CN107220672A - Acquisition methods between a kind of suitable warm area based on crop demand - Google Patents
Acquisition methods between a kind of suitable warm area based on crop demand Download PDFInfo
- Publication number
- CN107220672A CN107220672A CN201710400511.6A CN201710400511A CN107220672A CN 107220672 A CN107220672 A CN 107220672A CN 201710400511 A CN201710400511 A CN 201710400511A CN 107220672 A CN107220672 A CN 107220672A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- mtd
- mtr
- msubsup
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Abstract
The present invention is acquisition methods between a kind of suitable warm area based on crop demand, based on Gen Wen and intensity of illumination, temperture of leaves, CO2Concentration coupled relation, sets up between photosynthetic rate forecast model, the suitable root warm area of acquisition;First, crop is carried out by environment pre-adaptation processing using incubator, secondly, uses portable photosynthetic rate test instrument to measure different temperature, temperture of leaves, CO with nested experiment method2Net Photosynthetic Rate under the conditions of concentration, intensity of illumination, analyze the coupling between Net Photosynthetic Rate and envirment factor, photosynthetic rate forecast model is set up using Support Vector Machines for Regression, optimal temperture of leaves, CO under the conditions of different temperature are found using Multiple-population Genetic Algorithm2Concentration, intensity of illumination and corresponding maximum photosynthesis rate, are obtained between suitable root warm area, and it is too low too high on the photosynthetic influence of water planting crops to be prevented effectively from Summer and winter root temperature, is facility water planting crops temperture of leaves, CO2Good basis has been established in the regulation and control of the envirment factors such as concentration, intensity of illumination.
Description
Technical field
The invention belongs to reading intelligent agriculture technical field, obtained between more particularly to a kind of suitable warm area based on crop demand
Method.
Background technology
Photosynthesis is as the leading indicator for weighing plant dry matter accumulation, by root temperature, temperature, CO2, the ring such as intensity of illumination
The influence of the border factor is very big, and illumination is one of photosynthesis of plant essential condition, CO2It is the important of photosynthesis of plant
Participant, air themperature is to improve activities of enzymes in leaf, chlorophyll content, and then improves the necessary requirement of photosynthetic capacity.And
Root temperature directly influences the root growth and Nutrient Absorption of facility water planting crops, and Gen Wenyi is low by summer high temperature and winter in addition
The influence of temperature, causes the root growth and Nutrient Absorption of romaine lettuce to meet the growth demand of aerial part, has a strong impact on crop
Photosynthesis and yield, it has also become influence facility water planting crops grow and photosynthetic principal element.
In recent years, many scholars do to plant photosynthetic rate model and the related envirment factor regulation-control model of photosynthesis
Numerous studies, also achieve some achievements, and wherein Li Run scholars etc. are have studied under the conditions of different temperature under the conditions of water planting to life
Dish growth and the influence of content of mineral substances, foundation is provided for the regulation and control of root temperature.But, not in view of under the conditions of specific root temperature
Temperture of leaves, CO2Concentration, intensity of illumination are on the photosynthetic influence of water planting romaine lettuce.The system summaries such as Fu Guohai crop root zone temperature
It is that good basis has been established in the regulation and control of root temperature to facilities horticulture crop root and the Ecophysiological Effects and mechanism of action of canopy.Korea Spro
Sub- equality have studied under summer high temperature influence of the different root temperature processing to tomato plant strain growth and to Stoma of Leaves, as a result show with
Root temperature rise causes drought stress to plant.It can be seen that growth of a temperature to facility water planting crops has a very big impact, suitably
Searching between root warm area is necessary.
For problem above, present invention research is in different temperature, temperture of leaves, CO2Water planting romaine lettuce under the conditions of concentration, intensity of illumination
Photosynthesis characteristics, set up photosynthetic rate forecast model using Support Vector Machines for Regression (SVR), sought using Multiple-population Genetic Algorithm
The optimal temperture of leaves looked under the conditions of different temperature, CO2Concentration, intensity of illumination and corresponding maximum photosynthesis rate, obtain suitable
Between root warm area, the root temperature of chamber facility water planting romaine lettuce is set to maintain optimum range, photosynthesis reaches most preferably, solves winter or summer
Root temperature it is too low or it is too high to romaine lettuce photosynthesis and yield effect the problem of.
The content of the invention
In order to overcome the shortcoming of above-mentioned prior art, it is an object of the invention to provide a kind of based on the suitable of crop demand
Acquisition methods between root warm area, root temperature, temperture of leaves, CO have been coupled by setting up2The photosynthetic rate of the envirment factors such as concentration, intensity of illumination
Forecast model, realizes acquisition and application between suitable root warm area.
To achieve these goals, the technical solution adopted by the present invention is:
Acquisition methods between a kind of suitable warm area based on crop demand, it is characterised in that comprise the following steps:
Step 1, set up with temperture of leaves, CO2Concentration, intensity of illumination, root temperature are input, and Net Photosynthetic Rate is the photosynthetic speed of output
Rate forecast model, model formation is:
Wherein, output f (x) represents the Net Photosynthetic Rate of prediction, input signal x=(X '1,X′2,X′3,X′4)T, X '1、X
′2、X′3、X′4Respectively root temperature, temperture of leaves, CO2Concentration, intensity of illumination, w are weight vector, and b is biasing, and Φ (x) reflects to be non-linear
Function is penetrated, l is training set sample to { (xi,yi), i=1,2,3 ..., l } in training sample number, xiIt is the i-th training sample
Input column vector, It is i × d dimension real number fields, d is column vector dimension, and σ is width
Parameter, aiAnd ai *For the optimal solution of following formula:
Wherein K (xi,xj)=Φ (xi)Φ(xj) it is kernel function, yiFor corresponding output valve, yi∈ R, ε miss to stop training
Difference, c is penalty factor;
Step 2, based on above-mentioned model, under the conditions of different temperature, optimal temperture of leaves, CO are found2Concentration, intensity of illumination and
Corresponding maximum photosynthesis rate, is obtained in optimal temperture of leaves, CO2Between suitable warm area under the conditions of concentration, intensity of illumination.
The step 1 photosynthetic rate forecast model is set up using Support Vector Machines for Regression (SVR) modeling method, the step
Rapid 2 carry out optimizing using Multiple-population Genetic Algorithm (MPGA).
The step 1 photosynthetic rate forecast model establishment step is as follows:
Step 1.1, sample data is obtained
Incubator is used to provide a suitable constant external environment for crop, culture the temperature inside the box is set as 20 DEG C, wet
Degree is set as 50%, CO2Concentration is set as 400 μ L/L, while determining Net Photosynthetic Rate using photosynthetic instrument, is adopted in experimentation
With the temperature around the multiple submodule control on demand blade of photosynthetic instrument apolegamy, CO2Concentration and intensity of illumination parameter, wherein,
Utilize temperature control module setting 10,15,20,25,30 DEG C of totally 5 temperture of leaves gradients;Utilize CO2Injection module sets carbon dioxide volume
Than for 400,800,1200 μ L/L totally 3 gradients;Using LED light source module obtain 0,20,50,100,300,500,550,600,
700μmol/(m2S) totally 9 photon flux density (Photo flux density, PFD) gradients, are set using humidification module
Leaf chamber humidity is 50%, in addition, obtain 13 in heating water bath mode, 15,17,21,25,29 DEG C of totally 6 root temperature gradients, with nesting
Mode carries out 810 groups of experiments altogether, and every group of experiment randomly selects 3 plants of plant of the same age and do retest, so as to be formed with temperture of leaves, CO2
Concentration, intensity of illumination, root temperature are input, and Net Photosynthetic Rate is 810 groups of experiment sample collection of output;
Step 1.2, photosynthetic rate forecast model is built
Mode input signal is x=(X '1,X′2,X′3,X′4)T, X '1、X′2、X′3、X′4Respectively root temperature, temperture of leaves, CO2It is dense
Degree, intensity of illumination, output signal TO, the photosynthetic rate that network calculations are obtained is represented, every group of correspondence actual measurement photosynthetic rate is religion
Teacher's signal Td, photosynthetic rate forecast model T is set up by SVMs coaching methodd' (x), training process use 80% data
Collection collects as training set, 20% data set as checking, and photosynthetic rate forecast model performance is carried out using different verification mode
Checking analysis.
The theoretical foundation that photosynthetic rate forecast model is set up by SVMs coaching method is as follows:
If the training set sample containing l training sample is to for { (xi,yi), i=1,2,3 ..., l }, wherein, xiIt is i-th
The input column vector of individual training sample, d is column vector dimension,It is i × d dimension real number fields,yi∈ R,
For corresponding output valve;
Being located at the linear regression function set up in high-dimensional feature space is
F (x)=w Φ (x)+b
Wherein x is input vector, and w is weight vector, and b is biasing, and Φ (x) is nonlinear mapping function.
Define the linear insensitive loss functions of ε
Wherein f (x) is the predicted value that regression function is returned;Y is corresponding actual value, if representing predicted value and actual value
Between difference be less than or equal to ε, then loss be equal to 0;
For linear regression problem, problem is changed into seeking an optimal hyperlane so that in given accuracy (ε >=0) condition
Under can free from errors be fitted y, i.e., the distance of all sample points to optimal hyperlane is all not more than ε;In view of allowable error
Situation, can introduce slack variable ξi, ξi *>=0 its optimization problem converts corresponding quadratic programming problem:
Wherein C is penalty factor, and C is bigger to represent that the sample punishment for being more than ε to training error is bigger, and ε defines recurrence letter
Several error requirements, the smaller errors for representing regression function of ε are smaller, then Solve problems can be converted into dual problem:
Wherein ai, ai *For optimal solution;
Then optimum regression function is:
The genetic algorithm searching process on multiple populations is as follows:
Step 2.1, initialization of population
It is 40 to design initial population individual lengths, with root temperature (Gw) for variable, temperture of leaves (Tair), CO2, intensity of illumination
(Par) it is optimization aim, finds maximum photosynthesis rate, randomly generate initial population P (t), divided by information exchange model:P(t)
={ P1 (t) ..., Pi (t) ..., Pn (t) }, wherein n are packet count, and then packet calculates each Pi(t) (i=1,2 ..., n) in
The fitness of individual;
Step 2.2, the determination of control parameter
Each population takes different control parameters, crossover probability PcWith mutation probability PmValue determine algorithm global search
With the equilibrium of local search ability, it is calculated as follows:
In formula:Pc(1), Pm(1) it is respectively initial crossover probability and mutation probability;G is genetic manipulation algebraically;C, m are friendship
Fork, the siding-to-siding block length of mutation operation;M is population invariable number;frandTo produce the function of random number;PcIn [0.7,0.9] is interval with
Machine is produced, PmRandomly generated in [0.001,0.05] interval;
Step 2.2, immigrant's operator and artificial selection operator
By migrating operator Immigrant contacts, multi-species cooperative is realized, the worst individual in target population is used
The optimum individual of source population is replaced, and in every generation of evolution, the optimum individual for selecting other populations by artificial selection operator is put
Enter elite population to be preserved, elite population is without genetic manipulation, it is ensured that the optimum individual that each population produces be not destroyed and
Lose.
Obtained in the step 2 in optimal temperture of leaves, CO2After between suitable warm area under the conditions of concentration, intensity of illumination, then base
Obtained between Curvature Theory carries out suitable root warm area, step is as follows:
Based on the coupled relation of root temperature and maximum photosynthesis rate obtained by optimizing, equation below is obtained using fitting of a polynomial:
Y (T)=- 0.0001106T5+0.01174T4-0.4943T3+10.12T2-99.85T+396.4
Maximum photosynthesis rate curve is obtained using Curvature Theory and rises flex point and decline flex point, and corresponding of this flex point
Temperature, can be obtained between suitable root warm area, curvature estimation formula is using curvature estimation analysis:
Wherein:Y is coupling gained root temperature formula, and K is calculating gained curvature.
