CN117892861A - Crop growth prediction method and system - Google Patents

Crop growth prediction method and system Download PDF

Info

Publication number
CN117892861A
CN117892861A CN202311779334.9A CN202311779334A CN117892861A CN 117892861 A CN117892861 A CN 117892861A CN 202311779334 A CN202311779334 A CN 202311779334A CN 117892861 A CN117892861 A CN 117892861A
Authority
CN
China
Prior art keywords
data
sub
growth
layer
prediction
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
Application number
CN202311779334.9A
Other languages
Chinese (zh)
Inventor
程念胜
蔡钦智
文兆明
杨晓红
聂真知
梁华荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aisino Corp
Original Assignee
Aisino Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aisino Corp filed Critical Aisino Corp
Priority to CN202311779334.9A priority Critical patent/CN117892861A/en
Publication of CN117892861A publication Critical patent/CN117892861A/en
Pending legal-status Critical Current

Links

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
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Primary Health Care (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Animal Husbandry (AREA)
  • Mining & Mineral Resources (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Agronomy & Crop Science (AREA)

Abstract

The invention discloses a crop growth prediction method and a crop growth prediction system, wherein the crop growth prediction method comprises the following steps: acquiring agricultural monitoring data and preprocessing the agricultural monitoring data; extracting and selecting features based on the agricultural monitoring data to obtain key features related to crop growth; building a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model; and inputting the agricultural big data obtained in real time into the growth situation prediction optimization model to obtain a growth situation prediction result of the crops. The invention utilizes the crop growth data in the agricultural big data to build a crop model, and predicts the crop growth by using the model, thereby having the advantages of high efficiency and high accuracy and having wide application prospect in agricultural production.

Description

Crop growth prediction method and system
Technical Field
The invention relates to the technical field of agriculture, in particular to a crop growth prediction method and a crop growth prediction system.
Background
Although the technology of acquiring and analyzing agricultural big data has advanced to some extent, many problems still remain in the application of the technology in predicting the growth state of crops. For example, existing methods for predicting the growth state of crops lack accuracy and cannot effectively utilize agricultural big data for prediction, so that the guidance for agricultural production is limited.
The traditional crop growth condition monitoring method relies on agricultural workers to observe the crop to conduct field investigation, the prediction effect is poor, and real-time and individuation cannot be achieved. Large data on the order of trillions are produced due to the environmental and crop conditions produced each year. If the advanced deep learning method can be used for mining and analyzing, the method is favorable for realizing intelligent agriculture under the drive of big data.
Therefore, a method for predicting crop growth is needed.
Disclosure of Invention
The invention provides a crop growth state prediction method and a crop growth state prediction system, which aim to solve the problem of how to predict the growth state of crops.
In order to solve the above problems, according to an aspect of the present invention, there is provided a crop growth prediction method, the method comprising:
acquiring agricultural monitoring data and preprocessing the agricultural monitoring data;
extracting and selecting features based on the agricultural monitoring data to obtain key features related to crop growth;
building a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model;
and inputting the agricultural big data obtained in real time into the growth situation prediction optimization model to obtain a growth situation prediction result of the crops.
Preferably, wherein the acquiring agricultural monitoring data comprises:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
Preferably, wherein the preprocessing the agricultural monitoring data includes:
and cleaning, correcting and unifying the agricultural monitoring data.
Preferably, the method is based on a convolutional neural network, and combines the single-factor models to establish a growth prediction initial model for crop growth prediction of overall nonlinear multifactor;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
Preferably, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches
The output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
According to another aspect of the present invention, there is provided a crop growth prediction system, the system comprising:
the data acquisition unit is used for acquiring agricultural monitoring data and preprocessing the agricultural monitoring data;
the key feature acquisition unit is used for extracting and selecting features based on the agricultural monitoring data to acquire key features related to crop growth;
the model determining unit is used for establishing a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model;
the prediction unit is used for inputting the agricultural big data acquired in real time into the growth situation prediction optimization model to acquire a growth situation prediction result of the crops.
Preferably, the data acquisition unit acquires agricultural monitoring data, including:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
Preferably, the data acquisition unit performs preprocessing on the agricultural monitoring data, including:
and cleaning, correcting and unifying the agricultural monitoring data.
Preferably, the model building unit combines the single factor models based on a convolutional neural network to build an initial model of growth prediction for crop growth prediction with overall nonlinear multifactor;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
Preferably, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches
The output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
The invention provides a crop growth condition prediction method and a crop growth condition prediction system, wherein the crop growth condition prediction method comprises the following steps: acquiring agricultural monitoring data and preprocessing the agricultural monitoring data; extracting and selecting features based on the agricultural monitoring data to obtain key features related to crop growth; building a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model; and inputting the agricultural big data obtained in real time into the growth situation prediction optimization model to obtain a growth situation prediction result of the crops. The invention can fully exert the advantages of large agricultural data volume and complex structure, breaks through the defects of the traditional monitoring mode, provides finer and more reliable growth prediction decision support for fruit growers, assists the digital transformation of agriculture, and is hopeful to lead the agriculture of China to develop to the accurate and intelligent direction. The method of the invention utilizes the crop growth data in the agricultural big data to establish a crop model, and predicts the crop growth by using the model, thereby having the advantages of high efficiency and high accuracy and having wide application prospect in agricultural production.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a flow chart of a crop growth prediction method 100 according to an embodiment of the present invention;
FIG. 2 is a logic flow diagram in accordance with an embodiment of the present invention;
fig. 3 is a schematic structural view of a crop growth prediction system 300 according to an embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
The technical problem solved by the invention is that the traditional crop growth monitoring method relies on the field investigation of crops observed by the eyes of farm technicians, has poor prediction effect and cannot realize real-time and individuation. Large data on the order of trillions are produced due to the environmental and crop conditions produced each year. If the advanced deep learning method can be used for mining and analyzing, the method is favorable for realizing intelligent agriculture under the drive of big data.
Fig. 1 is a flowchart of a crop growth prediction method 100 according to an embodiment of the present invention. As shown in fig. 1, the crop growth prediction method provided by the embodiment of the invention can fully exert the advantages of large agricultural data volume and complex structure, breaks through the defects of the traditional monitoring mode, provides finer and more reliable growth prediction decision support for fruit growers, assists in digitally transforming agriculture, and is hopeful to lead the agriculture of China to develop to the accurate and intelligent directions. The method of the invention utilizes the crop growth data in the agricultural big data to establish a crop model, and predicts the crop growth by using the model, thereby having the advantages of high efficiency and high accuracy and having wide application prospect in agricultural production. The crop growth prediction method 100 provided by the embodiment of the invention starts from step 101, and in step 101, agricultural monitoring data is acquired and preprocessed.
Preferably, wherein the acquiring agricultural monitoring data comprises:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
Preferably, wherein the preprocessing the agricultural monitoring data includes:
and cleaning, correcting and unifying the agricultural monitoring data.
Referring to fig. 2, in the present invention, environmental data affecting the growth of agricultural crops is collected by using internet of things or remote sensing technology, including: meteorological data, soil data, temperature data and humidity data; the measure data comprises: and the crop generation data, the pest condition data and the crop management data are subjected to cleaning and arrangement, including data preprocessing, data standardization and unification processing, so as to ensure the quality and consistency of the data.
In step 102, feature extraction and selection is performed based on the agricultural monitoring data to obtain key features related to crop growth.
In the invention, the data are subjected to feature extraction and selection according to the expertise and statistical analysis method in the agricultural field to obtain the key features related to the crop growth.
In step 103, a growth prediction initial model for crop growth prediction is established based on a convolutional neural network, the key features are taken as input, a growth stage is taken as output, and the growth prediction initial model is trained to obtain a growth prediction optimization model.
Preferably, the method is based on a convolutional neural network, and combines the single-factor models to establish a growth prediction initial model for crop growth prediction of overall nonlinear multifactor;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
Preferably, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches, and the output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
In the invention, when a model is built, a single factor influence model is built by using a convolutional neural network, each influence factor is taken as input, a growth stage is taken as output, and the model is built by using a convolutional neural network architecture. When the model is trained, the trained model is utilized to predict the future crop growth process, and the prediction result is evaluated and corrected according to the actual observation data, so that the prediction accuracy is further improved.
Wherein, the initial model of growth condition prediction includes: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
Preferably, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches, and the output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
In step 104, the agricultural big data obtained in real time is input into the growth situation prediction optimization model to obtain the growth situation prediction result of the crops.
In the invention, as shown in fig. 2, real-time or recent agricultural big data is input into a crop growth model to obtain a growth state prediction result of crops during model prediction. The predicted outcome may also be analyzed to provide scientific decisions for agricultural production.
The invention has the beneficial effects that:
1. the method improves the accuracy of crop growth prediction, utilizes rich agricultural big data to establish a high-precision crop model, can more accurately reflect the actual condition of crop growth, is beneficial to farmers and agricultural managers to better know the growth state and the change trend of crops, and takes corresponding management measures in time.
2. The method of the invention utilizes the big agricultural data and advanced technical means to realize the precise agricultural management, and can carry out the precise agricultural management according to the characteristics of different plots and different crops. By analyzing the big data, the difference and potential problems of different plots are identified, and a personalized management scheme is provided for each plot. This helps to reduce waste of resources and improve efficiency and sustainability of agricultural production.
3. The method provides decision support for agricultural production, such as optimal sowing time, irrigation quantity and timely sprinkling irrigation of pesticides, by predicting the growth vigor of crops.
4. Reducing risk and uncertainty, crop growth is affected by a variety of factors including climate change, soil conditions, plant diseases and insect pests, and the like. The method can provide prediction and assessment of crop growth through comprehensive analysis and modeling of multi-source data, and helps farmers and agricultural managers to better cope with risks and uncertainties. The information of the crop growth situation can be obtained in time, so that farmers can be helped to take corresponding measures, and loss caused by unpredictable factors is reduced.
Fig. 3 is a schematic structural view of a crop growth prediction system 300 according to an embodiment of the present invention. As shown in fig. 3, a crop growth prediction system 300 according to an embodiment of the present invention includes: a data acquisition unit 301, a key feature acquisition unit 302, a model determination unit 303, and a prediction unit 304.
Preferably, the data acquisition unit 301 is configured to acquire agricultural monitoring data, and perform preprocessing on the agricultural monitoring data.
Preferably, the data acquisition unit 301 acquires agricultural monitoring data, including:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
Preferably, the data acquisition unit 301 performs preprocessing on the agricultural monitoring data, including:
and cleaning, correcting and unifying the agricultural monitoring data.
Preferably, the key feature acquiring unit 302 is configured to perform feature extraction and selection based on the agricultural monitoring data, and acquire key features related to crop growth.
Preferably, the model determining unit 303 is configured to establish a growth prediction initial model for crop growth prediction based on a convolutional neural network, and train the growth prediction initial model with the key feature as input and the growth stage as output, so as to obtain a growth prediction optimization model.
Preferably, the model building unit 303 combines the single factor models based on a convolutional neural network to build an initial model of growth prediction for crop growth prediction with overall nonlinear multifactor;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
Preferably, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches
The output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
Preferably, the prediction unit 304 is configured to input the agricultural big data obtained in real time into the growth situation prediction optimization model, so as to obtain a growth situation prediction result of the crop.
The crop growth prediction system 300 according to the embodiment of the present invention corresponds to the crop growth prediction method 100 according to another embodiment of the present invention, and will not be described herein.
The invention has been described with reference to a few embodiments. However, as is well known to those skilled in the art, other embodiments than the above disclosed are equally possible within the scope of the invention.
In general, all terms used in the present invention are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/an/the [ means, component, etc. ]" are to be interpreted openly as referring to at least one instance of said means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, and any modifications and equivalents are intended to be included within the scope of the invention.

Claims (10)

1. A method for predicting crop growth, the method comprising:
acquiring agricultural monitoring data and preprocessing the agricultural monitoring data;
extracting and selecting features based on the agricultural monitoring data to obtain key features related to crop growth;
building a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model;
and inputting the agricultural big data obtained in real time into the growth situation prediction optimization model to obtain a growth situation prediction result of the crops.
2. The method of claim 1, wherein the acquiring agricultural monitoring data comprises:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
3. The method of claim 1, wherein the preprocessing the agricultural monitoring data comprises:
and cleaning, correcting and unifying the agricultural monitoring data.
4. The method of claim 1, wherein the method combines single factor models based on a convolutional neural network to build an initial model of growth prediction for crop growth prediction for overall nonlinear multifactorial;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
5. The method of claim 4, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches
The output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
6. A crop growth prediction system, the system comprising:
the data acquisition unit is used for acquiring agricultural monitoring data and preprocessing the agricultural monitoring data;
the key feature acquisition unit is used for extracting and selecting features based on the agricultural monitoring data to acquire key features related to crop growth;
the model determining unit is used for establishing a growth condition prediction initial model for crop growth condition prediction based on a convolutional neural network, taking the key characteristics as input, taking a growth stage as output, and training the growth condition prediction initial model to obtain a growth condition prediction optimization model;
the prediction unit is used for inputting the agricultural big data acquired in real time into the growth situation prediction optimization model to acquire a growth situation prediction result of the crops.
7. The system of claim 6, wherein the data acquisition unit acquires agricultural monitoring data, comprising:
acquiring environmental data and measure data affecting crop growth by utilizing an Internet of things or remote sensing technology; wherein the environmental data includes: meteorological data, soil data, temperature data and humidity data; the measure data comprises: crop generation data, pest condition data, and crop management data.
8. The system of claim 6, wherein the data acquisition unit pre-processes the agricultural monitoring data, comprising:
and cleaning, correcting and unifying the agricultural monitoring data.
9. The system according to claim 6, wherein the model building unit combines the single-factor models based on a convolutional neural network to build an overall nonlinear multi-factor initial model for growth prediction of crops;
the initial model for growth prediction comprises: the system comprises a first processing layer, more than two parallel sub-convolution neural network layers and a second processing layer; the output ends of the first processing layer are respectively connected with the input ends of the more than two parallel sub-convolution neural network layers, and the output ends of the more than two parallel sub-convolution neural network layers are respectively connected with the input ends of the second processing layer; after the data input into the first processing layer is processed by the first processing layer, the data can be processed by the more than two parallel sub-convolution neural network layers respectively, and the more than two sub-processing results obtained by processing can be overlapped on the second processing layer to obtain a processing result.
10. The system of claim 9, wherein the sub-convolutional neural network layer comprises a hybrid convolutional layer; wherein the hybrid convolution layer comprises: a sub-input layer, a sub-processing layer and five parallel sub-convolution branches; the output ends of the sub-input layers are respectively connected with the input ends of the five parallel sub-convolution branches
The output ends of the five parallel sub-convolution branches are respectively connected with the input ends of the sub-processing layers; the data input into the mixed convolution layer through the sub-input layer can be processed through the five parallel sub-convolution branches respectively, and the processed five sub-convolution branch processing results can be overlapped on the sub-processing layer to obtain the mixed convolution layer processing result.
CN202311779334.9A 2023-12-22 2023-12-22 Crop growth prediction method and system Pending CN117892861A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311779334.9A CN117892861A (en) 2023-12-22 2023-12-22 Crop growth prediction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311779334.9A CN117892861A (en) 2023-12-22 2023-12-22 Crop growth prediction method and system

Publications (1)

Publication Number Publication Date
CN117892861A true CN117892861A (en) 2024-04-16

Family

ID=90643436

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311779334.9A Pending CN117892861A (en) 2023-12-22 2023-12-22 Crop growth prediction method and system

Country Status (1)

Country Link
CN (1) CN117892861A (en)

Similar Documents

Publication Publication Date Title
Skobelev et al. Development of models and methods for creating a digital twin of plant within the cyber-physical system for precision farming management
US20220248616A1 (en) Irrigation control with deep reinforcement learning and smart scheduling
CN105302096A (en) Factory intelligent scheduling method
US20220414795A1 (en) Crop disease prediction and treatment based on artificial intelligence (ai) and machine learning (ml) models
CN107103395B (en) Short-term early warning method for crop pests
CN117652386A (en) Water-saving irrigation control system
CN116295662B (en) Crop growth state monitoring method and device, electronic equipment and medium
Nyakuri et al. IoT and AI based smart soil quality assessment for data-driven irrigation and fertilization
CN117575094B (en) Crop yield prediction and optimization method and device based on digital twin
CN117974348B (en) Wisdom agricultural thing networking monitoring system
CN117322214A (en) Crop fertilizer accurate application method and system based on neural network
CN116703639A (en) Soil fertility assessment and fertilization suggestion system and method based on deep learning
CN109685676A (en) Intelligent liquid manure management method and system
CN117455141A (en) Water, fertilizer and pesticide integrated irrigation equipment regulation and control method and system based on Internet of things
CN117892861A (en) Crop growth prediction method and system
CN111524023A (en) Greenhouse adjusting method and system
Zhang et al. PVIDSS: developing a WSN-based irrigation decision support system (IDSS) for viticulture in protected area, Northern China
Yang Modelling phenological development, yield and quality of lucerne (Medicago sativa L.) using APSIM next generation: A thesis submitted in partial fulfillment of the requirement for the Degree of Doctor of Philosophy at Lincoln University
CN115660236B (en) Crop weather period prediction method, device, electronic equipment and storage medium
CN117784290B (en) Sudden drought early warning method and system based on Bayesian neural network
KR20240052516A (en) The method of integrating heterogeneous environments growth data, and the method of controlling the growth conditions of the hamp
CN118246604A (en) Crop modularization growth data acquisition and growth prediction system
Wang Research on Intelligent Agricultural Monitoring and Control System Based on Neural Networks in the Internet of Things Environment
CN118708168A (en) Technology development system based on artificial intelligence technology
CN116386031A (en) Fruit tree nutrient stress diagnosis method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication