CN113205205A - Wheat scab prediction method based on deep forest algorithm - Google Patents
Wheat scab prediction method based on deep forest algorithm Download PDFInfo
- Publication number
- CN113205205A CN113205205A CN202110377903.1A CN202110377903A CN113205205A CN 113205205 A CN113205205 A CN 113205205A CN 202110377903 A CN202110377903 A CN 202110377903A CN 113205205 A CN113205205 A CN 113205205A
- Authority
- CN
- China
- Prior art keywords
- wheat
- wheat scab
- prediction method
- method based
- period
- 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
- 241000209140 Triticum Species 0.000 title claims abstract description 64
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 64
- 206010039509 Scab Diseases 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 40
- 241000196324 Embryophyta Species 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 13
- 241000223195 Fusarium graminearum Species 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 235000013305 food Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Development Economics (AREA)
- Agronomy & Crop Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a wheat scab prediction method based on a deep forest algorithm. The wheat scab prediction method based on the deep forest algorithm comprises the following steps: step S1: through collecting, sorting and summarizing databases of wheat scab occurrence conditions of years, screening out wheat scab occurrence processes by using a characteristic selection algorithm, and combining the experience of plant protection experts to perform theoretical demonstration analysis and correction; step S2: in the process of characteristic selection, analysis is carried out according to different growth periods of wheat, and finally, three relative bonds are determined in the process of wheat growth. The wheat scab prediction method based on the deep forest algorithm has the advantages that models are continuously optimized and corrected, timeliness and reliability of the wheat scab prediction method are greatly improved, prediction depending on professionals is liberated, experience and scientific prediction models are combined, and the wheat scab prediction method has higher application value in a large range.
Description
Technical Field
The invention relates to the technical field of wheat scab, in particular to a wheat scab prediction method based on a deep forest algorithm.
Background
Wheat is one of main food crops in China, and is infected by a plurality of diseases in the growth process, wherein scab is mainly used, the disease has wide disease scope and large damage area, the yield and the quality of wheat are directly influenced, great threat is brought to national food safety, and the direct economic loss of farmers in China is caused.
At present, most of prediction inventions of wheat scab are judged and predicted by experience models, the timeliness and the range of the prediction inventions are limited to a certain extent, the prediction inventions cannot be applied in a large range, the dependence degree on people is higher, and certain limitation exists in efficiency.
Therefore, a new wheat scab prediction method based on a deep forest algorithm is needed to solve the technical problem.
Disclosure of Invention
In order to solve the technical problems, the invention provides the wheat scab prediction method based on the deep forest algorithm, which greatly improves the timeliness and reliability, liberates the prediction of a professional, combines the experience with a scientific prediction model and has higher application value in a large range.
The invention provides a wheat scab prediction method based on a deep forest algorithm, which comprises the following steps:
step S1: by collecting, sorting and summarizing a database of wheat scab occurrence conditions of the past year, screening out factors having larger influence in the wheat scab occurrence process by using a characteristic selection algorithm, and performing theoretical demonstration analysis and correction by combining with the experience of plant protection experts;
step S2: in the process of characteristic selection, analysis is carried out according to different growth periods of wheat, and finally, three periods of relevant bonds in the process of wheat growth are determined, wherein the three periods are respectively a late growth period, a flowering period (early heading period) and a heading flowering period, and influence factors are respectively selected in the three periods;
step S3: determining whether the good factor generation returns to the result for verification and has expressiveness, and further verifying whether the factor selection is reasonable;
step S4: in the training process of the model, according to the three periods of the late growth period, the flowering period (early heading period) and the heading and flowering period, the model is trained according to the characteristic factors, a deep forest algorithm is adopted, a plurality of forests are included in the middle, data are input from the previous layer, the output result is used as the input of the lower layer, the layer-by-layer structure in the CNN is adopted, the class vector generated by each forest is generated by K-fold cross validation, a frame of the whole prediction model is built, and the result is finally output;
step S5: after the model training is completed, the model needs to be tested, and the best scheme for testing is to perform review and evaluation on data of the past year.
Preferably, there are three factors affecting wheat scab in step S1, the first is a meteorological factor, the second is a resistance factor of wheat variety, and the third is a source factor of wheat scab (fusarium graminearum).
Preferably, in the step S2, the time length of the late growth period of the medium and small wheat is 70-80 days, the time length of the flowering period (early heading period) of the wheat is 6-7 days, and the time length of the heading flowering period is 38-42 days.
Preferably, in the step S3, a good factor is actually selected to verify the rationality, and if the rationality is left, the factor is not reasonable and needs to be reselected, and in addition, the factor is added in the opinion of the expert in time to participate in the whole process of selecting the characteristic factor in real time.
Preferably, in the step S4, in the actual prediction, we need to perform a lot of training on the model in the early stage, and continuously optimize and adjust the training model.
Compared with the related technology, the wheat scab prediction method based on the deep forest algorithm has the following beneficial effects:
1. from the perspective of reliability and practicability, the practical theoretical experience of experts is combined, the influence factors of morbidity are analyzed, the prediction model of wheat scab is trained through a machine learning mode and a deep learning theory, the model is continuously optimized and corrected under the guidance of plant protection professionals, so that the timeliness and the reliability of the prediction model are greatly improved, the prediction depending on professionals is liberated, the experience is combined with the scientific prediction model, and the prediction model has higher application value in a large range;
2. different characteristic factors are selected for the wheat scab in different periods, and the prediction model is trained according to the characteristic factors in different periods during model training, and is trained in a machine learning mode in a deep forest algorithm in combination with a deep learning theory, so that the accuracy of the scab model is further improved;
3. the core of the prediction algorithm is based on a deep forest algorithm, influence factors of wheat scab are added, influence factors of wheat scab are screened out from different angles through feature selection and suggestions and analysis given by plant protection experts, a model is trained in a machine learning mode and in combination with a deep learning theory, and the adaptability of the model is continuously optimized. And predicting the occurrence degree of wheat scab in the past year through model reinspection, comparing with the actual situation to determine the accuracy of the model, analyzing and evaluating the model again, and finally determining the effectiveness and the practicability of the model.
Drawings
FIG. 1 is a schematic flow diagram of a wheat scab prediction method based on a deep forest algorithm provided by the invention.
Detailed Description
The invention is further described with reference to the following figures and embodiments.
Please refer to fig. 1, wherein fig. 1 is a schematic flow chart of a wheat scab prediction method based on a deep forest algorithm according to the present invention. The method comprises the following steps:
step S1: by collecting, sorting and summarizing a database of wheat scab occurrence conditions of the past year, screening out factors having larger influence in the wheat scab occurrence process by using a characteristic selection algorithm, and performing theoretical demonstration analysis and correction by combining with the experience of plant protection experts;
step S2: in the process of characteristic selection, analysis is carried out according to different growth periods of wheat, and finally, three periods of relevant bonds in the process of wheat growth are determined, wherein the three periods are respectively a late growth period, a flowering period (early heading period) and a heading flowering period, and influence factors are respectively selected in the three periods;
step S3: determining whether the good factor generation returns to the result for verification and has expressiveness, and further verifying whether the factor selection is reasonable;
step S4: in the training process of the model, according to the three periods of the late growth period, the flowering period (early heading period) and the heading and flowering period, the model is trained according to the characteristic factors, a deep forest algorithm is adopted, a plurality of forests are included in the middle, data are input from the previous layer, the output result is used as the input of the lower layer, the layer-by-layer structure in the CNN is adopted, the class vector generated by each forest is generated by K-fold cross validation, a frame of the whole prediction model is built, and the result is finally output;
step S5: after the model training is completed, the model needs to be tested, and the best scheme for testing is to perform review and evaluation on data of the past year.
Three factors influencing the wheat scab in the step S1 are recorded, wherein the first factor is a meteorological factor, the second factor is a resistance factor of a wheat variety, and the third factor is a source factor of wheat scab (fusarium graminearum), and the three factors are recorded to influence the occurrence of the wheat scab, so that the occurrence probability of the wheat scab is determined to be higher due to the factor.
