CN116420487A - Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence - Google Patents
Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN116420487A CN116420487A CN202310340355.4A CN202310340355A CN116420487A CN 116420487 A CN116420487 A CN 116420487A CN 202310340355 A CN202310340355 A CN 202310340355A CN 116420487 A CN116420487 A CN 116420487A
- Authority
- CN
- China
- Prior art keywords
- soil
- growth
- fertilizer
- snc
- sample data
- 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
- 238000002360 preparation method Methods 0.000 title claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 239000002881 soil fertilizer Substances 0.000 title claims abstract description 13
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 239000002689 soil Substances 0.000 claims abstract description 95
- 230000012010 growth Effects 0.000 claims abstract description 86
- 239000003337 fertilizer Substances 0.000 claims abstract description 67
- 235000021049 nutrient content Nutrition 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 37
- 235000015097 nutrients Nutrition 0.000 claims abstract description 34
- 238000005286 illumination Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 14
- 239000011573 trace mineral Substances 0.000 claims abstract description 11
- 235000013619 trace mineral Nutrition 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 238000013138 pruning Methods 0.000 claims abstract description 10
- 238000007637 random forest analysis Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 4
- 239000000523 sample Substances 0.000 claims description 36
- 238000012360 testing method Methods 0.000 claims description 18
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 12
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 239000011575 calcium Substances 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 239000011777 magnesium Substances 0.000 claims description 8
- 239000011701 zinc Substances 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 6
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 239000012153 distilled water Substances 0.000 claims description 6
- 229910052757 nitrogen Inorganic materials 0.000 claims description 6
- 239000011574 phosphorus Substances 0.000 claims description 6
- 229910052698 phosphorus Inorganic materials 0.000 claims description 6
- 239000011591 potassium Substances 0.000 claims description 6
- 229910052700 potassium Inorganic materials 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 230000035558 fertility Effects 0.000 claims description 5
- ZOXJGFHDIHLPTG-UHFFFAOYSA-N Boron Chemical compound [B] ZOXJGFHDIHLPTG-UHFFFAOYSA-N 0.000 claims description 4
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 4
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 4
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 claims description 4
- 229910052796 boron Inorganic materials 0.000 claims description 4
- 229910052791 calcium Inorganic materials 0.000 claims description 4
- 229910052742 iron Inorganic materials 0.000 claims description 4
- 229910052749 magnesium Inorganic materials 0.000 claims description 4
- 229910052725 zinc Inorganic materials 0.000 claims description 4
- 239000003153 chemical reaction reagent Substances 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000012488 sample solution Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000011550 stock solution Substances 0.000 claims description 3
- 241000196324 Embryophyta Species 0.000 description 6
- 230000004720 fertilization Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008635 plant growth Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- WZLMXYBCAZZIRQ-UHFFFAOYSA-N [N].[P].[K] Chemical compound [N].[P].[K] WZLMXYBCAZZIRQ-UHFFFAOYSA-N 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004737 colorimetric analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000021048 nutrient requirements Nutrition 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C21/00—Methods of fertilising, sowing or planting
- A01C21/007—Determining fertilization requirements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Soil Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- Environmental Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Animal Husbandry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Fertilizing (AREA)
Abstract
The invention discloses a soil fertilizer preparation method, a system, equipment and a storage medium based on artificial intelligence, wherein the method comprises the following steps: acquiring humidity H, temperature T, illumination intensity L, soil pH value PH, nutrient content SNC, trace elements and crop growth conditions of a designated area for multiple times in the growth period of crops; storing the data matrix into a database as original sample data according to the time period; pruning optimization processing is carried out on the original sample data, and a characteristic value with the largest influence is screened out to obtain training sample data; training and learning the training sample data by using a random forest algorithm to obtain a growth model; inputting the humidity H, the temperature T, the illumination intensity L, the pH value of soil, the nutrient content SNC, microelements and the growth situation of a region to be fertilized into a growth model to obtain the optimal soil content NR, pH, temperature, humidity and actual soil content SNC of crops for nutrients; calculating the fertilizer dosage according to the nutrient content FNC of the fertilizer and the fertilizer formula.
Description
Technical Field
The invention relates to the technical field of soil fertilizer preparation, in particular to a soil fertilizer preparation method, a system, equipment and a storage medium based on artificial intelligence.
Background
With the rapid development of the agricultural industry in China, soil nutrient balance and soil fertility management have become important links in agricultural production. And the precise fertilization is realized, the growth and development of crops and the high-efficiency increase of the yield are ensured, and the support of a modern soil fertilizer preparation technology is needed. However, the traditional manual fertilizer preparation method has the following defects: low production efficiency, high cost, difficulty in adapting to different soil types and crop requirements, incapability of quickly adapting to environmental changes and the like.
Patent CN108684278B discloses an intelligent fertilizer preparation method, device and system, which obtains soil nutrient detection value, PH value, topography, soil property, fertilization habit and/or historical yield according to position information; calculating the soil nutrient supply according to the soil nutrient detection value; acquiring nutrient demand according to crop information; and calculating the nutrient application amount according to the nutrient demand and the soil nutrient supply amount.
The intelligent fertilizer preparation method is based on fertilizer application habit and historical yield, ignores influence of climate on crops, and also has the problem of incapability of quickly adapting to environmental changes.
Disclosure of Invention
The invention aims to solve the technical problems of the prior art, and aims to provide a soil fertilizer preparation method based on artificial intelligence, so as to solve the pain points and problems of the traditional soil fertility detection method, enable soil fertilization to be more accurate and efficient and improve crop yield and quality.
The invention aims at providing a soil fertilizer distribution system based on artificial intelligence.
The third object of the present invention is to provide a computer device.
A fourth object of the present invention is to provide a computer storage medium.
In order to achieve the purpose, the invention provides a soil fertilizer preparation method based on artificial intelligence, which comprises the following steps:
s1, acquiring climate parameters, soil parameters and growth situation images of crops in a designated area for multiple times in a growth period of the crops, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and microelements, and the growth situation is obtained according to the growth situation images;
s2, storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are obtained each time into a database in a data matrix according to a time period, and taking the data as original sample data;
s3, pruning optimization processing is carried out on the original sample data obtained each time, and characteristic values with the largest influence are screened out to obtain training sample data;
s4, training and learning the training sample data by using a random forest algorithm to obtain related reasoning rules, and establishing a growth model of the relationship among soil nutrients, environmental factors and crop growth;
s5, acquiring humidity H, temperature T, illumination intensity L, soil pH value PH, nutrient content SNC, trace elements and growth conditions of a region to be fertilized, and inputting a growth model to obtain optimal soil content NR, PH, temperature, humidity and actual soil content SNC of crops on the nutrients;
s6, detecting nutrient contents FNC of various fertilizers;
s7, calculating the fertilizer dosage according to a fertilizer preparation formula, and customizing proper fertilizer types and dosage for crops in a to-be-prepared fertilizer area;
the formula of the fertilizer is as follows: the amount of fertilizer needed to be added nn= (the amount of crop demand for nutrients nr—the nutrient content SNC in the soil)/the nutrient content FNC in the fertilizer.
As a further improvement, in step S1, the temperature T, the humidity H, the illumination intensity L of a certain period of time are detected by means of a weather environment monitoring station;
the method comprises the steps of performing bottom-up layered sampling on soil, measuring the pH value of a soil sample solution by adopting a pH automatic detector, detecting the nutrient content of the soil by using a fertilizer detector, and inputting sampling detection data into a cloud computing platform to obtain nutrient content SNC and trace elements, wherein the nutrient content SNC comprises three elements: nitrogen N%, phosphorus P%, potassium K%, microelements including calcium Ca, iron Fe, magnesium Mg, boron B, zinc Zn;
the growth conditions include 1-non-vegetation, 2-poor growth, 3-normal growth, 4-good growth and 5-weed.
Further, step S3 includes:
s31, loading original sample data, and evaluating a characteristic value by adopting a decision tree algorithm by means of a scikit-learn third party library;
s32, training a decision tree model by using a DecisionTreeRegresor;
and S33, calculating the mean square error according to the feature importance sequence, and determining the good growth characteristics.
