CN117322214B - Crop fertilizer accurate application method and system based on neural network - Google Patents
Crop fertilizer accurate application method and system based on neural network Download PDFInfo
- Publication number
- CN117322214B CN117322214B CN202311620141.9A CN202311620141A CN117322214B CN 117322214 B CN117322214 B CN 117322214B CN 202311620141 A CN202311620141 A CN 202311620141A CN 117322214 B CN117322214 B CN 117322214B
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- soil
- crop
- screening vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003337 fertilizer Substances 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 39
- 238000012216 screening Methods 0.000 claims description 189
- 239000013598 vector Substances 0.000 claims description 160
- 239000002689 soil Substances 0.000 claims description 136
- 230000008859 change Effects 0.000 claims description 89
- 230000004720 fertilization Effects 0.000 claims description 54
- 238000003062 neural network model Methods 0.000 claims description 42
- 238000013135 deep learning Methods 0.000 claims description 41
- 235000021049 nutrient content Nutrition 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 21
- 210000002569 neuron Anatomy 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 150000003839 salts Chemical class 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 15
- 238000003306 harvesting Methods 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 235000015097 nutrients Nutrition 0.000 claims description 13
- 238000013480 data collection Methods 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000013075 data extraction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- IJGRMHOSHXDMSA-UHFFFAOYSA-N nitrogen Substances N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 5
- 229910052757 nitrogen Inorganic materials 0.000 claims description 5
- 229910052698 phosphorus Inorganic materials 0.000 claims description 5
- 239000011574 phosphorus Substances 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- QJGQUHMNIGDVPM-UHFFFAOYSA-N nitrogen group Chemical group [N] QJGQUHMNIGDVPM-UHFFFAOYSA-N 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 5
- 241000196324 Embryophyta Species 0.000 description 8
- 230000008676 import Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000011591 potassium Substances 0.000 description 2
- 229910052700 potassium Inorganic materials 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012272 crop production Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015816 nutrient absorption Nutrition 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C21/00—Methods of fertilising, sowing or planting
- A01C21/005—Following a specific plan, e.g. pattern
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Soil Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a precise application method and a precise application system of crop fertilizers based on a neural network, which belong to the field of data processing systems specially suitable for management purposes.
Description
Technical Field
The invention belongs to the technical field of data processing systems specially suitable for management purposes, and particularly relates to a crop fertilizer accurate application method and system based on a neural network.
Background
According to researches, crop producers can blindly increase the application amount of fertilizer in order to achieve the aim of high yield and harvest, and because different varieties of crops have different nutrient absorption amounts and absorption ratios, excessive fertilizer input causes residual nutrients which cannot be absorbed and utilized by the crops to be accumulated in soil year by year, so that the soil environment is deteriorated, the crop yield is also reduced year by year, therefore, scientific and accurate fertilization is one of important components in a crop production operation system, the difficulty of accurate fertilization mainly lies in the formulation of a decision-making method, however, the existing fertilization method has a great number of contradictions with the current production practice, for example, the nutrient balance method has a great number of pending coefficients, the interaction among the nutrients cannot be reflected, and the fertilization amount calculation error is larger; the fertilizer effect method has the advantages of long test period, poor repeatability among years, easy occurrence of a saddle-shaped curve, large test workload, large error of predicted fertilization amount, difficulty in guiding actual production due to a large amount of accumulated data, inaccurate prediction in the prior art, and the problems in the prior art;
for example, in chinese patent application publication No. CN115063252a, a method and system for accurately applying crop fertilizer based on neural network are disclosed, comprising: acquiring an original training sample; carrying out data cleaning on the original training sample to obtain a training sample after data cleaning; normalizing the training sample after data cleaning to obtain a normalized training sample; clustering the normalized training samples to obtain a plurality of clustering centers; inputting a plurality of clustering centers into a preset neural network for training to obtain a fertilizer accurate application model; the current soil nutrient content of the production land and the target crop yield are input into a fertilizer accurate application model to determine the corresponding fertilization amount as an optimal fertilization scheme. According to the invention, through data cleaning and clustering of the training samples, the convergence of the neural network can be accelerated, and the fertilization quantity prediction precision of different crop target yields under certain soil conditions can be greatly improved;
Also disclosed in, for example, chinese patent application publication No. CN116267151a is a method for judging the fertilizing amount of crops, characterized by: according to the planting information which is acquired by farmers in the land, including the soil texture of the land, crops and related parameters of applied fertilizers, the farmers adopt an indoor calculation mode to obtain an absorption balance value of the release of nitrogen, phosphorus and potassium of the nutrients in unit area which are absorbed by the crops to be planted, and according to the balance value, the application quantity of the nitrogen, phosphorus and potassium nutrients of the crops to be planted is judged.
The problems proposed in the background art exist in the above patents: the difficulty of accurate fertilization mainly lies in the establishment of a decision-making method, however, the existing fertilization method has a great number of contradictions with the current production practice, for example, the nutrient balance method has a great number of undetermined coefficients, the interaction between nutrients cannot be reflected, and the fertilization amount calculation error is large; the fertilizer effect method has the advantages of long test period, poor repeatability among years, easy occurrence of a saddle-shaped curve, large test workload, large error of predicted fertilization amount, difficulty in guiding actual production of a large amount of accumulated data, inaccurate prediction in the prior art, and the application designs a precise application method and system of crop fertilizer based on a neural network for solving the problems.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a precise application method and a precise application system for crop fertilizers based on a neural network.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the crop fertilizer precise application method based on the neural network comprises the following specific steps:
s1, a data collection module collects historical planting data in the crop growing process and stores the historical planting data in a storage, wherein the historical planting data comprises historical soil type data, historical climate condition change data, historical crop variety data, historical crop growing stage data, historical fertilization amount and historical yield data;
s2, importing the obtained historical planting data in the crop growing process into a data screening strategy, and cleaning and screening the data to obtain screening historical planting data;
s3, based on screening historical planting data, constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growth stage data and output into crop harvest;
s4, acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data corresponding to a fertilizing field before fertilizing, and importing the data into a deep learning neural network model constructed, so as to acquire the actual fertilizer application amount corresponding to the crop yield with the maximum output;
S5, applying fertilizer to the appointed position of the fertilization field by the fertilizer applying module according to the obtained actual fertilizer applying amount corresponding to the maximum crop yield.
Specifically, the step S1 includes the following specific steps:
s11, acquiring historical soil type data through a soil data extraction module, and acquiring historical climate condition change data through a climate condition extraction module, wherein the historical soil type data comprise data of historical soil pH values, historical soil salinity and historical soil available nutrient contents of a planting area, and the historical climate condition change data comprise historical temperature change curves and historical humidity change curves of the planting area;
s12, collecting historical unit area fertilization data of a planting area through a fertilization amount collection module, collecting historical unit area yield of the planting area through a product collection module, and integrating historical soil pH value, historical soil salinity, historical soil effective nutrient content, historical temperature change curve, historical humidity change curve, historical unit area fertilization data and historical unit area yield of a planting area corresponding to planting varieties of the planting area into vector forms for storage and transmission, wherein the soil effective nutrient content is nitrogen content and phosphorus content in soil.
Specifically, the data filtering policy in S2 includes the following specific contents:
s21, extracting all vectors formed by the pH value of the historical soil, the salt content of the historical soil, the effective nutrient content of the historical soil, the historical temperature change curve, the historical humidity change curve, the data of the fertilization amount in a historical unit area and the yield in the historical unit area of a planting area of a corresponding planting area, screening a plurality of groups of vectors which are in the same variety and the same crop growth stage as the fertilization, and setting the vectors as an initial screening vector set;
s22, acquiring a temperature change curve and a humidity change curve of a weather forecast in the fertilization period, acquiring the pH value, the salt content and the effective nutrient content of soil in the fertilization area, integrating the soil pH value, the salt content and the effective nutrient content into a vector form, and setting the vector form as a screening vector;
s23, importing the obtained initial screening vector set and the current screening vector into a soil difference value calculation formula to calculate a soil difference value between one of the initial screening vector set and the current screening vector, wherein the soil difference value calculation formula is as follows:wherein k is 1i The difference value, x, between the ith initial screening vector and the current screening vector of the initial screening vector set phi Soil pH, x in the ith initial screening vector of the set of initial screening vectors ph For the pH value of the soil in the current screening vector, x hyi The salt content, x, of the soil in the ith initial screening vector of the initial screening vector set hy For the salt content of the soil in the current screening vector, x yxi For the soil effective nutrient amount, x in the ith initial screening vector of the initial screening vector set yx Lambda is the effective nutrient quantity of soil in the current screening vector 1 Lambda is the pH value of soil with a ratio coefficient 2 Lambda is the salt content ratio coefficient of soil 3 Is the effective nutrient content of soil and has a ratio coefficient of lambda 1 +λ 2 +λ 3 =1。
Here, λ is here 1 、λ 2 And lambda (lambda) 3 The value taking mode is that the same plant is planted in different soil environments, the yield difference of the planted plant is obtained, the data is imported into fitting software for fitting, and the optimal lambda meeting the accuracy is obtained 1 、λ 2 And lambda (lambda) 3 Is a value of (2);
specifically, the data screening policy in S2 further includes the following specific steps:
s24, importing the acquired initial screening vector set and the current screening vector into a weather difference value calculation formula to calculate the weather difference value of one of the initial screening vector set and the current screening vector, wherein the weather difference value calculation formula is as follows: Wherein beta is 1 Is the temperature duty ratio coefficient beta 2 Is the humidity duty ratio, k 2i For the weather difference value of the ith initial screening vector and the current screening vector of the initial screening vector set, z () is the length of the vector, A i And (U.A) is the intersection of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector of the initial screening vector set, A i U.A is the union of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector in the initial screening vector set, B i And n B is the intersection of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector of the initial screening vector set, B i U.B is the union of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector, wherein beta 1 +β 2 =1;
Here, β is here 1 β 2 The value taking mode is that the same plant is planted in the same soil under different weather conditions, the yield difference of the planted plant is obtained, the data is imported into fitting software for fitting, and the optimal beta meeting the accuracy is obtained 1 β 2 Is a value of (2);
s25, acquiring a weather difference value of one initial screening vector of the initial screening vector set and the current screening vector, and importing the soil difference value into an integral difference value calculation formula to calculate an integral difference value of the one initial screening vector of the initial screening vector set and the current screening vector, wherein the integral difference value calculation formula is as follows: k (k) i =k 2i +k 1i Wherein k is i The integral difference value of the ith initial screening vector and the current screening vector of the initial screening vector set is obtained;
s26, arranging the calculated overall difference values in an ascending order, and taking historical planting data corresponding to a plurality of groups of initial screening vectors with minimum overall difference values as screening historical planting data.
Specifically, the specific content of S3 includes the following specific steps:
s31, acquiring a plurality of groups of screening historical planting data, namely fertilizer application amount, soil type data, climate condition change data, crop variety data, actual crop growth stage data and crop harvest construction, wherein the construction is input into the actual fertilizer application amount, the actual soil type data, the actual climate condition change data, the actual crop variety data and the actual crop growth stage data, and the deep learning neural network model is output into the crop harvest;
s32, dividing the extracted screening historical planting data into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using 30% of parameter test sets, and outputting an optimal initial deep learning neural network model meeting preset crop harvesting accuracy as the deep learning neural network model, wherein an output strategy formula of a specific neuron in the deep learning neural network model is as follows: Wherein ynp +1 is the output of n+1 layer p neurons, +.>For the connection weight of the n-th layer neuron i and the n+1 layer p term neuron,/>Representing the nth layer of nervesOutput of meta,/, I>The offset representing the linear relationship of the n-th layer neuron i to the n+1 layer p term neuron, σ () represents the Sigmoid activation function.
Specifically, the specific content of S4 includes the following specific steps:
s41, acquiring soil type data of fertilization time of a fertilization point through a soil data extraction module before fertilization, and simultaneously acquiring subsequent weather and climate condition change data of weather forecast by a climate condition extraction module;
s42, importing the obtained real-time soil type data, the real-time climate condition change data, the real-time crop variety data and the real-time crop growth stage data of the obtained corresponding fertilizer application field into a constructed deep learning neural network model, and obtaining the actual fertilizer application amount corresponding to the crop yield with the maximum output.
The crop fertilizer accurate application system based on the neural network is realized based on the crop fertilizer accurate application method based on the neural network, and comprises a data collection module, a data screening module, a neural network construction module, an actual fertilizer application amount acquisition module, a fertilizer application module and a control module, wherein the data collection module is used for collecting historical planting data in the growth process of crops and storing the historical planting data in a storage, the data screening module is used for importing the historical planting data in the growth process of the obtained crops into a data screening strategy to clean and screen the data to obtain screening historical planting data, and the neural network construction module is used for constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growth stage data and outputting the data into crops.
Specifically, the actual fertilizer application amount acquisition module is used for acquiring actual fertilizer application amount corresponding to the maximum crop yield output from a deep learning neural network model constructed by importing real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data of a corresponding fertilizer application field, the fertilizer application module is used for applying fertilizer to a designated position of the fertilizer application field according to the obtained actual fertilizer application amount corresponding to the maximum crop yield, and the control module is used for controlling the operation of the data collection module, the data screening module, the neural network construction module, the actual fertilizer application amount acquisition module and the fertilizer application module.
An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the above-mentioned crop fertilizer precise application method based on the neural network by calling the computer program stored in the memory.
A computer readable storage medium storing instructions that when executed on a computer cause the computer to perform a neural network-based crop fertilizer precision application method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of collecting historical planting data in a crop growing process, storing the historical planting data in a storage, wherein the historical planting data comprises historical soil type data, historical climate condition change data, historical crop variety data, historical crop growing stage data, historical fertilization amount and historical yield data, importing the obtained historical planting data in the crop growing process into a data screening strategy to clean and screen the data to obtain screening historical planting data, constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growing stage data and outputting the actual fertilizer application amount, acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growing stage data of a field to be fertilized, importing the obtained actual fertilizer application amount which corresponds to the maximum crop yield into the constructed deep learning neural network model, applying fertilizer to a designated position of the field according to the obtained actual fertilizer application amount which corresponds to the maximum crop yield, predicting the fertilization amount by means of the neural network, and simultaneously improving the fertilization amount, and further improving the accuracy of the fertilization before the fertilization and the screening.
Drawings
FIG. 1 is a schematic flow chart of a precise application method of crop fertilizer based on a neural network;
fig. 2 is a schematic diagram of the whole framework of the crop fertilizer precise application system based on the neural network.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1, an embodiment of the present invention is provided: the crop fertilizer precise application method based on the neural network comprises the following specific steps:
s1, a data collection module collects historical planting data in the crop growing process and stores the historical planting data in a storage, wherein the historical planting data comprises historical soil type data, historical climate condition change data, historical crop variety data, historical crop growing stage data, historical fertilization amount and historical yield data;
it should be noted that, S1 includes the following specific steps:
s11, acquiring historical soil type data through a soil data extraction module, and acquiring historical climate condition change data through a climate condition extraction module, wherein the historical soil type data comprise data of historical soil pH values, historical soil salinity and historical soil available nutrient contents of a planting area, and the historical climate condition change data comprise historical temperature change curves and historical humidity change curves of the planting area;
Here, expressed by the code, the following is a simple C language code for collecting the historical soil type data and the historical climate condition change data by the soil data extraction module and the climate condition extraction module:
this simple example demonstrates how historical soil type data and historical climate change data can be extracted by two modules and data extracted and printed out in a master function, in practical applications, more complex data processing and module interactions may be required depending on the particular situation;
s12, collecting historical unit area fertilization data of a planting area through a fertilization amount collection module, collecting historical unit area yield of the planting area through a product collection module, and integrating historical soil pH value, historical soil salinity, historical soil effective nutrient content, historical temperature change curve, historical humidity change curve, historical unit area fertilization data and historical unit area yield of a planting area corresponding to planting varieties of the planting area into vector forms for storage and transmission, wherein the soil effective nutrient content is nitrogen content and phosphorus content in soil;
s2, importing the obtained historical planting data in the crop growing process into a data screening strategy, and cleaning and screening the data to obtain screening historical planting data;
It should be noted that, the data filtering policy in S2 includes the following specific contents:
s21, extracting all vectors formed by the pH value of the historical soil, the salt content of the historical soil, the effective nutrient content of the historical soil, the historical temperature change curve, the historical humidity change curve, the data of the fertilization amount in a historical unit area and the yield in the historical unit area of a planting area of a corresponding planting area, screening a plurality of groups of vectors which are in the same variety and the same crop growth stage as the fertilization, and setting the vectors as an initial screening vector set;
s22, acquiring a temperature change curve and a humidity change curve of a weather forecast in the fertilization period, acquiring the pH value, the salt content and the effective nutrient content of soil in the fertilization area, integrating the soil pH value, the salt content and the effective nutrient content into a vector form, and setting the vector form as a screening vector;
s23, importing the obtained initial screening vector set and the current screening vector into a soil difference value calculation formula to calculate a soil difference value between one of the initial screening vector set and the current screening vector, wherein the soil difference value calculation formula is as follows:wherein k is 1i The difference value, x, between the ith initial screening vector and the current screening vector of the initial screening vector set phi Soil pH, x in the ith initial screening vector of the set of initial screening vectors ph For the pH value of the soil in the current screening vector, x hyi The salt content, x, of the soil in the ith initial screening vector of the initial screening vector set hy For the salt content of the soil in the current screening vector, x yxi For the soil effective nutrient amount, x in the ith initial screening vector of the initial screening vector set yx Lambda is the effective nutrient quantity of soil in the current screening vector 1 Lambda is the pH value of soil with a ratio coefficient 2 Lambda is the salt content ratio coefficient of soil 3 Is the effective nutrient content of soil and has a ratio coefficient of lambda 1 +λ 2 +λ 3 =1。
Here, λ is here 1 、λ 2 And lambda (lambda) 3 The value taking mode is that the same plant is planted in different soil environments, the yield difference of the planted plant is obtained, and the data is imported into fitting softwareObtaining optimal lambda conforming to accuracy rate by line fitting 1 、λ 2 And lambda (lambda) 3 Is a value of (2);
the data screening strategy in S2 further comprises the following specific steps:
s24, importing the acquired initial screening vector set and the current screening vector into a weather difference value calculation formula to calculate the weather difference value of one of the initial screening vector set and the current screening vector, wherein the weather difference value calculation formula is as follows: Wherein beta is 1 Is the temperature duty ratio coefficient beta 2 Is the humidity duty ratio, k 2i For the weather difference value of the ith initial screening vector and the current screening vector of the initial screening vector set, z () is the length of the vector, A i And (U.A) is the intersection of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector of the initial screening vector set, A i U.A is the union of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector in the initial screening vector set, B i And n B is the intersection of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector of the initial screening vector set, B i U.B is the union of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector, wherein beta 1 +β 2 =1;
Here, β is here 1 β 2 The value taking mode is that the same plant is planted in the same soil under different weather conditions, the yield difference of the planted plant is obtained, the data is imported into fitting software for fitting, and the optimal beta meeting the accuracy is obtained 1 β 2 Is a value of (2);
s25, acquiring a weather difference value and a soil difference value of one initial screening vector of the initial screening vector set and the current screening vector, and importing the weather difference value and the soil difference value into one initial screening vector of the initial screening vector set and the current screening vector in the integral difference value calculation formula The screening vector calculates the integral difference value, and the integral difference value calculation formula is as follows: k (k) i =k 2i +k 1i Wherein k is i The integral difference value of the ith initial screening vector and the current screening vector of the initial screening vector set is obtained;
s26, arranging the calculated overall difference values in an ascending order, and taking historical planting data corresponding to a plurality of groups of initial screening vectors with minimum overall difference values as screening historical planting data;
s3, based on screening historical planting data, constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growth stage data and output into crop harvest;
the specific content of S3 includes the following specific steps:
s31, acquiring a plurality of groups of screening historical planting data, namely fertilizer application amount, soil type data, climate condition change data, crop variety data, actual crop growth stage data and crop harvest construction, wherein the construction is input into the actual fertilizer application amount, the actual soil type data, the actual climate condition change data, the actual crop variety data and the actual crop growth stage data, and the deep learning neural network model is output into the crop harvest;
The following is a simple example, in which a model using a deep learning neural network is written in Python to predict crop harvest;
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from keras.models import Sequential
from keras.layers import Dense
#1. Loading historical planting data
data=pd.read_csv("historical_planting_data.csv")
#2 preparation of data
X=data[['fertilizer_amount','soil_type','climate_change','crop_variety','growth_stage']]
y=data['yield']
# conversion of classified data into one-hot code
X=pd.get_dummies(X,columns=['soil_type','climate_change','crop_variety','growth_stage'])
#3 data preprocessing
scaler=StandardScaler()
X=scaler.fit_transform(X)
#4 splitting the dataset into a training set and a test set
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)
#5 building a neural network model
model=Sequential()
model.add(Dense(64,input_dim=X_train.shape[1],activation='relu'))
model.add(Dense(32,activation='relu'))
model.add(Dense(1,activation='linear'))
model.compile(optimizer='adam',
loss='mean_squared_error')
#6 model training
model.fit(X_train,y_train,epochs=50,batch_size=32,validation_data=(X_test,y_test))
#7 prediction Using model
y_pred=model.predict(X_test)
#8. Evaluation of model Performance
loss=model.evaluate(X_test,y_test)
print("Test loss:",loss)
Note that this is just a simple example, and in practical applications, more factors, such as model selection, super parameter tuning, feature engineering, etc., need to be considered, and the model may need to be adjusted and optimized according to the actual data and requirements. In addition, this example uses a Keras library to build neural network models;
s32, dividing the extracted screening historical planting data into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using 30% of parameter test sets, and outputting an optimal initial deep learning neural network model meeting preset crop harvesting accuracy as the deep learning neural network model, wherein an output strategy formula of a specific neuron in the deep learning neural network model is as follows: Wherein->For the output of n+1 layer p term neurons,/->For the connection weight of the n-th layer neuron i and the n+1 layer p term neuron,/>Representing the output of the n-th layer neuron i, < ->A bias representing the linear relationship of the n-th layer neuron i and the n+1 layer p term neuron, σ () representing a Sigmoid activation function;
s4, acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data corresponding to a fertilizing field before fertilizing, and importing the data into a deep learning neural network model constructed, so as to acquire the actual fertilizer application amount corresponding to the crop yield with the maximum output;
the specific content of S4 includes the following specific steps:
s41, acquiring soil type data of fertilization time of a fertilization point through a soil data extraction module before fertilization, and simultaneously acquiring subsequent weather and climate condition change data of weather forecast by a climate condition extraction module;
s42, importing the obtained real-time soil type data, the real-time climate condition change data, the real-time crop variety data and the real-time crop growth stage data of the corresponding fertilizer application field into a constructed deep learning neural network model, and obtaining the actual fertilizer application amount corresponding to the crop yield with the maximum output;
S5, applying fertilizer to the appointed position of the fertilization field by the fertilizer applying module according to the obtained actual fertilizer applying amount corresponding to the maximum crop yield.
The method comprises the steps of storing historical planting data in a storage in a collected crop growing process, wherein the historical planting data comprise historical soil type data, historical climate condition change data, historical crop variety data, historical crop growing stage data, historical fertilization amount and historical yield data, importing the obtained historical planting data in the crop growing process into a data screening strategy to clean and screen the data to obtain screening historical planting data, constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growing stage data and outputting the actual fertilizer application amount, acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growing stage data of a corresponding fertilizing field, importing the obtained actual fertilizer application amount which is corresponding to the maximum crop yield into the constructed deep learning neural network model, applying fertilizer to a designated position of the fertilizing field according to the obtained actual fertilizer application amount which is corresponding to the maximum crop yield, predicting the fertilizing amount by means of the neural network, and simultaneously improving the fertilizing amount, and accurately cleaning and screening the obtained fertilizer application data before the prediction.
Example 2
As shown in fig. 2, the system for precisely applying the crop fertilizer based on the neural network is realized based on the method for precisely applying the crop fertilizer based on the neural network, and comprises a data collection module, a data screening module, a neural network construction module, an actual fertilizer application amount acquisition module, a fertilizer application module and a control module, wherein the data collection module is used for collecting historical planting data in the growth process of crops and storing the historical planting data in the growth process of the crops in a storage, the data screening module is used for importing the historical planting data in the growth process of the crops into a data screening strategy to clean and screen the data to obtain screening historical planting data, and the neural network construction module is used for constructing a deep learning neural network model which is input into the actual fertilizer application amount, the actual soil type data, the actual climate condition change data, the actual crop variety data and the actual crop growth stage data based on the screening historical planting data and outputting the data into the crop harvest.
In this embodiment, the actual fertilizer application amount acquisition module is configured to acquire actual fertilizer application amount corresponding to the maximum crop yield output from the deep learning neural network model constructed by acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data of the corresponding fertilizer application field, the fertilizer application module is configured to apply fertilizer to a designated position of the fertilizer application field according to the obtained actual fertilizer application amount corresponding to the maximum crop yield, and the control module is configured to control operations of the data collection module, the data screening module, the neural network construction module, the actual fertilizer application amount acquisition module and the fertilizer application module.
Example 3
The present embodiment provides an electronic device including: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the above-described neural network-based crop fertilizer precise application method by calling a computer program stored in the memory.
The electronic device may be configured or configured differently to produce a larger difference, and may include one or more processors (Central Processing Units, CPU) and one or more memories, where the memories store at least one computer program loaded and executed by the processors to implement a neural network-based crop fertilizer precise application method provided by the above method embodiments. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Example 4
The present embodiment proposes a computer-readable storage medium having stored thereon an erasable computer program;
When the computer program runs on the computer equipment, the computer equipment is caused to execute the crop fertilizer precise application method based on the neural network.
For example, the computer readable storage medium can be Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), magnetic tape, floppy disk, optical data storage device, etc.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the partitioning of units is merely one way of partitioning, and there may be additional ways of partitioning in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (4)
1. The crop fertilizer accurate application method based on the neural network is characterized by comprising the following specific steps of:
s1, a data collection module collects historical planting data in the crop growing process and stores the historical planting data in a storage, wherein the historical planting data comprises historical soil type data, historical climate condition change data, historical crop variety data, historical crop growing stage data, historical fertilization amount and historical yield data;
s2, importing the obtained historical planting data in the crop growing process into a data screening strategy, and cleaning and screening the data to obtain screening historical planting data;
S3, based on screening historical planting data, constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growth stage data and output into crop harvest;
s4, acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data corresponding to a fertilizing field before fertilizing, and importing the data into a deep learning neural network model constructed, so as to acquire the actual fertilizer application amount corresponding to the crop yield with the maximum output;
s5, applying fertilizer to the appointed position of the fertilization field by the fertilizer application module according to the obtained actual fertilizer application amount corresponding to the maximum crop yield; the S1 comprises the following specific steps:
s11, acquiring historical soil type data through a soil data extraction module, and acquiring historical climate condition change data through a climate condition extraction module, wherein the historical soil type data comprise data of historical soil pH values, historical soil salinity and historical soil available nutrient contents of a planting area, and the historical climate condition change data comprise historical temperature change curves and historical humidity change curves of the planting area;
S12, collecting historical unit area fertilization data of a planting area through a fertilization amount collection module, collecting historical unit area yield of the planting area through a product collection module, and integrating historical soil pH value, historical soil salinity, historical soil effective nutrient content, historical temperature change curve, historical humidity change curve, historical unit area fertilization data and historical unit area yield of a planting area corresponding to planting varieties of the planting area into vector forms for storage and transmission, wherein the soil effective nutrient content is nitrogen content and phosphorus content in soil; the data screening strategy in the S2 comprises the following specific contents:
s21, extracting all vectors formed by the pH value of the historical soil, the salt content of the historical soil, the effective nutrient content of the historical soil, the historical temperature change curve, the historical humidity change curve, the data of the fertilization amount in a historical unit area and the yield in the historical unit area of a planting area of a corresponding planting area, screening a plurality of groups of vectors which are in the same variety and the same crop growth stage as the fertilization, and setting the vectors as an initial screening vector set;
s22, acquiring a temperature change curve and a humidity change curve of a weather forecast in the fertilization period, acquiring the pH value, the salt content and the effective nutrient content of soil in the fertilization area, integrating the soil pH value, the salt content and the effective nutrient content into a vector form, and setting the vector form as a screening vector;
S23, importing the obtained initial screening vector set and the current screening vector into a soil difference value calculation formula to calculate a soil difference value between one of the initial screening vector set and the current screening vector, wherein the soil difference value calculation formula is as follows:wherein k is 1i The difference value, x, between the ith initial screening vector and the current screening vector of the initial screening vector set phi Soil pH, x in the ith initial screening vector of the set of initial screening vectors ph For the pH value of the soil in the current screening vector, x hyi The salt content, x, of the soil in the ith initial screening vector of the initial screening vector set hy For the salt content of the soil in the current screening vector, x yxi For the soil effective nutrient amount, x in the ith initial screening vector of the initial screening vector set yx Lambda is the effective nutrient quantity of soil in the current screening vector 1 Lambda is the pH value of soil with a ratio coefficient 2 Lambda is the salt content ratio coefficient of soil 3 Is the effective nutrient content of soil and has a ratio coefficient of lambda 1 +λ 2 +λ 3 =1; the data screening strategy in S2 further comprises the following specific steps:
s24, importing the acquired initial screening vector set and the current screening vector into a weather difference value calculation formula to calculate the weather difference value of one of the initial screening vector set and the current screening vector, wherein the weather difference value calculation formula is as follows: Wherein beta is 1 Is the temperature duty ratio coefficient beta 2 Is the humidity duty ratio, k 2i For the weather difference value of the ith initial screening vector and the current screening vector of the initial screening vector set, z () is the length of the vector, A i And (U.A) is the intersection of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector of the initial screening vector set, A i U.A is the union of the temperature change curve in the ith initial screening vector and the temperature change curve in the current screening vector in the initial screening vector set, B i And n B is the intersection of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector of the initial screening vector set, B i U.B is the union of the humidity change curve in the ith initial screening vector and the humidity change curve in the current screening vector, wherein beta 1 +β 2 =1;
S25, acquiring a weather difference value of one initial screening vector of the initial screening vector set and the current screening vector, and importing the soil difference value into an integral difference value calculation formula to calculate an integral difference value of the one initial screening vector of the initial screening vector set and the current screening vector, wherein the integral difference value calculation formula is as follows: k (k) i =k 2i +k 1i Wherein k is i The integral difference value of the ith initial screening vector and the current screening vector of the initial screening vector set is obtained;
s26, arranging the calculated overall difference values in an ascending order, and taking historical planting data corresponding to a plurality of groups of initial screening vectors with minimum overall difference values as screening historical planting data; the method is characterized in that the specific content of the S3 comprises the following specific steps:
s31, acquiring a plurality of groups of screening historical planting data, namely fertilizer application amount, soil type data, climate condition change data, crop variety data, actual crop growth stage data and crop harvest construction, wherein the construction is input into the actual fertilizer application amount, the actual soil type data, the actual climate condition change data, the actual crop variety data and the actual crop growth stage data, and the deep learning neural network model is output into the crop harvest;
s32, dividing the extracted screening historical planting data into a 70% parameter training set and a 30% parameter test set; inputting 70% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using 30% of parameter test sets, and outputting an optimal initial deep learning neural network model meeting preset crop harvesting accuracy as the deep learning neural network model, wherein an output strategy formula of a specific neuron in the deep learning neural network model is as follows: Wherein->For the output of n+1 layer p term neurons,/->For the connection weight of the n-th layer neuron i and the n+1 layer p term neuron,representing the output of the n-th layer neuron i, < ->A bias representing the linear relationship of the n-th layer neuron i and the n+1 layer p term neuron, σ () representing a Sigmoid activation function; the specific content of the S4 comprises the following specific steps:
s41, acquiring soil type data of fertilization time of a fertilization point through a soil data extraction module before fertilization, and simultaneously acquiring subsequent weather and climate condition change data of weather forecast by a climate condition extraction module;
s42, importing the obtained real-time soil type data, the real-time climate condition change data, the real-time crop variety data and the real-time crop growth stage data of the obtained corresponding fertilizer application field into a constructed deep learning neural network model, and obtaining the actual fertilizer application amount corresponding to the crop yield with the maximum output.
2. The precise application system of crop fertilizer based on the neural network is realized based on the precise application method of crop fertilizer based on the neural network according to claim 1, and is characterized by comprising a data collection module, a data screening module, a neural network construction module, an actual fertilizer application amount acquisition module, a fertilizer application module and a control module, wherein the data collection module is used for collecting historical planting data in the growth process of crops and storing the historical planting data in the growth process of the crops in a storage, the data screening module is used for importing the obtained historical planting data in the growth process of the crops into a data screening strategy to clean and screen the data to obtain screening historical planting data, and the neural network construction module is used for constructing a deep learning neural network model which is input into actual fertilizer application amount, actual soil type data, actual climate condition change data, actual crop variety data and actual crop growth stage data and outputting the data into crops; the practical fertilizer application amount acquisition module is used for acquiring practical fertilizer application amount corresponding to the maximum crop yield output in a deep learning neural network model constructed by acquiring real-time soil type data, real-time climate condition change data, real-time crop variety data and real-time crop growth stage data of a corresponding fertilizer application field, the fertilizer application module is used for applying fertilizer to a designated position of the fertilizer application field according to the obtained practical fertilizer application amount corresponding to the maximum crop yield, and the control module is used for controlling the operation of the data collection module, the data screening module, the neural network construction module, the practical fertilizer application amount acquisition module and the fertilizer application module.
3. A human-machine interaction device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the method for applying crop fertilizer precisely according to claim 1, wherein the processor executes a method for applying crop fertilizer precisely based on a neural network by calling a computer program stored in the memory.
4. A computer readable storage medium storing instructions that when executed on a computer cause the computer to perform a neural network-based crop fertilizer precision application method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311620141.9A CN117322214B (en) | 2023-11-30 | 2023-11-30 | Crop fertilizer accurate application method and system based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311620141.9A CN117322214B (en) | 2023-11-30 | 2023-11-30 | Crop fertilizer accurate application method and system based on neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117322214A CN117322214A (en) | 2024-01-02 |
CN117322214B true CN117322214B (en) | 2024-02-09 |
Family
ID=89275954
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311620141.9A Active CN117322214B (en) | 2023-11-30 | 2023-11-30 | Crop fertilizer accurate application method and system based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117322214B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117577212A (en) * | 2024-01-17 | 2024-02-20 | 山东商务职业学院 | Ecological agriculture information service management system |
CN117688404B (en) * | 2024-02-02 | 2024-05-10 | 北京市农林科学院智能装备技术研究中心 | Intelligent fertilization formula decision method, intelligent fertilization formula decision device, intelligent fertilization formula decision equipment, intelligent fertilization formula decision medium and program product |
CN118114818B (en) * | 2024-02-27 | 2024-07-23 | 威尔芬(北京)科技发展有限公司 | Intelligent prediction method for sweet orange flower essential oil yield based on big data |
CN117882546B (en) * | 2024-03-13 | 2024-05-24 | 山西诚鼎伟业科技有限责任公司 | Intelligent planting method for agricultural operation robot |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101452505A (en) * | 2008-12-26 | 2009-06-10 | 熊凯 | System for fertilization compositions based on earth measurement |
CN101578936A (en) * | 2009-05-27 | 2009-11-18 | 中国农业大学 | Fertilization processing method and system |
CN101950323A (en) * | 2010-08-20 | 2011-01-19 | 江苏省农业科学院 | Method for recommending application rate of crop nitrogenous fertilizers based on soil nutrient balance |
CN103823371A (en) * | 2014-02-12 | 2014-05-28 | 无锡中科智能农业发展有限责任公司 | Neural network model-based agricultural precise fertilization system and fertilization method thereof |
CN107220903A (en) * | 2017-06-23 | 2017-09-29 | 深圳市盛路物联通讯技术有限公司 | A kind of reading intelligent agriculture management method and system |
CN107832892A (en) * | 2017-11-17 | 2018-03-23 | 北京大学 | A kind of lumpily seed selection decision optimization method based on Combinatorial Optimization |
WO2019111527A1 (en) * | 2017-12-08 | 2019-06-13 | コニカミノルタ株式会社 | Fertilization designing method and fertilization designing device |
CN109964611A (en) * | 2019-04-16 | 2019-07-05 | 中国农业大学 | A kind of field crop Tree Precise Fertilization method and system |
CN111557159A (en) * | 2020-05-20 | 2020-08-21 | 安徽农业大学 | Water and fertilizer integrated machine control system with crop nutrient demand analysis function and control method thereof |
CN113439520A (en) * | 2021-07-21 | 2021-09-28 | 中国农业科学院农业环境与可持续发展研究所 | Intelligent decision-making method and system for crop irrigation and fertilization |
CN114662742A (en) * | 2022-03-09 | 2022-06-24 | 北京市农林科学院智能装备技术研究中心 | Dynamic decision method and device for field irrigation and fertilization system |
CN115063252A (en) * | 2022-06-08 | 2022-09-16 | 山东省农业科学院 | Crop fertilizer accurate application method and system based on neural network |
CN115952931A (en) * | 2023-03-14 | 2023-04-11 | 华智生物技术有限公司 | Intelligent rice fertilization method, system, equipment and medium |
CN116420487A (en) * | 2023-03-31 | 2023-07-14 | 广西数字供销科技有限公司 | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence |
CN116579872A (en) * | 2023-04-25 | 2023-08-11 | 江苏华源节水股份有限公司 | Accurate irrigation decision-making method based on crop growth model and weather forecast |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10881045B2 (en) * | 2016-03-04 | 2021-01-05 | Nutrien Ag Solutions (Canada) Inc. | System and method for prescribing fertilizer application rates for spatial distribution of a product |
US11263707B2 (en) * | 2017-08-08 | 2022-03-01 | Indigo Ag, Inc. | Machine learning in agricultural planting, growing, and harvesting contexts |
EP4118418A1 (en) * | 2020-03-11 | 2023-01-18 | Viewnetic Ltd. | Systems and methods for monitoring plants in plant growing areas |
-
2023
- 2023-11-30 CN CN202311620141.9A patent/CN117322214B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101452505A (en) * | 2008-12-26 | 2009-06-10 | 熊凯 | System for fertilization compositions based on earth measurement |
CN101578936A (en) * | 2009-05-27 | 2009-11-18 | 中国农业大学 | Fertilization processing method and system |
CN101950323A (en) * | 2010-08-20 | 2011-01-19 | 江苏省农业科学院 | Method for recommending application rate of crop nitrogenous fertilizers based on soil nutrient balance |
CN103823371A (en) * | 2014-02-12 | 2014-05-28 | 无锡中科智能农业发展有限责任公司 | Neural network model-based agricultural precise fertilization system and fertilization method thereof |
CN107220903A (en) * | 2017-06-23 | 2017-09-29 | 深圳市盛路物联通讯技术有限公司 | A kind of reading intelligent agriculture management method and system |
CN107832892A (en) * | 2017-11-17 | 2018-03-23 | 北京大学 | A kind of lumpily seed selection decision optimization method based on Combinatorial Optimization |
WO2019111527A1 (en) * | 2017-12-08 | 2019-06-13 | コニカミノルタ株式会社 | Fertilization designing method and fertilization designing device |
CN109964611A (en) * | 2019-04-16 | 2019-07-05 | 中国农业大学 | A kind of field crop Tree Precise Fertilization method and system |
CN111557159A (en) * | 2020-05-20 | 2020-08-21 | 安徽农业大学 | Water and fertilizer integrated machine control system with crop nutrient demand analysis function and control method thereof |
CN113439520A (en) * | 2021-07-21 | 2021-09-28 | 中国农业科学院农业环境与可持续发展研究所 | Intelligent decision-making method and system for crop irrigation and fertilization |
CN114662742A (en) * | 2022-03-09 | 2022-06-24 | 北京市农林科学院智能装备技术研究中心 | Dynamic decision method and device for field irrigation and fertilization system |
CN115063252A (en) * | 2022-06-08 | 2022-09-16 | 山东省农业科学院 | Crop fertilizer accurate application method and system based on neural network |
CN115952931A (en) * | 2023-03-14 | 2023-04-11 | 华智生物技术有限公司 | Intelligent rice fertilization method, system, equipment and medium |
CN116420487A (en) * | 2023-03-31 | 2023-07-14 | 广西数字供销科技有限公司 | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence |
CN116579872A (en) * | 2023-04-25 | 2023-08-11 | 江苏华源节水股份有限公司 | Accurate irrigation decision-making method based on crop growth model and weather forecast |
Non-Patent Citations (3)
Title |
---|
利用神经网络建立土壤施肥模型的应用研究;滕青芳, 秦春林, 党建武;兰州铁道学院学报(第04期);第54-57页 * |
基于改进的BP神经网络集成的作物精准施肥模型;于合龙;赵新子;陈桂芬;万保成;高杰;;农业工程学报(第12期);第193-198页 * |
烤烟施肥数学模型及推荐施肥专家***研究;周孚美;陈小虎;;湖南农业科学(第12期);第68-72页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117322214A (en) | 2024-01-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117322214B (en) | Crop fertilizer accurate application method and system based on neural network | |
Cournede et al. | Some parameter estimation issues in functional-structural plant modelling | |
US20200250768A1 (en) | Intelligent soybean production management method and system | |
US20220248616A1 (en) | Irrigation control with deep reinforcement learning and smart scheduling | |
CN114818888B (en) | Soil composition data fusion method and system based on multi-channel Kalman filtering | |
CN116595333B (en) | Soil-climate intelligent rice target yield and nitrogen fertilizer consumption determination method | |
CN109964611A (en) | A kind of field crop Tree Precise Fertilization method and system | |
KR102387765B1 (en) | Method and apparatus for estimating crop growth quantity | |
CN110119767A (en) | A kind of cucumber green house temperature intelligent detection device based on LVQ neural network | |
CN117688404B (en) | Intelligent fertilization formula decision method, intelligent fertilization formula decision device, intelligent fertilization formula decision equipment, intelligent fertilization formula decision medium and program product | |
CN107368687B (en) | Optimal selection method and device for meteorological unit production model | |
Kalaiarasi et al. | Crop yield prediction using multi-parametric deep neural networks | |
Sharma et al. | Precision Agriculture and Its Future | |
CN117455066A (en) | Corn planting accurate fertilizer distribution method based on multi-strategy optimization random forest, electronic equipment and storage medium | |
Chaudhary et al. | A critical review on hybrid framework for precise farming with application of Machine Learning (ML) and Internet of Things (IoT) | |
US20230082714A1 (en) | Soil Property Model Using Measurements of Properties of Nearby Zones | |
Sharma et al. | Crop yield prediction using hybrid deep learning algorithm for smart agriculture | |
Güçlü et al. | Pollen performance modelling with an artificial neural network on commercial stone fruit cultivars | |
Jiang et al. | Application and evaluation of an improved LSTM model in the soil moisture prediction of southeast chinese tobacco-producing areas | |
Fredj et al. | CropWaterNeed: a machine learning approach for smart agriculture | |
Moswa et al. | Corn yield prediction using crop growth and machine learning models | |
Jiao et al. | [Retracted] Prediction Model of Rice Seedling Growth and Rhizosphere Fertility Based on the Improved Elman Neural Network | |
Bobade et al. | Design of Smart Irrigation System Based on MLA | |
CN118014133A (en) | Rice field cultivation system biomass prediction method and terminal equipment | |
Priya et al. | A survey on deep learning based IoT approach for precision crop suggestion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |