constructed observation operator to assimilate the inversion leaf area index data and the simulation leaf area index data to obtain the assimilation leaf area index data.
According to the crop yield estimation method provided by the invention, the inversion processing is performed on the remote sensing data to obtain the inversion leaf area index data, and the inversion leaf area index data comprises the following steps:
calculating to obtain vegetation index data of each sampling point based on the remote sensing data;
inputting the vegetation index data of each sampling point into an inversion model to obtain inversion leaf area index data output by the inversion model;
the inversion model is obtained by performing iterative training based on historical remote sensing data and measured leaf area index data of each training sampling point.
According to the crop yield estimation method provided by the invention, the inversion model is obtained by training based on the following steps:
acquiring historical remote sensing data and measured leaf area index data of each training sampling point;
calculating to obtain vegetation index data of each training sampling point based on the historical remote sensing data;
and performing iterative training on the initial regression model based on the vegetation index data and the actually measured leaf area index data of each training sampling point to obtain the inversion model.
According to the crop yield estimation method provided by the invention, the acquiring of the multi-dimensional parameter information of the region to be measured comprises the following steps:
obtaining a plurality of model parameter combinations;
and based on each model parameter combination and the actually measured leaf area index data, obtaining an optimized initial parameter combination of the crop growth model by utilizing a preset parameter optimization algorithm through iterative calculation, and taking the optimized initial parameter combination as the multi-dimensional parameter information.
The invention also provides a crop yield estimation device, comprising:
the acquisition module is used for acquiring multi-dimensional parameter information and remote sensing data of the area to be measured;
the simulation module is used for inputting the multidimensional parameter information to a crop growth model to obtain simulated leaf area index data output by the crop growth model;
the assimilation module is used for carrying out assimilation coupling processing on the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilation leaf area index data;
the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period;
and the yield estimation module is used for inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor executes the program to implement any of the crop yield estimation methods described above.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of crop yield estimation as described in any of the above.
According to the crop yield estimation method, the crop yield estimation device, the crop yield estimation equipment and the crop yield estimation storage medium, the leaf area index data are used as the assimilation quantity in the assimilation coupling process, the divergence phenomenon is avoided, the assimilation coupling processing is carried out on the remote sensing data and the simulated leaf area index data by combining the weight coefficient of each growth period, the influence of each growth period on the growth of crops can be accurately reflected, the assimilation coupling effect of the crop model and the remote sensing data is effectively improved, and the accuracy of crop yield estimation is further improved.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a method for estimating crop yield according to the present invention;
FIG. 2 is a schematic diagram of a crop yield estimation apparatus according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the invention. As used in one or more embodiments of the present invention, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present invention refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used herein to describe various information in one or more embodiments of the present invention, such information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present invention. The word "if" as used herein may be interpreted as "at \8230; \8230when" or "when 8230; \8230when", depending on the context.
FIG. 1 is a schematic flow chart of a method for estimating crop yield according to the present invention. As shown in fig. 1, the method for estimating crop yield comprises:
the multi-dimensional parameter information comprises meteorological data, soil data and crop parameters, the meteorological data comprises data such as solar radiation, highest daily temperature, lowest daily temperature, rainfall, relative daily humidity and average daily wind speed, and the crop parameters comprise parameters such as effective light energy utilization rate, specific leaf area, accumulated temperature and leaf distribution coefficient.
The remote sensing data comprise remote sensing image data corresponding to MODIS, MCD15, GLASS and Sentinel2, preferably, in the embodiment, L2A-level data of the Sentinel2 remote sensing image are selected, and the L2A-level data mainly comprise atmospheric bottom reflectivity data subjected to radiometric calibration and atmospheric correction.
the crop growth model is a process-oriented and mechanistic dynamic model, and can dynamically and quantitatively describe a series of physiological processes in crop growth, development, grain formation and yield formation processes, wherein the crop mechanism model comprises an MCWLA series model, a CERES series model, an APSIM model, a WOFOST model and the like. The crops may include corn, rice, wheat and soybean crops.
It should be further noted that before inputting the multidimensional parameter information into the crop growth model for simulation, calibration of crop parameters of the crop growth model is required, specifically, sensitivity analysis is performed on the crop growth model in the prediction area, for example: and realizing parameter global sensitivity analysis of the crop growth model by means of sensitivity and uncertainty professional analysis software Simlab. The parametric global sensitivity analysis is as follows: firstly, uniformly distributing all input parameters of a preset crop growth model in a value range, and further respectively and randomly sampling by utilizing a Monte Carlo method to obtain a plurality of model parameter combinations; then, inputting the generated model parameter combination into a crop growth model to obtain a simulated leaf area index corresponding to the model parameter combination; and finally, calculating the first-order sensitivity index and the total sensitivity index of each parameter in the model parameter combination by using an Extended Fourier Amplitude Sensitivity Test (EFAST), and determining the parameter with higher sensitivity and the parameter with lower sensitivity or insensitivity. Furthermore, for parameters with low or low sensitivity, a default value of the model can be used, and for parameters with high sensitivity, the optimal parameter combination is obtained by calibrating the actual measurement leaf area index data and the simulated leaf area index corresponding to the model parameter combination through an optimization algorithm, so that the optimal parameter combination is used as the multi-dimensional parameter information and substituted into the crop growth model to simulate the crop growth condition.
Specifically, the meteorological data, the soil data and the crop parameters in the multi-dimensional parameter information are input into the crop growth model, so as to determine the simulated leaf area index data according to the result output by the crop growth model.
the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period;
it should be noted that, first, according to the historical crop yield of the crop in the region to be measured and the historical monitoring data of any one growth period, a yield prediction model corresponding to each growth period is respectively constructed and obtained, and then, the coefficient proportion of the yield prediction model corresponding to each growth period in the whole growth period can be calculated, so that the growth period weights corresponding to different growth periods are obtained. Therefore, assimilation coupling treatment is carried out on growth period weights corresponding to different growth periods, and the coupling assimilation effect of the crop growth model and remote sensing data is greatly improved.
Specifically, the remote sensing data is firstly inverted to obtain inverted leaf area index data, optionally, a regression model between the vegetation index data and the leaf area index is pre-constructed, and then the vegetation index data corresponding to the remote sensing data is calculated, so that the vegetation index data corresponding to the remote sensing data is input into the regression model, and the inverted leaf area index data output by the regression model can be obtained.
Further, utilizing a preset assimilation algorithm to assimilate growth period weights corresponding to different growth periods and the inverted leaf area index data to a simulation process of a crop growth model, specifically, constructing an observation operator of the preset assimilation algorithm based on the growth period weights corresponding to the different growth periods, and further utilizing an assimilation algorithm of the newly constructed observation operator to assimilate the inverted leaf area index data and the simulated leaf area index data to obtain the assimilated leaf area index data, wherein the preset assimilation algorithm is an EnSRF filtering algorithm, the EnSRF is a deterministic filtering algorithm which does not disturb observation data, and the EnSRF filtering algorithm reserves an integrated prediction and estimation mode of a background error covariance in an aggregate filtering algorithm. When an observation operator of an assimilation algorithm is constructed, the influence of different growth periods of crops on the assimilation process is comprehensively considered, so that the coupling effect of the crop model and remote sensing data can be effectively improved.
And 14, inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
Specifically, the crop growth model is re-driven by the assimilation leaf area index data, and the crop yield estimation result of the region to be detected, which is output by the crop growth model, can be obtained.
According to the embodiment of the invention, the leaf area index data is used as the assimilation quantity in the assimilation coupling process, so that the phenomenon of violent oscillation in the simulation process is avoided, and the assimilation coupling processing is performed on the remote sensing data and the simulated leaf area index data by combining the weight coefficient of each growth period, so that the influence of each growth period on the growth of crops can be accurately reflected, the assimilation coupling effect of the crop model and the remote sensing data is effectively improved, and the accuracy of crop yield evaluation is further improved.
In an embodiment of the present invention, the assimilating and coupling the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilating leaf area index data includes: carrying out inversion processing on the remote sensing data to obtain inversion leaf area index data; and calculating to obtain the assimilation leaf area index data by utilizing a preset assimilation algorithm based on the weight of each growth period, the inversion leaf area index data and the simulation leaf area index data. Wherein, the assimilation leaf area index data is calculated by using a preset assimilation algorithm based on the weight of each growth period, the inversion leaf area index data and the simulation leaf area index data, and the method comprises the following steps: constructing an observation operator in the preset assimilation algorithm based on each growth period weight; and utilizing a preset assimilation algorithm of a newly constructed observation operator to assimilate the inversion leaf area index data and the simulation leaf area index data to obtain the assimilation leaf area index data.
It should be noted that the preset assimilation algorithm is an EnSRF filtering algorithm, the EnSRF filtering algorithm is a deterministic filtering algorithm for solving the problem of filter divergence in the EnKF Kalman filtering algorithm, the EnSRF filtering algorithm reserves an integrated simulation and estimation mode of background error covariance in the EnKF Kalman filtering algorithm, and an analytic equation is redefined. The analysis samples in the EnSRF filtering algorithm contain the mean value and the deviation of the samples, observation data do not need to be interfered, and the accuracy of the analysis error covariance is higher than that of the EnKF ensemble Kalman filtering algorithm. And a linearization standard observation operator is arranged in the EnSRF filtering algorithm.
Specifically, calculating vegetation index data of the remote sensing data, performing inversion processing on the vegetation index data of the remote sensing data by using a pre-constructed regression model between the vegetation index data and the leaf area index to obtain inverted leaf area index data, and further, in order to accurately reflect the influence of each growth stage on the growth of crops and improve the accuracy of an assimilation result, in this embodiment, a new observation operator of an EnSRF filter algorithm is constructed by combining weights of each growth stage, wherein the new observation operator in the EnSRF filter algorithm can be represented as G m =H m D m ，G m Representing a matrix of m x p, H m Expressing linearized standard viewsMeasure operator, m represents degree of freedom, by H m P represents the number of the growth periods and is controlled by Dm, wherein Dm represents a tangential mode from initial time integration to time m, and D is present in the weight of the growth period of each growth period m In the matrix, the observation operators can be projected to the space with the same number as the analog values. And then assimilating the inversion leaf area index data and the simulation leaf area index data by using a preset assimilation algorithm of a newly-constructed observation operator to obtain the assimilation leaf area index data.
According to the embodiment of the invention, the influence of different growth periods of crops on the assimilation process is further considered when the observation operator is constructed, so that the weight coefficient of each growth period in the observation operator on the assimilation coupling process is determined, the coupling effect of the crop model and the remote sensing data is effectively improved, and the accuracy of crop yield evaluation is improved.
In an embodiment of the present invention, the performing inversion processing on the remote sensing data to obtain inverted leaf area index data includes:
calculating vegetation index data of each sampling point based on the remote sensing data; inputting the vegetation index data of each sampling point into an inversion model to obtain inversion leaf area index data output by the inversion model; the inversion model is obtained by performing iterative training based on historical remote sensing data and measured leaf area index data of each training sampling point.
The Vegetation Index data includes NDVI (Normalized Vegetation Index), CI (Vegetation Index), SPEI (Normalized Precipitation Evapotranspiration Index), and other Vegetation Index data.
Specifically, calculating vegetation index data of each sampling point based on the remote sensing data, inputting the vegetation index data of each sampling point into an inversion model, and determining inversion leaf area index data of each sampling point according to a result output by the inversion model, wherein the inversion model is obtained by performing iterative training based on the vegetation index data of each training sampling point calculated by historical remote sensing data and the actually measured leaf area index data of each training sampling point, and understandably, learning a logistic regression relationship between the vegetation index data and the leaf area index data of each training sampling point by the inversion model, so that the vegetation index data of each sampling point calculated according to the remote sensing data is calculated by the inversion model to obtain the inversion leaf area index data.
In one embodiment, the inverse model is trained based on the following steps:
acquiring historical remote sensing data and actually measured leaf area index data of each training sampling point; calculating to obtain vegetation index data of each training sampling point based on the historical remote sensing data; and performing iterative training on the initial regression model based on the vegetation index data and the actually measured leaf area index data of each training sampling point to obtain the inversion model.
It should be noted that the inversion model is a model obtained by training a logistic regression algorithm.
Specifically, historical remote sensing data and actually measured leaf area index data of each training sampling point are obtained, vegetation index data of each training sampling point are obtained through calculation based on the historical remote sensing data, in the iterative training process, the vegetation index data of any training sampling point are input into an initial inversion model, a leaf area index predicted value output by the initial inversion model is obtained, a model loss value is obtained through calculation based on the leaf area index predicted value and the leaf area index data, then a base model loss value is obtained, the initial inversion model is subjected to parameter updating, model training is finished, then next model training is carried out until a preset training finishing condition is reached, and the inversion model is obtained, wherein the preset training finishing condition comprises loss convergence, a maximum iteration number threshold value and the like.
According to the embodiment of the invention, through the scheme, the inversion model is obtained by training the actual measurement leaf area index data based on the historical remote sensing data and each training sampling point, so that the inversion leaf area index data corresponding to the remote sensing data can be obtained through accurate inversion of the inversion model.
In one embodiment of the present invention, the birth period weights corresponding to different birth periods are determined based on the following steps:
obtaining historical crop yield of crops in the area to be detected and historical monitoring data of different growth periods; constructing a yield prediction model corresponding to each growth period based on the historical crop yield and the historical monitoring data of different growth periods; and fusing the yield prediction models corresponding to the growth periods by using a preset weight optimization algorithm to obtain a growth period weight coefficient of each yield prediction model.
It should be noted that the historical monitoring data of different growth periods refers to data that each growth period stage has an influence on crop yield, for example, data such as the stem number, height, and seed number of a crop, wherein the monitoring data corresponding to different growth periods are different.
Specifically, historical monitoring data corresponding to crops in the area to be tested in each growth period are obtained, historical crop yield of the crops in the area to be tested is obtained, iterative training is carried out according to the historical crop yield and the historical monitoring data of any growth period by using a logistic regression algorithm to obtain a yield prediction model corresponding to any growth period, and the specific training process of the model is as follows: inputting the historical monitoring data of the growth period into an initial prediction model to obtain a predicted value output by the initial prediction model, further calculating to obtain a loss value according to the predicted value and the historical crop yield, further updating model parameters in the model to be initially predicted based on the loss value, finishing the training process, and then performing the next training. And in the training process, judging whether the updated initial prediction model meets a preset training end condition, if so, taking the updated initial prediction model as a yield prediction model corresponding to the growth period, and if not, continuing to train the model.
As will be understood, it is assumed that the rice growth period includes the striking growth period, the jointing growth period, the heading growth period and the maturing growth period. For the green turning birth period, the historical monitoring data of the green turning birth period comprises stem number FQJS; for the birth control period, the historical monitoring data of the birth control period comprises height BJGD and stem number BJJS; for the heading breeding period, historical monitoring data of the heading breeding period comprise effective stem number CSYX and one-time branch number CSYC; for the mature fertility period, historical monitoring data for the mature fertility period includes high RSGD, total stem number RSZJ, and number of fruiting grains RSJS. And obtaining the historical crop yield CLSD of the rice.
Further, according to the historical monitoring data of different growth periods, respectively constructing yield prediction models corresponding to the growth periods, wherein the expression of the yield prediction models corresponding to the green turning growth period is as follows: CLSD = d × FQJS + e, and the expression of the yield prediction model corresponding to the birth control period is as follows: CLSD = f × BJGD + h × BJJS + i, and the expression of the yield prediction model corresponding to the heading breeding period is as follows: CLSD = j × CSYX + k × CSYC + l, and the expression of the yield prediction model corresponding to the mature fertility stage is: CLSD = m × RSGD + n × RSZJ + o × RSJS + p. Wherein d and e are model parameters of a yield prediction model corresponding to the green turning growth period; f. h and i are model parameters of a yield prediction model corresponding to the jointing growth period; j. k and l are model parameters of a yield prediction model corresponding to the heading growth period; and m, n, o and p are model parameters of a yield prediction model corresponding to the mature breeding period.
Further, based on the yield prediction models corresponding to the respective growth periods, a preset weight optimization algorithm is used for calculating and determining the coefficient ratio of the yield prediction models corresponding to the respective growth periods in the whole growth period, so as to construct and obtain the yield prediction models corresponding to the whole growth period, and the coefficient ratio of the yield prediction models corresponding to the respective growth periods is used as the growth period weight coefficient of the yield prediction models corresponding to the respective growth periods, wherein the preset weight optimization algorithm comprises algorithms such as a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, an ant colony algorithm and the like, and preferably, in the embodiment, the genetic algorithm is selected. For example, the yield prediction model for the entire growth period is as follows: f =0.0703 xf three leaves +0.012 × F seven leaves +0.460 xf joints +0.054 xf heading +0.183 xf milk maturity +0.226 xf maturity, where 0.0703 represents the fertility stage weight coefficient of the yield prediction model corresponding to the three-leaf fertility period and 0.226 represents the fertility stage weight coefficient of the yield prediction model corresponding to the maturity fertility period.
According to the embodiment of the invention, the regression model of each growth period and the crop yield is established firstly, and then the yield prediction model of the whole growth period is established through the genetic algorithm, so that the growth period weight coefficient of the yield prediction model corresponding to each growth period is obtained through calculation, and the growth period weight coefficient corresponding to each growth period is applied to the assimilation algorithm, so that the influence of each growth period on the crop growth is combined, and the coupling effect of the crop model and the remote sensing data is effectively improved.
In an embodiment of the present invention, the acquiring multidimensional parameter information of the region to be measured includes:
obtaining a plurality of model parameter combinations; and based on each model parameter combination and the actually measured leaf area index data, obtaining an optimized initial parameter combination of the crop growth model by iterative calculation of a preset parameter optimization algorithm, and taking the optimized initial parameter combination as the multi-dimensional parameter information.
It should be noted that the actually measured leaf area index data is leaf area index data obtained by performing on-site measurement on each training sampling point in the area to be measured in advance, and each training sampling point may be set according to an actual sampling condition, which is not limited specifically herein.
Specifically, actual measurement leaf area index data of each sampling point in the region to be measured is obtained, any model parameter combination is input into a crop growth model before assimilation coupling processing, a simulation value corresponding to any model parameter combination is obtained, a cost loss value is obtained through calculation based on the simulation value corresponding to any model parameter combination and the actual measurement leaf area index data, furthermore, a preset parameter optimization algorithm is used for obtaining an optimal parameter combination of the crop growth model through multiple iterative calculations with the aim of minimizing the cost loss value, the optimal parameter combination serves as multi-dimensional parameter information, and therefore the difference between the simulated leaf area index data obtained through simulation of the crop growth model and the actual measurement leaf area index data is the minimum, wherein the preset parameter optimization algorithm comprises methods such as an SCE-UA algorithm, a gradient descent algorithm and a Newton method, and preferably the SCE-UA algorithm is selected for model parameter optimization. And further, after multi-dimensional parameter information is obtained through calculation, the multi-dimensional parameter information is used for driving and operating the crop growth model.
According to the embodiment of the invention, the optimized initial parameter combination of the crop growth model is obtained by iterative calculation through the preset parameter optimization algorithm through the simulated value of the crop growth model and the actually measured leaf area index data, so that the operation model is driven by the optimized initial parameter combination during yield evaluation, and the accuracy of yield evaluation is improved.
The following describes the crop yield estimation apparatus provided by the present invention, and the crop yield estimation apparatus described below and the crop yield estimation method described above can be referred to correspondingly.
Fig. 2 is a schematic structural diagram of a crop yield estimation apparatus according to an embodiment of the present invention, as shown in fig. 2, the apparatus includes:
the acquisition module 21 is used for acquiring multi-dimensional parameter information and remote sensing data of a region to be detected;
the simulation module 22 is configured to input the multidimensional parameter information to a crop growth model to obtain simulated leaf area index data output by the crop growth model;
the assimilation module 23 is configured to perform assimilation coupling processing on the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilation leaf area index data;
the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the area to be tested and the historical monitoring data of any growth period;
and the yield estimation module 24 is configured to input the assimilation leaf area index data to the crop growth model to obtain a crop yield estimation result output by the crop growth model.
The crop yield estimation device further comprises:
obtaining historical crop yield of crops in the area to be detected and historical monitoring data of different growth periods;
constructing a yield prediction model corresponding to each growth period based on the historical crop yield and the historical monitoring data of different growth periods;
and fusing the yield prediction models corresponding to the growth periods by using a preset weight optimization algorithm to obtain a growth period weight coefficient of each yield prediction model.
The assimilation module 23 is further configured to:
carrying out inversion processing on the remote sensing data to obtain inversion leaf area index data;
and calculating to obtain the assimilation leaf area index data by using a preset assimilation algorithm based on the growth period weight, the inversion leaf area index data and the simulation leaf area index data.
The assimilation module 23 is further configured to:
constructing an observation operator in the preset assimilation algorithm based on the weight of each growth period;
and utilizing a preset assimilation algorithm of a newly constructed observation operator to assimilate the inversion leaf area index data and the simulation leaf area index data to obtain the assimilation leaf area index data.
The assimilation module 23 is further configured to:
calculating vegetation index data of each sampling point based on the remote sensing data;
inputting the vegetation index data of each sampling point into an inversion model to obtain inversion leaf area index data output by the inversion model;
the inversion model is obtained by performing iterative training based on historical remote sensing data and actually measured leaf area index data of each training sampling point.
The crop yield estimation device further comprises:
acquiring historical remote sensing data and actually measured leaf area index data of each training sampling point;
calculating to obtain vegetation index data of each training sampling point based on the historical remote sensing data;
and performing iterative training on the initial regression model based on the vegetation index data and the actually measured leaf area index data of each training sampling point to obtain the inversion model.
The obtaining module 21 is further configured to:
obtaining a plurality of model parameter combinations;
and based on each model parameter combination and the actually measured leaf area index data, obtaining an optimized initial parameter combination of the crop growth model by iterative calculation of a preset parameter optimization algorithm, and taking the optimized initial parameter combination as the multi-dimensional parameter information.
It should be noted that the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are not repeated herein.
Fig. 3 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor) 310, a memory (memory) 320, a communication Interface (Communications Interface) 330 and a communication bus 340, wherein the processor 310, the memory 320 and the communication Interface 330 communicate with each other via the communication bus 340. The processor 310 may invoke logic instructions in the memory 320 to perform a crop yield estimation method comprising: acquiring multi-dimensional parameter information and remote sensing data of a region to be detected; inputting the multi-dimensional parameter information into a crop growth model to obtain simulated leaf area index data output by the crop growth model; carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilation leaf area index data; the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period; and inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
In addition, the logic instructions in the memory 320 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement a method for estimating crop yield provided by the above methods, the method comprising: acquiring multi-dimensional parameter information and remote sensing data of a region to be detected; inputting the multi-dimensional parameter information into a crop growth model to obtain simulated leaf area index data output by the crop growth model; carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on the weight of the growth period corresponding to different growth periods to obtain assimilation leaf area index data; the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period; and inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present 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 may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
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 present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill 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 (10)
1. A method for estimating crop yield, comprising:
acquiring multi-dimensional parameter information and remote sensing data of a region to be detected;
inputting the multi-dimensional parameter information into a crop growth model to obtain simulated leaf area index data output by the crop growth model;
carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on the weight of the growth period corresponding to different growth periods to obtain assimilation leaf area index data;
the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period;
and inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
2. The method of claim 1, wherein the growth phase weights for different growth phases are determined based on the following steps:
obtaining historical crop yield of crops in the area to be detected and historical monitoring data of different growth periods;
constructing a yield prediction model corresponding to each growth period based on the historical crop yield and the historical monitoring data of different growth periods;
and fusing the yield prediction models corresponding to the growth periods by using a preset weight optimization algorithm to obtain a growth period weight coefficient of each yield prediction model.
3. The method for estimating crop yield according to claim 1, wherein the assimilating and coupling the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilating leaf area index data comprises:
carrying out inversion processing on the remote sensing data to obtain inversion leaf area index data;
and calculating to obtain the assimilation leaf area index data by using a preset assimilation algorithm based on the growth period weight, the inversion leaf area index data and the simulation leaf area index data.
4. The method of claim 3, wherein the step of calculating the assimilation leaf area index data based on the weight of each growth period, the inversion leaf area index data and the simulation leaf area index data by using a predetermined assimilation algorithm comprises:
constructing an observation operator in the preset assimilation algorithm based on each growth period weight;
and utilizing a preset assimilation algorithm of a newly-constructed observation operator to assimilate the inversion leaf area index data and the simulation leaf area index data to obtain the assimilation leaf area index data.
5. The crop yield estimation method according to claim 3, wherein the inverting the remote sensing data to obtain inverted leaf area index data comprises:
calculating vegetation index data of each sampling point based on the remote sensing data;
inputting the vegetation index data of each sampling point into an inversion model to obtain inversion leaf area index data output by the inversion model;
the inversion model is obtained by performing iterative training based on historical remote sensing data and actually measured leaf area index data of each training sampling point.
6. The crop yield estimation method according to claim 5, wherein the inverse model is trained based on the following steps:
acquiring historical remote sensing data and actually measured leaf area index data of each training sampling point;
calculating to obtain vegetation index data of each training sampling point based on the historical remote sensing data;
and performing iterative training on the initial regression model based on the vegetation index data and the actually measured leaf area index data of each training sampling point to obtain the inversion model.
7. The method according to claim 6, wherein the obtaining the multi-dimensional parameter information of the area to be measured comprises:
obtaining a plurality of model parameter combinations;
and based on each model parameter combination and the actually measured leaf area index data, obtaining an optimized initial parameter combination of the crop growth model by utilizing a preset parameter optimization algorithm through iterative calculation, and taking the optimized initial parameter combination as the multi-dimensional parameter information.
8. An apparatus for estimating crop yield, comprising:
the acquisition module is used for acquiring multi-dimensional parameter information and remote sensing data of the area to be measured;
the simulation module is used for inputting the multidimensional parameter information to a crop growth model to obtain simulated leaf area index data output by the crop growth model;
the assimilation module is used for carrying out assimilation coupling treatment on the remote sensing data and the simulated leaf area index data based on growth period weights corresponding to different growth periods to obtain assimilation leaf area index data;
the growth period weights corresponding to different growth periods are obtained by calculation based on yield prediction models corresponding to the growth periods, and the yield prediction model corresponding to any growth period is obtained by performing iterative training based on the historical crop yield of the crops in the region to be detected and the historical monitoring data of any growth period;
and the yield estimation module is used for inputting the assimilation leaf area index data into the crop growth model to obtain a crop yield estimation result output by the crop growth model.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executed on the processor, wherein the processor executes the program to perform the method of crop yield estimation according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the method for crop yield estimation according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576177.7A CN115600771A (en) | 2022-12-09 | 2022-12-09 | Crop yield estimation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576177.7A CN115600771A (en) | 2022-12-09 | 2022-12-09 | Crop yield estimation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115600771A true CN115600771A (en) | 2023-01-13 |
Family
ID=84852723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211576177.7A Pending CN115600771A (en) | 2022-12-09 | 2022-12-09 | Crop yield estimation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600771A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485040A (en) * | 2023-06-13 | 2023-07-25 | 中国农业大学 | Seed vitality prediction method, system, electronic equipment and storage medium |
| CN116579521A (en) * | 2023-05-12 | 2023-08-11 | 中山大学 | Yield prediction time window determining method, device, equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651096A (en) * | 2012-04-28 | 2012-08-29 | 中国农业大学 | Method for estimating yield of winter wheat by assimilating characteristics of leaf area index time-sequence curve |
| CN111598243A (en) * | 2020-04-30 | 2020-08-28 | 中国科学院空天信息创新研究院 | Leaf area index inversion model based on SAR and WFV data |
| CN112183428A (en) * | 2020-10-09 | 2021-01-05 | 浙江大学中原研究院 | Wheat planting area segmentation and yield prediction method |
| CN113361191A (en) * | 2021-05-24 | 2021-09-07 | 中国科学院空天信息创新研究院 | Pixel scale winter wheat yield remote sensing estimation method based on multi-scenario simulation |
| US20220061236A1 (en) * | 2020-08-25 | 2022-03-03 | The Board Of Trustees Of The University Of Illinois | Accessing agriculture productivity and sustainability |
-
2022
- 2022-12-09 CN CN202211576177.7A patent/CN115600771A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651096A (en) * | 2012-04-28 | 2012-08-29 | 中国农业大学 | Method for estimating yield of winter wheat by assimilating characteristics of leaf area index time-sequence curve |
| CN111598243A (en) * | 2020-04-30 | 2020-08-28 | 中国科学院空天信息创新研究院 | Leaf area index inversion model based on SAR and WFV data |
| US20220061236A1 (en) * | 2020-08-25 | 2022-03-03 | The Board Of Trustees Of The University Of Illinois | Accessing agriculture productivity and sustainability |
| CN112183428A (en) * | 2020-10-09 | 2021-01-05 | 浙江大学中原研究院 | Wheat planting area segmentation and yield prediction method |
| CN113361191A (en) * | 2021-05-24 | 2021-09-07 | 中国科学院空天信息创新研究院 | Pixel scale winter wheat yield remote sensing estimation method based on multi-scenario simulation |
Non-Patent Citations (2)
| Title |
|---|
| 刘可群 等: "江汉平原水稻长势遥感监测及估产模型", 《华中师范大学学报（自然科学版）》 * |
| 张树誉 等: "基于同化叶面积指数和条件植被温度指数的冬小麦单产估测", 《干旱地区农业研究》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579521A (en) * | 2023-05-12 | 2023-08-11 | 中山大学 | Yield prediction time window determining method, device, equipment and readable 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 |
| CN116485040A (en) * | 2023-06-13 | 2023-07-25 | 中国农业大学 | Seed vitality prediction method, system, electronic equipment and storage medium |
| CN116485040B (en) * | 2023-06-13 | 2023-09-08 | 中国农业大学 | Seed vitality prediction method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115600771A (en) | Crop yield estimation method, device, equipment and storage medium | |
| Matsumura et al. | Maize yield forecasting by linear regression and artificial neural networks in Jilin, China | |
| EP3641531A1 (en) | Method and system for selecting a plant variety | |
| Cournede et al. | Some parameter estimation issues in functional-structural plant modelling | |
| Lagarrigues et al. | Approximate Bayesian computation to recalibrate individual-based models with population data: Illustration with a forest simulation model | |
| JP6885394B2 (en) | Information processing system, information processing device, simulation method and simulation program | |
| JP2021056573A (en) | Crop growth prediction program, crop growth prediction method, and crop growth prediction device | |
| US20180173823A1 (en) | Simulation device, simulation method, and recording medium for storing program | |
| CN112418498A (en) | Temperature prediction method and system for intelligent greenhouse | |
| Buis et al. | The STICS crop model and associated software for analysis, parameterization, and evaluation | |
| CN116485040B (en) | Seed vitality prediction method, system, electronic equipment and storage medium | |
| CN114662742A (en) | Dynamic decision method and device for field irrigation and fertilization system | |
| Ellis | Using Bayesian growth models to predict grape yield | |
| CN113393057A (en) | Wheat yield integrated prediction method based on deep fusion machine learning model | |
| Patel et al. | LSTM-RNN Combined Approach for Crop Yield Prediction On Climatic Constraints | |
| JP2020171217A (en) | Method, apparatus and program for predicting yield | |
| CN116629453B (en) | Remote sensing yield estimation method suitable for whole crop growth period | |
| Beillouin et al. | Azodyn-Barley, a winter-barley crop model for predicting and ranking genotypic yield, grain protein and grain size in contrasting pedoclimatic conditions | |
| JP7140086B2 (en) | Fruit Vegetable Plant and Fruit Tree Cultivation Management Apparatus, Learning Device, Fruit Vegetable Plant and Fruit Tree Cultivation Management Method, Learning Model Generation Method, Fruit Vegetable Plant and Fruit Tree Cultivation Management Program, and Learning Model Generation Program | |
| CN111783538A (en) | Remote sensing estimation method and device for wheat biomass, electronic equipment and storage medium | |
| JPWO2019003441A1 (en) | Prediction device, prediction method, prediction program, and gene estimation device | |
| Ahuja et al. | A synthesis of current parameterization approaches and needs for further improvements | |
| CN115039549B (en) | Crop planting and fertilizing information processing method and system | |
| EP3474167A1 (en) | System and method for predicting genotype performance | |
| Geetha et al. | A time-series based yield forecasting model using stacked lstm to predict the yield of paddy in cauvery delta zone in tamilnadu |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230113 |
|
| RJ01 | Rejection of invention patent application after publication |