Further, step S4 includes:
s41, classifying training sample data by utilizing a random forest algorithm by means of a scikit-learn third party library to obtain a prediction model;
s42, testing the obtained prediction model according to training sample data, verifying the accuracy of the prediction model, optimizing the model, and inputting the data of each test into a maintenance classifier;
and S43, repeating the steps S41 to S42, and repeatedly maintaining and correcting the prediction model until the output growth prediction accuracy reaches 95%.
Further, step S5 includes:
s51, respectively sucking 2mL of distilled water by using a suction pipe as a blank, sucking 2mL+1 drops of fertilizer nutrient mixed standard stock solution of the distilled water by using the suction pipe as a standard, and sucking 2mL of a water sample to be detected by using the suction pipe;
s52, respectively dripping a drop of a reagent to be tested of the fertilizer into the three test tubes in the step S51, and shaking uniformly;
and S53, transferring the liquid in the three test tubes in the step S52 into a cuvette after five minutes, and detecting by using a fertilizer nutrient detector to obtain the nutrient content FNC (nitrogen, phosphorus and potassium content) of the fertilizer.
In order to achieve the second purpose, the invention provides a soil fertilizer preparation system based on artificial intelligence, comprising:
the acquisition module is used for acquiring climate parameters, soil parameters and growth situation images of crops of a designated area, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and trace elements, and the growth situation is obtained according to the growth situation images;
the storage module is used for storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are acquired each time into a database in a data matrix according to a time period and taking the data as original sample data;
the pruning optimization module is used for carrying out pruning optimization on the original sample data obtained each time, screening out the characteristic value with the largest influence, and obtaining training sample data;
the training module is used for training and learning the training sample data by applying a random forest algorithm to obtain related reasoning rules and establishing a growth model of the relationship among soil nutrients, environmental factors and crop growth;
the judging module is used for inputting the humidity H, the temperature T, the illumination intensity L, the pH value PH of soil, the nutrient content SNC, the microelements and the growth situation of the area to be fertilized into the growth model to obtain the optimal soil content NR, PH, temperature, humidity and the actual soil content SNC of crops for the nutrients;
the fertilizer preparation module is used for calculating the fertilizer dosage according to the nutrient content FNC of the fertilizer and a fertilizer preparation formula and customizing the proper fertilizer type and dosage for the crops in the area to be prepared.
In order to achieve the third purpose, the invention provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the soil fertilization method based on artificial intelligence when executing the computer program.
In order to achieve the fourth object, the present invention provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the artificial intelligence-based soil fertilizing method described above.
Advantageous effects
Compared with the prior art, the invention has the advantages that:
the invention can efficiently and rapidly analyze soil, automatically prepare the optimal fertilizer formula according to plant demands, and has the following advantages:
1. the soil fertility is improved, and various fertilizers required by crops can better meet the growth needs of plants through reasonable formula collocation, so that the soil fertility is improved.
2. The plant growth capacity is enhanced, the nutrient components required by the plants are more accurate, and the requirements of the plants can be better met, so that the plant growth capacity is enhanced.
3. The soil fertilizer preparation method based on the artificial intelligence algorithm saves time and cost, realizes quick and automatic fertilizer preparation, saves labor and material costs, and improves working efficiency.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will be further described with reference to specific embodiments in the drawings.
Referring to fig. 1, an artificial intelligence-based soil fertilizer preparation method comprises the following steps:
s1, acquiring climate parameters, soil parameters and growth situation images of crops in a designated area for multiple times in a growth period of the crops, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and microelements, and the growth situation is obtained according to the growth situation images;
s2, storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are obtained each time into a database in a data matrix according to a time period, and taking the data as original sample data;
s3, pruning optimization processing is carried out on the original sample data obtained each time, and characteristic values with the largest influence are screened out to obtain training sample data;
s4, training and learning training sample data by using a random forest algorithm to obtain related reasoning rules, and establishing a growth model of the relationship between soil nutrients, environmental factors and crop growth;
s5, acquiring humidity H, temperature T, illumination intensity L, soil pH value PH, nutrient content SNC, trace elements and growth conditions of a region to be fertilized, and inputting a growth model to obtain optimal soil content NR, PH, temperature, humidity and actual soil content SNC of crops for nutrients;
s6, detecting nutrient contents FNC of various fertilizers;
s7, calculating the fertilizer dosage according to a fertilizer preparation formula, and customizing proper fertilizer types and dosage for crops in a to-be-prepared fertilizer area;
the formula of the fertilizer is as follows: the amount of fertilizer needed to be added nn= (the amount of crop demand for nutrients nr—the nutrient content SNC in the soil)/the nutrient content FNC in the fertilizer.
In step S1, the temperature T, the humidity H, the illumination intensity L of a certain period of time may be detected by means of a weather environment monitoring station.
Soil samples can be manually collected, soil is subjected to bottom-up layered sampling, the PH value of a soil sample solution is measured by a PH automatic detector, the nutrient content of the soil is detected by a fertilizer detector, sampling detection data are input into a cloud computing platform, and nutrient content SNC and trace elements are obtained, wherein the nutrient content SNC comprises three elements: nitrogen N%, phosphorus P%, potassium K%, and microelements including calcium Ca%, iron Fe%, magnesium Mg%, boron B% and zinc Zn%.
Of course, the method can also be installed in soil by means of various sensors to automatically detect the pH value PH of the soil, the nutrient content SNC and trace elements.
The growth conditions can be divided into 5 types, including 1-non-vegetation, 2-poor growth, 3-normal growth, 4-good growth and 5-weed.
The step S3 includes:
s31, loading original sample data, and evaluating characteristic values by adopting a decision tree algorithm by means of a scikit-learn third party library. The following is implemented in programming:
# load data.
data＝pd.read_csv('agriculture_data.csv')
Twelve characteristics of # temperature, humidity, illumination intensity L, PH, nitrogen, phosphorus, potassium, calcium, iron, magnesium, boron, zinc were taken as input characteristics.
X＝data[['H','T','L','PH','SNC','N％','P％','K％','Ca％','Fe％','Mg％','B％','Zn％']]
# growth vigour and yield as output tags.
y＝data['yield']。
Step S32, training a decision tree model by using a DecisionTreeRegresor. The following is implemented in programming:
# the depth of the tree is controlled by setting the max_depth parameter.
tree＝DecisionTreeRegressor(max_depth＝3)
tree.fit(X,y)
# model was predicted and evaluated.
y_pred＝tree.predict(X)。
And S33, calculating the mean square error according to the feature importance sequence, and determining the good growth characteristics. The following is implemented in programming:
and (5) sorting the importance of the features, calculating the mean square error, and finally arranging the importance of the features in a descending order and printing the result.
feature_importances＝dict(zip(X.columns,
tree.feature_importances_))
sorted_feature_importances＝sorted(feature_importances.items(),
key＝lambda x:x[1],reverse＝True)
for feature,importance in sorted_feature_importances:
print(f"{feature}:{importance}")。
The step S4 includes:
s41, classifying training sample data by utilizing a random forest algorithm by means of a scikit-learn third party library to obtain a prediction model. The following is implemented in programming:
import numpy as np
from sklearn.naive_bayes
import GaussianNB,MultinomialNB,BernoulliNB
training data #
X＝np.array([[1,2,3,4],[1,3,4,4],[2,4,5,5],[2,5,6,5],[3,4,5,6])
# growth vigor label (1: non-vegetation, 2: poor growth vigor, 3: normal growth vigor, 4: good growth vigor, 5: weed)
y＝np.array([1,1,4,2,3,5])
clf＝GaussianNB()
clf.fit(X,y)
# receives imaging hotspot X set data and y label, trains non-vegetation, has poor growth vigor, common growth vigor, better growth vigor and weed model
clf.transform(x,y)
# predicts crop growth.
S42, testing the obtained prediction model according to the training sample data, verifying the accuracy of the prediction model, optimizing the model, and inputting the data of each test into a maintenance classifier. The following is implemented in programming:
CSV file for# loading soil nutrient and crop growth data set
data＝np.loadtxt('crop_growth_data.csv',delimiter＝',')
Splitting a data set into a training set and a testing set using a train_test_split function #
X_train,X_test,y_train,y_test＝train_test_split(data[:,:-1],data[:,-1],test_size＝0.3,random_state＝42)
# a Support Vector Machine (SVM) classifier object was created and trained for 10 iterations
clf＝SVC(kernel＝'linear')
Training classifier # and calculating precision on test set by using accuracy_score function after each iteration and outputting to control console
for i in range (10): # 10 training runs
clf.fit(X_train,y_train)
y_pred＝clf.predict(X_test)
acc＝accuracy_score(y_test,y_pred)
print(f'Accuracy of iteration{i}:{acc:.4f}')
Optimal soil content NR, PH, temperature and humidity and actual soil content SNC of# output crops for nutrients
print(f"Final Nutrient requirements:{acc:.4f}")。
And S43, repeating the steps S41 to S42, and repeatedly maintaining and correcting the prediction model until the output growth prediction accuracy reaches 95%.
In the step S5, a colorimetric method is adopted, and a fertilizer nutrient detector is used for detection. Comprising the following steps:
s51, respectively sucking 2mL of distilled water by using a suction pipe as a blank, sucking 2mL+1 drops of fertilizer nutrient mixed standard stock solution of the distilled water by using the suction pipe as a standard, and sucking 2mL of a water sample to be detected by using the suction pipe;
s52, respectively dripping a drop of a reagent to be tested of the fertilizer into the three test tubes in the step S51, and shaking uniformly;
and S53, transferring the liquid in the three test tubes in the step S52 into a cuvette after five minutes, and detecting by using a fertilizer nutrient detector to obtain the nutrient content FNC (nitrogen phosphorus potassium content) (unit: mg/L) of the fertilizer.
Step S7 is implemented in programming as follows:
calculating the amount of fertilizer to be added
NN＝(NR-SNC)/FNC
# output result
print (f "the amount of fertilizer to be added is: { NN:.2f } mg/L").
An artificial intelligence based soil fertilizing system comprising:
the acquisition module is used for acquiring climate parameters, soil parameters and growth situation images of crops of a designated area, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and trace elements, and the growth situation is obtained according to the growth situation images;
the storage module is used for storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are acquired each time into a database in a data matrix according to a time period and taking the data as original sample data;
the pruning optimization module is used for carrying out pruning optimization on the original sample data obtained each time, screening out the characteristic value with the largest influence, and obtaining training sample data;
the training module is used for training and learning training sample data by applying a random forest algorithm to obtain related reasoning rules and establishing a growth model of the relationship among soil nutrients, environmental factors and crop growth;
the judging module is used for inputting the humidity H, the temperature T, the illumination intensity L, the pH value PH of soil, the nutrient content SNC, the microelements and the growth conditions of the to-be-fertilized area into the growth model to obtain the optimal soil content NR, the PH, the temperature, the humidity and the actual soil content SNC of crops for the nutrients;
the fertilizer preparation module is used for calculating the fertilizer dosage according to the nutrient content FNC of the fertilizer and a fertilizer preparation formula and customizing the proper fertilizer type and dosage for the crops in the area to be prepared.
The computer equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the soil fertilizing method based on artificial intelligence when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the artificial intelligence based soil fertilizing method described above.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these do not affect the effect of the implementation of the present invention and the utility of the patent.
Claims (8)
1. The soil fertilizer preparation method based on artificial intelligence is characterized by comprising the following steps of:
s1, acquiring climate parameters, soil parameters and growth situation images of crops in a designated area for multiple times in a growth period of the crops, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and microelements, and the growth situation is obtained according to the growth situation images;
s2, storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are obtained each time into a database in a data matrix according to a time period, and taking the data as original sample data;
s3, pruning optimization processing is carried out on the original sample data obtained each time, and characteristic values with the largest influence are screened out to obtain training sample data;
s4, training and learning the training sample data by using a random forest algorithm to obtain related reasoning rules, and establishing a growth model of the relationship among soil nutrients, environmental factors and crop growth;
s5, acquiring humidity H, temperature T, illumination intensity L, soil pH value PH, nutrient content SNC, trace elements and growth conditions of a region to be fertilized, and inputting a growth model to obtain optimal soil content NR, PH, temperature, humidity and actual soil content SNC of crops on the nutrients;
s6, detecting nutrient contents FNC of various fertilizers;
s7, calculating the fertilizer dosage according to a fertilizer preparation formula, and customizing proper fertilizer types and dosage for crops in a to-be-prepared fertilizer area;
the formula of the fertilizer is as follows: the amount of fertilizer needed to be added nn= (the amount of crop demand for nutrients nr—the nutrient content SNC in the soil)/the nutrient content FNC in the fertilizer.
2. The artificial intelligence based soil fertility method according to claim 1, wherein in step S1, the temperature T, the humidity H, the illumination intensity L of a certain period of time are detected by means of a meteorological environment monitoring station;
the method comprises the steps of performing bottom-up layered sampling on soil, measuring the pH value of a soil sample solution by adopting a pH automatic detector, detecting the nutrient content of the soil by using a fertilizer detector, and inputting sampling detection data into a cloud computing platform to obtain nutrient content SNC and trace elements, wherein the nutrient content SNC comprises three elements: nitrogen N%, phosphorus P%, potassium K%, microelements including calcium Ca, iron Fe, magnesium Mg, boron B, zinc Zn;
the growth conditions include 1-non-vegetation, 2-poor growth, 3-normal growth, 4-good growth and 5-weed.
3. The artificial intelligence based soil fertilizing method as set forth in claim 1, wherein the step S3 includes:
s31, loading original sample data, and evaluating a characteristic value by adopting a decision tree algorithm by means of a scikit-learn third party library;
s32, training a decision tree model by using a DecisionTreeRegresor;
and S33, calculating the mean square error according to the feature importance sequence, and determining the good growth characteristics.
4. The artificial intelligence based soil fertilizing method as set forth in claim 1, wherein the step S4 includes:
s41, classifying training sample data by utilizing a random forest algorithm by means of a scikit-learn third party library to obtain a prediction model;
s42, testing the obtained prediction model according to training sample data, verifying the accuracy of the prediction model, optimizing the model, and inputting the data of each test into a maintenance classifier;
and S43, repeating the steps S41 to S42, and repeatedly maintaining and correcting the prediction model until the output growth prediction accuracy reaches 95%.
5. The artificial intelligence based soil fertilizing method as set forth in claim 1, wherein the step S5 includes:
s51, respectively sucking 2mL of distilled water by using a suction pipe as a blank, sucking 2mL+1 drops of fertilizer nutrient mixed standard stock solution of the distilled water by using the suction pipe as a standard, and sucking 2mL of a water sample to be detected by using the suction pipe;
s52, respectively dripping a drop of a reagent to be tested of the fertilizer into the three test tubes in the step S51, and shaking uniformly;
and S53, transferring the liquid in the three test tubes in the step S52 into a cuvette after five minutes, and detecting by using a fertilizer nutrient detector to obtain the nutrient content FNC (nitrogen, phosphorus and potassium content) of the fertilizer.
6. Soil is joined in marriage fertile system based on artificial intelligence, its characterized in that includes:
the acquisition module is used for acquiring climate parameters, soil parameters and growth situation images of crops of a designated area, wherein the climate parameters comprise humidity H, temperature T and illumination intensity L, the soil parameters comprise soil pH value PH, nutrient content SNC and trace elements, and the growth situation is obtained according to the growth situation images;
the storage module is used for storing the humidity H, the temperature T, the illumination intensity L, the soil pH value PH, the nutrient content SNC, the microelements and the growth conditions which are acquired each time into a database in a data matrix according to a time period and taking the data as original sample data;
the pruning optimization module is used for carrying out pruning optimization on the original sample data obtained each time, screening out the characteristic value with the largest influence, and obtaining training sample data;
the training module is used for training and learning the training sample data by applying a random forest algorithm to obtain related reasoning rules and establishing a growth model of the relationship among soil nutrients, environmental factors and crop growth;
the judging module is used for inputting the humidity H, the temperature T, the illumination intensity L, the pH value PH of soil, the nutrient content SNC, the microelements and the growth situation of the area to be fertilized into the growth model to obtain the optimal soil content NR, PH, temperature, humidity and the actual soil content SNC of crops for the nutrients;
the fertilizer preparation module is used for calculating the fertilizer dosage according to the nutrient content FNC of the fertilizer and a fertilizer preparation formula and customizing the proper fertilizer type and dosage for the crops in the area to be prepared.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the artificial intelligence based soil fertilizing method of any one of claims 1-5 when executing the computer program.
8. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the artificial intelligence based soil fertilizing method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310340355.4A CN116420487A (en) | 2023-03-31 | 2023-03-31 | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310340355.4A CN116420487A (en) | 2023-03-31 | 2023-03-31 | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116420487A true CN116420487A (en) | 2023-07-14 |
Family
ID=87084825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310340355.4A Pending CN116420487A (en) | 2023-03-31 | 2023-03-31 | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116420487A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117322214A (en) * | 2023-11-30 | 2024-01-02 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
| CN117976081A (en) * | 2024-04-02 | 2024-05-03 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
-
2023
- 2023-03-31 CN CN202310340355.4A patent/CN116420487A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117322214A (en) * | 2023-11-30 | 2024-01-02 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
| CN117322214B (en) * | 2023-11-30 | 2024-02-09 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
| CN117976081A (en) * | 2024-04-02 | 2024-05-03 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116420487A (en) | Soil fertilizer preparation method, system, equipment and storage medium based on artificial intelligence | |
| Urena et al. | A machine vision system for seeds quality evaluation using fuzzy logic | |
| CN101578936B (en) | Fertilization processing method and system | |
| Dent et al. | The role of biological simulation models in farming systems research | |
| Salim et al. | Urban farming activities in southeast asia: A review and future research direction | |
| CN116258060A (en) | Soil testing formula fertilization method based on machine learning | |
| Beneduzzi et al. | Fertilizer recommendation methods for precision agriculture–a systematic literature study | |
| Bhattacharya et al. | An Integrated Decision-Support System for Increasing Crop Yield Based on Progressive Machine Learning and Sensor Data | |
| Chaudhary et al. | A critical review on hybrid framework for precise farming with application of Machine Learning (ML) and Internet of Things (IoT) | |
| CN117408430A (en) | Soil improvement evaluation system for agricultural planting based on big data | |
| Monica et al. | Soil NPK prediction using enhanced genetic algorithm | |
| Tenreiro et al. | Simulating water lateral inflow and its contribution to spatial variations of rainfed wheat yields | |
| Abdullaev et al. | Precision agriculture in the north of Kazakhstan. | |
| Zhang et al. | Artificial intelligence in soil management: The new frontier of smart agriculture | |
| CN115690609A (en) | Method for monitoring growth vigor of crops in growth period | |
| CN114004389A (en) | Hybrid method for crop yield prediction | |
| CN113408701A (en) | Convolutional neural network soil organic matter analysis model construction system and method | |
| Gopi et al. | Prediction of Paddy Yield based on IoT Data using GRU Model in Lowland Coastal Regions | |
| CN113435574A (en) | Convolutional neural network soil quick-acting potassium analysis model construction system and method | |
| CN113408700A (en) | Convolutional neural network soil alkaline hydrolysis nitrogen analysis model construction system and method | |
| CN111289725A (en) | Farmland soil organic carbon reserve estimation method and system combining model and time sequence sampling | |
| Antwi | Integrated Soil Fertility Management as a Potential for Ghana’s Development: The Geospatial Approach | |
| Mittal et al. | Implementation and Identification of Crop based on Soil Texture using AI | |
| CN117852720A (en) | Agricultural multidimensional fertilization prediction method based on machine learning classification and regression algorithm | |
| CN117035471B (en) | Fertilizing decision method and system based on multi-vegetation index image |
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 |