CN109840855A - A method of reproduction initial stage prediction tomato whether the underproduction - Google Patents
A method of reproduction initial stage prediction tomato whether the underproduction Download PDFInfo
- Publication number
- CN109840855A CN109840855A CN201910169105.2A CN201910169105A CN109840855A CN 109840855 A CN109840855 A CN 109840855A CN 201910169105 A CN201910169105 A CN 201910169105A CN 109840855 A CN109840855 A CN 109840855A
- Authority
- CN
- China
- Prior art keywords
- tomato
- underproduction
- variable
- model
- prediction
- 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
Abstract
Present invention relates particularly to it is a kind of reproduction initial stage prediction tomato whether the method for the underproduction, belong to and utilize nutrient content forecast production technical field in plant.The method of the present invention includes the following steps: will whether the underproduction is as dependent variable, as independent variable and variable combination is arranged in the physical signs of the tomato leaf of flower bud differentiation period, establishes Logic Regression Models respectively according to the combination of different variables and dependent variable；Tomato group is divided into training set sample and verifying collection sample, the logistic regression coefficient of each model is then determined using training set sample；Then using verifying collection sample, prediction verifying is carried out to the model that logistic regression coefficient has been determined, the highest model of prediction accuracy is filtered out according to prediction verification result.The present invention utilizes the physical signs of tomato itself for the first time, establishes the model in reproduction initial stage prediction tomato yield, has all established theoretical basis for tomato underproduction early warning and high yield optimal conditions.
Description
Technical field
Present invention relates particularly to it is a kind of reproduction initial stage prediction tomato whether the method for the underproduction, belong to and utilize nutrition in plant
Content prediction throughput techniques field.
Background technique
The reproductive growth of tomato has its distinctive development models, is generally divided into: " flower bud differentiation period " (first stage) " opens
Flower is beared fruit the phase " (second stage), " Fruit I phase " (phase III), " Fruit II phase " (fourth stage) and picking time.
It is generally believed that more early detection nutritional deficiency, the more underproduction of early prediction yield, more early intervention and extra-nutrition, to tomato
The maintenance and volume increase of fruit yield are more advantageous.It is not disclosed in the prior art by establishing model, in early prediction tomato yield
Method, be unable to satisfy the forecast demand of the even small-scale farmer of regional economy.
A kind of utilization mangrove trophonemata is disclosed in the Chinese invention patent application file that publication No. is CN107356727A
The method whether mark prediction heavy metal in soil pollutes.This method is using the nutritive index of mangrove as necromancer under independent variable, mangrove
The content of heavy metal to be measured establishes Logic Regression Models as dependent variable in earth.And using Logic Regression Models as judgment criteria into
Row verifying, accuracy rate then model success 90% or more；Then it is sampled in area to be measured, whether Prediction of Soil Heavy Metal is dirty
Dye.
Summary of the invention
The purpose of the present invention is to provide it is a kind of reproduction initial stage prediction tomato whether the method for the underproduction, this method can be
Tomato reproduction initial stage predict tomato whether the underproduction.
To achieve the above object, the technical solution of the present invention is as follows:
A method of reproduction initial stage prediction tomato whether the underproduction, comprising the following steps:
1) as independent variable and variable combination is arranged in the physical signs of the tomato leaf of flower bud differentiation period, according to different
The combination of variable and dependent variable establish Logic Regression Models respectively；The physical signs includes that object element content, organic matter contain
Amount；The object element includes metallic element and nonmetalloid, the metallic element be calcium, iron, potassium, magnesium, sodium, in zinc extremely
Few one kind；The nonmetalloid is nitrogen and/or phosphorus；The dependent variable be whether the underproduction；
2) using the physical signs of the tomato leaf in training set sample as independent variable, using whether the underproduction is used as because becoming
Amount, is trained the Logic Regression Models, determines the logistic regression coefficient of model；The training set sample includes normal group
Sample and nutritional deficiency group sample；
3) physical signs of the tomato leaf in verifying collection sample is brought into as independent variable and logic has been determined in step 2)
The model of regression coefficient, obtains prediction result；The actual result of the prediction result of different models and verifying collection sample is compared, screening
The highest model of prediction accuracy out；The verifying collection sample includes normal group sample and nutritional deficiency group sample；
4) it is predicted using the model that step 3) filters out whether tomato to be predicted the underproduction occurs.
The present invention screens the physical signs of tomato leaf in tomato reproductive development " flower bud differentiation period " stage early stage,
Selected section physical signs, then establish index and whether the model of the underproduction, predicted using model tomato whether the underproduction.This hair
It is bright that for tomato, whether the underproduction using the physical signs of tomato itself as marker establishes the prediction model of superelevation accuracy rate.
The present invention just establishes Production Forecast Models at tomato reproduction initial stage, facilitate peasant household or enterprise can also intervene yield when
Phase carries out effective operation, avoids the generation of the underproduction, be more of practical significance.Whether of the invention predicts tomato at reproduction initial stage
The method of the underproduction is that the following tomato underproduction early warning and high yield optimal conditions have all established theoretical basis.
The variable combination includes that entire variable combines, and the entire variable combination is by all indexs in the physical signs
It is obtained as independent variable.Entire variable combination is all calculated all factors relevant to result, because the factor of consideration is more,
The result theoretically obtained can be more accurate.
The variable combination includes AIC optimum combination, and the AIC optimum combination is that the AIC value of corresponding model is the smallest
Variable combination.The smallest set of variables of AIC value build jointly vertical model for prediction tomato whether the underproduction accuracy rate it is higher.
The variable combination includes that significant difference combines, and the significant difference combination includes normal group sample and nutritional deficiency
The variable of group sample physical signs significant difference.Influence of the physical signs variable for yield with significant difference may be compared with
Greatly, therefore by significant difference combination it takes into account.
The tomato leaf is plant top the 4th leaf down.Since first and second leaves at the top of plant are new
Leave piece can only guarantee that the locating growth phase of plant is the same and cannot be guaranteed the development of all plant in practical planting process
Time phase is just the same, therefore cannot select newborn blade.In addition, also there are no complete for the third piece leaf at the top of plant down
Sizing, length and width are also inconsistent.And from the 4th leaf of plant down for the tomato of contemporaneity, form and state are
Compare unification, the physiological phenomenon of aging will not occur.
Detailed description of the invention
Fig. 1 is Model I~model III ROC curve figure in the embodiment of the present invention 1.
Specific embodiment
It is of the invention reproduction initial stage prediction tomato whether the method for the underproduction, comprising the following steps:
1) as independent variable and variable combination is arranged in the physical signs of the tomato leaf of flower bud differentiation period, according to different
The combination of variable and dependent variable establish Logic Regression Models respectively；The physical signs includes that object element content, organic matter contain
Amount；The object element includes metallic element and nonmetalloid, the metallic element be calcium, iron, potassium, magnesium, sodium, in zinc extremely
Few one kind；The nonmetalloid is nitrogen and/or phosphorus；The dependent variable be whether the underproduction；
2) using the physical signs of the tomato leaf in training set sample as independent variable, using whether the underproduction is used as because becoming
Amount, is trained the Logic Regression Models, determines the logistic regression coefficient of model；The training set sample includes normal group
Sample and nutritional deficiency group sample；
3) physical signs of the tomato leaf in verifying collection sample is brought into as independent variable and logic has been determined in step 2)
The model of regression coefficient, obtains prediction result；The actual result of the prediction result of different models and verifying collection is compared, is filtered out pre-
Survey the highest model of accuracy；The verifying collection sample includes normal group sample and nutritional deficiency group sample；4) step 3) is used
The model filtered out is predicted whether tomato to be predicted the underproduction occurs.
The dependent variable is the underproduction or the not underproduction.The not underproduction is normal volume, and the underproduction is according to determining
What normal volume determined, if yield and normal tomato yield have significant difference, and it is lower than identified normal volume, then to subtract
It produces.
Whether in the method for the underproduction, the normal group of sample is to pour MS nutrient solution to reproduction initial stage prediction tomato of the invention
Tomato sample, nutritional deficiency group sample is the tomato sample for only pouring Aquaponic.
Whether reproduction initial stage prediction tomato of the invention is in the method for the underproduction, the content of organic matter in measurement tomato leaf
Shi Liyong oil bath heating disappears the method boiled to accelerate the oxidation of organic matter, makes oxidation of coal in blade organic matter at carbon dioxide,
And dichromic acid ion is reduced into trivalent chromic ion, the ferrous standard solution of remaining potassium bichromate titrates, according to organic
Carbon is oxidized the variation of front and back dichromic acid amount of ions, so that it may calculate the content of organic carbon or organic matter.
It is of the invention in reproduction initial stage prediction tomato whether in the method for the underproduction, using AIC value as one of evaluation model
Characteristic value passes through the quality of AIC judgment models.AIC information criterion, that is, Akaike information criterion is to measure
Statistical model is fitted a kind of standard of Optimality, since it is that Japan statistician Chi Chi expands time foundation and development, again
Claim akaike information criterion, it is established on the conceptual foundation of entropy, and complexity and this model that can weigh estimated model are quasi-
Close the Optimality of data.The number for increasing free parameter improves the Optimality of fitting, AIC encourage the Optimality of data fitting but
It is to try to the case where avoiding the occurrence of overfitting (Overfitting).So top-priority model should be AIC value it is the smallest that
One.The method of red pond information criterion is to find the model that can be best explained data but include minimum free parameter.
The present invention is further explained in the light of specific embodiments.
Embodiment 1
The present embodiment reproduction initial stage prediction tomato whether the underproduction method the following steps are included:
(1) tomato is cultivated
To tomato wild type " beautiful spring " seed bought in scientia Agricultura Sinica research institute (Beijing Haidian) seed retail department
(Lycopersicon esculentum Mill ev.Lichun) is cultivated, after seedling length to one heart stage of two leaves, field planting
It is 20cm to diameter, in the big flowerpot of a height of 20cm, plants 152 basins (strain) altogether, be then placed in temperature-controlling green house.When experiment
Between from July to October, greenhouse daytime temperature be 25~30 DEG C, nocturnal temperature be 18~20 DEG C, relative humidity be 60~
80%, daily illumination 16h.
Matrix in flowerpot is the turfy soil that mass ratio is 1:1 and vermiculite head.In 152 plants of plantation, wherein 76 plants long-term
Watering, 76 plants of pouring 1/4MS nutrient solutions are (in 1/4MS nutrient solution: calcium nitrate 945mg/L, potassium nitrate 607mg/L, ammonium phosphate
115mg/L, magnesium sulfate 493mg/L, iron salt solutions 2.5mg/L, microelement 5mg/L, pH=6.0)
(2) measurement of the content of physical signs
Plant grows to flower bud differentiation period, chooses at the top of plant the 4th leaf down, in an oven by leaf at a temperature of 180 DEG C
Sheet material is dried completely, and material is crushed to obtain to dry powder completely with grinding, then carries out element determination.
1) metallic element is tested
It weighs 0.1g dry powder to be added in 100mL kelvin bottle, addend, which drips, keeps sample wet, and it is (close that the 3mL concentrated sulfuric acid is then added
Degree is 1.84g/mL, is analyzed pure) and 10 drop perchloric acid (mass fraction is 60~70%, is analyzed pure), it shakes up.It is small that one is put in bottleneck
Funnel, heating, which disappears, on adjustable electric cooking stove boils, until solution colour turns white and transparent in kelvin bottle, is further continued for boiling 20min, cooling
The boil liquid that disappears afterwards is carefully washed in 100mL volumetric flask from kelvin bottle with water, and repeated flushing kelvin bottle keeps mixture in bottle complete
Portion washes in volumetric flask, is then diluted with water to scale, shakes up, and stands clarification, and carefully Aspirate supernatant carries out subsequent phosphorus member
The measurement of cellulose content.Make reagent blank control group with deionized water simultaneously.Calcium is used respectively, and iron, potassium, magnesium, sodium, Zn-ef ficiency standard specimen matches
Standard curve processed.Then successively liquid containing is entered in ICP, carries out constituent content mensure.
2) measurement of organic matter
It takes 0.1g dry powder to be put into Boiling tube (outer diameter 25mm, length 100mm), is added 5mL 0.8000mol/L's with suction pipe
K2Cr2O7Then the 5mL concentrated sulfuric acid (density 1.84g/mL, chemistry are pure) is added with syringe in standard solution, and carefully rotation is shaken
It is even.Oil bath pan (built-in solid paraffin or blade oil) is heated to 180~190 DEG C in advance, Boiling tube is inserted into wire mesh cage, then
It puts it into oil bath pan and heats, kettle temperature should be controlled at this time at 170~180 DEG C, and solution is made to keep boiling 5min, then
Wire mesh cage is taken out, after test tube is slightly cold, cleaning the oil liquid outside test tube with clean paper, (solution after such as boiling is indicated in green
Potassium bichromate dosage is insufficient, should weigh blade dry powder again and reform；Solution after boiling such as solution is in yellow or yellow green, then continues
It is tested).Mixture in test tube is washed in 250mL conical flask after cooling, makes bottle inner volume in 60~80mL or so, adds 3
~4 drop N- phenylanthranilic acid indicator, are titrated, colourshifting process is by brownish red through purple with 0.2mol/L ferrous sulfate solution
It is terminal to blue-green.Record ferrous sulfate dosage.
When measuring the content of organic matter, it is necessary to make 2~3 blank calibration.Blade dry powder is not added in blank calibration, but is added
0.1~0.5g quartz sand, it is identical when other steps are with measurement blade dry powder, ferrous sulfate dosage is recorded, then asks it flat
Mean value.
0.8000mol/L K used2Cr2O7Standard solution is prepared by following methods: 39.2245g potassium bichromate adds 400mL
Water, heating make to dissolve, and are settled to 1L with water after cooling.0.2mol/L ferrous sulfate solution used is prepared by following methods: 56.0g
Ferrous sulfate or 80.0g iron ammonium sulfate, are dissolved in water, add the 15mL concentrated sulfuric acid, are settled to 1L with water.N- phenylanthranilic acid
Indicator is prepared by following methods: molten 0.2g indicator in 100mL mass fraction be 0.2% sodium carbonate liquor in, slightly it is hot simultaneously
It is stirred continuously, promotes the indicator dissolution for floating on surface.
The method for calculating the content of organic matter in blade according to the dosage of ferrous sulfate are as follows:
Organic matter (%)=organic carbon (%) × 1.724 (2)
In formula:The concentration of standard solution, mol/L；
The volume of standard solution, mL；
V0--- the average value of the volume for the ferrous sulfate solution that blank is spent when demarcating, mL；
V --- the volume of the ferrous sulfate solution spent when titration plant sample, mL；
0.003 --- the molal weight of 1/4 carbon atom, g/mol；
1.1 --- oxidation adjusting coefficient；
1.724 --- organic carbon is converted into the coefficient of organic matter；
m1--- the quality of blade dry powder, g；
k2--- the moisture conversion coefficient for being converted into drying will be air-dried, is 1 in the present embodiment.
3) measurement of nitrogen content
It weighs 0.1g dry powder and is sent into dry kelvin bottom of bottle portion, after adding a small amount of deionized water to soak, 2g accelerator is added
(100g potassium sulfate, 10g Salzburg vitriol and 1g selenium powder are finely ground in mortar, are sufficiently mixed and are uniformly made.) and the 5mL concentrated sulfuric acid
(density 1.84g/mL is analyzed pure), shakes up.Kelvin bottle is placed in disappear to boil to disappear on furnace and is boiled, boil liquid to be disappeared all become it is greyish white slightly
After band green, it is further continued for disappearing and boils 1h.Disappear to boil and finish, it is cooling, it is to be distilled.Disappear boil while, two parts of blank determinations are done, except being not added
Outside blade dry powder, other operations are identical.