The time length of the late growth period of the medium and small wheat in the step S2 is 70-80 days, the time length of the flowering period (early heading period) of the wheat is 6-7 days, the time length of the flowering period of the heading is 38-42 days,
according to the analysis of the wheat in three periods, the statistics record is carried out in the later growth period of the wheat, the flowering period (early heading period) of the wheat and each time length of the heading flowering period.
In the step S3, a good factor is actually selected to verify the rationality, and if the rationality is left, the rationality is not required to be reselected, and in addition, the expert opinion is added to the correction factor in time to participate in the whole process of selecting the characteristic factor in real time.
It should be noted that, the proper characteristic factor is found in time according to the opinion of the expert.
In the actual prediction in step S4, a large amount of training needs to be performed on the model in the early stage, the training model is continuously optimized and adjusted, the prediction depending on professionals is liberated, and the model is continuously optimized and adjusted, and is combined with the model predicted after continuous optimization, so that the timeliness and reliability of the model are greatly improved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. A wheat scab prediction method based on a deep forest algorithm is characterized by comprising the following steps:
step S1: by collecting, sorting and summarizing a database of wheat scab occurrence conditions of the past year, screening out factors having larger influence in the wheat scab occurrence process by using a characteristic selection algorithm, and performing theoretical demonstration analysis and correction by combining with the experience of plant protection experts;
step S2: in the process of characteristic selection, analysis is carried out according to different growth periods of wheat, and finally, three periods of relevant bonds in the process of wheat growth are determined, wherein the three periods are respectively a late growth period, a flowering period (early heading period) and a heading flowering period, and influence factors are respectively selected in the three periods;
step S3: determining whether the good factor generation returns to the result for verification and has expressiveness, and further verifying whether the factor selection is reasonable;
step S4: in the training process of the model, according to the three periods of the late growth period, the flowering period (early heading period) and the heading and flowering period, the model is trained according to the characteristic factors, a deep forest algorithm is adopted, a plurality of forests are included in the middle, data are input from the previous layer, the output result is used as the input of the lower layer, the layer-by-layer structure in the CNN is adopted, the class vector generated by each forest is generated by K-fold cross validation, a frame of the whole prediction model is built, and the result is finally output;
step S5: after the model training is completed, the model needs to be tested, and the best scheme for testing is to perform review and evaluation on data of the past year.
2. The wheat scab prediction method based on the deep forest algorithm as claimed in claim 1, wherein there are three factors affecting wheat scab in step S1, the first is a meteorological factor, the second is a resistance factor of wheat variety, and the third is a wheat scab (fusarium graminearum) source factor.
3. The wheat scab prediction method based on the deep forest algorithm as claimed in claim 1, wherein in step S2, the time length of the late growth period of the wheat is 70-80 days, the time length of the flowering period (pre-heading period) of the wheat is 6-7 days, and the time length of the heading and flowering period is 38-42 days.
4. The wheat scab prediction method based on the deep forest algorithm according to claim 1, characterized in that good factors are actually selected in step S3 to verify the rationality, and are left in the rationality, and are not re-selected in the rationality, and in addition, the correction factors added by the expert' S opinion are timely participated in the whole characteristic factor selection process in real time.
5. The wheat scab prediction method based on the deep forest algorithm as claimed in claim 1, wherein in the step S4, in the actual prediction, we need to do a lot of training to the model in the early stage, and continuously optimize and adjust the training model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110377903.1A CN113205205A (en) | 2021-04-08 | 2021-04-08 | Wheat scab prediction method based on deep forest algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110377903.1A CN113205205A (en) | 2021-04-08 | 2021-04-08 | Wheat scab prediction method based on deep forest algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113205205A true CN113205205A (en) | 2021-08-03 |
Family
ID=77026426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110377903.1A Pending CN113205205A (en) | 2021-04-08 | 2021-04-08 | Wheat scab prediction method based on deep forest algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113205205A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116028834A (en) * | 2023-02-28 | 2023-04-28 | 中国农业科学院植物保护研究所 | Wheat scab prediction method based on XGBoost algorithm |
CN117610733A (en) * | 2023-12-04 | 2024-02-27 | 中国地质大学(北京) | Mineral product prediction method, device, equipment and medium based on deep forest |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106845544A (en) * | 2017-01-17 | 2017-06-13 | 西北农林科技大学 | A kind of stripe rust of wheat Forecasting Methodology based on population Yu SVMs |
US20200342226A1 (en) * | 2019-04-23 | 2020-10-29 | Farmers Edge Inc. | Yield forecasting using crop specific features and growth stages |
-
2021
- 2021-04-08 CN CN202110377903.1A patent/CN113205205A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106845544A (en) * | 2017-01-17 | 2017-06-13 | 西北农林科技大学 | A kind of stripe rust of wheat Forecasting Methodology based on population Yu SVMs |
US20200342226A1 (en) * | 2019-04-23 | 2020-10-29 | Farmers Edge Inc. | Yield forecasting using crop specific features and growth stages |
Non-Patent Citations (3)
Title |
---|
姚卫平;: "贵池区小麦赤霉病发病程度中期预测模型", 基层农技推广, no. 03 * |
徐敏等: "随机森林机器算法在江苏省小麦赤霉病病穗率预测中的应用", 气象学报, pages 143 - 153 * |
赵超越;张友华;: "小麦赤霉病神经网络和偏最小二乘预测模型", 吉首大学学报(自然科学版), no. 04 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116028834A (en) * | 2023-02-28 | 2023-04-28 | 中国农业科学院植物保护研究所 | Wheat scab prediction method based on XGBoost algorithm |
CN116028834B (en) * | 2023-02-28 | 2023-12-12 | 中国农业科学院植物保护研究所 | Wheat scab prediction method based on XGBoost algorithm |
CN117610733A (en) * | 2023-12-04 | 2024-02-27 | 中国地质大学(北京) | Mineral product prediction method, device, equipment and medium based on deep forest |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10606862B2 (en) | Method and apparatus for data processing in data modeling | |
CN109242149B (en) | Student score early warning method and system based on education data mining | |
CN109032829A (en) | Data exception detection method, device, computer equipment and storage medium | |
CN113205205A (en) | Wheat scab prediction method based on deep forest algorithm | |
CN111881302B (en) | Knowledge graph-based bank public opinion analysis method and system | |
EP4075281A1 (en) | Ann-based program test method and test system, and application | |
CN112700325A (en) | Method for predicting online credit return customers based on Stacking ensemble learning | |
CN112756759B (en) | Spot welding robot workstation fault judgment method | |
CN111783818B (en) | Xgboost and DBSCAN-based accurate marketing method | |
CN104484548B (en) | A kind of improved sequential Fault Diagnosis Strategy optimization method | |
Kiss et al. | Predicting dropout using high school and first-semester academic achievement measures | |
CN109711707B (en) | Comprehensive state evaluation method for ship power device | |
CN111930601A (en) | Deep learning-based database state comprehensive scoring method and system | |
CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
CN103281555B (en) | Half reference assessment-based quality of experience (QoE) objective assessment method for video streaming service | |
CN112990569A (en) | Fruit price prediction method | |
CN106156845A (en) | A kind of method and apparatus for building neutral net | |
CN114091794A (en) | Patent value evaluation model training method, evaluation method, device and equipment | |
CN105675807A (en) | Evaluation method of atrazine residue based on BP neural network | |
TWI833098B (en) | Intellectual quality management method, electronic device and readable storage medium | |
CN113869973A (en) | Product recommendation method, product recommendation system, and computer-readable storage medium | |
KR20120103310A (en) | Calculation system and the method of a highest bid price using by database | |
KR101632537B1 (en) | Technical ripple effect analysis method | |
Lokhande et al. | Crop Recommendation System Using Machine Learning | |
CN113936804A (en) | System for constructing model for predicting risk of continuous air leakage after lung cancer resection |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210803 |