CN111476503B - Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data - Google Patents
Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data Download PDFInfo
- Publication number
- CN111476503B CN111476503B CN202010332084.4A CN202010332084A CN111476503B CN 111476503 B CN111476503 B CN 111476503B CN 202010332084 A CN202010332084 A CN 202010332084A CN 111476503 B CN111476503 B CN 111476503B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- oil palm
- prediction
- oil
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q10/06—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
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and system for predicting oil palm crude oil production using multi-source heterogeneous data includes: the data acquisition unit acquires multi-source heterogeneous data of the image oil palm crude oil yield in a target area, and processes and stores the acquired data in a uniform standard format; the data integration unit integrates and counts the multi-source heterogeneous data in a uniform and standard format to respectively obtain historical data and prediction index data; the test unit carries out statistical analysis and mining on the historical data to obtain training data and test data, selects a prediction model by utilizing the training data, carries out evaluation optimization on the prediction model by utilizing the test data and selects an optimal prediction model; and the prediction unit inputs the prediction index data into the optimal prediction model to predict the yield of the oil palm crude oil. The intelligent prediction of the oil palm crude oil yield in the middle and last days of the month in the large range of the fields of oil palm growth monitoring and production management is fast, timely and accurate.
Description
Technical Field
The invention relates to the field of oil palm crude oil yield estimation, in particular to a method and a system for predicting oil palm crude oil yield by utilizing multi-source heterogeneous data.
Background
Oil palm crude oil production has been an important piece of information of concern and key basis for decision making by national government agencies, oil palm large-scale planting agencies and enterprises, oil palm pressing plants, oil palm refineries, oil palm crude oil by-product producers, bulk grease traders, and bulk grease futures.
Meanwhile, the yield of the fresh oil palm fruit clusters, the unit yield of the fresh oil palm fruit clusters, the squeezing rate of the crude oil palm and the unit yield of the crude oil palm related to the production process of the crude oil palm provide key information for understanding production for all large related benefits.
The method for acquiring the crude oil yield of the oil palm at present is mainly based on the collection, arrangement, summarization and statistics of data in the process of oil palm production operation of oil palm crude oil organizations and enterprises, and the method relates to more personnel, more work types, long time consumption, repeated auditing, easy error making, serious delay and the like, so that serious information loss is brought when the crude oil yield of the oil palm needs to be quickly, timely and accurately known, and the production and market decision is difficult to be made timely.
Therefore, the problems of the prior art are to be further improved and developed.
Disclosure of Invention
The object of the invention is: in order to solve the problems in the prior art, the invention aims to provide a method and a system for rapidly, timely and accurately predicting the crude oil yield of oil palm in the upper, middle and lower late days of the month in a large range by utilizing multi-source heterogeneous data to count the field of oil palm growth monitoring and production management.
The technical scheme is as follows: in order to solve the technical problems, the technical scheme provides a method for predicting the yield of oil palm crude oil by using multi-source heterogeneous data, which comprises the following steps:
the data acquisition unit acquires multi-source heterogeneous data of the image oil palm crude oil yield in a target area, and processes and stores the acquired data in a uniform standard format;
step two, the data integration unit integrates and counts the multi-source heterogeneous data in a uniform and standard format to respectively obtain historical data and prediction index data;
thirdly, the test unit performs statistical analysis and mining on the historical data to obtain training data and test data, selects a prediction model by using the training data, evaluates and optimizes the prediction model by using the test data, and selects an optimal prediction model;
and step four, inputting the prediction index data into the optimal prediction model by the prediction unit to predict the yield of the oil palm crude oil.
The method for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data comprises the first step of,
a1, acquiring the planting distribution, area and tree age structure data of the oil palm trees by an oil palm measuring and calculating module, and processing and storing the acquired data according to a uniform standard format;
b1, acquiring a remote sensing image of a target area by the remote sensing acquisition module, extracting growth information of each time period and each area, oil palm tree canopy and oil palm tree height data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format;
step c1, the weather index module collects the weather key index data of the target area, and processes and stores the collected weather key index data according to a uniform standard format;
d1, collecting the data of the unit yield and output of the fresh fruit clusters, the unit yield and output of the oil palm crude oil and the oil extraction rate by a production statistical module, and processing and storing each data according to a uniform standard format;
and e1, the planting management module collects the data of planting management and fertilization, the factory operating rate, the price of the oil palm crude oil and the price of the bulk oil products, and processes and stores all the data according to a unified standard format.
