CN118296971B - Crop weathered phenotype prediction method, system, device and storage medium - Google Patents
Crop weathered phenotype prediction method, system, device and storage medium Download PDFInfo
- Publication number
- CN118296971B CN118296971B CN202410723950.0A CN202410723950A CN118296971B CN 118296971 B CN118296971 B CN 118296971B CN 202410723950 A CN202410723950 A CN 202410723950A CN 118296971 B CN118296971 B CN 118296971B
- Authority
- CN
- China
- Prior art keywords
- data
- wheatgrow
- substituting
- model
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 238000004088 simulation Methods 0.000 claims abstract description 57
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000012937 correction Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 239000002689 soil Substances 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000035945 sensitivity Effects 0.000 claims description 12
- 238000011161 development Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000001556 precipitation Methods 0.000 claims description 8
- 238000009331 sowing Methods 0.000 claims description 8
- QGZKDVFQNNGYKY-UHFFFAOYSA-O Ammonium Chemical compound [NH4+] QGZKDVFQNNGYKY-UHFFFAOYSA-O 0.000 claims description 3
- 229910002651 NO3 Inorganic materials 0.000 claims description 3
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 claims description 3
- 239000004927 clay Substances 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 230000004720 fertilization Effects 0.000 claims description 3
- 238000003973 irrigation Methods 0.000 claims description 3
- 230000002262 irrigation Effects 0.000 claims description 3
- 239000005416 organic matter Substances 0.000 claims description 3
- 229920006395 saturated elastomer Polymers 0.000 claims description 3
- 241000209140 Triticum Species 0.000 abstract description 24
- 235000021307 Triticum Nutrition 0.000 abstract description 24
- 238000010801 machine learning Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 230000018109 developmental process Effects 0.000 description 9
- 238000011160 research Methods 0.000 description 9
- 230000007246 mechanism Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012272 crop production Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000037039 plant physiology Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a crop weathered phenotype prediction method, a system, a device and a storage medium, comprising the following steps: acquiring related data of crops to be tested; substituting WheatGrow related data in the related data into WheatGrow for parameter correction to obtain crop parameters; substituting WheatGrow related data and crop parameters in the related data into WheatGrow to obtain the weather period of each variety; substituting the data of the highest temperature and the data of the lowest temperature into a CDD algorithm to calculate and obtain the accumulated low temperature day of each weather period; grouping the accumulated low-temperature days and accumulated values of other data which are not substituted into WheatGrow in the related data by taking the physical period as a division standard, and dividing the accumulated low-temperature days and the accumulated values into a training set and a testing set; substituting the training set into LSTM for training; substituting the test set into the trained LSTM to obtain a simulation result. The invention can improve the simulation precision of the model on the wheat waiting period.
Description
Technical Field
The invention belongs to the technical field of crop cultivation prediction, and particularly relates to a crop weathered phenotype prediction method, a system, a device and a storage medium.
Background
In recent years, the crop growth model is widely applied in the aspect of simulating the climatic period of wheat, and particularly, the WheatGrow model is widely adopted in the research of simulating the growth of wheat due to strong adaptability and wide application range. A considerable part of research focuses on the influence of genotype and climate change on the climatic period of wheat, and has higher requirements on simulation accuracy. However, the crop growth model is mainly constructed by relying on historical empirical data, high-precision wheat climatic period simulation is difficult to realize under the conditions of multiple genotypes, multiple latitude and complex climate, and how to improve the climatic period simulation precision becomes an important challenge for limiting the deep application of the wheat climatic period simulation model at the present stage.
Machine learning models and crop growth models are the main methods of wheat climatic simulation that are widely used. Machine learning models are sufficient for high-precision simulation because they do not require model calibration and evaluation using detailed field production and management data. Are often applied to practice accumulation in richer data sets to simulate the wheat climates with high accuracy. But it does not have the ability to explain the mechanisms and underlying processes of crop growth and is difficult to gain acceptance in the field of research focusing on the mechanisms of wheat growth and development. The crop growth model can integrate the knowledge of plant physiology, agriculture, soil science and agricultural weather into the model, and can reflect the comprehensive effects of variety genotypes, environmental conditions and management measures, thereby becoming another effective tool for quantifying and evaluating the influences of climate change, adaptability measures and the like on crop production. At the beginning of the establishment of a crop growth model, researchers have insufficient research on the mechanism of crop growth and development, do not have deep research on gene-environment interaction effect, and have the inherent defects of low flexibility of input data of the crop growth model, poor function expandability and the like due to the addition of a technical barrier in actual application; the crop growth model constructed under the background cannot flexibly accept new type data, does not have the capability of expressing new effects in the growth and development process of crops, and is difficult to connect with the research of the high-precision requirement of the current simulation result. How to combine the expandability of the machine learning input data and the easy mining capability of the data characteristic effect with the mechanism interpretability of the crop growth model, and ensure the mechanism interpretability of the crop growth while improving the simulation precision becomes a technical problem.
The current method for combining the crop growth model and the machine learning model is single, the main stream method is to jointly drive the machine learning model to carry out secondary modeling by using the output of the crop growth model and the phenotype data, the research is mainly focused on how to use a more efficient and complex machine learning method, the method does not analyze the daily process and the mechanistic data output of the crop growth model, only the simulation result is used as the input of the machine learning model, and only the final result is fitted by using the machine learning model, so that the aim of removing the simulation error of the crop growth model is fulfilled. The simulation mode does not have mechanism interpretability, has the inherent defects of low flexibility of crop growth model input data, poor function expandability and the like, and is difficult to meet the high-precision simulation requirement.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the crop weathered period phenotype prediction method, system, device and storage medium can improve the simulation precision of a model on the wheat weathered period and meet the research requirement of high-precision simulation on the wheat weathered period.
The invention is realized in the following way: a method for predicting the crop weathered phenotype, comprising the steps of:
Step one, acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and observation data of a climatic period;
Substituting data related to the WheatGrow model in the related data into the WheatGrow model for parameter correction to obtain crop parameters of each variety, wherein the crop parameters comprise basic early attribute parameters, temperature sensitivity parameters, photoperiod sensitivity parameters and physiological development time parameters;
step three, substituting data related to WheatGrow models in the related data into WheatGrow models subjected to parameter correction for simulation to obtain the weather period of each variety;
Substituting the day highest temperature data and the day lowest temperature data in the meteorological data into a CDD algorithm for calculation to obtain accumulated low temperature days of each weather period;
step five, grouping the accumulated low-temperature days in the step four and the accumulated values of other data which are not substituted into WheatGrow models in the related data by taking the physical period as a dividing standard;
step six, dividing the grouping data in the step five into a training set and a testing set;
substituting the training set into an LSTM model to train the LSTM model;
and step eight, substituting the test set into the trained LSTM model for testing, and obtaining a simulation result.
Further, the method also comprises a step nine, wherein the simulation results in the step three and the simulation results in the step eight are respectively evaluated by taking the RMSE and the R 2 as evaluation indexes.
Further, the meteorological data comprise day highest temperature data, day lowest temperature data, day sunshine hours data and precipitation amount data; the soil data comprises soil depth data, soil layer thickness data, PH value data, volume weight data, clay content data, actual water content data, field water holding capacity data, permanent wilting point data, saturated water content data, organic matter content data, full N content data, nitrate N content data, ammonium N content data, quick-acting P content data, full P content data, quick-acting K content data, slow-acting K content data and CaCO 3 data; the management measure data comprise sowing date data, sowing mode data, line spacing data, irrigation data and fertilization data.
Further, the calculation formula of the accumulated low temperature day is as follows:
T max is the highest day temperature data, t min is the lowest day temperature data, i is the number of hours, and j is the number of days.
Further, the corresponding data which are not substituted into the WheatGrow model in the first step are precipitation data and sunshine duration data.
The invention also provides a crop weathered phenotype prediction system, which comprises:
The acquisition module is used for acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and observation data of a climatic period;
the parameter correction module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model to perform parameter correction to obtain crop parameters of each variety, wherein the crop parameters comprise basic early attribute parameters, temperature sensitivity parameters, photoperiod sensitivity parameters and physiological development time parameters;
The weathered period calculation module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model subjected to parameter correction for simulation to obtain the weathered period of each variety;
the CDD algorithm module is used for substituting the daily highest temperature data and the daily lowest temperature data in the meteorological data into the CDD algorithm for calculation to obtain the accumulated low temperature day of each weather period;
the grouping module is used for grouping the accumulated low-temperature days output by the CDD algorithm module and the accumulated values of other data which are not substituted into the WheatGrow model in the related data by taking the weather period as a division standard;
the dividing module is used for dividing the grouping data output by the grouping module into a training set and a testing set;
the training module is used for substituting the training set into the LSTM model to train the LSTM model;
And the test module is used for substituting the test set into the LSTM model obtained by the training module to test, so as to obtain a simulation result.
Further, the system also comprises an evaluation module, which is used for respectively evaluating the simulation result in the third step and the simulation result in the eighth step by taking the RMSE and the R 2 as evaluation indexes.
Further, the CDD algorithm module is preset with the following calculation formula:
CDD j is cumulative low temperature day, t max is day maximum temperature data, t min is day minimum temperature data, i is number of hours, j is number of days.
The invention also provides a crop weathered phenotype prediction device, which comprises: a processor and a memory for storing a computer program for executing the computer program to carry out the steps of the above method.
The invention also provides a storage medium storing a computer program executable by a processor to implement the steps of the above method.
The beneficial effects brought by the invention are as follows:
(1) Compared with the error elimination method of splicing machine learning input ends at the output ends of the existing crop growth model, the method can input new data and new effect results into the machine learning model in a time slice segmentation mode according to the wheat waiting periods simulated by the crop growth model, so that the effect of each growth stage is responded, the error of each stage is eliminated, the final purpose of improving the simulation precision is achieved, and the simulation process has stronger mechanism interpretability and robustness.
(2) The invention analyzes the whole process of simulating the waiting period of the crop growth model to analyze the defects of inconvenience of data input, hysteresis of new effect and the like of the crop growth model, and uses the advantages of the machine learning model to make up the defects, thereby fundamentally solving the errors, but not simply eliminating the errors.
(3) Based on the daily simulation function of the crop growth model, the invention segments new data which are unacceptable by the crop growth model, the gene-environment interaction effect which is not simulated, the new effect in the crop growth and development process and the like according to the daily simulation data of the crop model, and fuses the segmented data into the wheat waiting period simulation work by means of the data expandability and the effect mining capability of the machine learning model, so that the machine learning model and the crop growth model construct a fusion model under the condition of not losing the original advantages, the simulation precision of the model on the wheat waiting period is improved, and the research requirement of simulating the wheat waiting period phenotype with high precision and high flux is met.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of the grouping in step five of the present invention;
FIG. 3 is a schematic diagram of the working principle of the LSTM model in the present invention;
FIG. 4 is an evaluation chart of the simulation result for the third step in the present invention;
Fig. 5 is an evaluation chart of the simulation result for the step eight in the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
Taking wheat heading period of GABI wheat groups as an example, the crop weathered phenotype prediction method in the invention comprises the following steps:
Step one, acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and heading stage observation data. In this step, the weather data includes day maximum temperature data, day minimum temperature data, day hours data, and precipitation amount data. The soil data comprises soil depth data, soil layer thickness data, PH value data, volume weight data, clay content data, actual water content data, field water holding capacity data, permanent wilting point data, saturated water content data, organic matter content data, full N content data, nitrate N content data, ammonium N content data, quick-acting P content data, full P content data, quick-acting K content data, slow-acting K content data and CaCO 3 data. The management measure data comprise sowing date data, sowing mode data, line spacing data, irrigation data and fertilization data.
In this step, the distribution of the experimental sites of the data sources is shown in the following table:
；
The experimental data of GABI wheat at different experimental sites and different years are shown in the table above, and include experimental sites, variety numbers, experimental years, experimental groups and phenotypic information.
All experimental data in this table were from GABI wheat population containing a total of 274 varieties of wheat tested at a total of 6 experimental sites Lindau, andelu, janville, saultain, wohlde and SELIGENSTADT, respectively.
And preprocessing after acquiring the data, and processing the data format into a format conforming to a specific database, so as to establish a wheat heading date database, and uploading the database to the Github for data hosting.
And step two, correcting variety parameters by utilizing a variety parameter correction function of the WheatGrow model. For the WheatGrow model, interactions between the model and the database are established so that the model can read the relevant data to calculate the basic early attribute parameters (IE), temperature sensitivity parameters (TS), photoperiod sensitivity Parameters (PS) and physiological development time Parameters (PVT) for each wheat variety. The four variety parameters are corrected and then input into a database for standby in a simulation process.
And thirdly, simulating the heading stage by using a simulation function of the WheatGrow model subjected to parameter correction. And carrying out batch simulation through interaction established between the database and the WheatGrow model to obtain the weathers of each variety. In this example, the time of sowing, emergence, tillering, jointing, booting and heading can be obtained through simulation.
And fourthly, substituting the day highest temperature data and the day lowest temperature data in the meteorological data into a CDD algorithm for calculation to obtain the accumulated low temperature day of each weather period. The step fully considers new data which is unacceptable by WheatGrow models, thereby realizing the segmentation of data which simulate the 'gene-environment' interaction effect, the new effect in the growth and development process of crops and the like. In this step, the calculation formula for accumulating low temperature days is:
T max is the highest day temperature data, t min is the lowest day temperature data, i is the number of hours, and j is the number of days.
And fifthly, grouping the accumulated low-temperature days in the fourth step and the accumulated values of other data which are not substituted into WheatGrow models in the related data by taking the physical period as a division standard. In the step, the corresponding data which are not substituted into WheatGrow models are precipitation data and sunshine duration data. And calculating the accumulated precipitation data sigma P and the accumulated sunshine duration data sigma S of each weather period according to the weather periods obtained by simulation. The grouping data X nm{CDDnm,∑Pnm,∑Snm which are related to each waiting period are obtained by utilizing three accumulated data, n is used as a variety, m is the number of stages from sowing to heading, and m in the example is 1-5, namely a seedling emergence period, a tillering period, a jointing period, a booting period and a heading period.
Step six, dividing the grouping data in the step five into a training set and a testing set according to the proportion of 1:1.
And seventhly, substituting the training set into the LSTM model to train the LSTM model. The LSTM model in the training stage is constructed based on Pytorch, batch input of large-flux data is met, num_layers is set to 2, hidden_size is set to 16, and model training times are set to 10000 times.
And step eight, substituting the test set into the trained LSTM model for testing, and obtaining a simulation result, namely, a weather period corresponding to the specific CDD, sigma P and sigma S values.
And step nine, after simulation results of all the group data are obtained, adopting RMSE and R 2 as evaluation indexes to evaluate the simulation results of the WheatGrow model and the simulation results of the fused LSTM model and WheatGrow model respectively. As shown in fig. 4 and 5, for the GABI wheat population, the RMSE value of the simulation result using the WheatGrow model alone was significantly higher than the RMSE value of the simulation result of the fusion LSTM model and WheatGrow model, and the correction process (i.e., training process) of the heading date simulation accuracy of the fusion LSTM model and WheatGrow model on the heading date dataset of the GABI variety wheat was decreased by more than 1 day compared to the WheatGrow model alone, while the simulation process (i.e., testing process) was decreased by more than 0.7 day.
Based on the same inventive concept, the invention also provides a crop weathered phenotype prediction system, which comprises an acquisition module, a parameter correction module, a weathered period calculation module, a CDD algorithm module, a grouping module, a dividing module, a training module, a testing module and an evaluation module.
The acquisition module is used for acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and observation data of a weatherperiod.
The parameter correction module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model to perform parameter correction to obtain crop parameters of each variety, wherein the crop parameters comprise basic early attribute parameters, temperature sensitivity parameters, photoperiod sensitivity parameters and physiological development time parameters.
And the weathered period calculation module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model subjected to parameter correction for simulation to obtain the weathered period of each variety.
The CDD algorithm module is used for substituting the day highest temperature data and the day lowest temperature data in the meteorological data into the CDD algorithm for calculation to obtain the accumulated low temperature day of each weather period. The CDD algorithm module is preset with the following calculation formula:
CDD j is cumulative low temperature day, t max is day maximum temperature data, t min is day minimum temperature data, i is number of hours, j is number of days.
And the grouping module is used for grouping the accumulated low-temperature days output by the CDD algorithm module and the accumulated values of other data which are not substituted into the WheatGrow model in the related data by taking the weather period as a division standard.
The dividing module is used for dividing the grouping data output by the grouping module into a training set and a testing set.
The training module is used for substituting the training set into the LSTM model to train the LSTM model.
And the test module is used for substituting the test set into the LSTM model obtained by the training module to test, so as to obtain a simulation result.
The evaluation module is used for respectively evaluating the simulation result in the third step and the simulation result in the eighth step by taking the RMSE and the R 2 as evaluation indexes.
Based on the same inventive concept, the invention also provides a crop weathered phenotype prediction device, which comprises: a processor and a memory for storing a computer program for executing the computer program to carry out the steps of the above method.
Based on the same inventive concept, the present invention also provides a storage medium storing a computer program executable by a processor to implement the steps of the above method.
In the description of the present invention, it should be understood that the terms "upper," "lower," "left," "right," and the like indicate an orientation or a positional relationship based on that shown in the drawings, and are merely for convenience of description and for simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, as well as a specific orientation configuration and operation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.
In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (7)
1. A method for predicting the phenotype of a crop in a climatic period, comprising the steps of:
Step one, acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and observation data of a climatic period;
Substituting data related to the WheatGrow model in the related data into the WheatGrow model for parameter correction to obtain crop parameters of each variety, wherein the crop parameters comprise basic early attribute parameters, temperature sensitivity parameters, photoperiod sensitivity parameters and physiological development time parameters;
step three, substituting data related to WheatGrow models in the related data into WheatGrow models subjected to parameter correction for simulation to obtain the weather period of each variety;
Substituting the day highest temperature data and the day lowest temperature data in the meteorological data into a CDD algorithm for calculation to obtain accumulated low temperature days of each weather period; the calculation formula of the accumulated low temperature day is as follows:
T max is the highest day temperature data, t min is the lowest day temperature data, i is the number of hours, j is the number of days;
Step five, grouping the accumulated low-temperature days in the step four and the accumulated values of other data which are not substituted into WheatGrow models in the related data by taking the physical period as a dividing standard; other data which are not substituted into WheatGrow models are precipitation data and sunlight hours data;
step six, dividing the grouping data in the step five into a training set and a testing set;
substituting the training set into an LSTM model to train the LSTM model;
and step eight, substituting the test set into the trained LSTM model for testing, and obtaining a simulation result.
2. The method according to claim 1, further comprising the step of evaluating the simulation result in the step three and the simulation result in the step eight, respectively, using RMSE and R 2 as evaluation indexes.
3. The method of claim 1, wherein the meteorological data comprises highest day temperature data, lowest day temperature data, solar hours data, precipitation data; the soil data comprises soil depth data, soil layer thickness data, PH value data, volume weight data, clay content data, actual water content data, field water holding capacity data, permanent wilting point data, saturated water content data, organic matter content data, full N content data, nitrate N content data, ammonium N content data, quick-acting P content data, full P content data, quick-acting K content data, slow-acting K content data and CaCO 3 data; the management measure data comprise sowing date data, sowing mode data, line spacing data, irrigation data and fertilization data.
4. A crop weatherometer phenotype prediction system, comprising:
The acquisition module is used for acquiring related data of crops to be detected, wherein the related data comprise meteorological data, soil data, management measure data and observation data of a climatic period;
the parameter correction module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model to perform parameter correction to obtain crop parameters of each variety, wherein the crop parameters comprise basic early attribute parameters, temperature sensitivity parameters, photoperiod sensitivity parameters and physiological development time parameters;
The weathered period calculation module is used for substituting data related to the WheatGrow model in the related data into the WheatGrow model subjected to parameter correction for simulation to obtain the weathered period of each variety;
The CDD algorithm module is used for substituting the daily highest temperature data and the daily lowest temperature data in the meteorological data into the CDD algorithm for calculation to obtain the accumulated low temperature day of each weather period; the CDD algorithm module is preset with the following calculation formula:
CDD j is cumulative low temperature day, t max is day maximum temperature data, t min is day minimum temperature data, i is number of hours, j is number of days;
The grouping module is used for grouping the accumulated low-temperature days output by the CDD algorithm module and the accumulated values of other data which are not substituted into the WheatGrow model in the related data by taking the weather period as a division standard; other data which are not substituted into WheatGrow models are precipitation data and sunlight hours data;
the dividing module is used for dividing the grouping data output by the grouping module into a training set and a testing set;
the training module is used for substituting the training set into the LSTM model to train the LSTM model;
And the test module is used for substituting the test set into the LSTM model obtained by the training module to test, so as to obtain a simulation result.
5. The system of claim 4, further comprising an evaluation module for evaluating the simulation result in the third step and the simulation result in the eighth step, respectively, using RMSE and R 2 as evaluation indexes.
6. A crop weatherometer phenotype prediction device comprising a processor and a memory, the memory being for storing a computer program, the processor being for executing the computer program to carry out the steps of the method of claim 1.
7. A storage medium storing a computer program executable by a processor to perform the steps of the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410723950.0A CN118296971B (en) | 2024-06-05 | 2024-06-05 | Crop weathered phenotype prediction method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410723950.0A CN118296971B (en) | 2024-06-05 | 2024-06-05 | Crop weathered phenotype prediction method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118296971A CN118296971A (en) | 2024-07-05 |
| CN118296971B true CN118296971B (en) | 2024-10-22 |
Family
ID=91678014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410723950.0A Active CN118296971B (en) | 2024-06-05 | 2024-06-05 | Crop weathered phenotype prediction method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118296971B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681169A (en) * | 2023-06-02 | 2023-09-01 | 河北省科学院地理科学研究所 | Method for evaluating influence of extreme climate on crop yield |
| CN117854590A (en) * | 2023-12-21 | 2024-04-09 | 南京农业大学 | Machine learning method for estimating genotype specific parameters of soybean climatic period simulation model by using SNP (Single nucleotide polymorphism) markers |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118016144A (en) * | 2022-11-03 | 2024-05-10 | 中国科学院分子植物科学卓越创新中心 | Method for constructing and predicting prediction model of rice heading period |
-
2024
- 2024-06-05 CN CN202410723950.0A patent/CN118296971B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681169A (en) * | 2023-06-02 | 2023-09-01 | 河北省科学院地理科学研究所 | Method for evaluating influence of extreme climate on crop yield |
| CN117854590A (en) * | 2023-12-21 | 2024-04-09 | 南京农业大学 | Machine learning method for estimating genotype specific parameters of soybean climatic period simulation model by using SNP (Single nucleotide polymorphism) markers |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118296971A (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284771B (en) | Tomato growth model determination method and device | |
| CN112598277B (en) | Method for evaluating yield difference of trans-regional reduced winter wheat and improving nitrogen fertilizer efficiency | |
| CN114638146A (en) | Crop irrigation water demand prediction method based on AquaCrop model and SVR | |
| CN110705182B (en) | Crop breeding adaptive time prediction method coupling crop model and machine learning | |
| CN109800921B (en) | Regional winter wheat yield estimation method based on remote sensing phenological assimilation and particle swarm optimization | |
| CN110909933A (en) | Agricultural drought rapid diagnosis and evaluation method coupling crop model and machine learning language | |
| CN115455086A (en) | Method and system for estimating agricultural irrigation water consumption of irrigated area | |
| CN116485040B (en) | Seed vitality prediction method, system, electronic equipment and storage medium | |
| CN116681169A (en) | Method for evaluating influence of extreme climate on crop yield | |
| CN116401882A (en) | Method for evaluating influence of surface ozone on winter wheat yield based on multi-factor stress | |
| CN114254964A (en) | Rice regional climate quality assessment method and system | |
| CN101427655A (en) | Multi-purpose evaluating method for sugarcane family | |
| CN118296971B (en) | Crop weathered phenotype prediction method, system, device and storage medium | |
| CN116502050B (en) | Dynamic interpolation method and system for global flux site evapotranspiration observation loss | |
| CN112364710A (en) | Plant electric signal classification and identification method based on deep learning algorithm | |
| CN113762768B (en) | Agricultural drought dynamic risk assessment method based on natural gas generator and crop model | |
| CN117408430A (en) | Soil improvement evaluation system for agricultural planting based on big data | |
| CN114972301A (en) | Weed detection method and system based on multi-scale fusion | |
| CN116050047A (en) | Leaf area index prediction method | |
| MORI et al. | GCPE: The global dataset of crop phenological events for agricultural and earth system modeling | |
| CN111667167B (en) | Agricultural grain yield estimation method and system | |
| CN117436710B (en) | Drought assessment method based on crop model | |
| CN111528066B (en) | Agricultural irrigation control method and system | |
| CN111768044B (en) | Method and system for monitoring cotton aphid number in seedling stage of cotton | |
| CN118901368A (en) | Orchard water and fertilizer regulation and control method and system |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 211225 Jiangsu Nanjing Lishui District Baima Town National Agricultural Science and Technology Park Nanjing Agricultural University base Applicant after: NANJING AGRICULTURAL University Address before: Weigang Xuanwu District of Nanjing Jiangsu province 210095 No. 1 Applicant before: NANJING AGRICULTURAL University Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |