CN106503856A - Test design method for artificial neural network method Optimal Medium - Google Patents
Test design method for artificial neural network method Optimal Medium Download PDFInfo
- Publication number
- CN106503856A CN106503856A CN201610948640.4A CN201610948640A CN106503856A CN 106503856 A CN106503856 A CN 106503856A CN 201610948640 A CN201610948640 A CN 201610948640A CN 106503856 A CN106503856 A CN 106503856A
- Authority
- CN
- China
- Prior art keywords
- neural network
- artificial neural
- test
- matrix
- culture medium
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 31
- 238000013461 design Methods 0.000 title claims abstract description 14
- 239000001963 growth medium Substances 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 19
- 239000002609 medium Substances 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 8
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 8
- 240000004808 Saccharomyces cerevisiae Species 0.000 claims description 8
- 239000008103 glucose Substances 0.000 claims description 8
- 239000002054 inoculum Substances 0.000 claims description 8
- 239000007788 liquid Substances 0.000 claims description 8
- 238000013401 experimental design Methods 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 abstract description 10
- 210000002569 neuron Anatomy 0.000 abstract description 7
- 238000005457 optimization Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- MYWUZJCMWCOHBA-VIFPVBQESA-N methamphetamine Chemical compound CN[C@@H](C)CC1=CC=CC=C1 MYWUZJCMWCOHBA-VIFPVBQESA-N 0.000 description 2
- 238000012803 optimization experiment Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 241000123113 Phellinus igniarius Species 0.000 description 1
- 210000000979 axoneme Anatomy 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a kind of test design method for artificial neural network method Optimal Medium, n different values in m influence factor in culture medium, the span of each influence factor are constituted matrix, different rows respectively takes a value and forms one group of experiment B in a matrixk,j, so as to obtain the test set β of s × n groups test, selecting t rows, and often capable one value of each taking-up in a matrix, composition has the checking set γ of t element, and verifies that set γ, in set β is tested, at least occurs once, at most occurs λ time.The present invention, so that each factor can be considered by equilibrium in culture medium, culture experiment is carried out using the method, and the experimental result for obtaining is applied to artificial neural network, each neuron in artificial neural network is covered well can, and train neuron to reflect the interactivity between culture medium each element so that in the case where experimental group number is as few as possible, to reach the training best to artificial neural network.
Description
Technical field
The present invention relates to medium optimization, and in particular to for the EXPERIMENTAL DESIGN side of artificial neural network method Optimal Medium
Method.
Background technology
Culture medium is and the nutrient for constituting by a certain percentage in order to produce bacteria growing, breeding, metabolism and synthetic product
Multiple factors such as matter, nitrogen source, carbon source and trace element in component all can produce impact, culture medium to the growth of Phellinus igniarius (L. ex Fr.) Quel. and metabolism
Optimize the optimal proportion that culture medium is found using technological means, to reach maximum production.
In medium optimization, most representational prior art is Response surface meth od (Response Surface
Methods)：In the analysis of multifactor quantity process test, result of the test (dependent variable) and multiple experimental factors can be analyzed
Regression relation between (independent variable), this recurrence possibly curve or bent relation of plane, thus referred to as response surface analysis.Such as agriculture
Crop yield is relevant with the dose of several fertilizer, can set up the recurrence between yield and fertilising key element by regression analyses and close
System, so as to try to achieve optimal fertilizer application formula, in the hope of maximum output.The maximum shortcoming of the method i.e., in the feelings that optimizing factors are excessive
Under condition, it is necessary first to determined using experiment of single factor and screening test method for designing (Plackett-Burman Design)
Significant factor in each factor of culture medium, so that, centered on significant factor, carry out response surface experiment.Wherein experiment of single factor
Using often very big deviation is caused to testing accuracy, this is because experiment of single factor have ignored each factor in culture medium
Reciprocal action, assert that these factors are that individually culture medium is worked；Screening test method for designing can only also filter out some and show
The factor is write, equally ignores the reciprocal action between factor.
And the artificial neural network method Optimal Medium for newly rising at present, a kind of brand-new mould is provided for medium optimization
Formula.Artificial neural network considers each factor in culture medium, then in simulative neural network neuron transmission information mode
These factors are modeled.The great advantage of artificial neural network has the ability of intellectual learning, i.e., using existing examination
Test result (Medium Proportion and corresponding yield) to be trained network, after carrying out certain training, artificial neural network
Judge best medium proportioning and maximum production.Artificial neural network compared to Response surface meth od advantage i.e. to all cultures
Axoneme is all comprehensively considered.But it is existing substantial amounts of result of the test using the premise of artificial neural network, merely
It is low that mass propgation experimentation cost height, efficiency are carried out for this purpose.
As can be seen here, the reciprocal action of each factor or needs in culture medium are ignored in the method presence of current medium optimization
Carry out the problem that mass propgation test causes high cost, efficiency low.
Content of the invention
The technical problem to be solved be current medium optimization method exist ignore in culture medium each because
The reciprocal action of element needs to carry out the problem that mass propgation test causes high cost, efficiency low.
In order to solve above-mentioned technical problem, the technical solution adopted in the present invention there is provided a kind of for ANN
The test design method of network method Optimal Medium, comprises the following steps：
First, by n different value group in m influence factor in culture medium, the span of each influence factor
Into following matrix:
Then, in above-mentioned matrix, t rows, 1≤t≤m, and often capable one value of each taking-up, composition is arbitrarily selected to have t individual
The checking set γ of element, and verify that set γ, in the test according to following condition design, at least occurs once, to having more
Existing λ time, λ >=1, per group of test Bk,jFollowing condition should be met：
(1)In each element both from above-mentioned matrix, and be taken respectively from matrix
Different rows, 1≤j1,j2,...,jm；
J=1 is made, 2 ... n, then have the such test of n groups, βk={ Bk,1,Bk,2,...Bk,nRepresent this n groups test
Set；K=1 is made, 2 ..., s, β={ β1, β2..., βs, so as to obtain the test of s × n groups；
(2) to each βk={ Bk,1,Bk,2,...Bk,n, k=1,2 ..., s, it is desirable toThat is Bk,j(j=1,2 ..., union n) is just
It is well the element in whole matrix；
Finally, by the EXPERIMENTAL DESIGN scheme β={ β obtained according to above method1, β2..., βsTested, and will examination
The training that structure is applied to artificial neural network is tested, so as to obtain the artificial neuron that can accurately embody culture medium factor and yield
Network.
In such scheme, m=6, and each influence factor respectively inoculum concentration, liquid amount, temperature, pH value, yeast is dense
Degree and concentration of glucose.
In such scheme, the span of inoculum concentration is 5g/L～7g/L, and liquid amount is 50ml～100ml, and temperature is
27.5 DEG C～32.5 DEG C, pH value is 6～8, and yeast concentration is 4g/L～8g/L, and concentration of glucose is 45g/L～85g/L.
In such scheme, t=2.
In such scheme, λ=3.
The present invention, overcomes dependence of the conventional experimental technique to experiment of single factor so that each factor can be equal in culture medium
Weighing apparatus consideration, and the interactivity between factor is embodied, so that optimization experiment is more accurate；Culture examination is carried out using the method
Test, and the experimental result for obtaining is applied to artificial neural network, each god in artificial neural network can be covered well
Through unit, and neuron is trained to reflect the interactivity between culture medium each element so that in experimental group number feelings as few as possible
Under condition, the training best to artificial neural network is reached.
Specific embodiment
The present invention is described in detail with reference to specific embodiment.
Test design method provided by the present invention for artificial neural network method Optimal Medium is comprised the following steps：
First, by n different value group in m influence factor in culture medium, the span of each influence factor
Into following matrix:
Then, in above-mentioned matrix, select t rows, 1≤t≤m, and often capable one value of each taking-up, composition that there is t element
Checking set γ, and verify that set γ, in the test according to following condition design, at least occurs once, λ at most occurs
Secondary, λ >=1, per group of test Bk,jFollowing condition should be met：
(1)In each element both from above-mentioned matrix, and be taken respectively from matrix
Different rows, 1≤j1,j2,...,jm；
J=1 is made, 2 ... n, then have the such test of n groups, βk={ Bk,1,Bk,2,...Bk,nRepresent this n groups test
Set；K=1 is made, 2 ..., s, β={ β1, β2..., βs, so as to obtain the test of s × n groups；
(2) to each βk={ Bk,1,Bk,2,...Bk,n, k=1,2 ..., s, it is desirable toThat is Bk,j(j=1,2 ..., union n) is just
It is well the element in whole matrix；
Finally, by the EXPERIMENTAL DESIGN scheme β={ β obtained according to above method1, β2..., βsTested, and will examination
The training that structure is applied to artificial neural network is tested, so as to obtain the artificial neuron that can accurately embody culture medium factor and yield
Network.
In such scheme, m=6, and each influence factor respectively inoculum concentration, liquid amount, temperature, pH value, yeast is dense
Degree and concentration of glucose.
In such scheme, the span of inoculum concentration is 5g/L～7g/L, and liquid amount is 50ml～100ml, and temperature is
27.5 DEG C～32.5 DEG C, pH value is 6～8, and yeast concentration is 4g/L～8g/L, and concentration of glucose is 45g/L～85g/L.
In such scheme, t=2.In 6 influence factors, the value of two influence factors is selected to verify collection to constitute
Close, more easy to operate, also more reasonable.
In such scheme, λ=3.
The application is illustrated now by specific embodiment：
Influence factor m is 6, and is respectively：Inoculum concentration, liquid amount, temperature, pH value, yeast concentration, concentration of glucose,
Each factor takes three values respectively, i.e. n=3, concrete value condition are as follows：
Inoculum concentration：5g/L,6g/L,7g/L；
Liquid amount：50ml,75ml,100ml；
Temperature：27.5℃,30℃,32.5℃；
PH value：6,7,8；
Yeast concentration：4g/L,6g/L,8g/L；
Concentration of glucose：45g/L,70g/L,85g/L；
As matrix
For above value, s=3 is made, the test of following 9 groups of parameter settings can be obtained：
β1={ a=5g/L, b=75ml, c=32.5 DEG C, d=7, e=4g/L, f=70g/L },
{ a=6g/L, b=50ml, c=30 DEG C, d=6, e=8g/L, f=45g/L },
{ a=7g/L, b=100ml, c=27.5 DEG C, d=8, e=6g/L, f=85g/L } }；
β2={ a=5g/L, b=100ml, c=30 DEG C, d=8, e=6g/L, f=45g/L },
{ a=6g/L, b=75ml, c=27.5 DEG C, d=7, e=4g/L, f=85g/L },
{ a=7g/L, b=50ml, c=32.5 DEG C, d=6, e=8g/L, f=70g/L } }；
β3={ a=5g/L, b=50ml, c=27.5 DEG C, d=6, e=8g/L, f=85g/L },
{ a=6g/L, b=100ml, c=32.5 DEG C, d=8, e=6g/L, f=70g/L },
{ a=7g/L, b=75ml, c=30 DEG C, d=7, e=4g/L, f=45g/L } }；
In above EXPERIMENTAL DESIGN, make t=2, composition that there is the checking set γ of 2 elements, such as (a=5g/L, b=
100ml), (a=5g/L, b=50ml), (a=5g/L, b=75ml) etc., are only occurred in that once in 9 groups of tests respectively)；
Such as (d=7, e=4g/L), (d=8, e=6g/L), (d=6, e=8g/L) are occurred in that in 9 groups of tests respectively
3 times), then 1≤λ≤3, therefore, not only ensure that the repetitive rate of the value of two factors is less, will not be too dependent on some
Element, it is ensured that the coverage rate of each value, will not omit, meet condition；
By the training of the fermentation yield market demand carried out according to above 9 groups of EXPERIMENTAL DESIGN to ANN, so as to obtain
To the artificial neural network that can accurately embody culture medium factor and yield.
The present invention, overcomes dependence of the conventional experimental technique to experiment of single factor so that each factor can be equal in culture medium
Weighing apparatus consideration, and the interactivity between factor is embodied, so that optimization experiment is more accurate；Culture examination is carried out using the method
Test, and the experimental result for obtaining is applied to artificial neural network, each god in artificial neural network can be covered well
Through unit, and neuron is trained to reflect the interactivity between culture medium each element so that in experimental group number feelings as few as possible
Under condition, the training best to artificial neural network is reached.
The present invention is not limited to above-mentioned preferred forms, and anyone should learn the knot that makes under the enlightenment of the present invention
Structure change, every with of the invention with same or like technical scheme, each fall within protection scope of the present invention.
Claims (5)
1. the test design method of artificial neural network method Optimal Medium is used for, it is characterised in that comprised the following steps：
First, n different values in m influence factor in culture medium, the span of each influence factor are constituted such as
Lower matrix:
Then, in above-mentioned matrix, select t rows, 1≤t≤m, and often capable one value of each taking-up, composition that there is testing for t element
Card set γ, and verify that set γ, in the test according to following condition design, at least occurs once, at most occurs λ time, λ
>=1, per group of test Bk,jFollowing condition should be met：
(1)In each element both from above-mentioned matrix, and be taken respectively from matrix not
Colleague, 1≤j1,j2,Λ,jm；
J=1 is made, 2, Κ n then have the such test of n groups, βk={ Bk,1,Bk,2,ΚBk,nRepresent the set that this n group is tested；Order
K=1,2, Κ, s, β={ β1, β2, Κ, βs, so as to obtain the test of s × n groups；
(2) to each βk={ Bk,1,Bk,2,ΚBk,n, k=1,2, Κ, s, it is desirable toThat is Bk,j(j=1,2, Κ, union n) is just
It is the element in whole matrix；
Finally, by the EXPERIMENTAL DESIGN scheme β={ β obtained according to above method1, β2, Κ, βsTested, and by test structure
The training of artificial neural network is applied to, so as to obtain the artificial neural network that can accurately embody culture medium factor and yield.
2. the test design method of artificial neural network method Optimal Medium is used for as claimed in claim 1, it is characterised in that
M=6, and each influence factor is respectively inoculum concentration, liquid amount, temperature, pH value, yeast concentration and concentration of glucose.
3. the test design method of artificial neural network method Optimal Medium is used for as claimed in claim 2, it is characterised in that
The span of inoculum concentration is 5g/L～7g/L, and liquid amount is 50ml～100ml, and temperature is 27.5 DEG C～32.5 DEG C, and pH value is 6
～8, yeast concentration is 4g/L～8g/L, and concentration of glucose is 45g/L～85g/L.
4. the test design method of artificial neural network method Optimal Medium is used for as claimed in claim 2, it is characterised in that
T=2.
5. the test design method of artificial neural network method Optimal Medium is used for as claimed in claim 2, it is characterised in that
λ=3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610948640.4A CN106503856A (en) | 2016-10-26 | 2016-10-26 | Test design method for artificial neural network method Optimal Medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610948640.4A CN106503856A (en) | 2016-10-26 | 2016-10-26 | Test design method for artificial neural network method Optimal Medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503856A true CN106503856A (en) | 2017-03-15 |
Family
ID=58322096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610948640.4A Pending CN106503856A (en) | 2016-10-26 | 2016-10-26 | Test design method for artificial neural network method Optimal Medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503856A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859802A (en) * | 2019-01-10 | 2019-06-07 | 中国石油大学(华东) | A kind of Phellinus protein domain prediction threshold value method based on power spectrum |
| WO2022063341A1 (en) * | 2020-09-27 | 2022-03-31 | 深圳太力生物技术有限责任公司 | Basal culture medium development method, basal culture medium formulation and development, and system thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105373669A (en) * | 2015-11-28 | 2016-03-02 | 泰山医学院 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
-
2016
- 2016-10-26 CN CN201610948640.4A patent/CN106503856A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105373669A (en) * | 2015-11-28 | 2016-03-02 | 泰山医学院 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
Non-Patent Citations (1)
| Title |
|---|
| 高梦祥 等: ""基于人工神经网络的侧孢芽孢杆菌培养基的优化研究"", 《长江大学学报（自然科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859802A (en) * | 2019-01-10 | 2019-06-07 | 中国石油大学(华东) | A kind of Phellinus protein domain prediction threshold value method based on power spectrum |
| WO2022063341A1 (en) * | 2020-09-27 | 2022-03-31 | 深圳太力生物技术有限责任公司 | Basal culture medium development method, basal culture medium formulation and development, and system thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Comparing the grain yields of direct-seeded and transplanted rice: A meta-analysis | |
| Yang et al. | Agronomic and economic benefits of pea/maize intercropping systems in relation to N fertilizer and maize density | |
| Davis et al. | Comparative biogeochemical cycles of bioenergy crops reveal nitrogen-fixation and low greenhouse gas emissions in a Miscanthus× giganteus agro-ecosystem | |
| Liu et al. | Root distribution responses to three-dimensional soil heterogeneity in experimental mesocosms | |
| CN103064292A (en) | Biological fermentation adaptive control system and control method based on neural network inverse | |
| CN106503856A (en) | Test design method for artificial neural network method Optimal Medium | |
| CN117973707B (en) | Carbon emission analysis method and system based on full-element productivity improvement | |
| Guan et al. | Phosphorus fertilization modes affect crop yield, nutrient uptake, and soil biological properties in the rice–wheat cropping system | |
| Ye et al. | Effects of postponing topdressing-N on the yield of different types of japonica rice and its relationship with soil fertility | |
| Luo et al. | Assessing nitrogen availability in biobased fertilizers: Effect of vegetation on mineralization patterns | |
| FUkUDA et al. | Early diagnosis of productivity through a clock gene promoter activity using a luciferase bioluminescence assay in Arabidopsis thaliana | |
| DE112006003884T5 (en) | A method of improving organisms using profile profiling of total metabolite fluxes | |
| Rodríguez‐Miranda et al. | A seasonal simulation approach for culture depth influence on the temperature for different characterized microalgae strains | |
| Cheng et al. | Effects of controlled release urea formula and conventional urea ratio on grain yield and nitrogen use efficiency of direct-seeded rice | |
| Valkov et al. | An in vitro procedure for phenotypic screening of growth parameters and symbiotic performances in Lotus corniculatus cultivars maintained in different nutritional conditions | |
| CN116629492A (en) | Integrated learning optimization evaluation method for soil quality improvement effect | |
| Liu et al. | Soil Autotrophic Bacterial Community Structure and Carbon Utilization Are Regulated by Soil Disturbance—The Case of a 19-Year Field Study | |
| CN102169117A (en) | Evaluation system suitable for micro-ecosystem of soil with transgenic plants and application thereof | |
| CN105740211B (en) | One kind is based on the information convergence analysis method of honeycomb video-temperature acquisition system | |
| CN104598770B (en) | Wheat aphid quantitative forecasting technique and system based on human evolution's gene expression programming | |
| Cha-un et al. | Short-term and long-term soil carbon sequestration in rice field with energy crop rotation | |
| Romano et al. | Comparison of nitrogen fertilizer demand for wheat production between humid and semi-arid portions of the Argentinean Pampas using a mass balance method | |
| CN105925487A (en) | Culture method for improving sugar content of micro-algal cells | |
| CN103810403B (en) | Gene interaction based plant growth predication regulation and control method and system | |
| CN103168689B (en) | Short-period tissue culture method for peanuts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |