CN108153990B - Plant intelligent agent model design method for atmospheric pollution response - Google Patents

Plant intelligent agent model design method for atmospheric pollution response Download PDF

Info

Publication number
CN108153990B
CN108153990B CN201810025793.0A CN201810025793A CN108153990B CN 108153990 B CN108153990 B CN 108153990B CN 201810025793 A CN201810025793 A CN 201810025793A CN 108153990 B CN108153990 B CN 108153990B
Authority
CN
China
Prior art keywords
plant
response
agent
dose
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810025793.0A
Other languages
Chinese (zh)
Other versions
CN108153990A (en
Inventor
周红
曾祎瑾
肖文韬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen University
Original Assignee
Xiamen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen University filed Critical Xiamen University
Priority to CN201810025793.0A priority Critical patent/CN108153990B/en
Publication of CN108153990A publication Critical patent/CN108153990A/en
Application granted granted Critical
Publication of CN108153990B publication Critical patent/CN108153990B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A plant intelligent Agent model design method of atmospheric pollution response comprises a dose-response model and a parameterization definition part, wherein a sigmoidal dose-response curve for describing the relationship between exogenous pollutants and plant physiological response and four parameters required by the curve are obtained by simulating the response trend of plant agents; the plant Agent internal state collection part selects four attributes to abstract and express individual injury difference of the plant and defines state attribute information of the plant Agent based on a plant response mode of the first part of dose-response; and the plant Agent adaptive behavior rule part selects the response intensity index of the plant to the atmospheric pollutants, refines the rule for measuring the damage degree of the plant Agent, realizes the dynamic change of the plant to the response environment through the plant Agent behavior rule and the change of the plant Agent adaptive parameters on the adaptive modeling of the plant Agent, and establishes the plant Agent operation process. The invention has wide application background and application value.

Description

Plant intelligent agent model design method for atmospheric pollution response
Technical Field
The invention relates to the fields of system ecology and computer simulation, in particular to a plant intelligent body model design method for atmospheric pollution response.
Background
The Agent concept originated in the 60's of the 20 th century. MIT's computer academician and AI discipline founder Minsky, originally proposed Agents in the IT field, who thought that some social problems could be solved by inter-individual negotiations, and those with intelligence and interactivity were Agents. Since then, the concept of Agent was introduced into the fields of artificial intelligence and computers. The research of the computer science subject on the Agent technology provides the realization condition for the Agent-based simulation method, and the CAS theory in the complex system science subject is provided, so that the Agent develops into a methodology capable of analyzing the complex system from a specific technical tool.
The Agent-based modeling and simulation are powerful tools for solving complex adaptation systems, the research fields of multi-Agent technologies at home and abroad relate to environmental science, geography and ecology, social transition, political interaction, communication, medical treatment, military and the like, and the application is very wide. The social and economic fields are the most active places for Agent simulation application, individual people or organizations in social and economic systems have essential similarity with the agents, and the Agent technology can be used for simulating the emergence and self-organization phenomena of the human society. The application of the Agent in the engineering field is mainly software Agent, and the better interactive negotiation performance of the Agent is utilized. The application in engineering modeling simulation focuses on organizing and negotiating problems, and is mostly related to human behavior.
In summary, the research of the Agent simulation-based Agent model is mainly focused on the social and economic fields, and no plant Agent main body is designed.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art, and creatively provides a plant Agent model design method for responding to atmospheric pollution in an engineering ecosystem through a large amount of literature research in interdisciplinary fields and research on a response mechanism of plant pollution. According to the method, regardless of the design of the plant intelligent agent, after the relevant parameters of different plant intelligent agents are defined through a plant resistance experiment, various plant intelligent agents can be obtained.
The invention adopts the following technical scheme:
the plant intelligent agent model design method of the atmosphere pollution response is characterized in that: comprises the following parts
(1) Dose-response model and parametric definition: establishing a plant dose-response model by adopting a sigmoidal dose-response curve, and selecting four parameters for defining the sigmoidal dose-response curve;
(2) plant Agent internal state set: selecting four attributes to abstract and express individual injury differences of plants, wherein the four attributes comprise plant types, injury threshold values, intermediate reaction doses and injury grades;
(3) plant Agent adaptive behavior rules: and defining plant Agent behavior rules and plant Agent adaptability parameters based on the dose-response model and the four attributes, realizing the dynamic change of the plant to the response environment through the change of the plant Agent behavior rules and the plant Agent adaptability parameters, and establishing a plant Agent operation process.
A sigmoidal dose-response curve is given in a logarithmic model:
Figure GDA0002298928370000021
wherein y is the individual response at dose x and E [ y/x ] is the average response at dose x; alpha and are the upper and lower reaction limits of the curve, respectively; theta and beta are related to the slope and inflection point, respectively, of the sigmoidal dose response curve.
Modifying the logarithmic model to obtain a medium reaction dose EC50Plant dose-response model of (a):
Figure GDA0002298928370000031
the four parameters included baseline response, maximum response, intermediate response dose, and slope.
The plant types include susceptible plants, intermediate plants and resistant plants.
SO produced by plant leaves when 10% of visible injury symptoms occur2Concentration and time serve as the injury threshold.
The damage degree is divided into five grades which respectively represent the SO of the plants2The response condition of (2).
The plant Agent behavior rule is that the dose-response model is adopted to describe the atmospheric pollutant SO of the plant2The response condition of the plant is expressed by adopting the four attributes, the individual injury difference of the plant is expressed, the leaf area injury rate is selected as a reaction intensity index, and the damage degree of the plant Agent is measured according to a rule R5Can be described as:
R5：p-type∧threshold∧EC50∧dose→damagerate；
wherein p-type is plant type, threshold is injury threshold, EC50Is an intermediate reaction dosage
Figure GDA0002298928370000032
n is simulation hour, density (n) is pollutant hour concentration, represents the dual influence of pollutant concentration and time, and dose-response model is used for refining rule R5：
Figure GDA0002298928370000033
The parameter value β in the model is determined by the following equation:
Figure GDA0002298928370000034
the plant Agent adaptability parameters are defined as follows: the real-time vector of a single plant Agent at the moment t +1, which is composed of n internal state features, is as follows:
Figure GDA0002298928370000035
the adaptation of the individual state features at time t +1 is:
Figure GDA0002298928370000036
wherein the content of the first and second substances,
Figure GDA0002298928370000037
for all the influencing factors at the time t as a feedback function to the state n,
Figure GDA0002298928370000038
the weight parameter is a value range of 0-1.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
the invention provides a plant Agent model design method for responding to atmospheric pollution in an engineering ecosystem by comprehensively utilizing related knowledge of various disciplines. According to the method, regardless of the design of the plant intelligent agent, after the relevant parameters of different plant intelligent agents are defined through a plant resistance experiment, various plant intelligent agents can be obtained. The invention provides a brand-new theoretical visual angle for engineering environment influence evaluation, and has wide application background and application value.
Drawings
FIG. 1 is a flow chart of a method according to the present invention;
FIG. 2 is a parameter significance diagram of an S-shaped curve;
FIG. 3 is a schematic diagram of a plant Agent operation process;
FIG. 4 is a graph of the number of different injury grades of a sensitive plant of the plant Agent in the embodiment under a specific condition;
FIG. 5 is a graph showing the number of different damage levels of a medium plant in a specific condition of the plant Agent of the present embodiment;
FIG. 6 is a graph showing the number of different injury grades of the resistant plant of the plant Agent of this example under a specific condition.
Detailed Description
The invention is further described below by means of specific embodiments.
Referring to fig. 1 to 3, the plant intelligent Agent model design method based on the atmospheric pollution response comprises three parts, namely a dose-response model and a parameterization definition, a plant Agent internal state set and a plant Agent adaptive behavior rule. The dose-response model and the parameterization defining part are used for simulating the response trend of the plant Agent to obtain a sigmoidal dose-response curve for describing the relationship between the exogenous pollutants and the plant physiological response, and four parameters required for defining the curve. And the plant Agent internal state collection part selects four attributes to abstract and express individual injury difference of the plant based on the plant response mode of the first part of dose-response, and state attribute information of the plant Agent is defined. The plant Agent adaptive behavior rule part selects the response intensity index of the plant to the atmospheric pollutants, refines the rule for measuring the damage degree of the plant Agent, realizes the dynamic change of the plant to the response environment through the plant Agent behavior rule and the change of the plant Agent adaptive parameters on the adaptive modeling of the plant Agent, and establishes the plant Agent operation process.
1 dose-response model and Parametric definition
1) The degree of plant response to atmospheric pollution is influenced by both the concentration of the pollutant and the exposure time. The relationship between exogenous pollutants and plant physiological responses can be described by using a dose-response model, wherein the abscissa is dose (concentration multiplied by time) and the ordinate is response intensity. Dose-response curves can be obtained using scatter plots or statistical regression. The dosage can be single pollution or comprehensive pollution. Plant species, growth conditions, different response indicators and measurement endpoints all result in different response curve shapes. However, most dose responses are in an S-relationship, so the present invention uses sigmoidal curves to build an internal model of plant dose responses.
2) Sigmoidal dose response curves generally require four parameters to define: BaseLine (BaseLine) and maximum (MaxLine), i.e. bottom and top of the curve; can produce intermediate response doses (EC) between baseline and maximal responses50) (ii) a Slope (Slope). FIG. 2 is a parameter significance diagram of the S-shaped curve.
3) The S-fit equations given in different documents differ slightly, giving the S-fit equation expressed in a commonly used logarithmic model:
Figure GDA0002298928370000051
wherein E [ y/x ] is the average response at dose x; alpha and are the upper and lower reaction limits of the curve, respectively; theta and beta are respectively related to the slope and the inflection point of the curve;
4) the model is modified to obtain a medium reaction dose EC50Plant dose-response model of (a): :
Figure GDA0002298928370000061
the model is more suitable for simulating the reaction trend of plant agents on the basis of the existing information about the response condition of plants to atmospheric pollution, a parameter value beta is required, and the minimum and maximum reaction values alpha and EC are required to be known50And one is not equal to EC50Dose response relationship (x, E [ y/x)])。
2 plant Agent internal State aggregation
The plant is forced to be damaged by pollutants in the atmospheric Agent, the resistance of the plant is closely related to the self attribute, and the individual damage difference of the plant is abstractly expressed by selecting four attributes based on the plant response mode of dose-response, wherein the four attributes are respectively the plant type, the damage threshold, the intermediate response dose and the damage level. The specific description is as follows:
1) plant type (p-type):
the plant type is a key attribute reflecting the resistance of the plant to atmospheric pollution and the purification capacity, and influences the determination of other attribute values, and the invention defines the plant type set as: p-type ═ p1,p2,p3Represents sensitive, moderate and resistant plants, respectively. Sensitive plant to SO2The stimulation response is sensitive and strong, and the injury symptoms appear in a short time at a low concentration, while the resistant plants are resistant to SO2Has strong metabolism and resistance.
2) Injury threshold (threshold):
the injury threshold refers to the decontamination limit of the plant for the contaminant. According to the existing experimental data, the SO of 10% of visible injury symptoms is generated by plant leaves2Concentration and time as injury threshold in g/m3X h, determining rule R1Can be expressed as: r1：p–type→threshold；
The injury threshold can take three values according to plant types, and threshold is t1(0.4),t2(0.8),t3(1.4) }, rule R1Can be refined: if (p-type ═ p)n)，then(threshold＝tn) Wherein n is 1,2, 3.
3) Intermediate response dose (EC)50)：
EC50Is determined by the minimum and maximum response values of the dose-response curve to be simulated, not simply the dose at which the response rate reaches 50%, the S-curve, EC, simulating different response ranges50The value of (c) is also different. In addition to being related to the dependent variable interval, EC50Also needs a lot of experimental data as the basis, EC50Rule for determining value R2Can be expressed as:
Figure GDA0002298928370000071
different plant species, with reference to the plant resistance level, are directed to the contaminant SO2Is EC50＝{e1(1.27),e2(4.45),e3(6.95) }, the corresponding refining rule is:
if(p–type＝pn)，then(EC50＝en) Wherein n is 1,2, 3.
4) Injury rating (classification):
the invention divides the damage degree of plants into five grades: when the dose is less than the injury threshold value, namely the injury rate (damagelate) of the leaf area is less than 10%, the physiological function of the plant is considered not to be damaged, the residual metabolic capacity is still provided, the injury level is I level, and if the injury is stopped at the moment, the plant can automatically recover to a healthy state; when the damage rate of leaves reaches 10 percent but is less than 30 percent, the plants are slightly damaged by class II; when the injury rate is 30% -50%, the plants are moderately injured by grade III; 50% -70% of the injuries are serious IV-level injuries; more than 70 percent of the plants are severe injuries of grade V, the survival probability of the plants under the continuous severe injuries is 0, and the five injury grades are used for representing the SO of the plants2The response condition of (2).
With the increase of the time of exposing the plant Agent in the polluted atmosphere, the damage rate of the leaves is continuously increased, the damage grade is correspondingly changed, and the rule R is used3To describe the state transition as:
Figure GDA0002298928370000072
according to the analysis, the damage level of the plant Agent at a certain moment depends on the damage rate of the leaves at the moment, and a rule R is corresponded between the damage level and the damage rate4The formalization of (A) is described as follows:
if(damagerate＜10％),then(classification＝Ⅰ)
if(10％≤damagerate＜30％),then(classification＝Ⅱ)
if(30％≤damagerate＜50％),then(classification＝Ⅲ)
if(50％≤damagerate＜70％),then(classification＝Ⅳ)
if(damagerate≥70％),then(classification＝Ⅴ)
in summary, the status attribute information of a certain type of plant Agent can be described as:
p＝{p-type,threshold,EC50,classification}。
3 plant Agent adaptive behavior rules
1) Plant Agent behavior rules
In the engineering atmospheric environment response problem, the main action of the plant Agent is to absorb pollutants in the atmosphere, perform a series of physiological transformation and metabolic operations on a microscopic level in vivo, and after the accumulation degree of the pollutants exceeds the metabolic capability of the plant, the plant growth is influenced and different injury symptoms appear. The setting of the behavior rules requires knowing the relationship between the pollutant dose and the plant injury performance. Dose-response S model to describe the plant to atmospheric pollutants SO2The response condition of (2) is that the injury rate of leaf area (damagelate) is selected as a response intensity index, and the rule R for measuring the damage degree of the plant Agent is assumed that the response effect of the plant to the pollutant concentration and the contact time is consistent5Can be described as:
R5：p-type∧threshold∧EC50∧dose→damagerate；
wherein the dosage
Figure GDA0002298928370000081
n is the simulated hour and density (n) is the contaminant hour concentration, indicating the dual effect of contaminant concentration and time. Refinement of rule R with dose-response model5：
Figure GDA0002298928370000082
The parameter value β in the model is determined by the following equation:
Figure GDA0002298928370000083
2) plant Agent adaptive parameter definition
The adaptability of the plant Agent means that when the plant is influenced by the surrounding environment, the internal state of the plant is changed in an adaptive manner: one is the purification capacity and the other is the resistance capacity. The response mode of plants to the environment involves the coupling of a plurality of uncertain factors and has the characteristics of complexity, diversity and variability. The internal influence factor is described as one state characteristic of the plant Agent and can also be used as a cause to influence other internal state characteristics, so that the metabolic process presents nonlinear real-time change, and the plant adaptability is changed. The real-time vector of a single plant Agent at the moment t +1, which is composed of n internal state features, is as follows:
Figure GDA0002298928370000091
wherein the adaptability of the single state feature at the time t +1 is changed as follows:
Figure GDA0002298928370000092
wherein the content of the first and second substances,
Figure GDA0002298928370000093
for all the influencing factors at the time t as a feedback function to the state n,
Figure GDA0002298928370000094
the weight parameter is a value range of 0-1.
The expression of the nth state of the plant Agent at the t +1 moment is influenced by the state at the t moment and also subjected to the comprehensive feedback action of other related factors. The functional relationship of each state feature is different, and the adaptive change functions of the same state feature at different moments are also different. On the adaptive modeling of the plant Agent, the plant can dynamically change the response environment through the plant Agent behavior rule and the change of the adaptive parameter of the plant Agent, and the plant can be divided into three types. According to lineDefining plant initial parameters for rules and statistical literature data: injury threshold (threshold), median response dose (EC)50) The parameter value β is shown in the following table.
TABLE 3-1 Definitions of different resistant plant parameters
Figure GDA0002298928370000095
Figure GDA0002298928370000101
EC50And β is an internal parameter of the plant in response to contamination, with the adaptive change rule: a single plant Agent senses the damage rate of the plant agents adjacent to the single plant Agent, and the EC is determined according to the damage rate range50And new value of beta, so as to simulate the accelerated pollution process after plant interaction.
At the time t, the plant Agent receives the pollution information of the atmospheric Agent and combines the self-damage rate, selects the damage rule which accords with self resistance and adaptability in the rule base to make the damage response, simultaneously outputs the information for purifying pollutants, updates the damage state at the time t +1 according to the state transfer rule, and jointly influences the selection of the next rule for continuous circulation so as to realize the response of the plant Agent. FIG. 3 is a schematic diagram of a plant Agent operation process.
Examples
When atmospheric pollutants are spread to the position of a plant, the plant Agent can absorb a certain amount of pollutants to play an environmental purification role, but along with the increase of the step distance, the pollution amount and time acting on the plant are continuously accumulated, and the plant can show different damage symptoms. When the plant tolerance is exceeded, the plant dies and no longer purifies the atmospheric environment. According to the plant intelligent agent model design method of the atmospheric pollution response, a mathematical model of the plant response is established, and a simulation experiment is carried out in a computer.
Assuming that pollutants are uniformly distributed in each three-dimensional space grid and are constant; the meteorological condition is calm wind, and the influence of factors such as wind direction, wind speed and rainfall attraction on the diffusion of atmospheric pollutants is not considered. Although the concentration calculation of pollutants is based on a three-dimensional space, most of the existing interactive main body simulation platforms are built on a two-dimensional space, and the emphasis is on realizing the interactive result data output of the system, so that the pollutants can be assumed to be uniformly distributed in each three-dimensional space grid, and the concentration of the atmospheric pollutants is replaced by a plane.
The plant Agent is a carrying main body of the pollutant. By changing the characteristic parameters of the plants, the response rule of the plant intelligent agent in the atmospheric pollution area along with the change of time is simulated. And in each simulation time step, the plant Agent only absorbs pollutants in the grid and purifies the atmospheric environment in the grid area. The dose-response model described in this patent was designed with its main attributes and behavior parameters as shown in the following table.
TABLE 4-1 plant Agents Primary attributes and behavior parameters
Figure GDA0002298928370000111
And (3) carrying out program realization on the system and the main body model in a JAVA-based replay simulation environment, and carrying out statistics and analysis on output data of the simulation system to obtain an absorption simulation result of the plant Agent on the pollutants.
FIG. 4 is a graph of the number of different injury grades of the sensitive plant of the plant Agent in this embodiment under a specific condition. As can be seen from FIG. 4, the number of sensitive plants in the level II injury, level III injury and level IV injury reaches the maximum in 1600 steps, 2300 steps and 3200 steps, respectively, the number of level V injury plants increases from 2100 steps, and the sensitive plants in the area finally reach level V injury in 5500 steps. Fig. 5 is a graph of the number of different injury levels of medium plants of the plant Agent in this embodiment under a certain condition, and fig. 6 is a graph of the number of different injury levels of resistant plants of the plant Agent in this embodiment under a certain condition. As can be seen from FIGS. 5 and 6, the number of the medium plants and the resistant plants was changed as much as that of the sensitive plants, but the injury time was longer. The number of intermediate plants with grade II, III and IV lesions reached a maximum in 3000, 5000 and 8700 steps, respectively, almost twice as long as that of sensitive plants, while resistant plants take longer.
The invention provides a plant Agent model design method for responding to atmospheric pollution in an engineering ecosystem by comprehensively utilizing related knowledge of various disciplines. According to the method, regardless of the design of the plant intelligent agent, after the relevant parameters of different plant intelligent agents are defined through a plant resistance experiment, various plant intelligent agents can be obtained. Provides a brand-new theoretical visual angle for engineering environment influence evaluation, and has wide application background and application value.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.

Claims (4)

1. The plant intelligent agent model design method of the atmosphere pollution response is characterized in that: comprises the following parts
(1) Dose-response model and parametric definition: establishing a plant dose-response model by adopting a sigmoidal dose-response curve, and selecting four parameters for defining the sigmoidal dose-response curve; a sigmoidal dose-response curve is given in a logarithmic model:
Figure FDA0002482216960000011
wherein y is the individual response at a dose of x, E [ y/x]Is the average response at dose x; alpha and are the upper and lower reaction limits of the curve, respectively; θ and β are related to the slope and inflection point of the sigmoidal dose response curve, respectively; modifying the logarithmic model to obtain a medium reaction dose EC50Plant dose-response model of (a):
Figure FDA0002482216960000012
the four parameters include baseline response, maximum response, intermediate response dose, and slope;
(2) plant Agent internal state set: selecting four attributes to abstract and express individual injury differences of plants, wherein the four attributes comprise plant types, injury threshold values, intermediate reaction doses and injury grades;
(3) plant Agent adaptive behavior rules: defining plant Agent behavior rules and plant Agent adaptability parameters based on a dose-response model and four attributes, realizing dynamic change of plants to response environments through changes of the plant Agent behavior rules and the plant Agent adaptability parameters, and establishing a plant Agent operation process;
the plant Agent behavior rule is that the dose-response model is adopted to describe the atmospheric pollutant SO of the plant2The response condition of the plant is expressed by adopting the four attributes, the individual injury difference of the plant is expressed, the leaf area injury rate is selected as a reaction intensity index, and the damage degree of the plant Agent is measured according to a rule R5Can be described as:
R5：p-type∧threshold∧EC50∧dose→damagerate；
wherein p-type is plant type, threshold is injury threshold, EC50Is an intermediate reaction dosage
Figure FDA0002482216960000021
n is simulation hour, density (n) is pollutant hour concentration, represents the dual influence of pollutant concentration and time, and dose-response model is used for refining rule R5：
Figure FDA0002482216960000022
The parameter value β in the model is determined by the following equation:
Figure FDA0002482216960000023
the plant Agent adaptability parameters are defined as follows: the real-time vector of a single plant Agent at the moment t +1, which is composed of n internal state features, is as follows:
Figure FDA0002482216960000024
the adaptation of the individual state features at time t +1 is:
Figure FDA0002482216960000025
wherein the content of the first and second substances,
Figure FDA0002482216960000026
for all the influencing factors at the time t as a feedback function to the state n,
Figure FDA0002482216960000027
the weight parameter is a value range of 0-1.
2. The method of claim 1, wherein the plant intelligent agent model is designed according to the atmospheric pollution response, and the method comprises the following steps: the plant types include susceptible plants, intermediate plants and resistant plants.
3. The method of claim 1, wherein the plant intelligent agent model is designed according to the atmospheric pollution response, and the method comprises the following steps: SO produced by plant leaves when 10% of visible injury symptoms occur2Concentration and time serve as the injury threshold.
4. The method of claim 1, wherein the plant intelligent agent model is designed according to the atmospheric pollution response, and the method comprises the following steps: the damage grades are divided into five grades which respectively represent the SO of the plants2The response condition of (2).
CN201810025793.0A 2018-01-11 2018-01-11 Plant intelligent agent model design method for atmospheric pollution response Active CN108153990B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810025793.0A CN108153990B (en) 2018-01-11 2018-01-11 Plant intelligent agent model design method for atmospheric pollution response

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810025793.0A CN108153990B (en) 2018-01-11 2018-01-11 Plant intelligent agent model design method for atmospheric pollution response

Publications (2)

Publication Number Publication Date
CN108153990A CN108153990A (en) 2018-06-12
CN108153990B true CN108153990B (en) 2020-10-30

Family

ID=62461287

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810025793.0A Active CN108153990B (en) 2018-01-11 2018-01-11 Plant intelligent agent model design method for atmospheric pollution response

Country Status (1)

Country Link
CN (1) CN108153990B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105547933A (en) * 2015-12-09 2016-05-04 中国科学院遥感与数字地球研究所 Atmospheric pollution monitoring method and device

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105547933A (en) * 2015-12-09 2016-05-04 中国科学院遥感与数字地球研究所 Atmospheric pollution monitoring method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于Multi_Agent的智能植物系统的构建与应用研究;吴升 等;《中国农业科技导报》;20171231;第19卷(第5期);第61-69页 *
植物对大气污染的响应机制;马艳丽 等;《陕西农业科学》;20131231;第41卷(第4期);第394-396页 *

Also Published As

Publication number Publication date
CN108153990A (en) 2018-06-12

Similar Documents

Publication Publication Date Title
Orlob Mathematical modeling of water quality: Streams, lakes and reservoirs
Guh et al. A neural network based model for abnormal pattern recognition of control charts
Bas et al. A modified genetic algorithm for forecasting fuzzy time series
CN110379463A (en) Marine algae genetic analysis and concentration prediction method and system based on machine learning
CN103440525B (en) Lake and reservoir water bloom emergency treatment decision-making method based on Vague value similarity measurement improved algorithm
Yin et al. A particle swarm optimization approach to composing serial test sheets for multiple assessment criteria
CN107679743B (en) Environment-friendly intelligent law enforcement emergency traceability scheduling management method based on big data
Mase et al. Capturing uncertainty in heavy goods vehicles driving behaviour
CN108153990B (en) Plant intelligent agent model design method for atmospheric pollution response
Hollenstein The dynamic systems perspective
Arya et al. Identification and classification of key variables and their role in environmental impact assessment: Methodology and software package intra
Chen et al. Artificial neural networks for risk decision support in natural hazards: A case study of assessing the probability of house survival from bushfires
Situngkir Emerging the emergence sociology: The philosophical framework of agent-based social studies
Randers The Potential in Simulation of Macro-Social Processes or How to be a Useful Builder of Simulation Models
Chitnis et al. Fuzzy MCDM approach for air quality assessment
CN115619209A (en) Electric power construction engineering risk evaluation system integrating correction parameter analytic hierarchy process
Wang et al. Soft computing and fuzzy logic
CN103679539A (en) Multilevel index projection pursuit dynamic clustering method and device
CN111861198B (en) Extraction and analysis method for mine team worker unsafe behavior propagation process
Hu et al. The application of hiwo–svm in analog circuit fault diagnosis
Fullér et al. On weighted possibilistic informational coefficient of correlation
Furze et al. Mathematical methods to quantify and characterise the primary elements of trophic systems
Jullien et al. Scaling properties of growth by kinetic clustering of clusters
CN110738398A (en) trial risk analysis method based on fuzzy number overall utility
Andrade et al. New Water and Biotic Quality Assessment Indices for a tropical reservoir based on fuzzy logic

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant