CN112734120A - Corn pest early warning method based on dynamic grid division - Google Patents
Corn pest early warning method based on dynamic grid division Download PDFInfo
- Publication number
- CN112734120A CN112734120A CN202110049330.XA CN202110049330A CN112734120A CN 112734120 A CN112734120 A CN 112734120A CN 202110049330 A CN202110049330 A CN 202110049330A CN 112734120 A CN112734120 A CN 112734120A
- Authority
- CN
- China
- Prior art keywords
- data
- corn
- loss
- early warning
- insect
- 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
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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 discloses a corn pest early warning method based on dynamic grid division. The corn pest early warning method comprises the following steps: collecting data to obtain original data; preprocessing original data; clustering and dynamically dividing the spatial grids, and outputting an association model of the insect disaster factors and the corn loss; analyzing and deciding the pesticide application quantity and economy to obtain space nutrient data and additional fertilizer data; according to the spatial nutrient data and the additional fertilizer data, the loss of the corn is predicted, and compared and analyzed with the actual loss; and filing the loss data of the current year into a data set, performing the next iteration, and returning to the step I to continue the model training. The invention uses a dynamic grid division method based on a data set obtained by measuring insect disaster core elements under space grid division to carry out rapid and accurate insect disaster dynamic early warning, guides farmers to release pesticides and reduces insect disaster loss to the lowest.
Description
Technical Field
The invention relates to a corn pest early warning method based on dynamic grid division, and belongs to the field of computer-aided diagnosis.
Background
For a long time, agricultural production is influenced by addresses and climate factors, and has the characteristics of complex dynamics, uncertainty, time-space multi-factor coupling and the like. The traditional technical means can not correctly and timely master the agricultural condition, so that the agricultural production is in a situation that informatization is backward and passive for a long time, and the great economic loss of farmers is often caused due to the insufficient early warning of insect disasters.
With the development of information technology, the traditional intensive agriculture does not meet the requirements of the development of the current economic society, and the perception of human beings is widened and the rapid transformation of the accurate agriculture is accelerated by combining the digital data management of a computer and high-efficiency data processing methods such as big data and machine learning.
The corn is a main economic crop in northeast regions, the accurate control and analysis of the whole corn planting period is beneficial to improving the corn loss, and economic benefits are created for farmers to lose poverty and governments.
Disclosure of Invention
The invention aims to provide a corn pest early warning method based on dynamic grid division to solve the problems in the prior art.
A corn pest early warning method based on dynamic grid division comprises the following steps:
step one, collecting data to obtain original data;
secondly, preprocessing the original data;
thirdly, clustering and dynamically dividing the space grids, and outputting an association model of the insect disaster factors and the corn loss;
fourthly, analyzing and deciding the quantity of the applied pesticides and the economical type to obtain space nutrient data and additional fertilizer data;
according to the space nutrient data and the additional fertilizer data, predicting the loss of the corn, and comparing and analyzing the loss with the actual loss;
and step six, filing the loss data of the current year into a data set, performing the next iteration, and returning to the step one to continue the model training.
Further, in the step one, the method specifically comprises the following steps:
firstly, accurately dividing grids according to a map;
measuring and recording the insect disaster factors and the corn yield in each grid by a five-point sampling method or a random sampling method, and stamping a time stamp;
step three, forming a time sequence of the pest disaster elements under any accurate positioning grid;
and step four, storing and archiving the collected data according to the map grid under accurate positioning.
Further, in the second step, the insect disaster factors comprise soil nutrients, weather conditions and insect source base numbers.
Further, in the second step, the method specifically comprises the following steps:
step two, inputting the original data collected in the step four;
secondly, denoising the original data;
step two, grading and screening the corn yield according to the requirement, and marking grading identification on the data;
and step two, filing and storing the same level data.
Further, in step two or three, the data classification criteria are:
typical samples have serious pest areas, namely pests are found and the large-scale yield reduction of the corns is shown as the characteristic that the corn yield is reduced in a cliff-breaking mode after data of map grid points are at a certain time sequence point;
typical samples are data of areas where general insect disasters occur, wherein insect pests and corn yield reduction is reflected, and the data of map grid points are reflected in the characteristic that the corn yield is reduced by a certain gradient after a certain time sequence point;
the atypical sample has no obvious characteristics and is embodied as the overall smooth data sample of the map grid point.
Further, in the third step, the method specifically comprises the following steps:
thirdly, performing data processing on the preprocessed data with the hierarchical identification by a fuzzy clustering method;
step two, extracting a data characteristic matrix and an aggregation center characteristic matrix, and calculating a new fuzzy partition matrix and a new fuzzy partition threshold according to the aggregation center characteristic matrix and the data characteristic matrix;
step three, continuously iterating the step three to dynamically update the fuzzy matrix edge to realize dynamic division of the space grid;
and step three, outputting a correlation model of the insect disaster factors and the corn loss based on the dynamic grid division result to assist in insect disaster early warning and decision of medicine application, performing regression analysis according to the data fitting result, and analyzing the loss of farmers.
Further, in the third and fourth steps, the disaster early warning method includes: and injecting real-time insect disaster elements into the correlation model of the corn loss, performing early warning on serious insect disasters and general insect disasters according to the boundary of the dynamic grid, and calculating the corn loss of the site according to the difference between the corn yield and the historical contemporaneous atypical sample or the real-time atypical sample or the weighted average value of the historical contemporaneous sample and the real-time atypical sample.
Further, in the fourth step and the fifth step, specifically: according to the time sequence of the current year and the historical data trend of the previous year, the corn planting is subjected to grading early warning and pesticide application guidance according to the insect disaster factors, the loss of farmers is analyzed according to the corn loss and the pesticide application cost, and the loss is predicted according to the pesticide application scheme finally selected by the farmers.
The invention has the following advantages:
1. and (3) adopting computer-aided agricultural production to research the time-space correlation between the insect disaster element and the corn loss, analyzing the correlation between the insect disaster element content and the loss according to the spatial characteristics of the insect disaster element data, and predicting the corn loss. Can effectively reduce insect pest threat in corn planting.
2. And a data preprocessing link is added, data is cleaned and time series filtering is carried out to realize data noise reduction, fitting result distortion caused by dead pixels in the data processing process is reduced, and data fitting efficiency and the output speed of the model are improved.
3. And a dynamic grid division method is adopted, so that the insect pest area is dynamically updated, and rapid prediction, early warning and response can be carried out on insect pests. Effectively reduces the insect damage.
4. By adopting a pesticide application decision combining multiple elements, the pest disaster elements, the pesticide application efficiency and the pesticide application cost are brought into pesticide application economy and analyzed, the local optimal solution of the decision is realized, and the pest damage is reduced to the maximum extent.
Drawings
FIG. 1 is a flow chart of a method of a corn pest early warning method based on dynamic grid division;
FIG. 2 is a flow chart of step one;
FIG. 3 is a flow chart of step two;
FIG. 4 is a flowchart of step three;
fig. 5 is a flowchart of step four and step five.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It is specifically noted that various embodiments disclosed in the present application or features included in the embodiments may be combined with each other without conflict.
Referring to fig. 1, a corn pest early warning method based on dynamic grid division includes the following steps:
step one, collecting data to obtain original data;
secondly, preprocessing the original data;
thirdly, clustering and dynamically dividing the space grids, and outputting an association model of the insect disaster factors and the corn loss;
fourthly, analyzing and deciding the quantity of the applied pesticides and the economical type to obtain space nutrient data and additional fertilizer data;
according to the space nutrient data and the additional fertilizer data, predicting the loss of the corn, and comparing and analyzing the loss with the actual loss;
and step six, filing the loss data of the current year into a data set, performing the next iteration, and returning to the step one to continue the model training.
Further, referring to fig. 2, in the step one, the method specifically includes the following steps:
firstly, accurately dividing grids according to a map;
measuring and recording the insect disaster factors and the corn yield in each grid by a five-point sampling method or a random sampling method, and stamping a time stamp;
step three, forming a time sequence of the pest disaster elements under any accurate positioning grid;
and step four, storing and archiving the collected data according to the map grid under accurate positioning.
Further, in the second step, the insect disaster factors comprise soil nutrients, weather conditions and insect source base numbers.
Further, referring to fig. 3, in the step two, the method specifically includes the following steps:
step two, inputting the original data collected in the step four;
secondly, denoising the original data;
step two, grading and screening the corn yield according to the requirement, and marking grading identification on the data;
and step two, filing and storing the same level data.
Further, in step two or three, the data classification criteria are:
typical samples have serious pest areas, namely pests are found and the large-scale yield reduction of the corns is shown as the characteristic that the corn yield is reduced in a cliff-breaking mode after data of map grid points are at a certain time sequence point;
typical samples are data of areas where general insect disasters occur, wherein insect pests and corn yield reduction is reflected, and the data of map grid points are reflected in the characteristic that the corn yield is reduced by a certain gradient after a certain time sequence point;
the atypical sample has no obvious characteristics and is embodied as the overall smooth data sample of the map grid point.
Further, as shown in fig. 4, in step three, the method specifically includes the following steps:
thirdly, performing data processing on the preprocessed data with the hierarchical identification by a fuzzy clustering method;
step two, extracting a data characteristic matrix and an aggregation center characteristic matrix, and calculating a new fuzzy partition matrix and a new fuzzy partition threshold according to the aggregation center characteristic matrix and the data characteristic matrix;
step three, continuously iterating the step three to dynamically update the fuzzy matrix edge to realize dynamic division of the space grid;
and step three, outputting a correlation model of the insect disaster factors and the corn loss based on the dynamic grid division result to assist in insect disaster early warning and decision of medicine application, performing regression analysis according to the data fitting result, and analyzing the loss of farmers.
Further, in the third and fourth steps, the disaster early warning method includes: and injecting real-time insect disaster elements into the correlation model of the corn loss, performing early warning on serious insect disasters and general insect disasters according to the boundary of the dynamic grid, and calculating the corn loss of the site according to the difference between the corn yield and the historical contemporaneous atypical sample or the real-time atypical sample or the weighted average value of the historical contemporaneous sample and the real-time atypical sample.
Further, referring to fig. 5, in step four and step five, specifically: according to the time sequence of the current year and the historical data trend of the previous year, the corn planting is subjected to grading early warning and pesticide application guidance according to the insect disaster factors, the loss of farmers is analyzed according to the corn loss and the pesticide application cost, and the loss is predicted according to the pesticide application scheme finally selected by the farmers.
Claims (8)
1. A corn pest early warning method based on dynamic grid division is characterized by comprising the following steps:
step one, collecting data to obtain original data;
secondly, preprocessing the original data;
thirdly, clustering and dynamically dividing the space grids, and outputting an association model of the insect disaster factors and the corn loss;
fourthly, analyzing and deciding the quantity of the applied pesticides and the economical type to obtain space nutrient data and additional fertilizer data;
according to the space nutrient data and the additional fertilizer data, predicting the loss of the corn, and comparing and analyzing the loss with the actual loss;
and step six, filing the loss data of the current year into a data set, performing the next iteration, and returning to the step one to continue the model training.
2. The corn pest early warning method based on dynamic grid division as claimed in claim 1, wherein in the step one, the method specifically comprises the following steps:
firstly, accurately dividing grids according to a map;
measuring and recording the insect disaster factors and the corn yield in each grid by a five-point sampling method or a random sampling method, and stamping a time stamp;
step three, forming a time sequence of the pest disaster elements under any accurate positioning grid;
and step four, storing and archiving the collected data according to the map grid under accurate positioning.
3. A corn pest early warning method based on dynamic grid division as claimed in claim 2, wherein in the first step, the pest factors include soil nutrients, weather conditions and pest source base number.
4. The corn pest early warning method based on dynamic grid division according to claim 1, characterized by specifically comprising the following steps in step two:
step two, inputting the original data collected in the step four;
secondly, denoising the original data;
step two, grading and screening the corn yield according to the requirement, and marking grading identification on the data;
and step two, filing and storing the same level data.
5. A corn pest early warning method based on dynamic grid division according to claim 4, wherein in the second step and the third step, the data grading standard is as follows:
typical samples have serious pest areas, namely pests are found and the large-scale yield reduction of the corns is shown as the characteristic that the corn yield is reduced in a cliff-breaking mode after data of map grid points are at a certain time sequence point;
typical samples are data of areas where general insect disasters occur, wherein insect pests and corn yield reduction is reflected, and the data of map grid points are reflected in the characteristic that the corn yield is reduced by a certain gradient after a certain time sequence point;
the atypical sample has no obvious characteristics and is embodied as the overall smooth data sample of the map grid point.
6. The corn pest early warning method based on dynamic grid division according to claim 1, characterized by comprising the following steps in step three:
thirdly, performing data processing on the preprocessed data with the hierarchical identification by a fuzzy clustering method;
step two, extracting a data characteristic matrix and an aggregation center characteristic matrix, and calculating a new fuzzy partition matrix and a new fuzzy partition threshold according to the aggregation center characteristic matrix and the data characteristic matrix;
step three, continuously iterating the step three to dynamically update the fuzzy matrix edge to realize dynamic division of the space grid;
and step three, outputting a correlation model of the insect disaster factors and the corn loss based on the dynamic grid division result to assist in insect disaster early warning and decision of medicine application, performing regression analysis according to the data fitting result, and analyzing the loss of farmers.
7. A corn pest early warning method based on dynamic grid division according to claim 1, wherein in the third and fourth steps, the method for disaster early warning is as follows: and injecting real-time insect disaster elements into the correlation model of the corn loss, performing early warning on serious insect disasters and general insect disasters according to the boundary of the dynamic grid, and calculating the corn loss of the site according to the difference between the corn yield and the historical contemporaneous atypical sample or the real-time atypical sample or the weighted average value of the historical contemporaneous sample and the real-time atypical sample.
8. The corn pest early warning method based on dynamic grid division according to claim 1, characterized in that in the fourth step and the fifth step, specifically: according to the time sequence of the current year and the historical data trend of the previous year, the corn planting is subjected to grading early warning and pesticide application guidance according to the insect disaster factors, the loss of farmers is analyzed according to the corn loss and the pesticide application cost, and the loss is predicted according to the pesticide application scheme finally selected by the farmers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110049330.XA CN112734120A (en) | 2021-01-14 | 2021-01-14 | Corn pest early warning method based on dynamic grid division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110049330.XA CN112734120A (en) | 2021-01-14 | 2021-01-14 | Corn pest early warning method based on dynamic grid division |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112734120A true CN112734120A (en) | 2021-04-30 |
Family
ID=75593062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110049330.XA Pending CN112734120A (en) | 2021-01-14 | 2021-01-14 | Corn pest early warning method based on dynamic grid division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734120A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114067532A (en) * | 2021-11-15 | 2022-02-18 | 宁夏农林科学院植物保护研究所（宁夏植物病虫害防治重点实验室） | Agricultural biological disaster monitoring and early warning big data system and method |
| CN116884041A (en) * | 2023-09-05 | 2023-10-13 | 肥城市林业保护发展中心 | Forestry insect disaster prediction method and system based on regional historical data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103395A (en) * | 2017-05-31 | 2017-08-29 | 宁波高新区鹏博科技有限公司 | A kind of short-term method for early warning of crop pests |
| CN111854847A (en) * | 2020-08-12 | 2020-10-30 | 中国科学院城市环境研究所 | Ecological environment Internet of things monitoring method and system based on scene-induced ecology |
-
2021
- 2021-01-14 CN CN202110049330.XA patent/CN112734120A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103395A (en) * | 2017-05-31 | 2017-08-29 | 宁波高新区鹏博科技有限公司 | A kind of short-term method for early warning of crop pests |
| CN111854847A (en) * | 2020-08-12 | 2020-10-30 | 中国科学院城市环境研究所 | Ecological environment Internet of things monitoring method and system based on scene-induced ecology |
Non-Patent Citations (3)
| Title |
|---|
| 于合龙: "精准农业生产中若干智能决策问题研究", 《中国博士学位论文全文数据库·农业科技辑》, pages 043 - 1 * |
| 司丽丽等: "基于地理信息系统的全国主要粮食作物病虫害实时监测预警系统的研制", 《植物保护学报》, vol. 33, pages 282 - 286 * |
| 王冬雪等: "基于 GA -RBF 融合算法的玉米病虫害产量损失预测研究", 《江苏农业科学》, vol. 47, no. 9, pages 263 - 266 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114067532A (en) * | 2021-11-15 | 2022-02-18 | 宁夏农林科学院植物保护研究所（宁夏植物病虫害防治重点实验室） | Agricultural biological disaster monitoring and early warning big data system and method |
| CN116884041A (en) * | 2023-09-05 | 2023-10-13 | 肥城市林业保护发展中心 | Forestry insect disaster prediction method and system based on regional historical data |
| CN116884041B (en) * | 2023-09-05 | 2023-11-10 | 肥城市林业保护发展中心 | Forestry insect disaster prediction method and system based on regional historical data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kumar et al. | Supervised machine learning approach for crop yield prediction in agriculture sector | |
| Kamath et al. | Crop yield forecasting using data mining | |
| Peters et al. | An integrated view of complex landscapes: a big data-model integration approach to transdisciplinary science | |
| CN114972843B (en) | Agricultural pest diagnosis and early warning system based on big data | |
| CN112734120A (en) | Corn pest early warning method based on dynamic grid division | |
| CN116681279B (en) | Forestry pest control risk assessment system based on data analysis | |
| Girondot | Estimating density of animals during migratory waves: a new model applied to marine turtles at nesting sites | |
| Li et al. | Improvement Of In-season Crop Mapping For Illinois Cropland Using Multiple Machine Learning Classifiers | |
| Wongchai et al. | Farm monitoring and disease prediction by classification based on deep learning architectures in sustainable agriculture | |
| AU2021103520A4 (en) | A system for monitoring health condition of a crop and a method there of | |
| CN113762788A (en) | Method and system for building farmland data model and portrait | |
| CN111968003B (en) | Crop disease prediction method based on crop ontology concept response | |
| Pawar et al. | The Role of Innovative Data Mining Approaches for Analyzing and Estimating the Crop Yield in Agriculture Among Emerging Nations | |
| Renju et al. | A review of crop yield prediction strategies based on machine learning and deep learning | |
| CN112734119A (en) | Corn yield prediction method based on spatial nutrient cluster analysis | |
| Alberto et al. | Hot spot area analysis of onion armyworm outbreak in Nueva Ecija using geographic information system | |
| Marta-Costa et al. | Approaches for sustainable farming systems assessment | |
| CN116681929A (en) | Wheat crop disease image recognition method | |
| CN109034392A (en) | The selection and system of a kind of Tilapia mossambica corss combination system | |
| Dogra et al. | Identifying indicators of sustainable smart agriculture driven by big data using modified total interpretive structural modeling (mtism) | |
| Fatima et al. | Semi-supervised learning in smart agriculture: A systematic literature review | |
| Akhtar et al. | Automated image analysis and improvisations to manage palm oil plantation | |
| Dahiya et al. | An Effective Detection of Litchi Disease using Deep Learning | |
| Mittal et al. | Implementation and Identification of Crop based on Soil Texture using AI | |
| Filippi et al. | Detecting causes of spatial variation in crop yield with interpretive machine learning. |
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 |