CN114219227A - Method and system for precise fertilization decision and plot level display - Google Patents
Method and system for precise fertilization decision and plot level display Download PDFInfo
- Publication number
- CN114219227A CN114219227A CN202111405027.5A CN202111405027A CN114219227A CN 114219227 A CN114219227 A CN 114219227A CN 202111405027 A CN202111405027 A CN 202111405027A CN 114219227 A CN114219227 A CN 114219227A
- Authority
- CN
- China
- Prior art keywords
- fertilizer
- content
- crop
- leaves
- absorption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The application relates to a method and a system for precise fertilization decision and plot level display, which comprises the steps of reading in map information; marking the plot of the planted crop on the map according to the ridge; calculating a production ratio value on each land; marking each plot with a yield ratio value or marking each plot with a specific color according to the yield ratio value. By directly displaying the shape and the production ratio of the land parcel on the map, related personnel can intuitively see the balanced fertilization condition of the land parcel in a certain area.
Description
Technical Field
The application belongs to the technical field of green agriculture big data, and particularly relates to a method and a system for accurate fertilization decision and plot level display.
Background
The variable fertilization technology is one of the core contents of precision agriculture, and implements positioning, timing and quantitative fertilization prescription farming by means of an information technology according to the spatial and temporal variation of crops and the growth environment thereof. The method aims to reduce fertilizer input to achieve the same income, improve the ecological environment of farmlands, improve the utilization rate of the fertilizer and obtain the best environmental and economic benefits.
In order to better show the economy of fertilization in a certain area, a method and a system capable of accurately making fertilization decisions and displaying the fertilization quantity of different plots on a map are continuously provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to solve the defects in the prior art, a method and a system for displaying the plot level based on an accurate fertilization decision are provided.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for precise fertilization decision and plot level display comprises the following steps:
s1: reading in map information;
s2: marking the plot of the planted crops on the map according to the ridges;
s3: calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as a recommended fertilizing amount;
s4: subtracting the original fertilizer content of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer to serve as a fertilizing recommendation scheme, and marking the fertilizing recommendation scheme on the plot of the map information;
s5: and clicking a corresponding plot on the map information to check the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot.
Preferably, in the method for precise fertilization decision and parcel level display, in the step S4, the parcel is divided into high, medium and low fertilization degrees according to the ratio of the fertilization amount to the original fertilizer content of the parcel, and classified according to three fertilization degrees of three fertilizers of nitrogen fertilizer, phosphate fertilizer and potassium fertilizer, and the classified marks are marked on the map, and in the step S5, the corresponding parcel on the map information is clicked to check the classified marks of the parcel.
Preferably, according to the method for accurate fertilization decision and parcel level display, different classification marks are represented on a map according to different colors.
Preferably, in the method for making a precise fertilization decision and displaying a plot grade, the calculation method of the production ratio value of each fertilizer in the step S3 is as follows:
s31: obtaining the initial content Z0 of soil fertilizer in an area where crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc of the previous year and the crop yield Yp of the current year, obtaining the residual fertilizer content Z of soil after the crops of the current year are harvested, obtaining the unit crop fertilizer absorption content Sk of the previous year and the fertilizer absorption content Sp of the crops of the previous year after fertilization, wherein the fertilizer amount used in the current cultivation is H;
s32: calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is the yield Yp of the crop in the current year multiplied by the unit crop fertilizer absorption content Sp applied in the current year;
calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year;
calculating the fertilizer loss amount, wherein the fertilizer loss amount S is multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I percent is equal to the fertilizer amount H multiplied by 100 percent used in cultivation;
s33: calculating a production ratio curve D of the steel tube,
wherein, P represents the price of the fertilizer, Py represents the price of the crop product, and the minimum value of the numerical curve of the yield ratio is solved to be used as the recommended fertilizing amount.
Preferably, in the method for precise fertilization decision and plot level display of the present invention, the method for obtaining the fertilizer absorption content Sp of the unit crop fertilized with fertilizer and the fertilizer absorption content Sk of the unit crop not fertilized with fertilizer comprises:
air-drying the harvested plants of the crops, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops which are fertilized and the fertilizer absorption content Sk of the unit crops which are not fertilized according to the sample proportion;
the air-dried plants comprise crop seeds, stems, leaves and roots, and the content of fertilizer elements is measured after the air-dried plants are crushed;
measuring the content of fertilizer elements of the stem leaves and the grain after air drying by using a convolutional neural network model;
the method comprises the following steps:
a1: training a convolutional neural network model device: training a convolutional neural network model device by using a photo of stem leaves and seeds which are air-dried to a specific water content and corresponding stem leaf fertilizer element content and seed fertilizer element content crop training set to obtain the convolutional neural network model device; when a training set is constructed, according to normal distribution, dividing a plurality of intervals according to the quality of stems and leaves or seeds, selecting corresponding quantity samples to construct the training set, taking the stems and leaves or seeds as a complete picture of the training set, and adjusting the parts, which are not the stems and leaves or the seeds, in the picture to be transparent through processing;
a2: in the element content identification process, new pictures of stems and leaves and seeds with unknown fertilizer element content of the stems and leaves and seed fertilizer element content air-dried to specific water content are taken as input, and the output of the convolutional neural network model is taken as the fertilizer element content of the stems and leaves and the fertilizer element content of the seeds;
in the identification process, the stems and leaves with the mass conforming to the normal distribution of the stems and leaves or the seeds are also selected as samples, and the fertilizer element content in each identified stem and leaf or seed is summed and then divided by the corresponding weight percentage to obtain the fertilizer element content of the test cell.
The invention also provides a system for accurate fertilization decision and plot level display, which comprises:
the map module is provided with a land parcel for planting a crop range marked according to a ridge;
the recommended fertilizing amount calculating module is used for calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as the recommended fertilizing amount;
the map identification module is used for subtracting the original fertilizer contents of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer to serve as a fertilizing recommendation scheme, and marking the fertilizing recommendation scheme on the plot of the map information;
the query module: and displaying the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot when the corresponding plot on the map information is clicked.
Preferably, in the system for accurate fertilization decision and display of plot level, the map identification module divides the plot into high, medium and low fertilization degrees according to the ratio of the fertilization amount to the original fertilizer content of the plot, divides the classification according to the three fertilization degrees of the nitrogenous fertilizer, the phosphatic fertilizer and the potash fertilizer, marks the classification on the map, and the query module selects the corresponding plot on the map information to check the classification mark of the plot.
Preferably, the accurate fertilization decision and plot level display system of the invention,
the recommended fertilizing amount calculating module comprises:
a data acquisition submodule: the method is used for obtaining the initial content Z0 of the soil fertilizer in the area where the crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc in the previous year and the crop yield Yp in the current year, obtaining the residual fertilizer content Z of the soil after the crops in the current year are harvested, obtaining the unit crop fertilizer absorption content Sk in the previous year and the fertilizer absorption content Sp in the previous year after fertilization, and the fertilizer amount used in the current cultivation is H;
a data processing submodule: the method is used for calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is equal to the yield Yp of the crop in the current year multiplied by the fertilizer absorption content Sp of the crop applied in the current year; calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year; calculating the fertilizer loss amount, wherein the fertilizer loss amount S is multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I percent is equal to the fertilizer amount H multiplied by 100 percent used in cultivation;
and a result calculation submodule: is used for calculating a production ratio curve D,
wherein P represents the fertilizer price in the current year, Py represents the crop product price after harvesting in the current year, and the minimum value of the numerical curve of the production ratio is solved to be used as the recommended fertilizer.
Preferably, in the system for precise fertilization decision and parcel level display of the present invention, the method for obtaining the fertilizer absorption content Sp of the unit crop fertilized with fertilizer and the fertilizer absorption content Sk of the unit crop non-fertilized with fertilizer comprises:
air-drying the harvested plants of the crops, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops which are fertilized and the fertilizer absorption content Sk of the unit crops which are not fertilized according to the sample proportion;
the air-dried plants comprise crop seeds, stems, leaves and roots, and the content of fertilizer elements is measured after the air-dried plants are crushed;
measuring the content of fertilizer elements of the stem leaves and the grain after air drying by using a convolutional neural network model;
the method comprises the following steps:
a1: training a convolutional neural network model device: training a convolutional neural network model device by using a photo of stem leaves and seeds which are air-dried to a specific water content and corresponding stem leaf fertilizer element content and seed fertilizer element content crop training set to obtain the convolutional neural network model device; when a training set is constructed, according to normal distribution, dividing a plurality of intervals according to the quality of stems and leaves or seeds, selecting corresponding quantity samples to construct the training set, taking the stems and leaves or seeds as a complete picture of the training set, and adjusting the parts, which are not the stems and leaves or the seeds, in the picture to be transparent through processing;
a2: in the element content identification process, new pictures of stems and leaves and seeds with unknown fertilizer element content of the stems and leaves and seed fertilizer element content air-dried to specific water content are taken as input, and the output of the convolutional neural network model is taken as the fertilizer element content of the stems and leaves and the fertilizer element content of the seeds;
in the identification process, the stems and leaves with the mass conforming to the normal distribution of the stems and leaves or the seeds are also selected as samples, and the fertilizer element content in each identified stem and leaf or seed is summed and then divided by the corresponding weight percentage to obtain the fertilizer element content of the test cell.
The present invention also provides a computer storage medium having stored thereon one or more instructions adapted to be loaded by a processor and to perform the above-described method.
The invention has the beneficial effects that:
the invention provides a method and a system for precise fertilization decision and plot level display, which comprises the steps of reading in map information; marking the plot of the planted crop on the map according to the ridge; calculating a production ratio value on each land; marking each plot with a yield ratio value or marking each plot with a specific color according to the yield ratio value. By directly displaying the shape and the production ratio of the land parcel on the map, related personnel can intuitively see the balanced fertilization condition of the land parcel in a certain area.
Drawings
The technical solution of the present application is further explained below with reference to the drawings and the embodiments.
Fig. 1 is a schematic diagram of a map with plots marked in the method for precise fertilization decision and plot level display according to the embodiment of the present application;
fig. 2 is a schematic diagram of a production ratio value displayed on a map in the method for precise fertilization decision and parcel level display according to the embodiment of the present application;
FIG. 3 is a flow chart of a method for precise fertilization decision and parcel level display according to an embodiment of the present application;
FIG. 4 is a table diagram of the "control", "stability" and "increase" of the N nitrogen, P phosphorus and K potassium fertilizing amount in the embodiment of the application;
fig. 5 is a block diagram of a convolutional neural network model device according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The technical solutions of the present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example 1
The embodiment provides a method for precise fertilization decision and plot level display, and the flow chart is shown in fig. 3, and includes the following steps:
s1: reading in map information;
s2: marking the plot of the planted crop on the map according to the ridge, as shown in figure 1;
s3: calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as a recommended fertilizing amount;
s4: subtracting the original fertilizer content of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount to serve as a fertilizing recommended scheme, and marking the fertilizing recommended scheme on the plot of the map information;
s5: and clicking a corresponding plot on the map information to check the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot.
In step S4, the plot is divided into high, medium and low fertilizing degrees according to the ratio of the fertilizing amount to the original fertilizing amount of the plot, for example (by way of example only) the fertilizing amount is less than 0 of the original fertilizing amount and is called "control" and is called low fertilizing degree, the fertilizing amount is 0-20% of the original fertilizing amount and is called "stable" and is called medium fertilizing degree, the fertilizing amount is more than 20% of the original fertilizing amount and is called "increase" and is called high fertilizing degree, and the fertilizing recommendation schemes can be divided into 27 types (permutation and combination of three elements and three fertilizing degrees):
controlling nitrogen, controlling phosphorus, controlling potassium, controlling nitrogen, controlling phosphorus, stabilizing potassium, controlling nitrogen, controlling phosphorus, increasing potassium, controlling nitrogen, stabilizing phosphorus, controlling potassium, controlling nitrogen, increasing phosphorus, increasing potassium, controlling nitrogen, increasing phosphorus, stabilizing potassium, controlling nitrogen, increasing phosphorus, increasing potassium;
nitrogen stabilization, phosphorus control, potassium control, nitrogen stabilization, phosphorus control, potassium stabilization, nitrogen stabilization, phosphorus control, potassium increment, nitrogen stabilization, phosphorus stabilization, potassium control, nitrogen stabilization, phosphorus increment, potassium increment;
nitrogen increasing, phosphorus controlling, potassium controlling, nitrogen increasing, phosphorus controlling, potassium stabilizing, nitrogen increasing, phosphorus controlling, potassium increasing, nitrogen increasing, phosphorus stabilizing, potassium controlling, nitrogen increasing, phosphorus controlling, potassium controlling, nitrogen increasing, phosphorus stabilizing, potassium stabilizing, nitrogen increasing, phosphorus stabilizing, potassium increasing;
the 27 categories may be categorically labeled and ultimately displayed on a map for easy viewing by an operator. Since usually 27 classmarks, usually 3-10 classmarks, will not exist at the same time, different classmarks can be represented in different colors for more intuitive display on the map.
As shown in fig. 4, a list of "control", "steady" and "increase" of the fertilizing amount of N nitrogen, P phosphorus and K potassium is shown, which is currently indicated as "nitrogen control-steady phosphorus-steady potassium";
the calculation method of the production ratio value in the step S3 comprises the following steps:
s31: obtaining the initial content Z0 of soil fertilizer in an area where crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc of the previous year and the crop yield Yp of the current year, obtaining the residual fertilizer content Z of soil after the crops of the current year are harvested, obtaining the unit crop fertilizer absorption content Sk of the previous year and the fertilizer absorption content Sp of the crops of the previous year after fertilization, wherein the fertilizer amount used in the current cultivation is H;
s32: calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is the yield Yp of the crop in the current year multiplied by the unit crop fertilizer absorption content Sp applied in the current year;
calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year;
calculating the fertilizer loss amount, wherein the fertilizer loss amount S is (1-I%) multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I = (the total absorption amount of crops to be fertilized Xp-the residual fertilizer content Zi in the soil after harvesting)/the fertilizer amount H multiplied by 100% used in cultivation;
s33: calculating the on-stream ratio D of the steel,
wherein P represents the price of the fertilizer and Py represents the price of the crop product.
The method for precise fertilization decision and plot level display in this embodiment is a ratio of fertilization newly-increased pure income to fertilization cost by calculating a production ratio D. In the embodiment, the profitability under the condition of fertilization and the condition of no fertilization are compared, and the economic value of the residual fertilizer in the area and the environmental impact value caused by fertilizer loss are comprehensively considered. The smaller the production ratio is, the higher the economic degree is, and the optimal fertilization scheme can be conveniently selected by calculating the production ratios of different areas (plots).
The fertilizer can be the most basic nitrogen fertilizer, phosphate fertilizer and potassium fertilizer;
respectively obtaining the fertilizer amount H of the three fertilizers, the residual fertilizer content Z of the harvested crops, the absorption content Sk of the unit crop fertilizer without fertilization and the absorption content Sp of the unit crop fertilizer without fertilization in the calculation process; respectively calculating the fertilizer loss of the three fertilizers;
in calculating the production ratio D, three fertilizers were added to the formula described in S33.
In step S32: the method for acquiring the fertilizer absorption content Sp of the unit crops and the fertilizer absorption content Sk of the unit crops in the previous year comprises the following steps:
and (3) air-drying the harvested plants of the crops, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops which are fertilized and the fertilizer absorption content Sk of the unit crops which are not fertilized according to the sample proportion.
And (3) crushing the air-dried plants including crop seeds, stems, leaves and roots, and measuring the content of fertilizer elements.
Taking rice as an example, the method for measuring the yield and the fertilizer element content comprises the following steps:
sampling: randomly taking 3 sample segments with the length of 1 m: after the whole crop is air-dried, the dry weight of stem leaves and the dry weight of ear wind are weighed, after ear threshing, air-dried grains are weighed, the dry weight (g) of the grains is called, and the content of fertilizer elements at the root of rice is not calculated because the root of the rice is still planted when the rice is harvested.
And measuring the content of fertilizer elements of the stem leaves and the seeds after air drying (the content of the fertilizer elements of the rice husks and the content of the fertilizer elements of the rice grains). The measurement of the stem leaf fertilizer element content and the seed grain fertilizer element content (the rice husk fertilizer element content and the rice grain fertilizer element content) is obtained by using the national standard measurement.
The content of fertilizer elements of stems and leaves and the content of fertilizer elements of grains can be measured by using a convolutional neural network model;
the specific method comprises the following steps:
a1: training a convolutional neural network model device: training a convolutional neural network model device by using the pictures of the stems and leaves and the grains which are air-dried to a specific water content and the corresponding stem and leaf fertilizer element content and grain fertilizer element content crop training set to obtain the convolutional neural network model device; when a training set is constructed, according to normal distribution, dividing a plurality of intervals by taking the quality of stems and leaves or seeds as a basis, selecting corresponding quantity of samples to construct the training set (namely, the quantity of the samples close to the average value in the whole test cell is the largest, and the quantity of the samples far away from the average value is smaller), taking the stems and leaves or the seeds as the training set as a complete picture, and adjusting the parts of the pictures, which are not the stems and leaves or the seeds, to be transparent through processing;
a2: in the element content identification process, new pictures of stems and leaves and seeds with unknown fertilizer element content of the stems and leaves and seed fertilizer element content air-dried to specific water content are taken as input, and the output of the convolutional neural network model is taken as the fertilizer element content of the stems and leaves and the fertilizer element content of the seeds;
in the identification process, the stems and leaves with the mass conforming to the normal distribution of the stems and leaves or the seeds are also selected as samples, and the fertilizer element content in each identified stem and leaf or seed is summed and then divided by the corresponding weight percentage to obtain the fertilizer element content of the test cell. Because the water content during training is equivalent to that during recognition, the influence of water on the recognition result can be ignored.
It should be noted that the convolutional neural network models for identifying the fertilizer element content of the stems and leaves and the fertilizer element content of the grains should be constructed respectively.
The picture size of the training set is the same as the picture size of the air-dried stems and leaves and seeds as the identification protocol, and the proportion of pixels of the picture to the actual article is the same (e.g. 10 pixels for 1cm of article).
According to the statistical principle, the grain yield (namely crop yield) of the whole test cell is calculated according to the sampling proportion, and the stem leaf fertilizer element content and the grain fertilizer element content of the whole test cell are calculated. And calculating the amount of the fertilizer used by the crops according to the proportion of the elements in the fertilizer. Meanwhile, a training set and an identification sample are constructed by taking normal distribution of mass as a standard, so that the identification accuracy can be improved.
The larger the amount of data in training, the better, at least 1 ten thousand should be.
The basic principle of the convolutional neural network model device is as follows: image input → computational features → output categories.
The method specifically comprises the following steps:
an input layer;
the characteristic extraction layer comprises a rolling layer and a pooling layer, and the rolling layer and the pooling layer comprise 7 layers such as layer1-layer 7; (convolution kernel of convolutional layer gradually decreases in size, pooling layer step size is the same as kernel size)
A first fully-connected layer;
a second fully connected layer;
and (5) outputting the layer.
The training algorithm can be common algorithms, such as a random gradient descent algorithm, an Adam algorithm, a RMSProp algorithm, an adagard algorithm and the like.
The convolutional neural network model device is composed of an input layer, a plurality of feature extraction layers, a full connection layer and an output layer, and parameters of each layer, such as the size of a pooling window, the size of a step length, the size of a convolutional kernel, the number of nodes and the like, are related according to the size of a picture of a training set, which is not the invention point of the embodiment and is not repeated herein.
The content of fertilizer elements in the stem leaves and the content of fertilizer elements in the seeds are taken as the total crop absorption amount of the whole test cell (according to different source areas, the total crop absorption amount is divided into the total crop absorption amount of fertilization and the total crop absorption amount of non-fertilization).
Example 2
The embodiment provides an accurate fertilization decision and parcel level display system, which is characterized by comprising:
the map module is provided with a land parcel for planting a crop range marked according to a ridge;
the recommended fertilizing amount calculating module is used for calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as the recommended fertilizing amount;
the map identification module is used for subtracting the original fertilizer contents of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer to serve as a fertilizing recommendation scheme, and marking the fertilizing recommendation scheme on the plot of the map information;
the query module: and displaying the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot when the corresponding plot on the map information is clicked.
In the map identification module, the plots are divided into high fertilization degrees, medium fertilization degrees and low fertilization degrees according to the ratio of the fertilization amount to the original fertilizer content of the plots, the plots are divided and classified according to three fertilization degrees of nitrogenous fertilizers, phosphate fertilizers and potash fertilizers, the classifications are marked on a map, and the query module selects corresponding plots on map information to check the classifications of the plots.
The recommended fertilizing amount calculating module specifically comprises:
a data acquisition submodule: the method is used for obtaining the initial content Z0 of the soil fertilizer in the area where the crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc in the previous year and the crop yield Yp in the current year, obtaining the residual fertilizer content Z of the soil after the crops in the current year are harvested, obtaining the unit crop fertilizer absorption content Sk in the previous year and the fertilizer absorption content Sp in the previous year after fertilization, and the fertilizer amount used in the current cultivation is H;
a data processing submodule: the method is used for calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is equal to the yield Yp of the crop in the current year multiplied by the fertilizer absorption content Sp of the crop applied in the current year; calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year; calculating the fertilizer loss amount, wherein the fertilizer loss amount S is (1-I%) multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I = (the total absorption amount of crops to be fertilized Xp-the residual fertilizer content Zi in the soil after harvesting)/the fertilizer amount H multiplied by 100% used in cultivation;
and a result calculation submodule: calculating a production ratio curve D of the steel tube,
wherein, P represents the fertilizer price in the current year, Py represents the crop product price after the harvest in the current year, and the minimum value of the numerical curve of the yield ratio is solved to be used as the recommended fertilizing amount.
The results of the three fertilizers were obtained by calculating the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer, respectively.
The data processing submodule and the result calculating submodule respectively acquire the fertilizer amount H of the three fertilizers in the calculation process, the residual fertilizer content Z of the soil after the crops in the current year are harvested, the fertilizer absorption content Sk of the unit crops in the previous year and the fertilizer absorption content Sp of the unit crops fertilized in the current year; respectively calculating the fertilizer loss of the three fertilizers;
in calculating the on-stream ratio D, three fertilizers need to be added to the formula in the result calculation submodule.
Further, the method for acquiring the fertilizer absorption content Sp of the fertilized unit crop and the fertilizer absorption content Sk of the unfertilized unit crop comprises the following steps:
and (3) air-drying the harvested plants, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops fertilized in the current year and the fertilizer absorption content Sk of the unit crops not fertilized in the current year according to the sample ratio.
Preferably, according to the agricultural balanced fertilization intelligent decision device considering environmental influence, air-dried plants comprise crop seeds, stems, leaves and roots, and the content of fertilizer elements is measured after the air-dried plants are crushed.
Example 3
The present embodiment provides a computer storage medium storing one or more instructions adapted to be loaded by a processor and execute the agricultural balanced fertilization intelligent decision method considering environmental impact as in embodiment 1.
In light of the foregoing description of the preferred embodiments according to the present application, it is to be understood that various changes and modifications may be made without departing from the spirit and scope of the invention. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
In light of the foregoing description of the preferred embodiments according to the present application, it is to be understood that various changes and modifications may be made without departing from the spirit and scope of the invention. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (10)
1. A method for precise fertilization decision and plot level display is characterized by comprising the following steps:
s1: reading in map information;
s2: marking the plot of the planted crops on the map according to the ridges;
s3: calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as a recommended fertilizing amount;
s4: subtracting the original fertilizer content of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer to serve as a fertilizing recommendation scheme, and marking the fertilizing recommendation scheme on the plot of the map information;
s5: and clicking a corresponding plot on the map information to check the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot.
2. The method as claimed in claim 1, wherein in step S4, the plot is divided into high, medium and low fertilizing degrees according to the ratio of the fertilizing amount to the original fertilizing amount of the plot, the classification is made according to the three fertilizing degrees of nitrogenous fertilizer, phosphate fertilizer and potash fertilizer, the classification is marked on the map, and in step S5, the classification mark of the plot is checked by selecting the corresponding plot on the map information.
3. The method of claim 2, wherein different classification labels are represented on the map in different colors.
4. The method for precise fertilization decision and parcel level display according to claim 1, wherein the calculation method of the production ratio value of each fertilizer in the step of S3 is:
s31: obtaining the initial content Z0 of soil fertilizer in an area where crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc of the previous year and the crop yield Yp of the current year, obtaining the residual fertilizer content Z of soil after the crops of the current year are harvested, obtaining the unit crop fertilizer absorption content Sk of the previous year and the fertilizer absorption content Sp of the crops of the previous year after fertilization, wherein the fertilizer amount used in the current cultivation is H;
s32: calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is the yield Yp of the crop in the current year multiplied by the unit crop fertilizer absorption content Sp applied in the current year;
calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year;
calculating the fertilizer loss amount, wherein the fertilizer loss amount S is (1-I%) multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I = (the total absorption amount of crops to be fertilized Xp-the residual fertilizer content Zi in the soil after harvesting)/the fertilizer amount H multiplied by 100% used in cultivation;
s33: calculating a production ratio curve D of the steel tube,
wherein, P represents the price of the fertilizer, Py represents the price of the crop product, and the minimum value of the numerical curve of the yield ratio is solved to be used as the recommended fertilizing amount.
5. The method for precise fertilization decision and parcel level display according to claim 4, wherein the method for obtaining the fertilizer uptake per unit crop Sp and the fertilizer uptake per unit crop Sk without fertilization comprises:
air-drying the harvested plants of the crops, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops which are fertilized and the fertilizer absorption content Sk of the unit crops which are not fertilized according to the sample proportion;
the air-dried plants comprise crop seeds, stems, leaves and roots, and the content of fertilizer elements is measured after the air-dried plants are crushed;
measuring the content of fertilizer elements of the stem leaves and the grain after air drying by using a convolutional neural network model;
the method comprises the following steps:
a1: training a convolutional neural network model device: training a convolutional neural network model device by using a photo of stem leaves and seeds which are air-dried to a specific water content and corresponding stem leaf fertilizer element content and seed fertilizer element content crop training set to obtain the convolutional neural network model device; when a training set is constructed, according to normal distribution, dividing a plurality of intervals according to the quality of stems and leaves or seeds, selecting corresponding quantity samples to construct the training set, taking the stems and leaves or seeds as a complete picture of the training set, and adjusting the parts, which are not the stems and leaves or the seeds, in the picture to be transparent through processing;
a2: in the element content identification process, new pictures of stems and leaves and seeds with unknown fertilizer element content of the stems and leaves and seed fertilizer element content air-dried to specific water content are taken as input, and the output of the convolutional neural network model is taken as the fertilizer element content of the stems and leaves and the fertilizer element content of the seeds;
in the identification process, the stems and leaves with the mass conforming to the normal distribution of the stems and leaves or the seeds are also selected as samples, and the fertilizer element content in each identified stem and leaf or seed is summed and then divided by the corresponding weight percentage to obtain the fertilizer element content of the test cell.
6. The utility model provides an accurate fertilization decision and plot level display system which characterized in that includes:
the map module is provided with a land parcel for planting a crop range marked according to a ridge;
the recommended fertilizing amount calculating module is used for calculating a numerical curve of the production ratio of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer on each land block, and solving the minimum value of the numerical curve of the production ratio as the recommended fertilizing amount;
the map identification module is used for subtracting the original fertilizer contents of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer in the plot from the recommended fertilizing amount of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer to serve as a fertilizing recommendation scheme, and marking the fertilizing recommendation scheme on the plot of the map information;
the query module: and displaying the fertilization recommendation scheme of the nitrogenous fertilizer, the phosphate fertilizer and the potash fertilizer of the plot when the corresponding plot on the map information is clicked.
7. The system of claim 6, wherein the map identification module classifies the plots into high, medium and low fertilization degrees according to a ratio of the fertilization rate to an original fertilizer content of the plots, classifies the plots according to three fertilization degrees of nitrogenous fertilizers, phosphatic fertilizers and potash fertilizers, marks the classifications on the map, and the query module selects the corresponding plots on the map information to view the classification marks of the plots.
8. The precision fertilization decision and parcel level display system of claim 6,
the recommended fertilizing amount calculating module comprises:
a data acquisition submodule: the method is used for obtaining the initial content Z0 of the soil fertilizer in the area where the crops are to be planted before cultivation, obtaining the current fertilizer price P, obtaining the crop yield Yc in the previous year and the crop yield Yp in the current year, obtaining the residual fertilizer content Z of the soil after the crops in the current year are harvested, obtaining the unit crop fertilizer absorption content Sk in the previous year and the fertilizer absorption content Sp in the previous year after fertilization, and the fertilizer amount used in the current cultivation is H;
a data processing submodule: the method is used for calculating the total crop absorption amount Xp applied in the current year, wherein the total crop absorption amount Xp applied in the current year is equal to the yield Yp of the crop in the current year multiplied by the fertilizer absorption content Sp of the crop applied in the current year; calculating the total crop absorption Xk in the previous year, wherein the total crop absorption Xk in the previous year is the crop yield Yk multiplied by the unit crop fertilizer absorption content Sk in the previous year; calculating the fertilizer loss amount, wherein the fertilizer loss amount S is (1-I%) multiplied by the total absorption amount Xp of the fertilized crops/area; the fertilizer utilization ratio I = (the total absorption amount of crops to be fertilized Xp-the residual fertilizer content Zi in the soil after harvesting)/the fertilizer amount H multiplied by 100% used in cultivation;
and a result calculation submodule: is used for calculating a production ratio curve D,
wherein P represents the fertilizer price in the current year, Py represents the crop product price after harvesting in the current year, and the minimum value of the numerical curve of the production ratio is solved to be used as the recommended fertilizer.
9. The system for precise fertilization decision and parcel level display according to claim 8, wherein the fertilizer uptake per unit crop Sp and fertilizer uptake per unit crop Sk without fertilization are obtained by:
air-drying the harvested plants of the crops, randomly extracting a part of the crops as samples by using a statistical method, measuring the content of fertilizer elements in the crops, and then estimating the fertilizer absorption content Sp of the unit crops which are fertilized and the fertilizer absorption content Sk of the unit crops which are not fertilized according to the sample proportion;
the air-dried plants comprise crop seeds, stems, leaves and roots, and the content of fertilizer elements is measured after the air-dried plants are crushed;
measuring the content of fertilizer elements of the stem leaves and the grain after air drying by using a convolutional neural network model;
the method comprises the following steps:
a1: training a convolutional neural network model device: training a convolutional neural network model device by using a photo of stem leaves and seeds which are air-dried to a specific water content and corresponding stem leaf fertilizer element content and seed fertilizer element content crop training set to obtain the convolutional neural network model device; when a training set is constructed, according to normal distribution, dividing a plurality of intervals according to the quality of stems and leaves or seeds, selecting corresponding quantity samples to construct the training set, taking the stems and leaves or seeds as a complete picture of the training set, and adjusting the parts, which are not the stems and leaves or the seeds, in the picture to be transparent through processing;
a2: in the element content identification process, new pictures of stems and leaves and seeds with unknown fertilizer element content of the stems and leaves and seed fertilizer element content air-dried to specific water content are taken as input, and the output of the convolutional neural network model is taken as the fertilizer element content of the stems and leaves and the fertilizer element content of the seeds;
in the identification process, the stems and leaves with the mass conforming to the normal distribution of the stems and leaves or the seeds are also selected as samples, and the fertilizer element content in each identified stem and leaf or seed is summed and then divided by the corresponding weight percentage to obtain the fertilizer element content of the test cell.
10. A computer storage medium having one or more instructions stored thereon, the instructions adapted to be loaded by a processor and to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405027.5A CN114219227A (en) | 2021-11-24 | 2021-11-24 | Method and system for precise fertilization decision and plot level display |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111405027.5A CN114219227A (en) | 2021-11-24 | 2021-11-24 | Method and system for precise fertilization decision and plot level display |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219227A true CN114219227A (en) | 2022-03-22 |
Family
ID=80698178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111405027.5A Pending CN114219227A (en) | 2021-11-24 | 2021-11-24 | Method and system for precise fertilization decision and plot level display |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219227A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049220A (en) * | 2022-05-25 | 2022-09-13 | 广东省科学院生态环境与土壤研究所 | Distributed regional nitrogen application amount estimation method, system, computer device and medium |
-
2021
- 2021-11-24 CN CN202111405027.5A patent/CN114219227A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049220A (en) * | 2022-05-25 | 2022-09-13 | 广东省科学院生态环境与土壤研究所 | Distributed regional nitrogen application amount estimation method, system, computer device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Detection of rice phenology through time series analysis of ground-based spectral index data | |
| Kassie et al. | Climate-induced yield variability and yield gaps of maize (Zea mays L.) in the Central Rift Valley of Ethiopia | |
| US20170270446A1 (en) | Agronomic systems, methods and apparatuses for determining yield limits | |
| Driessen et al. | Land-use systems analysis | |
| Zhao et al. | Canopy reflectance in cotton for growth assessment and lint yield prediction | |
| US20160309646A1 (en) | Agronomic systems, methods and apparatuses | |
| Heinemann et al. | Characterization of drought stress environments for upland rice and maize in central Brazil | |
| CN111241912A (en) | Multi-vegetation index rice yield estimation method based on machine learning algorithm | |
| CN106372592A (en) | Winter wheat plantation area calculation method based on winter wheat area index | |
| US20180276587A1 (en) | Farm work planning assistance system | |
| Yang et al. | A VI-based phenology adaptation approach for rice crop monitoring using UAV multispectral images | |
| CN113469112B (en) | Crop growth condition image identification method and system | |
| CN111798028A (en) | Crop yield prediction method and device, electronic equipment and storage medium | |
| CN111418323A (en) | Nitrogen fertilizer real-time recommendation method based on facility crop canopy coverage and plant height | |
| Liu et al. | Spatiotemporal changes of rice phenology in China under climate change from 1981 to 2010 | |
| CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
| CN115577866A (en) | Method and device for predicting waiting period, electronic equipment and storage medium | |
| Simic Milas et al. | Monitoring Landsat vegetation indices for different crop treatments and soil chemistry | |
| CN114219227A (en) | Method and system for precise fertilization decision and plot level display | |
| Li et al. | Estimation of nitrogen content in wheat using indices derived from RGB and thermal infrared imaging | |
| CN107437262B (en) | Crop planting area early warning method and system | |
| Sukojo et al. | Rice growth stages mapping with Normalized Difference Vegetation Index (NDVI) algorithm using sentinel-2 time series satellite imagery | |
| CN114154824A (en) | Agricultural balance fertilization intelligent decision method and device considering environmental influence | |
| CN116897670B (en) | Crop fertilization method, device, electronic equipment and storage medium | |
| Lee | Remote sensing-based assessment of Gross Primary Production (GPP) in agricultural ecosystems |
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 |