It is measured on the directly upper azotometer of the well-done sample that will disappear (if being full nitrogen with full-automatic azotometer final result
Percentage composition).The calculation of measurement result are as follows:
In formula: V --- the volume of sour standard solution used, mL when titration test solution；
V0--- the average external volume of sour standard solution used, mL when titration blank；
CH--- the concentration of sour standard solution, mol/L；
0.014 --- mM quality of nitrogen-atoms, g/mmol；
M --- dry powder quality, g.
When measuring nitrogen content using azotometer, when alkalization alkali used be 10mol/L sodium hydroxide solution (sodium hydroxide is
It is industrial or chemical pure).Boric acid used in absorbing ammonia is boric acid-indicator mixed solution.Wherein boric acid is to analyze pure, mass fraction
For 2% boric acid solution, indicator is that a small amount of 95% ethyl alcohol is added in 0.5g bromocresol green and 0.1g methyl red in agate mortar,
Grinding is until reagent all after dissolution plus 95% ethyl alcohol is formulated to 100mL.Before use, 20mL is added in every liter of boric acid solution
Mixed indicator, and reddish violet is adjusted to diluted alkaline.This liquid standing time is unsuitable too long, and such as pH value has change in use
Change, should be adjusted at any time with diluted acid or diluted alkaline.Using sour standard solution titrate when it is used acid be 0.005mol/L sulfuric acid or
0.01mol/L hydrochloric acid standard solution.
4) measurement of phosphorus content
It takes the 5~10mL of supernatant drawn in metal element content continuous mode to be placed in 50mL volumetric flask, adds water to 15
~20mL, adds 1 drop 2,4- dinitrophenol dinitrophenolate indicator, with 4mol/L sodium hydroxide solution adjust pH to solution be just in it is faint yellow, add
The anti-indicator of 5mL molybdenum antimony, is settled to scale with water, shakes up.After 30min on spectrophotometer, with 2cm cuvette, 700nm is selected
Wavelength colorimetric, blank test solution are reference liquid, adjust absorption value to zero, then survey the absorption value of each prepare liquid developing solution.In work
Make the phosphorus ppm number that developing solution is found on curve.
The calculating process of phosphorus content are as follows:
Full phosphorus pentoxide (P2O5, %) and=full phosphorus (P, %) × 2.29 (2)
In formula: the phosphorus ppm number (test value) for the developing solution that C-is looked into from working curve；
V-developing solution volume, 50mL；
Ts-points takes multiple,
(100 milliliters of prepare liquid volume, draw 5 milliliters of testing liquid)
M-blade dry powder quality, g；
106- the divisor for being converted into microgram gram；
2.29-are converted into phosphorus the coefficient of phosphorus pentoxide.
Molybdenum antimony it is anti-than method require developing solution in sulfuric acid concentration be 0.23~0.33mol/L.If acidity is less than 0.23mol/
It is shorter to stablize the time although colour developing is accelerated by L；If acidity is greater than 0.33mol/L, develop the color relatively slow.Molybdenum antimony is anti-than method requirement
Colour temp is 15 DEG C or more, if room temperature is lower than 15 DEG C, can be placed in 30~40 DEG C of insulating box and keeps 30min, is taken out
Colorimetric after cooling.
(3) Production rate
After tomato grows to " picking time ", all fruits are won, carry out every plant of weighing, and record.
(4) statistical analysis and model construction
1) it statisticallys analyze
Using the plant of pouring 1/4MS nutrient solution as normal group of nutrition (YZ), watering group is as nutritional deficiency group (YQ).It is right
The content of the physical signs of measurement take statistics credit analysis, as shown in table 1.
1 results of statistical analysis of table
As shown in Table 1, nutrition, which is normally organized, generates apparent yield difference with nutritional deficiency group tomato.Meanwhile in bud point
Change interim, N, P, K, there is also significant differences for the content of tetra- kinds of elements of Mg.Its medium multiple is approximately equal to YQ average value and YZ is average
The ratio of value, it is therefore intended that judge normal group of the nutrition relationship between each physical signs of nutritional deficiency group whether with reduction
Yield has correlation.
