CN115481795A - Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount - Google Patents
Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount Download PDFInfo
- Publication number
- CN115481795A CN115481795A CN202211109444.XA CN202211109444A CN115481795A CN 115481795 A CN115481795 A CN 115481795A CN 202211109444 A CN202211109444 A CN 202211109444A CN 115481795 A CN115481795 A CN 115481795A
- Authority
- CN
- China
- Prior art keywords
- corn
- amount
- ndre
- num1
- field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000618 nitrogen fertilizer Substances 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 35
- 240000008042 Zea mays Species 0.000 claims abstract description 125
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims abstract description 125
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims abstract description 121
- 235000005822 corn Nutrition 0.000 claims abstract description 121
- 101100517651 Caenorhabditis elegans num-1 gene Proteins 0.000 claims abstract description 36
- 230000007613 environmental effect Effects 0.000 claims abstract description 34
- 239000003337 fertilizer Substances 0.000 claims abstract description 33
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 6
- 238000002310 reflectometry Methods 0.000 claims description 9
- 241000196324 Embryophyta Species 0.000 claims description 8
- 101100129590 Schizosaccharomyces pombe (strain 972 / ATCC 24843) mcp5 gene Proteins 0.000 claims description 6
- 238000012885 constant function Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 4
- 235000009973 maize Nutrition 0.000 claims description 4
- 239000002689 soil Substances 0.000 claims description 4
- 238000009331 sowing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 240000006394 Sorghum bicolor Species 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C21/00—Methods of fertilising, sowing or planting
- A01C21/007—Determining fertilization requirements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Soil Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- Environmental Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Evolutionary Biology (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
Abstract
The invention provides a generation method of a recommendation model, a recommendation method of nitrogen fertilizer application amount and a device thereof, comprising the following steps: obtaining base fertilizer amount, V9-stage topdressing amount, corn yield actual value and environmental parameters corresponding to different Num1 corn farmlands, generating a recommendation model based on an Xgboost regression algorithm, and training the recommendation model by using the base fertilizer amount, the V9-stage topdressing amount, the corn yield and the environmental parameters of the Num1 corn farmlands. So that nitrogen application rates can be recommended.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a generation method of a recommendation model, a recommendation method of nitrogen fertilizer application amount and a device thereof.
Background
Optimizing nitrogen fertilizer management is crucial to optimizing corn yield, improving nitrogen fertilizer utilization efficiency, minimizing fertilizer input cost and environmental impact. Insufficient nitrogen fertilizer usage can cause significant reductions in protein content and grain yield. Over-fertilization can reduce the attributes of yield, quality, and various environmental issues. The purpose of nitrogen recommendation is to reduce the difference between the nitrogen supply and the oxygen demand of plants, so that the problem of recommending the application amount of nitrogen fertilizers to corn farmlands is an urgent need to be solved.
Disclosure of Invention
The invention aims to provide a generation method of a recommendation model, a recommendation method of nitrogen fertilizer application amount and a device thereof.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for generating a recommended model for recommending nitrogen fertilizer application amount, comprising the steps of: obtain Field of different Num1 corn fields i The corresponding base fertilizer amount, the topdressing amount in the V9 stage and the actual value Y of the corn yield i And an environmental parameter, where Num1 is a natural number, i =1, 2.., num1; generating a recommendation model based on an Xgboost regression algorithm, and utilizing Num1 corn farmland fields i Amount of basal fertilizer, amount of additional fertilizer in V9 stage, and corn yield Y i Training the recommendation model by using the environment parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i The predicted value of the corn constant of (1),
as a further improvement of one embodiment of the present invention, the corn farm Field i The environmental parameters of (a) include at least: corn farmland Field i The previous crop type is used for representing whether the previous crop is a leguminous plant or not, and the ploughing depth is used for representing whether the land is deeply ploughed or not.
As a further improvement of one embodiment of the present invention, the corn farm Field i The environmental parameters of (a) include at least: NDVI i 、CCCI i 、Macc i And NDRE i ,NDVI i =(R NIR,i -R RED,i )/(R NIR,i +R RED,i ),Macc i =(R NIR,i -R RedEdge,i )/(R NIR,i -R RED,i ),NDRE i =(R NIR,i -R RedEdge,i )/(R NIR,i +R RedEdge,i ),CCCI i =(NDRE i -NDRE min )/(NDRE max -NDRE min ),NDRE max =max(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ),NDRE min =min(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ) (ii) a Wherein R is NIR,i 、R RED,i And R RedEdge,i Respectively Field of corn farmland i The reflectivity of the corn in the V9 growth period in the near infrared band, the reflectivity of the red band and the reflectivity of the red edge band.
As a further improvement of one embodiment of the present invention, the corn farm Field i The environmental parameters of (a) include at least: AWDI i =PPT i *SDI i wherein, in the process, n is corn sowing Date and continuous Date j The number of days between the latest day of middle; at Num2 consecutive dates Date j Field of corn Field i The rainfall of (2) is Rain i,j The highest temperature is Tmax i,j And the minimum temperature is Tmin i,j (ii) a Num2 is a natural number, j =1,2.
The embodiment of the invention also provides a generation device of a recommendation model for recommending nitrogen fertilizer application amount, which comprises the following modules: an information acquisition module for acquiring Field of different Num1 corn fields i Base fertilizer amount, topdressing amount in V9 stage, and actual value Y of corn yield i And an environmental parameter, where Num1 is a natural number, i =1, 2.., num1; a recommendation model training module for generating a recommendation model based on Xgboost regression algorithm and using Num1 corn farmland fields i Amount of basal fertilizer, amount of additional fertilizer in V9 stage, and corn yield Y i Training the recommendation model by using the environmental parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i The predicted value of the maize constant of (c),
as a further improvement of one embodiment of the present invention, the corn farm Field i The environmental parameters of (a) include at least: corn farmland Field i The previous crop type is used for representing whether the previous crop is a leguminous plant or not, and the ploughing depth is used for representing whether the land is deeply ploughed or not.
The embodiment of the invention also provides a method for recommending the nitrogen fertilizer application amount, which comprises the following steps: executing the generation method and obtaining a recommendation model, obtaining environmental parameters of the corn farmland to be processed, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be processed based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the V9-stage topdressing amount; and generating a function G (x) = F (x) × CPRice-x × NPrice, obtaining a value XNum of which G (x) is the maximum x, and then recommending the nitrogen fertilizer application amount to be XNum, wherein CPRice is the price of the corn and NPrice is the price of the nitrogen fertilizer.
As a further improvement of an embodiment of the present invention,wherein, beta 0 、β 1 、β 2 And e is a constant, e is an error term,
the embodiment of the invention also provides a nitrogen fertilizer application amount recommending device, which comprises the following modules: the recommendation model generation module is used for executing the generation method and obtaining a recommendation model, obtaining environmental parameters of the corn farmland to be processed, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be processed based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the fertilizer application amount in the V9 stage; and the nitrogen fertilizer application amount generating module is used for generating a function G (x) = F (x) × CPRice-x × NPice to obtain a value XNum of which G (x) is x at maximum, and the recommended nitrogen fertilizer application amount is XNum, wherein CPRice is the price of the corn and NPice is the price of the nitrogen fertilizer.
As a further improvement of an embodiment of the present invention, the nitrogen fertilizer application amount generation module is further configured to:wherein, beta 0 、β 1 、β 2 And e is a constant, e is an error term,
compared with the prior art, the invention has the technical effects that: the embodiment of the invention provides a generation method of a recommendation model, a recommendation method of nitrogen fertilizer application amount and a device thereof, comprising the following steps: obtaining base fertilizer amount, V9-stage topdressing amount, corn yield actual value and environmental parameters corresponding to different Num1 corn farmlands, generating a recommendation model based on an Xgboost regression algorithm, and training the recommendation model by using the base fertilizer amount, the V9-stage topdressing amount, the corn yield and the environmental parameters of the Num1 corn farmlands. So that nitrogen application rates can be recommended.
Drawings
FIG. 1 is a flow chart illustrating a method for generating a recommendation model according to an embodiment of the present invention;
FIG. 2 is a diagram of experimental results of a method for generating a recommendation model in an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a recommendation method in an embodiment of the present invention;
fig. 4A and 4B are graphs of experimental results of the recommendation method in the embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes in accordance with the embodiments are within the scope of the present invention.
Terms such as "upper," "above," "lower," "below," and the like, used herein to denote relative spatial positions, are used for ease of description to describe one element or feature's relationship to another element or feature as illustrated in the figures. The spatially relative positional terms may be intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
In the experiment of the inventor, an experimental Field needs to be obtained firstly, and then the experimental Field is divided into Num1 blocks, so that Num1 corn farmland Field are obtained 1 、Field 2 、...、Field Num1 Optionally, dividing the Field into Num1 blocks of corn fields with equal area 1 、Field 2 、...、Field Num1 . It will be appreciated that, in carrying out the experiment, the corn farm Field 1 、Field 2 、...、Field Num1 The environmental parameters of (1) are determined, and the inventor can change the Field of each corn Field i Amount of base fertilizer and amount of top dressing at V9 stage, e.g. corn Field 1 、Field 2 、...、Field Num1 Are equal (e.g., 45 kg/ha each), corn Field 1 、Field 2 、...、Field Num1 The respective corresponding Num 1V 9-stage topdressing amounts of (A) can form an arithmetic progression (e.g., a minimum of 0 kg/ha, a maximum of 280 kg/ha, and a tolerance of 45 kg/ha), and during the corn harvesting season, field per corn Field can be obtained i Corn constant (i.e., actual value of corn yield Y) i )。
Here, the actual values of the amount of base fertilizer, the amount of additional fertilizer in the V9 stage, and the corn yield Y i And environmental parameters, etc. may be input by a user into a computer system, which then performs the method of generating the recommendation model.
As shown in fig. 1, the method comprises the following steps:
step 101: obtaining different Num1 corn farmland Field i The corresponding base fertilizer amount, the topdressing amount in the V9 stage and the actual value Y of the corn yield i And an environmental parameter, where Num1 is a natural number, i =1, 2.., num1;
step 102: generating a recommendation model based on an Xgboost regression algorithm, and utilizing Num1 corn farmland fields i Amount of basal fertilizer, amount of additional fertilizer in V9 stage, and corn yield Y i Training the recommendation model by using the environmental parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i The predicted value of the maize constant of (c),
in the method for generating the recommended model of this example, the base fertilizer amount, the V9 stage topdressing amount, and the actual corn yield value Y were measured i And the environmental parameters are combined together to establish an estimated production model which integrates a plurality of observation data sources and different growth period information. The model is simple and easy to operate.
Here, xgboost is an optimized distributed gradient enhancement library, which has the characteristics of high efficiency and flexibility, and implements a machine learning algorithm under the grapientboosting framework. XGboost provides parallel tree promotion, and can quickly and accurately solve a plurality of data science problems. The same code runs on the main distributed environment.
Here, a total of 2333 pieces of data were obtained (each piece of data included a corn Field) in the experiment i Base fertilizer amount, topdressing amount in V9 stage, and actual value Y of corn yield i And environmental parameters), wherein 1492 data used for training the recommended model, 467 data sets used for testing the recommended model, and 374 data sets used for verifying the recommended modelAnd (4) strip. The yield model prediction effect, test effect and verification effect are shown in the following table, and a scatter diagram of the actual measured yield and the predicted yield in the verification set is shown in fig. 2.
In this embodiment, the corn Field i The environmental parameters of (a) include at least: corn farmland Field i The previous crop type is used for representing whether the previous crop is leguminous plants, and the plowing depth is used for representing whether soil is deeply ploughed.
In this embodiment, the corn Field i The environmental parameters of (a) include at least:
NDVI i 、CCCI i 、Macc i and NDRE i ,NDVI i =(R NIR,i -R RED,i )/(R NIR,i +R RED,i ),Macc i =(R NIR,i -R RedEdge,i )/(R NIR,i -R RED,i ),NDRE i =(R NIR,i -R RedEdge,i )/(R NIR,i +R RedEdge,i ),CCCI i =(NDRE i -NDRE min )/(NDRE max -NDRE min ),NDRE max =max(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ),NDRE min =min(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ) (ii) a Wherein R is NIR,i 、R RED,i And R RedEdge,i Respectively Field of corn farmland i The reflectivity of the corn in the V9 growth period in the near infrared band, the reflectivity of the red band and the reflectivity of the red edge band.
Here, in practice, a plurality of sensors may be provided in the corn farm, with these sensors detecting R NIR,i 、R RED,i And R RedEdge,i For example, an active remote sensing sensor may be installed (in the inventor's experiments, such thatRapidSCAN CS-45 plant spectral measuring instrument) is used, the active remote sensing sensor can emit electromagnetic radiation waves with certain frequency to the corn canopy, then receive radiation information returned from the corn canopy and analyze the radiation information (for example, the purpose of identifying the corn canopy is achieved by analyzing the properties, characteristics and changes of echoes), so as to obtain R NIR,i 、R RED,i And R RedEdge,i 。
In this embodiment, the corn Field i The environmental parameters of (a) include at least:
AWDI i =PPT i *SDI i wherein, in the step (A), T Base =10℃,n is corn sowing Date and continuous Date j The number of days between the latest day; at Num2 consecutive dates Date j Field of corn Field i The rainfall is Rain i,j The highest temperature is Tmax i,j And the minimum temperature is Tmin i,j (ii) a Num2 is a natural number, j =1,2.
Here, a small weather station for collecting rainfall Rain for each purpose may be provided in the corn field i,j And temperature information.
The embodiment of the invention provides a generation device of a recommendation model for recommending nitrogen fertilizer application amount, which comprises the following modules:
the information acquisition module is used for acquiring Field of different Num1 corn fields i Base fertilizer amount, topdressing amount in V9 stage, and actual value Y of corn yield i And an environmental parameter, where Num1 is a natural number, i =1, 2.., num1;
a recommendation model training module for generating a recommendation model based on Xgboost regression algorithm and using Num1 corn farmland fields i Amount of base fertilizer, amount of top dressing at V9 stage, and corn yield Y i Training the recommendation model by using the environment parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i The predicted value of the corn constant of (1),
in this embodiment, the corn Field i Includes at least: corn farmland Field i The previous crop type is used for representing whether the previous crop is leguminous plants, and the plowing depth is used for representing whether soil is deeply ploughed.
In the third embodiment, a method for recommending the application amount of the nitrogen fertilizer is provided, as shown in fig. 3, and includes the following steps:
step 301: executing the generation method in the first embodiment to obtain a recommendation model, obtaining environmental parameters of the corn farmland to be treated, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be treated based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the V9-stage topdressing amount; step 302: and generating a function G (x) = F (x) × CPRice-x × NPrice, obtaining a value XNum of which G (x) is the maximum x, and then recommending the nitrogen fertilizer application amount to be XNum, wherein CPRice is the price of the corn and NPrice is the price of the nitrogen fertilizer.
Here, it is understood that G (x) = F (x) × CPrice-x × NPrice is the ultimate yield of the corn farm being treated, and thus, when G (x) is maximized, the x value XNum can be understood as the optimum nitrogen fertilizer application rate.
Here, fig. 4A and 4B are two functions Y = F (x) obtained by the inventors at the time of experiments, and among the two functions,
in the present embodiment, the first and second electrodes are,wherein, beta 0 、β 1 、β 2 And e is a constant, e is an error term,
the third embodiment provides a nitrogen fertilizer application amount recommending device, which comprises the following modules:
the recommendation model generation module is used for executing the generation method in the first embodiment to obtain a recommendation model, obtaining environmental parameters of a corn farmland to be processed, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be processed based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the V9-stage topdressing amount;
and the nitrogen fertilizer application amount generating module is used for generating a function G (x) = F (x) × CPRice-x × NPice to obtain a value XNum of which G (x) is x at maximum, and the recommended nitrogen fertilizer application amount is XNum, wherein CPice is the price of the corn and NPice is the price of the nitrogen fertilizer.
In this embodiment, the nitrogen fertilizer application amount generating module is further configured to:
it should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is merely a detailed description of possible embodiments of the present invention, and it is not intended to limit the scope of the invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for generating a recommended model for recommending nitrogen fertilizer application rates, comprising the steps of:
obtain Field of different Num1 corn fields i The corresponding base fertilizer amount, the topdressing amount in the V9 stage and the actual value Y of the corn yield i And an environmental parameter, where Num1 is a natural number, i =1, 2.., num1;
generating a recommendation model based on an Xgboost regression algorithm, and utilizing Num1 corn farmland fields i Amount of base fertilizer, amount of top dressing at V9 stage, and corn yield Y i Training the recommendation model by using the environment parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i Prediction of maize constantThe value of the sum of the values,
2. the method of claim 1, wherein the corn farm Field i The environmental parameters of (a) include at least:
corn farmland Field i The previous crop type is used for representing whether the previous crop is leguminous plants, and the plowing depth is used for representing whether soil is deeply ploughed.
3. The method of claim 1, wherein the corn farm Field i The environmental parameters of (a) include at least:
NDVI i 、CCCI i 、Macc i and NDRE i ,NDVI i =(R NIR,i -R RED,i )/(R NIR,i +R RED,i ),Macc i =(R NIR,i -R RedEdge,i )/(R NIR,i -R RED,i ),NDRE i =(R NIR,i -R RedEdge,i )/(R NIR,i +R RedEdge,i ),CCCI i =(NDRE i -NDRE min )/(NDRE max -NDRE min ),NDRE max =max(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ),NDRE min =min(NDRE 1 ,NDRE 2 ,...,NDRE Num1 ) (ii) a Wherein R is NIR,i 、R RED,i And R RedEdge,i Respectively Field of corn farmland i The reflectivity of the corn in the V9 growth period in the near infrared band, the reflectivity of the red band and the reflectivity of the red edge band.
4. The method of claim 1, wherein the corn farm Field i The environmental parameters of (a) include at least:
AWDI i =PPT i *SDI i wherein, in the step (A), T Base =10℃,n is corn sowing Date and continuous Date i The number of days between the latest day; at Num2 consecutive dates Date j Field of corn Field i The rainfall is Rain i,j The highest temperature is Tmax i,j And a minimum temperature of Tmin i,j (ii) a Num2 is a natural number, j =1,2.
5. Device for generating a recommendation model for recommending nitrogen application rates, characterized in that it comprises the following modules:
the information acquisition module is used for acquiring Field of different Num1 corn fields i Base fertilizer amount, topdressing amount in V9 stage, and actual value Y of corn yield i And an environmental parameter, wherein Num1 is a natural number, i =1, 2., num1;
a recommendation model training module for generating a recommendation model based on Xgboost regression algorithm and using Num1 corn farmland fields i Amount of base fertilizer, amount of top dressing at V9 stage, and corn yield Y i Training the recommendation model by using the environment parameters; in the recommendation model, the accuracy evaluation index includes: model determination coefficient R 2 A model root mean square error RMSE, and a relative root mean square error RRMSE, is the Field of corn farmland i The predicted value of the maize constant of (c),
6. the generation apparatus of claim 5, wherein the corn farm Field i Includes at least:
corn farmland Field i The previous crop type is used for representing whether the previous crop is leguminous plants, and the plowing depth is used for representing whether soil is deeply ploughed.
7. A method for recommending the application amount of a nitrogen fertilizer is characterized by comprising the following steps:
executing the generation method of any one of claims 1 to 4 and obtaining a recommendation model, obtaining environmental parameters of a corn farmland to be treated, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be treated based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the V9 stage topdressing amount;
and generating a function G (x) = F (x) × CPRice-x × NPice, and obtaining the value XNum of which the maximum G (x) is x, wherein the recommended nitrogen fertilizer application amount is XNum, wherein CPice is the price of the corn and NPice is the price of the nitrogen fertilizer.
9. a nitrogen fertilizer application amount recommending device is characterized by comprising the following modules:
the recommendation model generation module is used for executing the generation method of any one of claims 1 to 4 and obtaining a recommendation model, obtaining environmental parameters of the corn farmland to be treated, and generating a corn constant function Y = F (x) corresponding to the corn farmland to be treated based on the recommendation model, wherein Y is the corn yield, and x is the sum of the base fertilizer amount and the V9-stage topdressing amount;
and the nitrogen fertilizer application amount generating module is used for generating a function G (x) = F (x) × CPRrice-x × NPrice, and obtaining a value XNum when G (x) is the maximum x, so that the recommended nitrogen fertilizer application amount is XNum, wherein CPRrice is the price of the corn, and NPrice is the price of the nitrogen fertilizer.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211109444.XA CN115481795A (en) | 2022-09-13 | 2022-09-13 | Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount |
PCT/CN2023/112006 WO2024055784A1 (en) | 2022-09-13 | 2023-08-09 | Recommendation model generation method and apparatus, and nitrogen fertilizer application amount recommendation method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211109444.XA CN115481795A (en) | 2022-09-13 | 2022-09-13 | Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115481795A true CN115481795A (en) | 2022-12-16 |
Family
ID=84424112
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211109444.XA Pending CN115481795A (en) | 2022-09-13 | 2022-09-13 | Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115481795A (en) |
WO (1) | WO2024055784A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024055784A1 (en) * | 2022-09-13 | 2024-03-21 | 苏州得墨忒耳科技有限公司 | Recommendation model generation method and apparatus, and nitrogen fertilizer application amount recommendation method and apparatus |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105557166A (en) * | 2016-01-26 | 2016-05-11 | 石河子大学 | Drip irrigation cotton field nitrogen application management method based on GIS |
CN109757175B (en) * | 2019-03-18 | 2020-10-30 | 中国农业科学院农业资源与农业区划研究所 | Unmanned aerial vehicle monitoring-based corn water and fertilizer integrated variable fertilization method |
CN111418323B (en) * | 2020-05-12 | 2021-11-02 | 中国科学院南京土壤研究所 | Nitrogen fertilizer real-time recommendation method based on facility crop canopy coverage and plant height |
CN115481795A (en) * | 2022-09-13 | 2022-12-16 | 苏州得墨忒耳科技有限公司 | Generation method of recommendation model, and recommendation method and device of nitrogen fertilizer application amount |
-
2022
- 2022-09-13 CN CN202211109444.XA patent/CN115481795A/en active Pending
-
2023
- 2023-08-09 WO PCT/CN2023/112006 patent/WO2024055784A1/en unknown
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024055784A1 (en) * | 2022-09-13 | 2024-03-21 | 苏州得墨忒耳科技有限公司 | Recommendation model generation method and apparatus, and nitrogen fertilizer application amount recommendation method and apparatus |
Also Published As
Publication number | Publication date |
---|---|
WO2024055784A8 (en) | 2024-04-18 |
WO2024055784A1 (en) | 2024-03-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nasrallah et al. | Sentinel-1 data for winter wheat phenology monitoring and mapping | |
Zheng et al. | Detection of rice phenology through time series analysis of ground-based spectral index data | |
US10096073B2 (en) | Systems to prescribe and deliver fertilizer over agricultural fields and related methods | |
Kassie et al. | Climate-induced yield variability and yield gaps of maize (Zea mays L.) in the Central Rift Valley of Ethiopia | |
Fang et al. | Integration of MODIS LAI and vegetation index products with the CSM–CERES–Maize model for corn yield estimation | |
Zhang et al. | Evaluation of the APSIM-Wheat model in terms of different cultivars, management regimes and environmental conditions | |
Saddique et al. | Modelling future climate change impacts on winter wheat yield and water use: A case study in Guanzhong Plain, northwestern China | |
CN101949916B (en) | Remote sensing quantitative inversion method for soil moisture supply amount | |
CN110309985A (en) | A kind of crop yield prediction technique and system | |
Ortuani et al. | Assessing the effectiveness of variable-rate drip irrigation on water use efficiency in a Vineyard in Northern Italy | |
An-Vo et al. | Value of seasonal forecasting for sugarcane farm irrigation planning | |
Zhang et al. | Estimating wheat yield by integrating the WheatGrow and PROSAIL models | |
Millán et al. | Automatic irrigation scheduling on a hedgerow olive orchard using an algorithm of water balance readjusted with soil moisture sensors | |
Liu et al. | Winter wheat yield estimation based on assimilated Sentinel-2 images with the CERES-Wheat model | |
Amarasingha et al. | Aligning sowing dates with the onset of rains to improve rice yields and water productivity: modelling rice (Oryza sativa L.) yield of the Maha season in the dry zone of Sri Lanka. | |
WO2024055784A1 (en) | Recommendation model generation method and apparatus, and nitrogen fertilizer application amount recommendation method and apparatus | |
Ren et al. | Narrowing yield gaps and enhancing nitrogen utilization for Summer maize (Zea mays L) by combining the effects of Varying nitrogen fertilizer input and planting density in DSSAT simulations | |
CN116485757A (en) | Winter wheat total nitrogen content prediction method | |
Tatsumi | Effects of automatic multi-objective optimization of crop models on corn yield reproducibility in the USA | |
Uribeetxebarria et al. | A first approach to determine if it is possible to delineate in-season n fertilization maps for wheat using NDVI derived from sentinel-2 | |
CN116152007A (en) | Method and device for determining plant fertilization amount, terminal equipment and readable storage medium | |
Zou et al. | Combining spectral and texture feature of UAV image with plant height to improve LAI estimation of winter wheat at jointing stage | |
Jiang et al. | Predicting spatiotemporal yield variability to aid arable precision agriculture in New Zealand: A case study of maize-grain crop production in the Waikato region | |
Quansah et al. | CROPGRO-soybean model calibration and assessment of soybean yield responses to climate change | |
Kheir et al. | Integrating APSIM model with machine learning to predict wheat yield spatial distribution |
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 |