Compared with prior art, the beneficial effects of the invention are as follows:
1) a kind of coupling root temperature, temperture of leaves, CO are proposed2The photosynthetic rate forecast model of concentration, intensity of illumination.With root temperature,
Temperture of leaves, CO2, intensity of illumination for input, photosynthetic rate for output, using Support Vector Machines for Regression (SVR) build photosynthetic rate
Forecast model, is that good basis has been established in the acquisition between suitable root warm area.
2) a kind of Multiple-population Genetic Algorithm of new solution optimization problems is proposed.The algorithm employs two independences
And the mode on multiple populations of Different Evolutionary mechanism is evolved simultaneously, and the migration of individual is carried out in checkpoint, so that it is more to alleviate colony
Sample and the constringent contradiction of colony.Using the global and local collaboratively searching ability of the algorithm is strong, optimal speed is fast, dynamic environment
In the characteristics of there is stronger adaptability using photosynthetic rate as object function, find different warm bars using Multiple-population Genetic Algorithm
Optimal temperture of leaves under part, CO2Concentration, intensity of illumination and corresponding maximum photosynthesis rate.Draw under the conditions of different temperature
Maximum photosynthesis rate curve.
3) acquisition methods between a kind of suitable warm area based on Curvature Theory are proposed.Under the conditions of above-mentioned different root temperature most
On the basis of big photosynthetic rate curve, can accurately it be obtained between suitable root warm area using curvature estimation.Eye-observation is prevented effectively to make
Into error, solve winter or summer root temperature it is too low or it is too high on water planting crops root Nutrient Absorption and photosynthetic capacity influence
Problem.
The water planting romaine lettuce proposed by the present invention that is based on is in different temperature, temperture of leaves, CO2It is photosynthetic under the conditions of concentration, intensity of illumination
Between rate prediction model, and the suitable warm area obtained on the basis of this model.On the one hand seasonal variations are efficiently solved to draw
Rise root temperature it is too low or it is too high to Growth of Lettuce and qualitative effects the problem of.On the other hand, regulation and control water planting crops root temperature is in
Optimum range, is temperture of leaves, CO2Good basis has been established in the regulation and control of the envirment factors such as concentration, intensity of illumination.
Brief description of the drawings
Fig. 1 is that photosynthetic rate forecast model of the present invention is set up and suitably obtains flow chart between root warm area.
Fig. 2 is photosynthetic rate measured value of the present invention and predicted value comparative result figure.
Fig. 3 is optimal photosynthetic rate curve map under different root temperature of the invention.
Fig. 4 is acquisition figure (curvature curve figure) between the suitable warm area of the invention based on Curvature Theory.
Fig. 5 is acquisition figure (curvature first derived curve figure) between the suitable warm area of the invention based on Curvature Theory.
Fig. 6 is standard genetic optimizing evolutionary process figure (SGA evolutionary process) of the present invention.
Fig. 7 is the present invention hereditary optimizing evolutionary process figure (MPGA evolutionary process) on multiple populations.
Embodiment
Describe embodiments of the present invention in detail with reference to the accompanying drawings and examples.
A kind of water planting romaine lettuce that is based on is invented herein in different temperature, temperture of leaves, CO2It is photosynthetic under the conditions of concentration, intensity of illumination
Between rate prediction model, and the suitable warm area obtained on the basis of this model using Multiple-population Genetic Algorithm (MPGA).Ginseng
According to Fig. 1, process is set up as follows:
1st, materials and methods
1.1 test materials and method
This is tested on March 16, -2017 years on the 1st March in 2017 in the northern school machinery of Xibei Univ. of Agricultural & Forest Science & Technology and electronics work
Journey institute is carried out, and is " cream romaine lettuce " for experiment romaine lettuce kind, and cream romaine lettuce is in seedling stage, is derived from Xianyang, Shanxi province city Yangling District
Modern agriculture Demonstration Garden innovates garden, is cultivated using standard water planting mode, seedling length to 4-5 leaves, leaf blade size reaches 3*
5mm, the uniform seedling of the same age of growth selection health, growing way is tested.Experiment starts the previous day by romaine lettuce Seeding planting in special
Water planting container is used, MD1400 incubators is moved to and carries out environment pre-adaptation processing.Testing time is 8:30-11:30 and 14:30-17:
30, any agricultural chemicals is not sprayed during experiment, normal Greenhouse Water Culture management is carried out.
Experiment use Snijders companies of Holland production MD1400 incubators provided for cream romaine lettuce one suitably it is constant
External environment, culture the temperature inside the box be set as 20 DEG C, humidity set is 50%, CO2Concentration is set as 400 μ L/L, adopts simultaneously
The portable photosynthetic instrument of Li-6800XT types produced with LI-COR companies of the U.S. determines Net Photosynthetic Rate, is used in experimentation
Temperature, CO around the multiple submodule control on demand blade of photosynthetic instrument apolegamy2The parameters such as concentration, intensity of illumination.Wherein, utilize
Temperature control module setting 10,15,20,25,30 DEG C of totally 5 temperture of leaves gradients;Utilize CO2Injection module set carbon dioxide volume ratio as
400th, 800,1200 μ L/L totally 3 gradients;0,20,50,100,300,500,550,600,700 μ are obtained using LED light source module
mol/(m2S) totally 9 photon flux density (Photo flux density, PFD) gradients, utilize humidification module setting leaf chamber
Humidity is 50%, in addition, obtain 13 in heating water bath mode, 15,17,21,25,29 DEG C of totally 6 root temperature gradients, in a nesting relation
810 groups of experiments are carried out altogether, every group of experiment randomly selects 3 plants of plant of the same age and do retest, so as to be formed with temperture of leaves, CO2Concentration,
Intensity of illumination, root temperature are input, and Net Photosynthetic Rate is 810 groups of experiment sample collection of output.
1.2 method for establishing model
In order to set up optimal photosynthetic rate forecast model, Support Vector Machines for Regression is used for seedling stage cream romaine lettuce
(SVR) modeling method sets up photosynthetic rate forecast model, on the basis of photosynthetic rate forecast model, is calculated using heredity on multiple populations
Optimal temperture of leaves, CO under the conditions of method (MPGA) different temperature of searching2Concentration, intensity of illumination and corresponding maximum photosynthesis rate,
Between suitable warm area for obtaining water planting romaine lettuce.
1.2.1 photosynthetic rate forecast model is built
Herein use above-mentioned experiment sample, using Support Vector Machines for Regression (SVR) training error it is small the characteristics of, build back
Return type SVMs (SVR) photosynthetic rate forecast model, wherein mode input signal is x=(X '1,X′2,X′3,X′4)T, X
′1、X′2、X′3、X′4Respectively root temperature, temperture of leaves, CO2Concentration, intensity of illumination, output signal use TORepresent what network calculations were obtained
Photosynthetic rate, every group of correspondence actual measurement photosynthetic rate is teacher signal Td.Photosynthetic rate is set up by SVMs coaching method
Forecast model Td'(x).Training process is using 80% data set as training set, and 20% data set collects as checking, used
Different verification mode carries out the checking analysis of photosynthetic rate forecast model performance.
1.2.1.1 Support Vector Machines for Regression basic theories
(1) training set and test set are randomly generated
Experiment uses Nested simulation experiment mode with temperture of leaves, CO2Concentration, intensity of illumination, root temperature are input, and Net Photosynthetic Rate is defeated
Go out to measure 810 groups of experiment sample collection, wherein the training that the 80% 650 groups of sample datas for accounting for total sample are used to set up model
Collection, accounts for the test set that 20% 160 groups of samples of total sample are used to verify model, model checking is carried out using different method of calibration.
(2) establishment/training SVR regression models Support Vector Machines for Regression is initially to be used to solve two in the case of linear separability
The classification problem of class sample, its core concept is to find an optimal separating hyper plane so that all training samples are optimal from this
The error for plane of classifying is minimum, and class interval is maximized.
Without loss of generality, if the training set sample containing l training sample is to for { (xi,yi), i=1,2,3 ..., l },
Wherein,It is the input column vector of i-th of training sample, d is column vector dimension,It is i × d dimension real number fields,yi∈ R, are corresponding output valve.
Being located at the linear regression function set up in high-dimensional feature space is
F (x)=w Φ (x)+b (2-1)
Wherein x is input vector, and w is weight vector, and b is biasing, and Φ (x) is nonlinear mapping function.
Define the linear insensitive loss functions of ε
Wherein f (x) is the predicted value that regression function is returned;Y is corresponding actual value, if representing predicted value and actual value
Between difference be less than or equal to ε, then loss be equal to 0.
For linear regression problem, problem is changed into seeking an optimal hyperlane so that in given accuracy (ε >=0) condition
Under can free from errors be fitted y, i.e., the distance of all sample points to optimal hyperlane is all not more than ε;In view of allowable error
Situation, can introduce slack variable ξi, ξi *>=0 its optimization problem converts corresponding quadratic programming problem:
Wherein C is penalty factor, and C is bigger to represent that the sample punishment for being more than ε to training error is bigger, and ε defines recurrence letter
Several error requirements, the smaller errors for representing regression function of ε are smaller.
2-3 formulas Solve problems can be converted into dual problem:
Wherein ai, ai *For (2-4) formula optimal solution.
Solution above mentioned problem solution can obtain optimum regression function and be:
Wherein K (xi,xj)=Φ (xi)Φ(xj) it is kernel function.
(3) emulation testing
Constructed SVR regression models are verified using test sample collection data, model predication value, mean square error can be obtained
Difference, the coefficient of determination are estimated to constructed model.
According to above-mentioned theory, the photosynthetic rate forecast model built using Support Vector Machines for Regression (SVR), its photosynthetic speed
Rate measured value is with predicted value comparison diagram as shown in Fig. 2 the coefficient of determination is 0.9876, and mean square error is 0.7849, and intercept is
0.126.Therefore the linearity of the photosynthetic rate forecast model built using Support Vector Machines for Regression (SVR) is higher, is fitted journey
Degree is more preferable.
1.2.2 maximum photosynthesis rate optimizing under the conditions of different root temperature
On the basis of photosynthetic rate forecast model, using the overall situation and local optimal searching ability of Multiple-population Genetic Algorithm it is strong,
The characteristics of fast convergence rate, under the conditions of different temperature, find optimal temperture of leaves, CO2Concentration, intensity of illumination and corresponding maximum
Photosynthetic rate, is obtained in optimal temperture of leaves, CO2Between suitable warm area under the conditions of concentration, intensity of illumination.
Genetic algorithm searching process on multiple populations is as follows:
(1) initialization of population.
It is 40 to design initial population individual lengths, with root temperature (Gw) for variable, temperture of leaves (Tair), CO2, intensity of illumination
(Par) it is optimization aim, finds maximum photosynthesis rate.Initial population P (t) is randomly generated, is divided by information exchange model:P(t)
=P1 (t) ..., Pi (t) ..., Pn (t) }, wherein n is packet count and then is grouped each P of calculatingi(t) (i=1,2 ..., n) in
The fitness of individual.
(2) determination of control parameter.
Each population takes different control parameters, crossover probability PcWith mutation probability PmValue determine algorithm global search
With the equilibrium of local search ability, it can be calculated as follows:
In formula:Pc(1), Pm(1) it is respectively initial crossover probability and mutation probability;G is genetic manipulation algebraically;C, m are friendship
Fork, the siding-to-siding block length of mutation operation;M is population invariable number;frandTo produce the function of random number.
If PcValue is excessive, the defect individual in destructible colony;If value is too small, the speed for producing new individual is too slow.Pc
It is general to be randomly generated in [0.7,0.9] interval.PmIf value is excessive, it is possible to destroy many preferably individuals;If value
Too small, mutation operation produces new individual ability and suppresses the less able of precocious phenomenon.PmIt is general interval at [0.001,0.05]
Inside randomly generate.
(3) immigrant's operator and artificial selection operator.
By migrating operator Immigrant contacts, multi-species cooperative is realized, the worst individual in target population is used
The optimum individual of source population is replaced.In every generation of evolution, the optimum individual for selecting other populations by artificial selection operator is put
Enter elite population to be preserved.Elite population is without genetic manipulations such as selection, intersection, variations, it is ensured that each population produces most
Excellent individual is not destroyed and lost.
Optimizing can obtain optimal temperture of leaves under the conditions of different temperature, CO2Concentration, intensity of illumination and corresponding maximum photosynthetic speed
Rate, show that the maximum photosynthesis rate curve map under the conditions of different temperature is as shown in Figure 3, it is possible to find curve obtained has notable office
Portion flat region, represents position between suitable root warm area.
It can be obtained from Fig. 5 analyses, when standard genetic algorithm (SGA) optimizing evolved to for 35 generation, temperture of leaves under the conditions of different root temperature,
CO2Concentration, intensity of illumination optimizing reach stabilization.And Multiple-population Genetic Algorithm (MPGA) optimizing is when evolving to for 14 generation, different root temperature
Under the conditions of temperture of leaves, CO2Concentration, intensity of illumination optimizing reach stabilization, and training process does not occur concussion and local flat region, shown
Multiple-population Genetic Algorithm (MPGA) has global and local collaboratively searching ability well, while having good convergence.
1.2.3 obtained between the suitable warm area based on Curvature Theory
Based on the coupled relation of root temperature and maximum photosynthesis rate obtained by optimizing, formula (1) can be obtained using fitting of a polynomial, obtained
Take the maximum photosynthesis rate curve under the conditions of different temperature as shown in Figure 3.
Y (T)=- 0.0001106T5+0.01174T4-0.4943T3+10.12T2-99.85T+396.4 (1)
Maximum photosynthesis rate curve can be obtained using Curvature Theory and rise flex point and decline flex point, and corresponding of this flex point
Temperature, result shown in Fig. 4 and Fig. 5 can be obtained using curvature estimation, analysis can obtain suitable root warm area between be 20-28 DEG C.
Curvature estimation formula is:
Wherein:Y is coupling gained root temperature formula, and K is calculating gained curvature.
2nd, result and discussion
The present invention mainly have studied water planting romaine lettuce in different temperature, temperture of leaves, CO2, photosynthesis characteristics under intensity of illumination, and
Root temperature and temperture of leaves, CO2, coupled relation between intensity of illumination, analysis can obtain not only temperture of leaves, CO2, intensity of illumination influence water planting life
The photosynthetic capacity of dish, winter or summer root temperature is too low or the too high influence to water planting romaine lettuce is bigger, and the present invention is lost based on multiple populations
It is just proper between the suitable warm area of propagation algorithm (MPGA) optimizing to solve this problem in that.
2.1 photosynthetic rate forecast models are analyzed
Totally 810 groups of test sample collection is obtained using multiple-factor Nested simulation experiment, sample is divided into training set and test set, wherein
650 groups of training sets for setting up model, account for the 80% of total sample, and the remaining 160 groups test sets for verifying model account for gross sample
This 20%, model checking is carried out using different method of calibration.Secondly, root temperature, leaf are fitted using Support Vector Machines for Regression (SVR)
Temperature, CO2, coupled relation between intensity of illumination and photosynthetic rate, it is small using Support Vector Machines for Regression (SVR) training error
Feature, sets up accurate photosynthetic rate forecast model.Obtain photosynthetic rate measured value and predicted value Comparative result as shown in Fig. 2
Model training value is identical with predicted value, and its coefficient of determination is 0.9876, and mean square error is 0.7849, and intercept is 0.126.
2.2 are analyzed based on Multiple-population Genetic Algorithm optimizing result
On the basis of photosynthetic rate forecast model, using photosynthetic rate as object function, based on Multiple-population Genetic Algorithm
(MPGA) optimal temperture of leaves under the conditions of different temperature of searching, CO2Concentration, intensity of illumination and corresponding maximum photosynthesis rate, seek
It is excellent when evolving to for 14 generation, temperture of leaves, CO under the conditions of different root temperature2Concentration, intensity of illumination optimizing reach stabilization, draw at different
Optimal photosynthetic rate curve under the conditions of temperature.Training process does not occur concussion and local flat region, shows Multiple-population Genetic Algorithm
(MPGA) there is global and local collaboratively searching ability well relative to standard genetic algorithm (SGA), while having well
Convergence.
Obtained between the 2.3 suitable warm areas based on curvature estimation
Based on the maximum photosynthesis rate curve under the conditions of different temperature, suitable root warm area can be accurately obtained using curvature estimation
Between end points.As shown in Figure 6 and Figure 7, it is 20-28 DEG C that can obtain between suitable warm area of water planting romaine lettuce to search result, is prevented effectively from
Error caused by human eye observation.
Photosynthetic rate forecast model is built, is accurately obtained based on Curvature Theory between suitable root warm area.On the one hand, root temperature is regulated and controled
To suitable interval, root temperature caused by seasonal variations is effectively solved too high or too low to water planting crops root Nutrient Absorption and photosynthetic
The problem of capacity.On the other hand, based on Multiple-population Genetic Algorithm (MPGA) find different temperature under the conditions of optimal temperture of leaves,
CO2Concentration, intensity of illumination and corresponding maximum photosynthesis rate, are temperture of leaves, CO2Good base has been established in concentration, intensity of illumination regulation and control
Plinth.
Claims (6)
1. acquisition methods between a kind of suitable warm area based on crop demand, it is characterised in that comprise the following steps:
Step 1, using multiple-factor nesting test, measure test sample data, use Support Vector Machines for Regression build with root temperature,
Temperture of leaves, CO2Concentration, intensity of illumination are input, and Net Photosynthetic Rate is the photosynthetic rate forecast model of output;
Step 2, based on above-mentioned model, under the conditions of different temperature, optimal temperture of leaves, CO are found2Concentration, intensity of illumination and corresponding
Maximum photosynthesis rate, obtain in optimal temperture of leaves, CO2Between suitable warm area under the conditions of concentration, intensity of illumination.
2. acquisition methods between the suitable warm area based on crop demand according to claim 1, it is characterised in that the step
1 photosynthetic rate forecast model is set up using Support Vector Machines for Regression (SVR) modeling method, and the step 2 is lost using on multiple populations
Propagation algorithm (MPGA) carries out optimizing.
3. acquisition methods between the suitable warm area based on crop demand according to claim 2, it is characterised in that the step
1 photosynthetic rate forecast model establishment step is as follows:
Step 1.1, sample data is obtained
Incubator is used to provide a suitable constant external environment for crop, culture the temperature inside the box is set as 20 DEG C, and humidity is set
It is set to 50%, CO2Concentration is set as 400 μ L/L, while determining Net Photosynthetic Rate using photosynthetic instrument, light is used in experimentation
Temperature, CO around the multiple submodule control on demand blade of conjunction instrument apolegamy2Concentration and intensity of illumination parameter, wherein, utilize
Temperature control module setting 10,15,20,25,30 DEG C of totally 5 temperture of leaves gradients;Utilize CO2Injection module set carbon dioxide volume ratio as
400th, 800,1200 μ L/L totally 3 gradients;0,20,50,100,300,500,550,600,700 μ are obtained using LED light source module
mol/(m2S) totally 9 photon flux density (Photo flux density, PFD) gradients, utilize humidification module setting leaf chamber
Humidity is 50%, in addition, obtain 13 in heating water bath mode, 15,17,21,25,29 DEG C of totally 6 root temperature gradients, in a nesting relation
810 groups of experiments are carried out altogether, every group of experiment randomly selects 3 plants of plant of the same age and do retest, so as to be formed with temperture of leaves, CO2Concentration,
Intensity of illumination, root temperature are input, and Net Photosynthetic Rate is 810 groups of experiment sample collection of output;
Step 1.2, photosynthetic rate forecast model is built
Mode input signal is x=(X1',X'2,X3',X'4)T, X1'、X'2、X3'、X'4Respectively root temperature, temperture of leaves, CO2Concentration, light
According to intensity, output signal TO, the photosynthetic rate that network calculations are obtained is represented, every group of correspondence actual measurement photosynthetic rate is teacher signal
Td, photosynthetic rate forecast model T is set up by SVMs coaching methodd' (x), training process use 80% data set conduct
Training set, 20% data set collects as checking, and the checking point of photosynthetic rate forecast model performance is carried out using different verification mode
Analysis.
4. acquisition methods between the suitable warm area based on crop demand according to Claims 2 or 3, it is characterised in that described
The theoretical foundation for setting up photosynthetic rate forecast model by SVMs coaching method is as follows:
If the training set sample containing l training sample is to for { (xi,yi), i=1,2,3 ..., l }, wherein, xiIt is i-th of instruction
Practice the input column vector of sample,D is column vector dimension,It is i × d dimension real number fields,yi
∈ R, are corresponding output valve;
Being located at the linear regression function set up in high-dimensional feature space is
F (x)=w Φ (x)+b
Wherein x is input vector, and w is weight vector, and b is biasing, and Φ (x) is nonlinear mapping function.
Define the linear insensitive loss functions of ε
<mrow>
<mi>L</mi>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>&epsiv;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>|</mo>
<mi>y</mi>
<mo>-</mo>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>&le;</mo>
<mi>&epsiv;</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>|</mo>
<mi>y</mi>
<mo>-</mo>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>-</mo>
<mi>&epsiv;</mi>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>|</mo>
<mi>y</mi>
<mo>-</mo>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>&GreaterEqual;</mo>
<mi>&epsiv;</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein f (x) is the predicted value that regression function is returned;Y is corresponding actual value, if representing between predicted value and actual value
Difference be less than or equal to ε, then loss be equal to 0;
For linear regression problem, problem is changed into seeking an optimal hyperlane so that can under the conditions of given accuracy (ε >=0)
To be free from errors fitted y, i.e., the distance of all sample points to optimal hyperlane is all not more than ε;In view of the situation of allowable error,
Introduce slack variable ξi, ξi *>=0 its optimization problem converts corresponding quadratic programming problem:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>min</mi>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<mo>|</mo>
<mo>|</mo>
<mi>w</mi>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
<mo>+</mo>
<mi>C</mi>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&xi;</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<msubsup>
<mi>&xi;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>s</mi>
<mo>.</mo>
<mi>t</mi>
<mo>.</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mi>w</mi>
<mi>&Phi;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>b</mi>
<mo>&le;</mo>
<mi>&epsiv;</mi>
<mo>+</mo>
<msub>
<mi>&xi;</mi>
<mi>i</mi>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mi>w</mi>
<mi>&Phi;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
<mo>&le;</mo>
<mi>&epsiv;</mi>
<mo>+</mo>
<msubsup>
<mi>&xi;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>&xi;</mi>
<mi>i</mi>
</msub>
<mo>&GreaterEqual;</mo>
<mn>0</mn>
<mo>,</mo>
<msubsup>
<mi>&xi;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<mo>&GreaterEqual;</mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein C is penalty factor, and C is bigger to represent that the sample punishment for being more than ε to training error is bigger, and ε defines regression function
Error requirements, the smaller errors for representing regression function of ε are smaller, then Solve problems can be converted into dual problem:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<munder>
<mi>max</mi>
<mrow>
<mi>&alpha;</mi>
<mo>,</mo>
<msup>
<mi>&alpha;</mi>
<mo>*</mo>
</msup>
</mrow>
</munder>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>j</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mi>K</mi>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>)</mo>
</mrow>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mi>&epsiv;</mi>
<mo>+</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>&rsqb;</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>s</mi>
<mo>.</mo>
<mi>t</mi>
<mo>.</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>&le;</mo>
<mi>c</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>&le;</mo>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<mo>&le;</mo>
<mi>c</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein ai, ai *For optimal solution;
Finally giving optimum regression function is:
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>w</mi>
<mi>&Phi;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msup>
<msub>
<mi>a</mi>
<mi>i</mi>
</msub>
<mo>*</mo>
</msup>
<mo>)</mo>
</mrow>
<mi>K</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>b</mi>
<mo>.</mo>
</mrow>
5. acquisition methods between the suitable warm area based on crop demand according to claim 2, it is characterised in that described a variety of
Group's genetic algorithm searching process is as follows:
Step 2.1, initialization of population
It is 40 to design initial population individual lengths, with root temperature (Gw) for variable, temperture of leaves (Tair), CO2, intensity of illumination (Par) is excellent
Change target, find maximum photosynthesis rate, randomly generate initial population P (t), divided by information exchange model:P (t)={ P1
(t) ..., Pi (t) ..., Pn (t) }, wherein n is packet count, and then packet calculates each Pi(t) (i=1,2 ..., n) in it is individual
Fitness;
Step 2.2, the determination of control parameter
Each population takes different control parameters, crossover probability PcWith mutation probability PmValue determine algorithm global search drawn game
The equilibrium of portion's search capability, is calculated as follows:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>P</mi>
<mi>c</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>G</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>P</mi>
<mi>c</mi>
</msub>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>c</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>r</mi>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>,</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>P</mi>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>G</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>P</mi>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>m</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>r</mi>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>,</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
In formula:Pc(1), Pm(1) it is respectively initial crossover probability and mutation probability;G is genetic manipulation algebraically;C, m is intersect, change
The siding-to-siding block length of ETTHER-OR operation;M is population invariable number;frandTo produce the function of random number;PcThe random production in [0.7,0.9] is interval
It is raw, PmRandomly generated in [0.001,0.05] interval;
Step 2.2, immigrant's operator and artificial selection operator
By migrating operator Immigrant contacts, multi-species cooperative is realized, by the worst individual source kind in target population
The optimum individual of group is replaced, and in every generation of evolution, the optimum individual for selecting other populations by artificial selection operator is put into essence
Magnificent population is preserved, and elite population is without genetic manipulation, it is ensured that the optimum individual that each population produces is not destroyed and lost.
6. acquisition methods between the suitable warm area based on crop demand according to claim 1, it is characterised in that in the step
Rapid 2 obtain in optimal temperture of leaves, CO2After between suitable warm area under the conditions of concentration, intensity of illumination, then fitted based on Curvature Theory
Obtained between suitable root warm area, step is as follows:
Based on the coupled relation of root temperature and maximum photosynthesis rate obtained by optimizing, equation below is obtained using fitting of a polynomial:
Y (T)=- 0.0001106T5+0.01174T4-0.4943T3+10.12T2-99.85T+396.4
Maximum photosynthesis rate curve is obtained using Curvature Theory and rises flex point and decline flex point, and corresponding temperature of this flex point,
It can be obtained between suitable root warm area using curvature estimation analysis, curvature estimation formula is:
<mrow>
<mi>K</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mo>|</mo>
<msup>
<mi>y</mi>
<mrow>
<mo>&prime;</mo>
<mo>&prime;</mo>
</mrow>
</msup>
<mo>|</mo>
</mrow>
<msup>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>y</mi>
<mo>&prime;</mo>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>)</mo>
</mrow>
<mrow>
<mn>3</mn>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
</mfrac>
</mrow>
Wherein:Y is coupling gained root temperature formula, and K is calculating gained curvature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710400511.6A CN107220672A (en) | 2017-05-31 | 2017-05-31 | Acquisition methods between a kind of suitable warm area based on crop demand |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710400511.6A CN107220672A (en) | 2017-05-31 | 2017-05-31 | Acquisition methods between a kind of suitable warm area based on crop demand |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107220672A true CN107220672A (en) | 2017-09-29 |
Family
ID=59948102
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710400511.6A Pending CN107220672A (en) | 2017-05-31 | 2017-05-31 | Acquisition methods between a kind of suitable warm area based on crop demand |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107220672A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090693A (en) * | 2017-12-31 | 2018-05-29 | 西北农林科技大学 | The structure of the Optimum Regulation model of the photosynthetic desired value of facility of fusion efficiencies constraint and application |
CN108256181A (en) * | 2017-12-31 | 2018-07-06 | 西北农林科技大学 | The structure of the Optimum Regulation model of the facility carbon dioxide desired value of fusion efficiencies constraint and application |
CN110084354A (en) * | 2019-04-09 | 2019-08-02 | 浙江工业大学 | A method of based on genetic algorithm training ANN Control game role behavior |
CN111814303A (en) * | 2020-05-28 | 2020-10-23 | 西南交通大学 | Plant root mechanics model construction method and device and electronic equipment |
CN112697702A (en) * | 2020-12-31 | 2021-04-23 | 西北农林科技大学 | CO based on density distribution characteristics2Range finding method |
CN113822495A (en) * | 2021-10-20 | 2021-12-21 | 平安科技(深圳)有限公司 | Growth prediction method, device, equipment and medium based on machine learning model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200489A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Motion capture data key frame extraction method based on multi-population genetic algorithm |
CN105654203A (en) * | 2015-12-31 | 2016-06-08 | 西北农林科技大学 | Cucumber whole-course photosynthetic rate predicting model based on support vector machine, and establishing method |
CN105678405A (en) * | 2015-12-31 | 2016-06-15 | 西北农林科技大学 | Modeling method for cucumber GA-RBF photosynthetic rate prediction model integrated with stomatal conductance |
-
2017
- 2017-05-31 CN CN201710400511.6A patent/CN107220672A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200489A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Motion capture data key frame extraction method based on multi-population genetic algorithm |
CN105654203A (en) * | 2015-12-31 | 2016-06-08 | 西北农林科技大学 | Cucumber whole-course photosynthetic rate predicting model based on support vector machine, and establishing method |
CN105678405A (en) * | 2015-12-31 | 2016-06-15 | 西北农林科技大学 | Modeling method for cucumber GA-RBF photosynthetic rate prediction model integrated with stomatal conductance |
Non-Patent Citations (3)
Title |
---|
宋雪健 等: "基于多种群遗传算法的LQR振动主动控制研究", 《科学技术与工程》 * |
胡瑾 等: "基于遗传算法的番茄幼苗光合作用优化调控模型", 《农业工程学报》 * |
郝连军 等: "《高等数学》", 30 September 2014, 北京邮电大学出版社 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090693A (en) * | 2017-12-31 | 2018-05-29 | 西北农林科技大学 | The structure of the Optimum Regulation model of the photosynthetic desired value of facility of fusion efficiencies constraint and application |
CN108256181A (en) * | 2017-12-31 | 2018-07-06 | 西北农林科技大学 | The structure of the Optimum Regulation model of the facility carbon dioxide desired value of fusion efficiencies constraint and application |
CN108256181B (en) * | 2017-12-31 | 2021-03-26 | 西北农林科技大学 | Construction and application of optimal regulation and control model of facility carbon dioxide target value with integration of efficiency constraint |
CN110084354A (en) * | 2019-04-09 | 2019-08-02 | 浙江工业大学 | A method of based on genetic algorithm training ANN Control game role behavior |
CN111814303A (en) * | 2020-05-28 | 2020-10-23 | 西南交通大学 | Plant root mechanics model construction method and device and electronic equipment |
CN112697702A (en) * | 2020-12-31 | 2021-04-23 | 西北农林科技大学 | CO based on density distribution characteristics2Range finding method |
CN112697702B (en) * | 2020-12-31 | 2023-01-31 | 西北农林科技大学 | CO based on density distribution characteristics 2 Range finding method |
CN113822495A (en) * | 2021-10-20 | 2021-12-21 | 平安科技(深圳)有限公司 | Growth prediction method, device, equipment and medium based on machine learning model |
CN113822495B (en) * | 2021-10-20 | 2023-12-19 | 平安科技(深圳)有限公司 | Growth state prediction method, device, equipment and medium based on machine learning model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107220672A (en) | Acquisition methods between a kind of suitable warm area based on crop demand | |
Fourcaud et al. | Plant growth modelling and applications: the increasing importance of plant architecture in growth models | |
Chen et al. | Partitioning of daily evapotranspiration using a modified shuttleworth-wallace model, random Forest and support vector regression, for a cabbage farmland | |
Garnier et al. | Plant functional diversity: organism traits, community structure, and ecosystem properties | |
CN107329511B (en) | Based on the vegetable aquaculture luminous environment high efficiency regulatory method and system between suitable root warm area | |
Yu et al. | Simulation of the stomatal conductance of winter wheat in response to light, temperature and CO2 changes | |
CN105654203A (en) | Cucumber whole-course photosynthetic rate predicting model based on support vector machine, and establishing method | |
CN105678405B (en) | Modeling method for cucumber GA-RBF photosynthetic rate prediction model integrated with stomatal conductance | |
CN111915062B (en) | Greenhouse crop water demand regulation and control method with water utilization rate and photosynthesis rate being coordinated | |
CN112735511B (en) | Cold damage cucumber PSII potential activity prediction method based on QGA-SVR | |
CN107037090A (en) | A kind of photosynthesis Forecasting Methodology changed based on blade tensity | |
CN107145941A (en) | The real-time dynamic acquisition method of light requirement based on optimal light quality and photon flux density | |
CN105446142A (en) | Greenhouse CO2 gas fertilizer increasing method, device and system | |
Liu et al. | Prediction model of photosynthetic rate based on SOPSO-LSSVM for regulation of greenhouse light environment | |
Chen et al. | Competition for light interception in cotton populations of different densities | |
CN112381133A (en) | Method for determining reasonable sample number in forest ground biomass remote sensing estimation | |
CN110321627B (en) | Photosynthetic rate prediction method for photosynthetic potential of fused leaves | |
Wang et al. | Real-time monitoring of environmental information and modeling of the photosynthetic rate of tomato plants under greenhouse conditions | |
Popović et al. | Morpho-anatomical trait variability of the Norway spruce (Picea abies (L.) Karst.) needles in natural populations along elevational diversity gradient | |
Zhang et al. | Growth and Fruit Yields of Greenhouse Tomato under the Integrated Water and Fertilizer by Moistube Irrigation | |
Zeng et al. | Systems analysis of wheat stripe rust epidemics in China | |
CN105654242A (en) | Fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model, establishment method and application thereof | |
CN108229065A (en) | A kind of construction method and Forecasting Methodology of the Net Photosynthetic Rate prediction model based on xylophyta leaf morphology feature | |
Sun et al. | Effects of different irrigation modes on the growth, physiology, farmland microclimate characteristics, and yield of cotton in an oasis | |
Chen et al. | The response mechanism and threshold of spring wheat to rapid drought |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |
|
RJ01 | Rejection of invention patent application after publication |