CN101419623B - Geographical simulation optimizing system - Google Patents
Geographical simulation optimizing system Download PDFInfo
- Publication number
- CN101419623B CN101419623B CN2008102198242A CN200810219824A CN101419623B CN 101419623 B CN101419623 B CN 101419623B CN 2008102198242 A CN2008102198242 A CN 2008102198242A CN 200810219824 A CN200810219824 A CN 200810219824A CN 101419623 B CN101419623 B CN 101419623B
- Authority
- CN
- China
- Prior art keywords
- simulation
- data
- geographical
- optimization
- rule
- 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.)
- Expired - Fee Related
Links
- 238000004088 simulation Methods 0.000 title claims description 122
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000001413 cellular effect Effects 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims description 40
- 230000003993 interaction Effects 0.000 claims description 37
- 230000009466 transformation Effects 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 20
- 230000000694 effects Effects 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000002386 leaching Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000012913 prioritisation Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 2
- 238000010168 coupling process Methods 0.000 claims description 2
- 238000005859 coupling reaction Methods 0.000 claims description 2
- JCCNYMKQOSZNPW-UHFFFAOYSA-N loratadine Chemical compound C1CN(C(=O)OCC)CCC1=C1C2=NC=CC=C2CCC2=CC(Cl)=CC=C21 JCCNYMKQOSZNPW-UHFFFAOYSA-N 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 3
- 239000003795 chemical substances by application Substances 0.000 description 32
- 238000005516 engineering process Methods 0.000 description 5
- 238000013439 planning Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 239000012528 membrane Substances 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012732 spatial analysis Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a concept, a principle and software implementation of a geographic modeling and optimizing system, which are used for modeling, predicting, optimizing and displaying geographic patterns and processes. The invention has the advantages that a cellular automation, a multi-agent system and geographic optimized knowledge, which are dispersed at present, are systemically integrated so as to built the geographic modeling and optimizing system; and the geographic modeling and optimizing knowledge and soft engineering ideas and techniques are organically combined so that the geographic modeling and optimizing system is realized from a software angle.
Description
Technical field
The invention belongs to the geography information science and technology field, be specifically related to a kind of geographical simulation optimizing system that is used for simulating, predict, optimizing and show geographic patterns and process.
Technical background
Geographic Information System GIS begins new developing technology mid-term nineteen sixties, spatial data is learned on ground to combine with computer technology, by humane economy of epigeosphere and multiple information such as natural resources and environment are managed and analyzes, to grasp rules such as physical environment and economic geography key element.Be widely used in every field at present, comprised geography, mapping science, geology, environmental science, municipal administration, forestry, agricultural, ocean, and numerous areas such as ecommerce.Spatial analysis is one of basic function of GIS, and wherein stacked analysis, buffer zone analysis, network analysis etc. are spacial analytical method the most frequently used among the GIS.
But, although GIS has the ability of powerful spatial data management and processing aspect, function aspect the model a little less than, neo-confucian is to the demand of analysis aspects such as process contentedly.The space-time dynamic evolution of many geographical phenomenons is often even more important than the spatial framework of its final formation, such as city expansion, disease's spread, fire spread, population migration, economic development, desertification, flood inundation on tracks etc.Therefore, the space-time dynamic model has important effect to the complicacy of the system of studying geography.The differentiation of many geographical phenomenons has the complicated nonlinear systems feature, can't utilize simple effectively studying based on equational method, and the spatial simulation method is that instrument is explored in strong analysis.
Mainly utilize cellular automaton CA to come these complicated geographical processes are carried out sunykatuib analysis in recent years in the world, in order to reflect of the influence of different role such as humane factor and government, adopt the research of multi-agent system MAS aspect also to cause people's attention simultaneously to geographical process.In addition, the management and use of resource environment often relate to distributing rationally of space, need to use the instrument of some optimizations to assist the generation programme.Purpose is to dispose or use resource on space-time best, produces the greatest benefit value.The problem that relates to comprises distributing rationally of facility addressing, land use planning, water resource etc.
But these researchs all relatively disperse to carry out, can not carry out the mutual of information each other shares, can not arrive simulation and mutually promoting of optimizing, can not make complicated geographical process better simulate, optimize and predict, not form unified theory and technology frame system.
Summary of the invention
The objective of the invention is to remedy present GIS to the wretched insufficiency of process analysis procedure analysis function with generally lack the weakness of simulation and the instrument of optimizing class, GIS is carried out important expansion, provide general GIS senior spatial analysis and the geographical simulation and the optimizational function that can not provide, can satisfy preferably the resource environment of complexity and the simulation and the optimization demand of differentiation, for complicated resource environment and variation provide a kind of effective simulation and optimization tool.
In order to realize the foregoing invention purpose, the technical scheme of employing is as follows:
A kind of geographical simulation optimizing system, comprehensive cellular automaton, multi-agent system and biological intelligence are simulated, predict, are optimized and show geographic patterns and process; Described cellular automaton, multi-agent system and biological intelligence are incorporated into simulates influencing each other and interacting between the microcosmic entity together, and is defined as:
Wherein,
With
What represent is state and the position of entity i, and described entity comprises static cellular and removable intelligent body, and removable intelligent body further is subdivided into social intelligence's body and biological intelligence body, and Et and F are used for characterizing environment and interaction rule set respectively; Described interaction rule set comprises three subclass: F~(F
CA, F
SocialAgent, F
AnimalAgent), F wherein
CABe used for representing the interaction rule of static cellular, F
SocialAgentBe used for representing the interaction rule between social intelligence's body and their the residing environment, F
AnimalAgentBe used for interaction rule between characterising biological intelligence body and its external environment.
The present invention is by comprehensive cellular automaton (CA), multi-agent system (MAS) and biological intelligence (SI), a new notion-geographical simulation optimizing system (Geographical Simulation andOptimization System is proposed, GeoSOS), be used for simulating, predict, optimize and show geographic patterns and process.Geographical simulation optimizing system has adopted strategy from bottom to top to simulate nonlinear complex dynamic systems, and powerful simulation and optimizational function can be provided, and remedies the deficiency of existing Geographic Information System effectively.The microcosmic individuality also is introduced into wherein, is used for being reflected in the environmental lapse process interaction between nature, ecology and social system.Comprising the discrete entities that much can directly reflect geographic object in this system, for example, trees, river, school, airport etc.In system, comprising such two class entities: static cellular and removable intelligent body.Traditional grid Geographic Information System is mainly handled static cellular.Removable intelligent body can further be subdivided into social intelligence's body (social agents) and biological intelligence body (animal agents).Last class intelligence body can be used for expression crowd or tissue.Then a class then can be represented some artificial bio-membranes (artificial animals), for example ant or flock of birds and so on.This class intelligence body can replenish certain artificial intelligence for system, for space optimization is provided convenience.
Cellular automaton uses static cellular to represent the entity of fixing, and multi-agent system (MAS) and biological intelligence (SI) then use the intelligent body that moves to represent removable entity in the real world.The simulation of space-time dynamic process and optimization can show by the interaction between the microcosmic individuality.The reciprocation of this microcosmic individuality is mainly based on geography first law of Tobler, promptly on the space all entities all exist interrelated, entity and be adjacent that relevance is better than from its entity far away between the entity often.The rule and the behavior of intelligence body can be excavated from the training data of Geographic Information System and remote sensing.
By changing the various parameters of cellular automaton and multiple agent, can effectivelyly carry out the simulation and the analysis of view.Yet this class model is not with solving optimization problem.But growing demand not only needs to obtain true general layout, also needs the general layout that is optimized simultaneously.City planning often need be made compromise selection between reality and ideal.In addition, also needing us to take all factors into consideration economic factors to the addressing of main facilities and the optimization planning of traffic system, these planning will utilize dynamic change that very far-reaching influence is arranged to the soil in future.
Therefore, native system comprehensive simulation and Optimization Model solve all kinds of problems in the planning application.Up to now, all common tool and method that lacks integrated simulation simultaneously and optimization of most of research is learned.In GeoSOS, CA, MAS and SI are incorporated into and simulate influencing each other and interacting between the microcosmic entity together.
The present invention implements simulation and optimization by defining three class interaction rules.In CA, the interaction rule is called transformation rule again.These rules can not satisfy the application demand of MAS and AI fully, need a more general interaction rule to satisfy the widespread use of simulative optimization in the real world, and then the mutual relationship between reflection entity and their the residing external environment, determine the variation of their state, position and environment.
Core of the present invention is these interaction rule sets.Interactional intensity is relevant with space length between the entity, so introduce the basis of the law of universal gravitation as these rules of definition.The interaction rule set here comprises three subclass: F~(F
CA, F
SocialAgent, F
AnimalAgent), F
CABe used for representing the interaction rule (transformation rule) of CA, only consider natural factor.When usually studying the influence factor of state transitions of CA in fact, some natural factors based on the field function (for example degree of getting close to mutually and the position between the cellular) need be combined.F
SocialAgentBe used for representing the interaction rule between social intelligence's body (people or all kinds of tissue) and their the residing environment.City and economic theory are used to define the behavior of this class intelligence body usually.F
AnimalAgentBe used for being characterized in the artificial bio-membrane that seeks under the optimum solution route and the interaction rule between its external environment.Simple biological intelligence is used to guide the activity of these artificial bio-membrane's entities.
Although the degree of concern that is subjected to of MAS is greater than CA in recent years, still the can yet be regarded as important means of Simulation of Complex city dynamic change of CA.Isolated utilization MAS or CA be the good natural system of Simulation of Complex.CA can effectively catch the diffusion or the differentiation of geographical phenomenon, and its distinctive attribute has determined it can accomplish the simulate effect that MAS does not accomplish.The correlation technique of utilization GIS can well define and calculate the related physical factor of CA.Simultaneously, CA can solve the complex system simulation problem under the effect of multiple physical agent combined influence easily.
MAS can use removable intelligent body to represent the decision behavior of the mankind or tissue, is applicable to manual simulation's analogue system.The human interaction behavior of system simulation is subjected to the influence of its external environment.CA impliedly represents this interaction by substituting of natural quality variable.Yet MAS can well define influence between the mankind and the social factor for the utilization of removable intelligent body, strengthens the dirigibility in the space search.Thereby, CA and MAS are combined the complicated geographical process that can better simulate under many natures or the human factor influence.
The present invention introduces SI and further strengthens the optimization ability.Space optimization in the geography is usually directed to maximum population's coverage rate and minimum total travel distance thus problem.Facility addressing and its correlation model generally include position-allocation models and median problem, for example the NP difficult combinations optimal problem known of people.Artificial intelligence approach integrated into can well solve various point-like addressings and linear programming problem.
Realization of the present invention mainly comprises five steps: 1) by domain knowledge or local experience are excavated and define the interaction rule; 2) obtain starting condition, for example state and environment; 3) utilize the interaction rule to simulate and optimize; 4) come update mode, position and environment according to iterations; 5) will simulate with optimization and be coupled.
The 1st) step is to define the interaction rule by different Data Mining Tools.The spatial data that obtains from GIS can be used for defining the original state of cellular and landscape environment
(E
0).The state transitions rule is the key problem of CA.And sports rule determined intelligent body according between them or and its environment between mutual, how in the space, to move constantly at each.Definition interaction rule is the key point of GeoSOS operation.Some Knowledge Discovery instruments (M) can be used for obtaining these rules (F from training data (D)
CA, F
SocialAgent, F
AnimaLAgent).These empirical datas can obtain from GIS and remotely-sensed data storehouse.For the difference between simulated conditions and the reality being reduced to minimum, can use ' the method for trial and error '.Data digging method such as logistic regression, neural network and machine learning can be applied to these interaction rules of auxiliary definition.The general layout that simulation is come out will be carried out stacked analysis with actual general layout, verify by point-to-point mode.In addition, the similarity of general layout is primary under a lot of situations, therefore also can verify by a series of landscape indexes.
And the simulative optimization task need realize by following formula:
M:D(F
CA,F
SocialAgent,F
AnimalAgent) (3)
To simulate and optimize coupling, formula (6) and (7) can further be revised as:
The logical architecture that geographical simulation of the present invention and optimization system being embodied as in computing machine adopts presentation layer, logical layer, data Layer three-tier architecture to represent system;
Described presentation layer comprises user interface and data input/output interface;
Described logical layer comprises cellular automaton analog module, multi-agent system analog module, geographical space analysis optimization module, system model storehouse, and adopts the conventional data bus to carry out the data sharing between disparate modules and mutual in the logical layer;
Described data Layer obtains and required data is provided, and comprising: remotely-sensed data, GIS data, socioeconomic data, and expanding data;
Described number of data layers is reportedly passed logical layer and is analyzed and calculate, and presents to the user by logical layer.
The system model storehouse of described logical layer is provided with correlation models such as logistic regression simulation, neuron network simulation, and other extendability assembly.
The cellular automaton analog module of described logical layer is achieved as follows operation:
(1) transformation rule extracts
Extract transformation rule according to the model of selecting, can extract according to existing remotely-sensed data, leaching process also comprises functions such as model parameter calibration, to guarantee to extract the highest transformation rule of precision;
(2) simulation and forecast
According to the transformation rule that extracts, carry out the simulation or the prediction of geographical phenomenon.For example can carry out the simulation of Future Development trend, after reaching a certain default predicted condition, just finish forecasting process according to current transformation rule and remotely-sensed data;
(3) sunykatuib analysis evaluation
After carrying out the transformation rule extraction, Simulation result and actual result are compared and estimate, effect with the check simulation, and produce evaluation result intuitively, the user adjusts the parameter of transformation rule by evaluation result, carry out simulated experiment once more, through repeatedly circulating repeatedly the final transformation rule that obtains optimum;
(4) model contrast
The comparing function of simulate effect between supplying a model finds optimum transformation rule by contrast.
Aforesaid operations (2) also is included in real-time delta data is provided in the simulation and forecast process, mode with visual or textization is presented to the user simultaneously, to make things convenient for the user to grasp the process of real-time change, in urban land use change modeling process, can also produce the real-time inversion cuver of different land use type, with the continuous variation of reflection urban development.
The multi-agent system analog module of described logical layer is realized following operation:
(1) multiple agent and definition
The instrument of definition multiple agent is provided, determines intelligent body entity and behavior specific geographic environment under by the user, the while can also produce the simulation of the geographical phenomenon that the intelligent body that meets definition carries out;
(2) based on the simulation of multi-agent system
Simulation based on multi-agent system will utilize multi-agent system and cellular automaton simulation in conjunction with carrying out the simulation of geographical phenomenon, according to the entity and the behavior of the multiple agent that defines, the cellular automaton simulation be simulated and will be predicted as environmental factor;
(3) sunykatuib analysis evaluation
After using multiple agent combine to simulate or predict with the cellular automaton simulation, Simulation result is compared and estimates, check the effect of simulating.
What the geographical space analysis optimization module of described logical layer realized is operating as: under computer environment, finish geographical space analyze in the application of various optimized Algorithm or means, various prioritization schemes are used and are produced the optimization result in real data, excellent user interface is provided simultaneously, make things convenient for the user to be optimized the setting of parameter, and will optimize the result and export and use.
The data sharing of described logical layer is carried out mutual data interaction with the mutual uniform data format that adopts.
The invention has the advantages that: the cellular automaton that will disperse at present, multi-agent system and the geographical knowledge of optimizing have been carried out the integration of system, have constructed geographical simulation and optimization system; Geographical simulation is organically combined with optimizing knowledge and soft project thought and technology, realize from the software angle.
Description of drawings
Fig. 1 is a software architecture synoptic diagram of the present invention.
Embodiment
The present invention is described further below in conjunction with accompanying drawing.
Software architecture synoptic diagram of the present invention comprises presentation layer, logical layer and data Layer as shown in Figure 1.
Presentation layer is the superiors of system, and is directly mutual with the user.The availability of the design decision system interface of presentation layer and information input and the reliability of showing.It mainly finishes input, display system information and system's execution result output etc. of user instruction.Data presentation mainly be the data that system is read in and analyze in the process data, the result data that produce show.Data output can be output as the data that the user needs the form of appointment.
Logical layer is finished the core business logic of system, as various analyses in the system simulation and calculating etc., is the core and the key of system.The external manifestation of logical layer is the functional of system.Simultaneously, logical layer carries out data interaction and processing between presentation layer and data Layer.
The service logic that geographical simulation optimizing system is handled mainly comprises four parts: cellular automaton CA simulation, multi-agent system MAS simulation, geographical space optimization and simulation with optimize alternately.Different parts will design as different Component Galleries and make up.
The CA simulation mainly is to utilize cellular automaton to carry out work such as geographical phenomenon simulation, prediction according to transformation rule.Multiple agent simulation mainly is to utilize multi-agent system (MAS) and carry out geographical phenomenon simulation and prediction in conjunction with CA etc.Geoanalysis optimization partly is the application at the various optimisation strategy that proposed in the current geoanalysis.
Because what geographical simulation optimizing system was paid attention to is combining closely between geographical simulation and geographical the optimization, simulation can utilize mutually with the result who optimizes, and promotes mutually.Therefore, when system constructing, adopted the notion of " conventional data bus " to carry out the data sharing of Different Logic intermodule with mutual.The result of Simulation result and optimization can use the mode of " conventional data bus " similar industrial production line to carry out mutual transmission and promotion in internal system, finally reaches simulation and optimization result's optimum.
Simultaneously, the geographical simulation optimizing system theory has developed a lot of model methods, as logistic regression simulation, neuron network simulation method, based on data mining method etc.These models and method can be placed in the model bank logic module, call when needs use.Simultaneously, model bank also is independent of other modular assembly of system, can carry out independent modification and expansion, with the extendability of enhanced system.
The bottom of framework is a data Layer, is responsible for obtaining and provides data required data.The operable data source of system comprises: remotely-sensed data, GIS data, socioeconomic data or other data.Data Layer will obtain these data, pass to logical layer analysis, calculate, and finally present to the user.
In the total system framework, the user carries out the input of geographical simulation task by presentation layer, system passes to logical layer with order, obtain the data that analysis need be used by logical layer by data Layer, use corresponding logic module simultaneously, call corresponding model, carry out the transmission of intermodular data by the exchanges data bus, thereby obtain simulation, analysis and prediction result, and the result is represented to the user by presentation layer.If necessary, the intermediate result of analyzing can also be preserved by data Layer.
Simultaneously, when the structure of concrete assembly, follow the principle of object based programming, need be according to the corresponding object of different entity division (class), and set up mutual relationship between the class.
The function that software is realized is as follows:
Geographical simulation optimizing system need carry out simulation, the prediction of complicated geographical phenomenon and optimize.According to consequent systemic-function demand, the geographic model system mainly comprises a plurality of functional modules.
1, subscriber interaction component
Subscriber interaction component is finished the mutual of system and user, obtains user's input information and output system information and presents to the user.Comprise:
(1) data input
The data input function is read in data or the configuration information that geographical simulation optimizing system needs from the system outside, may be that the user imports or from the data source reading of data, for the data support is carried out in the systematic analysis of next carrying out.
(2) data presentation
This function shows raw image data in the system (as remotely-sensed data) and analog result with visual way, intuitively browse for the user.Text data uses the form of text to show, and other data (as the middle achievement data in the simulation) can display dynamically by visual control.
(3) data output
System can be output as image, text or other forms with data and the analysis result that produces in the analytic process, uses for the user.System can also provide general utility functionss such as printing, data derivation will export information such as result and export as outside achievement.
2, CA simulated assembly
The geographical phenomenon simulation based on cellular automaton is carried out in the CA simulation.The general step of CA simulation is to select proper model or method to carry out the extraction of CA transformation rule, carries out the simulation and the prediction of geographical phenomenon according to the transformation rule that obtains then.Therefore, the CA simulated assembly mainly comprises following function:
(1) the CA transformation rule extracts
System can extract transformation rule according to model of selecting or method, extracts according to existing real data (generally being the remotely-sensed data of multidate).Leaching process also comprises functions such as model parameter calibration, to guarantee to extract the highest transformation rule of precision.
(2) simulation and forecast
According to the transformation rule that extracts, can carry out the simulation and forecast of geographical phenomenon.System will carry out the simulation of Future Development trend according to current transformation rule and experimental data, after reaching a certain default predicted condition, just finish forecasting process, at last the analysis that also will provide correlation function to predict the outcome.
System can provide real-time delta data in the simulation and forecast process, presents to the user simultaneously in the mode of visual or textization, grasps the process of real-time change to make things convenient for the user.In urban land use change modeling process, system can produce the real-time inversion cuver of different land use type, with the continuous variation of reflection urban development.
(3) sunykatuib analysis evaluation
After carrying out the transformation rule extraction, Simulation result and actual result need be compared and estimate, with the effect of check simulation.System will provide the instrument of interpretation of result and evaluation, carry out the comparison (as using the pointwise pairing comparision) of precision, and produce evaluation result intuitively.The user can adjust the parameter of transformation rule by evaluation result, carries out simulated experiment once more, through repeatedly circulating repeatedly the final transformation rule that obtains optimum.
(4) model contrast
Based on the extraction of CA transformation rule, existing at present a lot of ripe researchs.At a certain specific survey region, may a certain specific method can obtain best simulate effect.Therefore, need carry out the contrast of multiple model and method, to determine that being best suited for this regional transformation rule simulates and predict.The comparing function of simulate effect between system will supply a model finds optimum transformation rule by contrast.
3, multi-agent system simulated assembly
By between the microcosmic intelligence body and and surrounding environment between interaction, in conjunction with cellular automaton, can better simulate the variation of geographical phenomenon from bottom to top.Therefore, the simulation based on multi-agent system mainly comprises following function:
(1) multiple agent and definition
Agent is the entity that has capacity of will in virtual environment, can carry out relevant decision-making.In different geographical simulation environment, need definition different intelligent body and decision behavior thereof.System will provide the instrument of definition multiple agent, determine intelligent body entity and behavior under the specific geographic environment by the user.Can also produce simultaneously the simulation of the geographical phenomenon that the intelligent body that meets definition carries out.
(2) based on the simulation of multi-agent system
Simulation based on multi-agent system will utilize multi-agent system and CA in conjunction with carrying out the simulation of geographical phenomenon.System simulates CA and predict as environmental factor according to the entity and the behavior of the multiple agent of definition.
(3) sunykatuib analysis evaluation
After using multiple agent combine to simulate or predict with CA, also to compare and estimate Simulation result, check the effect of simulating.System will provide the sunykatuib analysis evaluation of result function of similar CA simulation equally.
4, geoanalysis optimizational function assembly
Geoanalysis optimization mainly under computer environment, finish geographical space analyze in the application of various optimized Algorithm or means.System uses various prioritization schemes and produces the optimization result in real data.As ant colony optimization algorithm being applied in space Dynamic Location, the dynamic route selection of road.
System will provide excellent user interface, make things convenient for the user to be optimized the setting of parameter, and will optimize the result and export and use.
5, simulative optimization interactive function assembly
One big characteristics of geographical simulation optimizing system are with geographical simulation and optimize organic, seamless combining, and the result of geographical simulation and optimization can be used mutually, reach simulation and the unification of optimizing.
Therefore, simulation and the result who optimizes will adopt uniform data format, to carry out mutual data interaction.The geographical result who optimizes can offer geographical simulation and use, and improves the effect of geographical simulation.Equally, geographical simulation has also reflected geographical optimization effect.System provides support to this at functional hierarchy, makes the user of system carry out interactive operation easily, finishing simulation and optimizing of task.
6, systemic-function assembly
(1) system's setting
System can carry out the configuration of each functional module parameter, the configuration of model bank parameter, can also carry out the setting about the service function of system own simultaneously.
(2) localization is supported
System supports localization, can provide multilingual version (English, simplified Chinese character and traditional Chinese language version are arranged at present), to satisfy the international requirement of user.
(3) system update
System also will provide the function of automatic renewal, can in time find the renewal of version and be updated to latest edition automatically, guarantee that the user uses up-to-date software version.Also provide more new record with the variation of version of display after upgrading simultaneously.
(4) help
System will provide perfect help document, help the user to understand and using system.Simultaneously, in system used, help system was combined in the concrete operations, helps the better using system of user by modes such as explanation intuitively are provided.
Claims (11)
1. a geographical simulation optimizing system is characterized in that comprehensive cellular automaton, and multi-agent system and biological intelligence are simulated, predict, optimized and show geographic patterns and process;
Described cellular automaton, multi-agent system and biological intelligence are incorporated into simulates influencing each other and interacting between the microcosmic entity together, and is defined as:
Wherein, S
i tAnd L
i tWhat represent is state and the position of entity i, and described entity comprises static cellular and removable intelligent body, and removable intelligent body further is subdivided into social intelligence's body and biological intelligence body, and Et and F are used for characterizing environment and interaction rule set respectively;
Described interaction rule set comprises three subclass: F~(F
CA, F
SocialAgent, F
AnimalAgent), F wherein
CABe used for representing the interaction rule of static cellular, F
SocialAgentBe used for representing the interaction rule between social intelligence's body and their the residing environment, F
AnimalAgentBe used for interaction rule between characterising biological intelligence body and its external environment.
2. geographical simulation optimizing system according to claim 1 is characterized in that the realization of system comprises following five steps:
(1) definition interaction rule is obtained interaction rule set (F by Knowledge Discovery instrument M from training data D
CA, F
SocialAgent, F
AnimalAgent), and training data D can obtain from GIS and remotely-sensed data storehouse;
(2) obtain starting condition;
(3) utilize the interaction rule to simulate and optimize;
(4) come update mode, position and environment according to iterations;
(5) will simulate with optimization and be coupled.
3. geographical simulation optimizing system according to claim 2 is characterized in that described step (3) to (5) realizes by following formula:
M:D→(F
CA,F
SocialAgent,F
AnimalAgent) (3)
4. according to the described geographical simulation optimizing system of claim 3, it is characterized in that described formula (6), (7) are through simulation and optimize coupling, further are revised as:
5. according to claim 1 or 2 or 3 or 4 described geographical simulation optimizing systems, it is characterized in that the logical architecture that being embodied as in computing machine adopts presentation layer, logical layer, data Layer three-tier architecture to represent system;
Described presentation layer comprises user interface and data input/output interface;
Described logical layer comprises cellular automaton analog module, multi-agent system analog module, geographical space analysis optimization module, system model storehouse, and adopts the conventional data bus to carry out the data sharing between disparate modules and mutual in the logical layer;
Described data Layer obtains and required data is provided, and comprising: remotely-sensed data, GIS data, socioeconomic data, and expanding data;
Described number of data layers is reportedly passed logical layer and is analyzed and calculate, and presents to the user by logical layer.
6. geographical simulation optimizing system according to claim 5 is characterized in that the system model storehouse of described logical layer is provided with logistic regression simulation, neuron network simulation correlation model.
7. geographical simulation according to claim 6 and optimization system is characterized in that the cellular automaton analog module of described logical layer is achieved as follows operation:
(1) transformation rule extracts
Extract transformation rule according to the model of selecting, extract according to existing remotely-sensed data, leaching process also comprises the model parameter calibration operation, to guarantee to extract the highest transformation rule of precision;
(2) simulation and forecast
According to the transformation rule that extracts, carry out the simulation and forecast of geographical phenomenon, according to current transformation rule and remotely-sensed data, carry out the simulation of Future Development trend, after reaching a certain default predicted condition, just finish forecasting process;
(3) sunykatuib analysis evaluation
After carrying out the transformation rule extraction, Simulation result and actual result are compared and estimate, effect with the check simulation, and produce evaluation result intuitively, the user adjusts the parameter of transformation rule by evaluation result, carry out simulated experiment once more, through repeatedly circulating repeatedly the final transformation rule that obtains optimum;
(4) model contrast
The comparing function of simulate effect between supplying a model finds optimum transformation rule by contrast.
8. geographical simulation according to claim 7 and optimization system, it is characterized in that described operation (2) also is included in provides real-time delta data in the simulation and forecast process, mode with visual or textization is presented to the user simultaneously, to make things convenient for the user to grasp the process of real-time change, in urban land use change modeling process, can also produce the real-time inversion cuver of different land use type, with the continuous variation of reflection urban development.
9. geographical simulation according to claim 5 and optimization system is characterized in that the multi-agent system analog module of described logical layer is realized following operation:
(1) multiple agent and definition
The instrument of definition multiple agent is provided, determines intelligent body entity and behavior specific geographic environment under by the user, the while can also produce the simulation of the geographical phenomenon that the intelligent body that meets definition carries out;
(2) based on the simulation of multi-agent system
Simulation based on multi-agent system will utilize multi-agent system and cellular automaton simulation in conjunction with carrying out the simulation of geographical phenomenon, according to the entity and the behavior of the multiple agent that defines, the cellular automaton simulation be simulated and will be predicted as environmental factor;
(3) sunykatuib analysis evaluation
After using multiple agent combine to simulate or predict with the cellular automaton simulation, Simulation result is compared and estimates, check the effect of simulating.
10. geographical simulation according to claim 5 and optimization system, what it is characterized in that the geographical space analysis optimization module of described logical layer realizes is operating as: under computer environment, finish geographical space analyze in the application of various optimized Algorithm or means, various prioritization schemes are used and are produced the optimization result in real data, excellent user interface is provided simultaneously, make things convenient for the user to be optimized the setting of parameter, and will optimize the result and export and use.
11. geographical simulation according to claim 5 and optimization system is characterized in that the data sharing of described logical layer and adopt uniform data format to carry out mutual data interaction alternately.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008102198242A CN101419623B (en) | 2008-12-09 | 2008-12-09 | Geographical simulation optimizing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008102198242A CN101419623B (en) | 2008-12-09 | 2008-12-09 | Geographical simulation optimizing system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101419623A CN101419623A (en) | 2009-04-29 |
CN101419623B true CN101419623B (en) | 2010-09-08 |
Family
ID=40630412
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2008102198242A Expired - Fee Related CN101419623B (en) | 2008-12-09 | 2008-12-09 | Geographical simulation optimizing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101419623B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184328A (en) * | 2011-05-10 | 2011-09-14 | 南京大学 | Method for optimizing land use evolution CA model transformation rules |
CN102256327B (en) * | 2011-07-04 | 2014-01-22 | 南京邮电大学 | Self-adaptive topology control method for wireless sensor network |
CN102289581A (en) * | 2011-08-10 | 2011-12-21 | 武汉大学 | Method for simulating city expansion based on space function division |
CN102663512A (en) * | 2012-03-07 | 2012-09-12 | 同济大学 | Simulation prediction method for dynamic evolution simulation of urban greenbelt |
CN102722570B (en) * | 2012-06-04 | 2014-09-03 | 武汉大学 | Artificial immunity intelligent optimization system facing geographical space optimization |
CN104156618B (en) * | 2014-08-25 | 2019-02-05 | 南京田申田信息系统有限公司 | Economic data automatic analysis system based on map |
CN105550365A (en) * | 2016-01-15 | 2016-05-04 | 中国科学院自动化研究所 | Visualization analysis system based on text topic model |
CN109857462B (en) * | 2019-01-25 | 2021-07-09 | 东莞理工学院 | Background Docker task mapping method of remote sensing image visual editor |
CN110490787A (en) * | 2019-07-25 | 2019-11-22 | 沈振江 | A kind of method for building up of the multiple agent model of residential location choice |
-
2008
- 2008-12-09 CN CN2008102198242A patent/CN101419623B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN101419623A (en) | 2009-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101419623B (en) | Geographical simulation optimizing system | |
CN1987906B (en) | Method for dynamicaly predicting land use change | |
Ashour | Optimizing creatively in multi-objective optimization | |
CN102750732A (en) | Land resource utilization change dynamic prediction model based on GIS (Geographic Information System) and using method of dynamic prediction model | |
Jiang et al. | Generative urban design: A systematic review on problem formulation, design generation, and decision-making | |
Dai et al. | Agent-based model of land system: Theory, application and modelling framework | |
CN104732091A (en) | Cellular automaton river bed evolution prediction method based on natural selection ant colony algorithm | |
CN102722570B (en) | Artificial immunity intelligent optimization system facing geographical space optimization | |
Cao | [Retracted] Application Research and Case Analysis of Landscape Design in Artificial Intelligence Platform | |
Bollinger et al. | Facilitating model reuse and integration in an urban energy simulation platform | |
Grobman et al. | Computer-based form generation in architectural design—a critical review | |
Liu et al. | Research on the application mode of green environment design under the background of artificial intelligence | |
Caneparo | Semantic knowledge in generation of 3D layouts for decision-making | |
Liu et al. | Visualization system of Hlai ethnic village landscape design based on machine learning | |
Umoh et al. | A Review of Smart Green Building Technologies: Investigating The Integration And Impact of AI And IOT in Sustainable Building Designs | |
Cheng | Significance of Digital Landscape Architecture | |
Yang et al. | Cellular automata for studying historical spatial process of traditional settlements based on gaussian mixture model: a case study of Qiaoxiang village in Southern China | |
Gan et al. | UDGAN: A new urban design inspiration approach driven by using generative adversarial networks | |
Luca | Generative platform for urban and regional design | |
Zhang et al. | A systematic review of urban form generation and optimization for performance-driven urban design | |
Kimm | Classes of AI tools, techniques, and methods | |
Yang et al. | Construction and Application of a Landscape Design Teaching Platform Driven by Artificial Intelligence | |
Sudhira | Integration of agent-based and cellular automata models for simulating urban sprawl | |
Schaller et al. | GIS model applications for sustainable development and environmental planning at the regional level | |
Danylov | Information model of analysis of city as a complex dynamic system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100908 Termination date: 20121209 |