2) model construction
Using whether the underproduction as final result variable, is labeled as TC；Exposure variable includes N content % (labeled as R1), P content
(being labeled as R2), content of organic matter % (are labeled as R3), Ca content (ppm is labeled as R4), Fe content (ppm is labeled as R5), K
Content (ppm is labeled as R6), Mg content (ppm is labeled as R7), Na content (ppm is labeled as R8), Zn content (ppm, label
For R9).
It is combined by variable, establish Logic Regression Models using R language glm function: group is unified: R1+R2+R3+R4+R5+
R6+R7+R8+R9, combination two: R1+R2+R6+R7, combination three: R1+R3+R7+R9.
It randomly selects 50% inside the 50% and YZ data inside YQ data and is used as training set construction model；It is remaining
Data verify model as verifying collection.
(I) according to the data of variable each in training set, the unification of calculating group, combination two and combine three logistic regression coefficient and
AIC value.Calculated result is as shown in 2~table of table 4.
The logistic regression coefficient and AIC value of 2 groups of unifications of table
The logistic regression coefficient and AIC value of the combination of table 3 two
The logistic regression coefficient and AIC value of the combination of table 4 three
According to the AIC value for the model that group unification~combination three is established, top-priority model should combine three moulds established
Type.
(II) model evaluation is carried out with verifying collection
What model (respectively Model I, modelⅱ and model III) the evaluation verifying established with group unification~combination three was concentrated
Plant yield, the actual production then concentrated with verifying compare, by establishing the accuracy of prediction orthogonal matrix judgment models, in advance
It is as shown in table 5 to survey orthogonal matrix.
Table 5 predicts orthogonal matrix
In prediction orthogonal matrix, 0 is indicated normal (i.e. the not underproduction), and 1 indicates to lack (i.e. the underproduction), accuracy rate=(tp+
tn)/(tp+tn+fp+fn).The underproduction is thought when the yield of single plant fruit is subnormal 10% in the present embodiment.
The Model I established using group unification~combination three~the results are shown in Table 6 for model III judgement.
6 Model Is of table~model III judging result
According to table 6 it is found that the accuracy rate of Model I is 91%, the accuracy rate of modelⅱ is 92%, and the accuracy rate of model III is
95%.Top-priority according to accuracy rate should be that model III combines three.
(III) ROC curve evaluation model is utilized
ROC curve is made to Model I~model III of foundation, as shown in Figure 1.Model I~model III is determined according to ROC curve
AUC value be respectively 0.949,0.984,0.959.According to AUC value it is found that model III is the model preferably considered.
(5) forecast production
Characteristic value in conjunction with three models is as shown in table 7, confirms model III, that is, N content % (R1), content of organic matter %
(R3), the parameter combination of Mg content (ppm, R7), Zn content (ppm, R9) can achieve under the prediction of Logic Regression Models
The yield of the prediction tomato of accuracy rate 95% is very suitable to future implementation and application in the production of tomato.
7 three model feature values of table are summarized
In other embodiments of the invention, Logic Regression Models also are established to the conjunction of other set of variables, by verifying,
The model that the predictablity rate that his set of variables builds vertical Logic Regression Models jointly is established without the combination three in embodiment 1
Accuracy rate is high.
Claims (5)
1. it is a kind of reproduction initial stage prediction tomato whether the method for the underproduction, which comprises the following steps:
1) as independent variable and variable combination is arranged in the physical signs of the tomato leaf of flower bud differentiation period, according to different variables
Combination and dependent variable establish Logic Regression Models respectively；The physical signs includes object element content, the content of organic matter；Institute
Stating object element includes metallic element and nonmetalloid, and the metallic element is calcium, iron, potassium, magnesium, sodium, at least one in zinc
Kind；The nonmetalloid is nitrogen and/or phosphorus；The dependent variable be whether the underproduction；
2) using the physical signs of the tomato leaf in training set sample as independent variable, using whether the underproduction is as dependent variable,
The Logic Regression Models are trained, determine the logistic regression coefficient of model；The training set sample includes normal group sample
Sheet and nutritional deficiency group sample；
3) physical signs of the tomato leaf in verifying collection sample is brought into as independent variable and logistic regression has been determined in step 2)
The model of coefficient, obtains prediction result；The actual result of the prediction result of different models and verifying collection sample is compared, is filtered out pre-
Survey the highest model of accuracy；The verifying collection sample includes normal group sample and nutritional deficiency group sample；
4) it is predicted using the model that step 3) filters out whether tomato to be predicted the underproduction occurs.
2. it is according to claim 1 reproduction initial stage prediction tomato whether the method for the underproduction, which is characterized in that the variable
Combination includes that entire variable combines, and the entire variable combination is to obtain all indexs in the physical signs as independent variable.
3. it is according to claim 1 reproduction initial stage prediction tomato whether the method for the underproduction, which is characterized in that the variable
Combination includes AIC optimum combination, and the AIC optimum combination is the smallest variable combination of AIC value of corresponding model.
4. it is according to claim 1 reproduction initial stage prediction tomato whether the method for the underproduction, which is characterized in that the variable
Combination includes that significant difference combines, and the significant difference combination includes that normal group sample and nutritional deficiency group sample physical signs are poor
Different significant variable.
5. it is according to claim 1 reproduction initial stage prediction tomato whether the method for the underproduction, which is characterized in that the tomato
Blade is plant top the 4th leaf down.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910169105.2A CN109840855A (en) | 2019-03-06 | 2019-03-06 | A method of reproduction initial stage prediction tomato whether the underproduction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910169105.2A CN109840855A (en) | 2019-03-06 | 2019-03-06 | A method of reproduction initial stage prediction tomato whether the underproduction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109840855A true CN109840855A (en) | 2019-06-04 |
Family
ID=66885445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910169105.2A Pending CN109840855A (en) | 2019-03-06 | 2019-03-06 | A method of reproduction initial stage prediction tomato whether the underproduction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109840855A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261526A (en) * | 2019-06-24 | 2019-09-20 | 上海交通大学 | A kind of tomato flavor quality determination method based on tomato odor characteristic compound |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766135A (en) * | 2015-03-25 | 2015-07-08 | 中国农业科学院农业信息研究所 | Method, device and system for predicting crop yield |
| US20160290918A1 (en) * | 2014-09-12 | 2016-10-06 | The Climate Corporation | Forecasting national crop yield during the growing season |
| CN106295865A (en) * | 2016-08-02 | 2017-01-04 | 沈阳农业大学 | A kind of Forecasting Methodology of rice yield |
| CN107356727A (en) * | 2017-08-29 | 2017-11-17 | 河南科技大学 | The method that whether heavy metal pollutes in regional soil to be measured is predicted using mangrove nutritive index |
| CN108022023A (en) * | 2017-12-20 | 2018-05-11 | 深圳春沐源控股有限公司 | Plantation production prediction method, device and the storage medium of a kind of crops |
| CN108062602A (en) * | 2017-12-28 | 2018-05-22 | 江苏大学 | A kind of method for predicting greenhouse solanaceous vegetables crop assimilation products yield |
| CN108364101A (en) * | 2018-02-13 | 2018-08-03 | 河南科技大学 | A method of predicting insect pest using soil element content |
-
2019
- 2019-03-06 CN CN201910169105.2A patent/CN109840855A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160290918A1 (en) * | 2014-09-12 | 2016-10-06 | The Climate Corporation | Forecasting national crop yield during the growing season |
| CN104766135A (en) * | 2015-03-25 | 2015-07-08 | 中国农业科学院农业信息研究所 | Method, device and system for predicting crop yield |
| CN106295865A (en) * | 2016-08-02 | 2017-01-04 | 沈阳农业大学 | A kind of Forecasting Methodology of rice yield |
| CN107356727A (en) * | 2017-08-29 | 2017-11-17 | 河南科技大学 | The method that whether heavy metal pollutes in regional soil to be measured is predicted using mangrove nutritive index |
| CN108022023A (en) * | 2017-12-20 | 2018-05-11 | 深圳春沐源控股有限公司 | Plantation production prediction method, device and the storage medium of a kind of crops |
| CN108062602A (en) * | 2017-12-28 | 2018-05-22 | 江苏大学 | A kind of method for predicting greenhouse solanaceous vegetables crop assimilation products yield |
| CN108364101A (en) * | 2018-02-13 | 2018-08-03 | 河南科技大学 | A method of predicting insect pest using soil element content |
Non-Patent Citations (3)
| Title |
|---|
| 南小琴 等: "基于决策树算法的棉花产量预测研究", 《农村科技》 * |
| 涂仕华: "《常用肥料使用手册 修订版》", 31 January 2014, 出版发行 成都：四川科学技术出版社 * |
| 郭庆元: "《大豆农艺工培训教材》", 31 March 2008, 出版发行 北京：金盾出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261526A (en) * | 2019-06-24 | 2019-09-20 | 上海交通大学 | A kind of tomato flavor quality determination method based on tomato odor characteristic compound |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Butters et al. | A rapid method for the determination of total sulphur in soils and plants | |
| CN105699472B (en) | Flat tea place of production method of discrimination based on stable isotope proportional difference | |
| CN105758927B (en) | Method for simultaneously measuring iodine, boron, tin and germanium elements in soil | |
| CN104458616A (en) | Determining and analyzing method of content of chelated zinc in chelated potassium and zinc urea product | |
| CN102928379A (en) | Method for rapidly detecting polysaccharide content of health enhancement oral liquid by adopting near infrared spectrum technology | |
| CN105885831B (en) | Thiosemicarbazides contracting umbelliferone -8- aldehyde probe reagent and its preparation and application | |
| CN101419174A (en) | Method for detecting whole copper in soil | |
| CN104297461B (en) | A kind of method predicting Semen vignae sinensis yield | |
| CN109840855A (en) | A method of reproduction initial stage prediction tomato whether the underproduction | |
| CN107356727B (en) | The method that whether heavy metal pollutes in regional soil to be measured is predicted using mangrove nutritive index | |
| CN102565029A (en) | Method for measuring impurities in pure silver by electrical inductance-coupled plasma emission spectrometer | |
| CN109438386A (en) | A kind of identification aluminium ion and the difunctional fluorescence probe of zinc ion and its preparation method and application | |
| CN109829556A (en) | A kind of output of cotton prediction technique and system | |
| Jacobs et al. | Planktonic primary production in the western Dutch Wadden Sea | |
| CN101825588B (en) | Method for measuring contents of As and Sn elements in iron ore by adopting X-ray fluorescence spectrum melting method | |
| Reichman et al. | Probing the effects of light and temperature on diurnal rhythms of phytosiderophore release in wheat | |
| CN106153603A (en) | Measure the method for copper ferrum magnesium nickel manganese in Cast aluminium alloy gold simultaneously | |
| Taher et al. | Determination of trace amounts of iron by a simple fluorescence quenching method | |
| CN110352661A (en) | A kind of lithospermum euchromum Royle seed chemistry sprouts the determination method and germination method of effect | |
| CN108364101B (en) | Method for predicting insect damage by using soil element content | |
| CN101750281A (en) | Rice Fe2+ stress spectrum quantification identification method | |
| CN109541125A (en) | The measuring method of boron content in a kind of 2 pellet of boron carbide-zirconium | |
| CN114324309A (en) | ICP (inductively coupled plasma) measuring method for synchronously testing total hardness, phosphate radical and iron in industrial water | |
| CN206596378U (en) | A kind of many material mixing administration systems | |
| Weaver et al. | Wet chemical and UV-Vis spectrometric iron speciation in quenched low and intermediate level nuclear waste glasses |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190604 |