The method for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data comprises the following steps of:
a2, integrating multi-source heterogeneous data in a unified standard format according to regions and time by a data integration module to obtain integrated data;
and b2, the data statistics module makes statistics on the integrated data according to the region and time to respectively obtain historical data and prediction index data.
The method for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data comprises the following steps:
a3, the data exploration module explores and analyzes the historical data to obtain training data and test data;
b3, selecting a prediction model and model parameters by a model selection module through a training number;
and c3, inputting the test data into the prediction model by the model test module, and performing parameter optimization and model evaluation intersection to obtain the optimal prediction model.
The method for predicting the yield of the oil palm crude oil by using the multi-source heterogeneous data further comprises a fifth step of displaying the optimal prediction model prediction result by using a display module.
A system for predicting oil palm crude oil production using multi-source heterogeneous data, comprising:
the data acquisition unit is used for acquiring multi-source heterogeneous data of the image oil palm crude oil yield in a target area, and processing and storing the acquired data in a uniform standard format;
the data integration unit is used for integrating and counting the multi-source heterogeneous data in the uniform and standard format to respectively obtain historical data and prediction index data;
the test unit is used for carrying out statistical analysis and mining on the prediction historical data to obtain training data and test data, selecting a prediction model by using the training data, carrying out evaluation optimization on the prediction model by using the test data and selecting an optimal prediction model;
the prediction unit is used for inputting the prediction index data into the optimal prediction model to predict the yield of the oil palm crude oil;
the data acquisition unit, the data integration unit, the test unit and the prediction unit are sequentially connected, and the data integration unit is connected with the prediction unit.
The system for predicting the crude oil yield of the oil palm by utilizing the multi-source heterogeneous data comprises a data acquisition unit, a data integration unit and a data acquisition unit, wherein the data acquisition unit comprises an oil palm measuring and calculating module, a remote sensing acquisition module, a meteorological index module, a production statistics module and a planting management module, and the oil palm measuring and calculating module, the remote sensing acquisition module, the meteorological index module, the production statistics module and the planting management module are respectively connected with the data integration unit.
The system for predicting the crude oil yield of the oil palm by utilizing the multi-source heterogeneous data comprises an oil palm measuring and calculating module, a data processing module and a data processing module, wherein the oil palm measuring and calculating module is used for acquiring the planting distribution, area and tree age structure data of the oil palm trees, and processing and storing the acquired data according to a uniform standard format;
the remote sensing acquisition module is used for acquiring a remote sensing image of a target area, extracting growth information of each time period and each area, a palm tree canopy and palm tree height data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format;
the weather index module is used for collecting weather key index data of a target area, and processing and storing the collected weather key index data according to a uniform standard format;
the production statistical module is used for collecting the data of the unit yield and the output of the fresh fruit clusters, the unit yield and the output of the crude oil of the oil palm and the oil pressing rate, and processing and storing all the data according to a unified standard format;
and the planting management module is used for collecting planting management and fertilization data, factory operating rate, oil palm crude oil price and bulk oil product price data, and processing and storing all the data according to a unified standard format.
The system for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data comprises a data integration module and a data statistics module,
the data integration module integrates the multi-source heterogeneous data in a uniform standard format according to regions and time to obtain integrated data;
and the data statistics module is used for carrying out statistics on the integrated data according to the region and the time to respectively obtain historical data and prediction index data.
The system for predicting the crude oil yield of the oil palm by utilizing the multi-source heterogeneous data is characterized in that prediction index data of planting distribution, area and tree age structure of the oil palm trees are counted according to regions;
the information of the growth of each time period and each region of the oil palm trees, the oil palm tree canopy and the prediction index data of the oil palm tree height are counted according to the region;
and the prediction index data of the meteorological key indexes are counted to a specified time scale according to the regions.
The system for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data comprises a test unit, a data search module, a model selection module and a model test module, wherein the test unit comprises a data search module, a model selection module and a model test module;
the data exploration module is used for exploring and analyzing the prediction index data to obtain training data and test data;
the model selection module selects a prediction model and model parameters through a training number;
and the model test module inputs test data into the prediction model, and performs parameter optimization and model evaluation intersection to obtain an optimal prediction model.
The system for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data further comprises a display module, wherein the display module is connected with the prediction unit and used for displaying the prediction result of the optimal prediction model.
(III) the beneficial effects are as follows: the invention provides a method and a system for predicting crude oil yield of oil palm by utilizing multi-source heterogeneous data, which can be used for rapidly, timely and accurately predicting the crude oil yield of oil palm in the upper, middle and lower ten days of the month in a large range in the field of oil palm growth monitoring and production management.
Drawings
FIG. 1 is a schematic diagram of the process steps for predicting oil palm crude oil production using multi-source isomerization data according to the present invention;
FIG. 2 is a schematic diagram of the system connections for predicting oil palm crude oil production using multi-source heterogeneous data according to the present invention;
FIG. 3 is a schematic diagram of a process for predicting the crude oil yield of oil palm according to a preferred embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to preferred embodiments, and more details are set forth in the following description in order to provide a thorough understanding of the present invention, but it is apparent that the present invention can be embodied in many other forms different from the description herein and can be similarly generalized and deduced by those skilled in the art based on the practical application without departing from the spirit of the present invention, and therefore, the scope of the present invention should not be limited by the contents of this detailed embodiment.
The drawings are schematic representations of embodiments of the invention, and it is noted that the drawings are intended only as examples and are not drawn to scale and should not be construed as limiting the true scope of the invention.
As shown in fig. 1, the method for predicting oil palm crude oil production by using multi-source heterogeneous data comprises the following steps:
acquiring multi-source heterogeneous data of the image oil palm crude oil yield in a target area by a data acquisition unit, and processing and storing the acquired data in a uniform standard format;
step two, the data integration unit integrates and counts the multi-source heterogeneous data in a uniform and standard format to respectively obtain historical data and prediction index data;
thirdly, the test unit performs statistical analysis and mining on the historical data to obtain training data and test data, the training data selects a prediction model, the test data evaluates and optimizes the prediction model, and the optimal prediction model is selected;
inputting the prediction index data into an optimal prediction model by a prediction unit to predict the yield of the oil palm crude oil;
and fifthly, displaying the prediction result of the optimal prediction model by the display module.
The historical data includes metrics and production, and the predictive metrics data includes metrics.
The first step comprises the following steps of,
a1, acquiring the planting distribution, area and tree age structure data of the oil palm trees by an oil palm measuring and calculating module, and processing and storing the acquired data according to a uniform standard format;
b1, acquiring a remote sensing image of a target area by the remote sensing acquisition module, extracting growth information of each time period and each area, oil palm tree canopy and oil palm tree height data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format;
step c1, the weather index module collects the weather key index data of the target area, and processes and stores the collected weather key index data according to a uniform standard format;
d1, collecting the data of the unit yield and output of the fresh fruit clusters, the unit yield and output of the oil palm crude oil and the oil extraction rate by a production statistical module, and processing and storing each data according to a uniform standard format;
and e1, the planting management module collects the data of planting management and fertilization, the factory operating rate, the price of the oil palm crude oil and the price of the bulk oil products, and processes and stores all the data according to a unified standard format.
The second step comprises the following steps:
a2, integrating multi-source heterogeneous data in a unified standard format according to regions and time by a data integration module to obtain integrated data;
and b2, the data statistics module makes statistics on the integrated data according to the region and time to respectively obtain historical data and prediction index data.
The third step comprises:
a3, the data exploration module explores and analyzes the historical data to obtain training data and test data;
b3, selecting a learning model and model parameters by a model selection module through training numbers;
and c3, inputting the test data into the learning model by the model test module, and performing parameter optimization and model evaluation intersection to obtain an optimal prediction model.
The system for predicting the yield of the crude oil of the oil palm by utilizing the multi-source heterogeneous data comprises a data acquisition unit, a data integration unit, a test unit, a prediction unit and a display unit, as shown in figure 2.
The data acquisition unit, the data integration unit, the test unit, the prediction unit and the display unit are sequentially connected, wherein the data integration unit is connected with the prediction unit.
And the data acquisition unit is used for acquiring multi-source heterogeneous data of the image oil palm crude oil yield in the target area, and processing and storing the acquired data in a unified standard format.
The data acquisition unit comprises an oil palm measuring and calculating module, a remote sensing acquisition module, a meteorological index module, a production statistical module and a planting management module, wherein the oil palm measuring and calculating module, the remote sensing acquisition module, the meteorological index module, the production statistical module and the planting management module are respectively connected with the data integration unit.
The oil palm measuring and calculating module is used for acquiring data of planting distribution, area, tree age structure and the like of the oil palm trees, and processing and storing the acquired data according to a uniform standard format.
The remote sensing acquisition module is used for acquiring a remote sensing image of a target area, extracting the growth information of each time period and each area, the oil palm tree canopy, the oil palm tree height data, the oil palm tree planting terrain and other data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format.
And the meteorological index module is used for collecting the meteorological key index data of the target area, and processing and storing the collected meteorological key index data according to a uniform standard format. The meteorological key index data can be, but is not limited to, key index data such as the highest air temperature, the lowest air temperature, rainfall, humidity, net solar radiation, potential transpiration, Nino index and the like.
And the production statistical module is used for collecting the data of the unit yield and the output of the fresh fruit clusters, the unit yield and the output of the crude oil of the oil palm, the oil extraction rate and the like, and processing and storing all the data according to a unified standard format.
The planting management module is used for collecting data of planting management and fertilization data, factory operating rate, price of crude oil of oil palm, price of bulk oil products and the like, and processing and storing all the data according to a unified standard format.
And the data integration unit is used for integrating and counting the multi-source heterogeneous data in the uniform and standard format to obtain the prediction index data. The data integration unit comprises a data integration module and a data statistics module.
And the data integration module integrates the multi-source heterogeneous data in a uniform standard format according to regions and time to obtain integrated data. And the data statistics module is used for carrying out statistics on the integrated data according to the region and the time to respectively obtain historical data and prediction index data.
And (4) carrying out statistics on prediction index data such as the planting distribution, the area, the tree age structure and the like of the oil palm trees according to regions. And (4) carrying out statistics on the prediction index data of the oil palm trees, such as the growth information of each time period and each region, the oil palm tree canopy, the oil palm tree height and the like according to the region. And the prediction index data of the meteorological key indexes are counted to a specified time scale according to the regions.
And the test unit is used for carrying out statistical analysis and mining on the historical data to obtain training data and test data, the training data selects a prediction model, the test data carries out evaluation optimization on the prediction model, and the optimal prediction model is selected. The test unit comprises a data exploration module, a model selection module and a model test module.
And the data exploration module is used for exploring and analyzing the historical data to obtain training data and test data. The model selection module selects/obtains a prediction model and model parameters through the training number. And the model test module inputs test data into the prediction model, and performs parameter optimization and model evaluation to obtain an optimal prediction model. The test data may also be referred to as training data.
And the prediction unit is used for inputting the prediction index data into the optimal prediction model to predict the yield of the oil palm crude oil.
And the display module is connected with the prediction unit and is used for displaying the prediction result of the optimal prediction model.
The method and the system for predicting the crude oil yield of the oil palm utilize multi-source heterogeneous data to automatically collect data such as the planting area of the oil palm, the tree age of the oil palm, a remote sensing key index, a meteorological key index, planting production indexes and the like, design a targeted automatic processing and integrating process according to the characteristics of various data, and construct a prediction system for the crude oil, which integrates the multi-source heterogeneous data collection and processing, large-scale heterogeneous data storage and calculation, mass data collaborative scheduling and analysis, and multi-type model training and optimization into a whole.
The following is a description of a specific process for predicting the yield of oil palm crude oil according to a preferred embodiment of the present application.
As shown in fig. 3, the oil palm measurement and calculation module of the data acquisition unit may acquire data of oil palm tree planting distribution, area, tree age structure, and the like in a target area in a large range by a large-scale planting organization, a national government organization, or an artificial intelligence method of advanced self-research, and perform processing and storage of a uniform standard format on the acquired data, where the data processed in the uniform standard format is standard data. And meanwhile, the standard data are sent to the data integration unit, and a data integration module of the data integration unit integrates the standard data of the planting distribution, the area, the tree age structure and the like of the oil palm trees according to the region and time to obtain integrated data. And a data statistics module of the data integration unit is used for carrying out statistics on the integrated data such as the planting distribution, the area, the tree age structure and the like of the oil palm trees according to regions to respectively obtain historical data and prediction index data.
And a remote sensing acquisition module of the data acquisition unit is used for extracting growth information of the oil palm trees in each time period and in each area, oil palm tree canopy, oil palm tree height, oil palm tree planting terrain and other data from the remote sensing image, and processing and storing the acquired data in a unified standard format to obtain standard data. And meanwhile, the standard data are sent to the data integration unit, and a data integration module of the data integration unit integrates the growth information of the oil palm trees in each time period and region, the oil palm tree canopy, the oil palm tree height, the topography of the oil palm trees and other standard data according to the region and time to obtain integrated data. And a data statistics module of the data integration unit is used for carrying out statistics on integrated data of the growth information of the oil palm trees in each time period and region, the oil palm tree canopy, the oil palm tree height, the oil palm tree planting terrain and the like according to the region to respectively obtain indexes of historical data and prediction index data.
The meteorological index module of the data acquisition unit collects meteorological key index data such as the highest air temperature, the lowest air temperature, rainfall, humidity, net solar radiation, potential transpiration, Nino index and the like by compiling an automatic collection and processing tool, and carries out processing and storage of a unified standard format on the acquired data, wherein the data processed by the unified standard format is standard data. And meanwhile, the standard data is sent to the data integration unit, and a data integration module of the data integration unit integrates the standard data of the meteorological key indexes according to regions and time to obtain integrated data. And the data statistics module of the data integration unit is used for counting the standard data of the meteorological key indexes to a specified time scale according to regions to respectively obtain indexes of historical data and prediction index data.
The production statistical module of the data acquisition unit collects data such as fresh fruit cluster yield, fresh fruit cluster yield per unit, oil palm crude oil yield per unit, oil extraction rate and the like by compiling an automatic collection and arrangement tool, and carries out processing and storage on the acquired data in a unified standard format, wherein the data processed in the unified standard format is standard data. And meanwhile, the standard data are sent to the data integration unit, and the data integration module of the data integration unit integrates the standard data such as the yield of the fresh fruit clusters, the unit yield of the fresh fruit clusters, the yield of the oil palm crude oil, the unit yield of the oil palm crude oil, the oil extraction rate and the like according to regions and time to obtain integrated data. And a data statistics module of the data integration unit is used for carrying out statistics on the integrated data such as the yield of the fresh fruit clusters, the unit yield of the fresh fruit clusters, the yield of the oil palm crude oil, the unit yield of the oil palm crude oil, the oil extraction rate and the like to respectively obtain the indexes and the yield of the historical data and predict the indexes of the index data.
The planting management module of the data acquisition unit collects data such as planting management and fertilization, factory operating rate, price of crude oil of oil palm and price of bulk oil products, and carries out processing and storage of unified standard format on the obtained data, and the data processed by the unified standard format is standard data. The planting management module can also conclude the reproductive growth rule and the characteristic knowledge of the phenological period of the oil palm, and integrate the data into a form capable of being matched with other data according to requirements. And meanwhile, the standard data are sent to the data integration unit, and a data integration module of the data integration unit integrates the standard data such as planting management and fertilization, factory operating rate, oil palm crude oil price and bulk oil product price according to region and time to obtain integrated data. And a data statistics module of the data integration unit is used for carrying out statistics on integrated data such as planting management and fertilization, factory operating rate, price of crude oil of oil palm, price of bulk oil products and the like to respectively obtain indexes of historical data and prediction index data.
The processing of the unified standard format further comprises optimizing the image data or image pictures of the growth information of the region, the oil palm tree canopy, the oil palm tree height, the planting terrain of the oil palm tree and the like. The image data or the image picture can be preferably subjected to fine-granularity gray level processing, the picture resolution is preferably simplified to the fineness of one third to one fourth of the shot image picture, the simplified image picture is subjected to gray level processing, the object outline of the image data or the image picture is obtained according to the gray level picture of the image picture, and non-oil palm data in the image data or the image picture is rapidly removed through comparison of the outline pictures of the image pictures with the same image size ratio. For example, the oil palm trees are vertical trees and are as high as 10 meters or more, the outline of the object is quickly obtained through the outline of the gray-scale image of the image picture, the short plant images are quickly eliminated according to the outline of the object including the height of the object, and the accuracy rate of oil palm identification is improved.
The data exploration module of the test unit explores and analyzes historical data such as oil palm distribution range and area, oil palm tree age, remote sensing key indexes, meteorological key indexes, oil palm production statistics and the like, and the historical data are divided into training data and test data according to a certain principle, wherein the training data and the test data can be the same database, and no drastic limitation is made.
The model selection module of the test unit excavates oil palm planting distribution and area, oil palm tree age, remote sensing key indexes, meteorological data, oil palm production statistics and other training data including indexes and yield, selects a prediction model and model parameters. The prediction model may be a statistical model, a machine learning model, or the like, and is not limited herein.
And the model test module of the test unit inputs test data comprising indexes and yield into the prediction model, performs cross iterative training and testing on the prediction model, optimizes parameters of the selected prediction model, and performs precision evaluation to obtain an optimal prediction model.
Inputting the predicted data including the weather index data, the remote sensing index, the area, the tree age and the like of the key prediction into an optimal prediction model, and predicting the crude oil yield of the oil palm in the ten-month period to obtain the predicted crude oil yield of the oil palm.
The display unit displays the predicted oil palm crude oil production.
The above description is provided for the purpose of illustrating the preferred embodiments of the present invention and will assist those skilled in the art in more fully understanding the technical solutions of the present invention. However, these examples are merely illustrative, and the embodiments of the present invention are not to be considered as being limited to the description of these examples. For those skilled in the art to which the invention pertains, several simple deductions and changes can be made without departing from the inventive concept, and all should be considered as falling within the protection scope of the invention.
Claims (10)
1. The method for predicting the yield of the oil palm crude oil by utilizing the multi-source heterogeneous data is characterized by comprising the following steps of:
acquiring multi-source heterogeneous data of the image oil palm crude oil yield in a target area by a data acquisition unit, and processing and storing the acquired data in a uniform standard format;
the data acquisition unit comprises a remote sensing acquisition module, wherein the remote sensing acquisition module is used for acquiring a remote sensing image of a target area, extracting growth information of each time period and each area, a palm tree canopy, palm tree height data and palm tree planting terrain data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format;
the processing of the unified standard format also comprises the steps of respectively simplifying the growth information of the region, the oil palm tree canopy, the oil palm tree height and the topographic image data of oil palm tree planting or the image resolution of the image picture to one third to one fourth of the fineness of the shot image picture, carrying out gray level processing on the simplified image picture, obtaining the object outline of the image data or the image picture according to the gray level image of the image picture, and rapidly removing the non-oil palm data in the image data or the image picture by comparing the outline images of the image pictures with the same image size ratio;
step two, the data integration unit integrates and counts the multi-source heterogeneous data in a uniform and standard format to respectively obtain historical data and prediction index data;
thirdly, the test unit performs statistical analysis and mining on the historical data to obtain training data and test data, selects a prediction model by using the training data, evaluates and optimizes the prediction model by using the test data, and selects an optimal prediction model;
and step four, inputting the prediction index data into the optimal prediction model by the prediction unit to predict the yield of the oil palm crude oil.
2. The method for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 1, wherein the first step comprises,
a1, acquiring the planting distribution, area and tree age structure data of the oil palm trees by an oil palm measuring and calculating module, and processing and storing the acquired data according to a uniform standard format;
step c1, the weather index module collects the weather key index data of the target area, and processes and stores the collected weather key index data according to a uniform standard format;
d1, collecting the data of the unit yield and output of the fresh fruit clusters, the unit yield and output of the oil palm crude oil and the oil extraction rate by a production statistical module, and processing and storing each data according to a uniform standard format;
and e1, the planting management module collects the data of planting management and fertilization, the factory operating rate, the price of the oil palm crude oil and the price of the bulk oil products, and processes and stores all the data according to a unified standard format.
3. The method for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 1, wherein the second step comprises:
a2, integrating multi-source heterogeneous data in a unified standard format according to regions and time by a data integration module to obtain integrated data;
and b2, the data statistics module makes statistics on the integrated data according to the region and time to respectively obtain historical data and prediction index data.
4. The method for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 1, wherein the third step comprises:
a3, the data exploration module explores and analyzes the historical data to obtain training data and test data;
b3, selecting a prediction model and model parameters by a model selection module through training data;
and c3, inputting the test data into the prediction model by the model test module, and performing parameter optimization and model evaluation intersection to obtain the optimal prediction model.
5. The method for predicting oil palm crude oil yield by using multi-source heterogeneous data according to claim 1, further comprising a fifth step of displaying the prediction result of the optimal prediction model by a display module.
6. Utilize system of multisource isomerism data prediction oil palm crude oil production, its characterized in that includes:
the data acquisition unit is used for acquiring multi-source heterogeneous data of the image oil palm crude oil yield in a target area, and processing and storing the acquired data in a uniform standard format; the data acquisition unit comprises a remote sensing acquisition module, wherein the remote sensing acquisition module is used for acquiring a remote sensing image of a target area, extracting growth information of each time period and each area, a palm tree canopy, palm tree height data and palm tree planting terrain data from the remote sensing image, and processing and storing the extracted data according to a uniform standard format;
the processing of the unified standard format also comprises the steps of respectively simplifying the growth information of the region, the oil palm tree canopy, the oil palm tree height and the topographic image data of oil palm tree planting or the image resolution of the image picture to one third to one fourth of the fineness of the shot image picture, carrying out gray level processing on the simplified image picture, obtaining the object outline of the image data or the image picture according to the gray level image of the image picture, and rapidly removing the non-oil palm data in the image data or the image picture by comparing the outline images of the image pictures with the same image size ratio;
the data integration unit is used for integrating and counting the multi-source heterogeneous data in the uniform and standard format to respectively obtain historical data and prediction index data;
the test unit is used for carrying out statistical analysis and mining on the prediction historical data to obtain training data and test data, selecting a prediction model by using the training data, carrying out evaluation optimization on the prediction model by using the test data and selecting an optimal prediction model;
the prediction unit is used for inputting the prediction index data into the optimal prediction model to predict the yield of the oil palm crude oil;
the data acquisition unit, the data integration unit, the test unit and the prediction unit are sequentially connected, and the data integration unit is connected with the prediction unit.
7. The system for predicting crude oil yield of oil palm according to the multi-source heterogeneous data of claim 6, wherein the data acquisition unit comprises an oil palm measurement and calculation module, a meteorological index module, a production statistics module and a planting management module, and the oil palm measurement and calculation module, the remote sensing acquisition module, the meteorological index module, the production statistics module and the planting management module are respectively connected with the data integration unit.
8. The system for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 6, wherein the data integration unit comprises a data integration module, a data statistics module,
the data integration module integrates the multi-source heterogeneous data in a uniform standard format according to regions and time to obtain integrated data;
and the data statistics module is used for carrying out statistics on the integrated data according to the region and the time to respectively obtain historical data and prediction index data.
9. The system for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 6, wherein the testing unit comprises a data exploration module, a model selection module, and a model testing module;
the data exploration module is used for exploring and analyzing the prediction index data to obtain training data and test data;
the model selection module selects a prediction model and model parameters through a training number;
and the model test module inputs test data into the prediction model, and performs parameter optimization and model evaluation intersection to obtain an optimal prediction model.
10. The system for predicting oil palm crude oil production using multi-source heterogeneous data according to claim 6, further comprising a display module connected to the prediction unit for displaying the prediction results of the optimal prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332084.4A CN111476503B (en) | 2020-04-24 | 2020-04-24 | Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332084.4A CN111476503B (en) | 2020-04-24 | 2020-04-24 | Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111476503A CN111476503A (en) | 2020-07-31 |
| CN111476503B true CN111476503B (en) | 2021-04-30 |
Family
ID=71764113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010332084.4A Active CN111476503B (en) | 2020-04-24 | 2020-04-24 | Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476503B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257908B (en) * | 2020-09-30 | 2023-01-17 | 嘉应学院 | Mountain area agricultural multi-source heterogeneous data integration method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834813A (en) * | 2015-04-28 | 2015-08-12 | 南京邮电大学 | Statistic analysis processing method and device for multi-source heterogeneous data of internet of things |
| CN108197741A (en) * | 2017-12-29 | 2018-06-22 | 深圳春沐源控股有限公司 | Method and device for predicting plant yield |
| CN109635994A (en) * | 2018-10-23 | 2019-04-16 | 广东精点数据科技股份有限公司 | A kind of crop yield prediction technique for realizing the multi-source heterogeneous fusion of influence factor |
| CN109978234A (en) * | 2019-03-01 | 2019-07-05 | 北京农业信息技术研究中心 | Soil moisture content prediction, irrigation decision method and apparatus |
-
2020
- 2020-04-24 CN CN202010332084.4A patent/CN111476503B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834813A (en) * | 2015-04-28 | 2015-08-12 | 南京邮电大学 | Statistic analysis processing method and device for multi-source heterogeneous data of internet of things |
| CN108197741A (en) * | 2017-12-29 | 2018-06-22 | 深圳春沐源控股有限公司 | Method and device for predicting plant yield |
| CN109635994A (en) * | 2018-10-23 | 2019-04-16 | 广东精点数据科技股份有限公司 | A kind of crop yield prediction technique for realizing the multi-source heterogeneous fusion of influence factor |
| CN109978234A (en) * | 2019-03-01 | 2019-07-05 | 北京农业信息技术研究中心 | Soil moisture content prediction, irrigation decision method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111476503A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fan et al. | The future of Internet of Things in agriculture: Plant high-throughput phenotypic platform | |
| CN111045117B (en) | Climate monitoring and predicting platform | |
| CN106651004B (en) | Flood disaster prediction method based on rainfall flood disaster time-space database | |
| CN106980750B (en) | A kind of Soil Nitrogen estimation method of reserve based on typical correspondence analysis | |
| CN112579807A (en) | Smart agriculture full-period planting data cloud sharing platform based on cloud computing and big data analysis | |
| NL2029693B1 (en) | Remote sensing prediction method for fragrant pear maturity period based on multi-source remote sensing data | |
| CN108764527B (en) | Screening method for soil organic carbon library time-space dynamic prediction optimal environment variables | |
| CN108205718B (en) | Grain crop sampling yield measurement method and system | |
| CN111476503B (en) | Method and system for predicting oil palm crude oil yield by using multi-source heterogeneous data | |
| CN111476197A (en) | Oil palm identification and area extraction method and system based on multi-source satellite remote sensing image | |
| CN117694070A (en) | Nutrient element inversion evaluation and intelligent variable accurate fertilization decision system | |
| CN114693367A (en) | Agricultural product price big data monitoring and visualization system and method | |
| CN117770106A (en) | Digital twinning-based farmland irrigation method | |
| CN116703639A (en) | Soil fertility assessment and fertilization suggestion system and method based on deep learning | |
| CN116844043A (en) | Fruit tree state detection method and system | |
| CN103631999A (en) | NPP monitoring net sampling design method based on sampling point space-time representativeness | |
| Wei et al. | Application of remote sensing technology in crop estimation | |
| CN113344247B (en) | Deep learning-based power facility site selection prediction method and system | |
| McGlinchey | Computer crop model applications: developments in Swaziland | |
| KR101629178B1 (en) | Apparatus for technology life analysis using multiple patent indicators | |
| Bhavanandam | Wcp: Weather-based crop yield prediction using machine learning and big data analytics | |
| CN114462834A (en) | Regional portrait construction method and system based on multi-channel data fusion | |
| CN112734119A (en) | Corn yield prediction method based on spatial nutrient cluster analysis | |
| CN112488230A (en) | Crop water stress degree judging method and device based on machine learning | |
| Dissanayake et al. | Crop Yield Forecasting using Machine Learning Techniques-A Systematic Literature Review |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |