Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic Calibration Method of Variety Parameters of Crop Growth Period Model under Uncertain Conditions

An automatic correction and growth period technology, applied in the direction of evolutionary biology, biological systems, biostatistics, etc., can solve the problems of unrestricted parameters to be adjusted, uncertainty of model parameters, uncertainty of validity, etc., to achieve The effect of solving uncertainty and uncertainty caused by parameters, avoiding dependence, and improving accuracy

Active Publication Date: 2021-09-07
NANJING AGRICULTURAL UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the current common problems in the application of evolutionary algorithm to crop model parameter correction in uncertain environment are: (1) How to select the correction data set and fully mine the existing data information to avoid data inaccuracy to a certain extent; Certainty
In the process of random search, the evolutionary algorithm only pays attention to the fitting of the target variable, but the data set is incomplete when the parameters are corrected, and only part of the phenological period is selected as the target variable. The selected target phenology cannot well constrain all the parameters to be adjusted
(3) The ability of evolutionary algorithm parameter correction usually depends on specific types of problems, and the effectiveness of different evolutionary algorithms to solve problems also has uncertainty
(4) The problem of "different parameters with the same effect" will appear in the model calibration results, that is, the model parameters are uncertain

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic Calibration Method of Variety Parameters of Crop Growth Period Model under Uncertain Conditions
  • Automatic Calibration Method of Variety Parameters of Crop Growth Period Model under Uncertain Conditions
  • Automatic Calibration Method of Variety Parameters of Crop Growth Period Model under Uncertain Conditions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0101] Step 1: Preparation of historical meteorological data and selection of correction data sets of meteorological data samples in years with similar temperature and light conditions.

[0102] The daily meteorological data of 3 stations in Xinghua, Jiangsu, Nanjing, and Gaoyao, Guangdong are from the Meteorological Information Center of the National Meteorological Administration. The daily meteorological data of Jiangsu Taihu rice paddy area (Yixing) and Liyang come from the Jiangsu Provincial Meteorological Bureau. Meteorological data include daily maximum temperature (°C), daily minimum temperature (°C), sunshine hours (h / d), precipitation (mm), etc. Sow seeds to a depth of 2.5cm. refer to figure 2 The process of data preparation for the optimization of the parameters of the biological growth period model varieties, and finally the representative years are shown in Table 1.

[0103] Table 1 Test site and year data

[0104]

[0105] Liangyoupeijiu from 2007 to 2008 ...

Embodiment 2

[0169] In the prior art, the commonly used methods for selecting historical meteorological sample data for parameter optimization of crop growth period models include:

[0170] 1. Temperature selection method every other year

[0171] (1) Meteorological data preprocessing

[0172] The local annual meteorological data and the full growth period meteorological data were tested separately for the same reason as above. The daily maximum temperature and minimum temperature in the meteorological data are added and divided by two, and converted into the daily average temperature to construct a year-daily average temperature table.

[0173] (2) For the year-daily average temperature tables of the whole year and the whole growth period, calculate the average daily average temperature, sort according to the average value of daily average temperature, and extract the data of the odd-numbered years and add them to the parameter adjustment training set. The rest of the years serve as the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an automatic correction method for crop growth period model variety parameters under uncertain conditions, aiming at some key links in the coupling process of similarity measurement algorithm and self-adaptive differential evolution algorithm and crop growth period model under uncertain conditions. This method solves the problem of selecting a data set with large differences in temperature and light attributes over the years to represent the local climate conditions, as a sample data set for model variety parameter correction, that is, to screen out key phenological variables that can constrain all parameters as the target in the fitness function variables, when the variable measured data is missing, use cultivation knowledge to estimate its missing value; determine the evolutionary algorithm with adaptive feature difference to correct the model variety parameters; The similar algorithm selects a group of representative variety parameters with good robustness, which makes the simulation error minimum and has good stability, which is convenient for actual production practice.

Description

technical field [0001] The invention belongs to the technical field of digital crops, and is a cross field of a sequence data similarity analysis algorithm, an adaptive differential evolution algorithm and a crop stage development model. A comprehensive method for automatic selection of calibration sample sets and parameter automatic calibration for multi-parameter, nonlinear, discontinuous and multi-peak crop growth period model parameters is proposed. Background technique [0002] Phenological period prediction provides a unified time-scale measurement standard for crop growth model prediction, and is an important tool for analyzing the impact of climate change on crop growth and development time. The simulation results of the growth period model are affected by many factors such as genes, temperature and light environment, and there are uncertainties in the local application of the model, mainly in three aspects: data uncertainty, model structure uncertainty and model par...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G16B5/00G16B40/00G16B10/00
CPCG06F18/23213
Inventor 姜海燕赵空暖钱峥远李玉硕汤亮
Owner NANJING AGRICULTURAL UNIVERSITY