CN108876210A - A kind of recognition methods, system and the device of land use and change causal structure - Google Patents
A kind of recognition methods, system and the device of land use and change causal structure Download PDFInfo
- Publication number
- CN108876210A CN108876210A CN201810898406.4A CN201810898406A CN108876210A CN 108876210 A CN108876210 A CN 108876210A CN 201810898406 A CN201810898406 A CN 201810898406A CN 108876210 A CN108876210 A CN 108876210A
- Authority
- CN
- China
- Prior art keywords
- land use
- causal structure
- data
- change
- 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.)
- Pending
Links
- 230000001364 causal effect Effects 0.000 title claims abstract description 86
- 230000008859 change Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012360 testing method Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 18
- 238000005204 segregation Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 235000013399 edible fruits Nutrition 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004387 environmental modeling Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 239000002689 soil Substances 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 230000009850 completed effect Effects 0.000 description 1
- 230000021615 conjugation Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003455 independent Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses recognition methods, system and the devices of a kind of land use and change causal structure, and this approach includes the following steps：Obtain the data of the land use pattern variation of several periods in survey region and the data of impact factor；The data of the data and impact factor that are changed using land use pattern construct causal structure network as model variable；Based on the causality between each model variable in PC algorithm identification causal structure network, carsal graph model is obtained.The present invention comprehensively considers the relationship in survey region between land use pattern variation and impact factor, using the causality between each model variable in PC algorithm identification causal structure network, can efficiently identify causal structure between land system variable；This method can integrate the variation of each land use pattern in land system and not influence each factor of land use and change between homologous ray, be more in line with the complexity feature of land system.The present invention can be widely applied to environmental modeling field.
Description
Technical field
The present invention relates to environmental modeling field, especially a kind of recognition methods of land use and change causal structure, system
And device.
Background technique
Soil is carrier for the survival of mankind, is the important natural resources for supporting human being's production and life.Land system
It is related to the multifaceted factor such as society, economy, ecological environment, close association population, resource, grain security and environment etc. are multiple complete
Ball focal issue.When whole world change faces a severe challenge, by the cause and effect for deeply, meticulously studying man_land coupling system
Structure and reciprocation promote the development of land system theory and application, provide deep thinking for global change research due.
Land system is the dynamical system of people and soil interaction composition, thus in essence, the change of land system
The reason of changing substantially derived from two aspects:(1) in the different times of socio-economic development, people to the type of land output or
The demand of quantity changes, thus caused land use and change, can be referred to as endogenous variation or initiative variation；(2)
Since nature or artificial origin cause the attribute in soil to change, or social groups' target changes, and forces people not
The Land use systems for not changing land system are obtained, exophytic variation or passivity variation can be referred to as.
Currently, there is the method for two classes identification land use and change causal structure, first kind method is STOCHASTIC CONTROL experiment side
Method.Control is usually directed to the ability of the substitution value of the purposive some variables of setting of researcher, then compares these substitutions and sets
The effect of meter.Control experiment is widely used in the causal structure for identifying small scale land use change survey and driven factor, controls
System experiment is by being subject to artificial control to certain driving empirical factors.This method is only applicable to microcosmic probe into causal structure
Research, experimental result cannot be extrapolated to more large scale, the research of large spatial scale long time scale cannot be carried out.And
The variation of the land use change survey of land system and its mankind and natural driving factors often will be by least many decades ability
Show.In Large-scale areas, most applied statistics model carries out the identification of land use and change causal structure, such as principal component point
Analysis, structure equation models and Spatial Regression Model etc..
The limitation of these statistical models is：(1) correlation analysis cannot identify cause and effect, these statistics based on correlation analysis
Model can not identify land use and change causal structure；It (2) is independently of one another, not hand between these model hypothesis model independents variable
Interaction, therefore they are also independent for the response of dependent variable.However, in true land system, different soils
It often interacts between utilization and between driving factors, is interactional, these hypothesis have violated true land system
Complexity.Therefore, it needs to establish the new method for identifying land use and change causal structure.
Summary of the invention
In order to solve the above technical problems, it is an object of the invention to：There is provided one kind being capable of cause and effect between identification model variable
Relationship and the recognition methods of land use and change causal structure, system and the device for being more in line with land system complexity.
The first technical solution adopted by the present invention is：
A kind of recognition methods of land use and change causal structure, includes the following steps：
Obtain the data of the land use pattern variation of several periods in survey region and the data of impact factor；
The data of the data and impact factor that are changed using land use pattern construct causal structure net as model variable
Network；
Based on the causality between each model variable in PC algorithm identification causal structure network, carsal graph model is obtained.
Further, further comprising the steps of：
The data of data and impact factor to the variation of the land use pattern of acquisition carry out normal distribution-test, to not being inconsistent
The data for closing normal distribution carry out normal transformation.
Further, the causality based between each model variable in PC algorithm identification causal structure network, this
Step specifically includes：
Determine to close between any two model variable with the presence or absence of cause and effect in causal structure network by conditional independence tests
System；
By the identification of D law of segregation, there are the cause and effect directions between causal any two model variable.
Further, it is described by conditional independence tests determine in causal structure network between any two model variable whether
There are causality, the step for specifically include：
Further, it is described by conditional independence tests determine in causal structure network between any two model variable whether
There are causality, the step for specifically include：
The conditional mutual information value in causal structure network between any two model variable is calculated, judges the condition mutual trust
Whether breath value is greater than given threshold, if so, determining that there are causalities between two model variables；Conversely, then determining to be somebody's turn to do
Causality is not present between two model variables.
Further, the calculation formula of the conditional mutual information value is：
Wherein, X, Y and Z are three disjoint variables sets, I (X, Y | Z) indicate in the case where specified criteria Z X and Y it
Between conditional mutual information value, r, q and s respectively indicate the value number of X, Y and Z, and P () is probability function, xiIndicate i-th of X
Value, yjIndicate j-th of value of Y, zkIndicate k-th of value of Z.
Further, the carsal graph model includes between the node of several model variables and several expression model variables
The side of relationship.
Second of technical solution adopted by the present invention be：
A kind of identifying system of land use and change causal structure, including：
Module is obtained, the data and influence that the land use pattern for obtaining several periods in survey region changes
The data of the factor；
Construct module, the data of data and impact factor for changing using land use pattern are as model variable, structure
Build causal structure network；
Identification module, for obtaining based on the causality between each model variable in PC algorithm identification causal structure network
To carsal graph model.
Further, further include：
Inspection module, for the data of the land use pattern variation to acquisition and the data progress normal state point of impact factor
Cloth is examined, and carries out normal transformation to the data for not meeting normal distribution.
Further, the identification module includes：
Causality judging unit, for determining that any two model becomes in causal structure network by conditional independence tests
It whether there is causality between amount；
Cause and effect direction discernment unit, for there are causal any two model variables by the identification of D law of segregation
Between cause and effect direction.
The third technical solution adopted by the present invention is：
A kind of identification device of land use and change causal structure, including
Memory, for storing program；
Processor executes a kind of recognition methods of land use and change causal structure for loading described program.
The beneficial effects of the invention are as follows：The present invention comprehensively considers land use pattern variation and impact factor in survey region
Between relationship can effectively be known using the causality in PC algorithm identification causal structure network between each model variable
Causal structure between other land system variable, the defect of correlativity between land system variable can only be identified by compensating for conventional method；
This method can integrate the variation of each land use pattern in land system and not influence land use and change between homologous ray
Each factor, based on system combination visual angle identification variable between causal structure, be more in line with the complexity feature of land system, this
Invention can provide accurate technical support for the specified of land policy.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the recognition methods of land use and change causal structure of the present invention；
Fig. 2 is a kind of cause-and-effect diagram；
Fig. 3 be in a kind of specific embodiment of the present invention Guangdong province, 2005 to the cause and effect of land use and change between 2010
Figure.
Specific embodiment
The present invention is further detailed with specific embodiment with reference to the accompanying drawings of the specification.
Referring to Fig.1, a kind of recognition methods of land use and change causal structure, including step S100, S200 and S300.
Before executing the following steps, need first artificial setting model it is assumed that the assumed condition of model includes：(1) model
Variable meets normal distribution；(2) in order to guarantee the validity of data, a conspicuousness water will be arranged to conditional independence tests in we
Level values.Usually take α<0.05 or α<0.01.This shows that a possibility that its model is correct (probability) is 95% or 99%.
The number of data and impact factor that S100, the land use pattern for obtaining several periods in survey region change
According to.
Such as between collecting 2005 to 2010 years, the data of land use pattern variation and relevant impact factor.And it influences
The factor can be natural environmental factors, such as temperature or height above sea level, and impact factor is also possible to the social factor, such as GDP, soil
Policy or Engel coefficient etc..
S200, using land use pattern change data and impact factor data be used as model variable, building cause and effect knot
Network forming network.The causal structure network wherein constructed includes all model variables, sets when initial and deposits between all model variables
It is contacting.Wherein the relationship in causal structure network between model variable is indicated with side.Institute in the causal structure network just constructed
It is all connected together with side between some model variables, in subsequent identification process, will be determined as no causal two
Edge contract between variable.
S300, the causality in causal structure network between each model variable is identified based on PC algorithm, obtains cause-and-effect diagram
Model.PC algorithm is that Peter Spirtes and Clark Glymour invent a kind of algorithm, and PC algorithm can recognize that system becomes
The relevant information of causal structure between amount.The algorithm can identify the possible yes or no land use pattern variation of which variable
There may be or there is no causal structures between reason and the factor of influence land use pattern variation.PC algorithm is based on oriented
The mode of acyclic figure realizes the study to causal structure.As shown in Fig. 2, each land use pattern variation in land system
And in the system of impact factor composition, the causal structure between this system internal variable can be indicated with a directed acyclic graph,
This directed acyclic graph is exactly cause-and-effect diagram, and wherein V1, V2, V3 and V4 respectively represent a variable, the causal structure between each variable
It is to be indicated by directed edge, and the conditional probability distribution of available each variable.
The PC algorithm of the present embodiment can realize in R language, using the pcalg software package of R language can be used for completing because
The building of fruit graph model.
As preferred embodiment, in order to guarantee it is that all data all meet model it is assumed that the present embodiment further include with
Lower step：
S101, normal distribution-test is carried out to the data of land use pattern variation and the data of impact factor of acquisition,
Normal transformation is carried out to the data for not meeting normal distribution.Because model variable needs to meet normal distribution, increase this step
Suddenly it can guarantee the validity of data.
As preferred embodiment, the step S300 includes：
301, by conditional independence tests determine in causal structure network between any two model variable with the presence or absence of because
Fruit relationship；
Can be determined in this step by conditional independence tests in causal structure network any two model variable it
Between whether there is causality.When finding that causality is not present between two model variables, then delete in causal structure network,
Side between two model variables.There are two types of common conditional independence test methods, the first is chi square test, is for second
Conditional mutual information test.
302, by the identification of D law of segregation, there are the cause and effect directions between causal any two model variable.
Wherein, D law of segregation is a kind of graphic method for the cause and effect direction between judgment variable.
In D law of segregation, it is assumed that X, Y and Z are the Node subsets of three separation in cause-and-effect diagram.If every from X to Y
Paths all deposit a node W and meet following one of condition, then ZD is claimed to separate X and Y.
1) W is in Z, and an arrow is directed toward W, and another arrow comes out from W, i.e. X → W → Y；
2) W is in Z, and two arrows are all pointed out from W, i.e. X ← W → Y；
3) for the offspring of W and W not in Z, two arrows all point to W, i.e. X → W ← Y.
In cause-and-effect diagram, if ZD separates X and Y, under conditions of given Z, X and Y are independent.
As preferred embodiment, the step S301 is specially：
The conditional mutual information value in causal structure network between any two model variable is calculated, judges the condition mutual trust
Whether breath value is greater than given threshold, if so, determining that there are causalities between two model variables；Conversely, then determining to be somebody's turn to do
Causality is not present between two model variables.The given threshold can be 0.95 or 0.99.
Mutual information is defined as follows：
If X and Y is two disjoint variables sets, then the mutual information of X and Y is：
Wherein r and q is the value number of X and Y, and P () is probability function, and I (X, Y) indicates the association relationship between X and Y,
That is the degree of dependence between X and Y.Conjugation condition probability function and association relationship can derive conditional mutual information value.
The concept of conditional mutual information is as follows：
If X, Y and Z are 3 disjoint variables sets, then under conditions of giving Z, the conditional mutual information of X and Y are：
The calculation formula of the conditional mutual information value is：
Wherein, X, Y and Z are three disjoint variables sets, I (X, Y | Z) indicate in the case where specified criteria Z X and Y it
Between conditional mutual information value, i.e., in the case where specified criteria Z X and Y degree of dependence, r, q and s respectively indicate taking for X, Y and Z
It is worth number, P () is probability function, xiIndicate i-th of value of X, yjIndicate j-th of value of Y, zkK-th of expression Z takes
Value.
About conditional probability function P (), for single stochastic variable, its probability point is indicated with probability function P (X)
Cloth, for multiple stochastic variable X1,X2,……Xn, usually use joint probability distribution function P (X1,X2,……Xn) indicate variable
The probability of all combinations of states, and the sum of all functional values are 1.
If two stochastic variables X, both Y are independent, i.e., variation Y, variable Y do not nor affect on variable X, then have variable X
Following formula is set up：
P (X, Y)=P (X) P (Y)；
If multiple stochastic variable X1,X2,……XnIndependently of each other, then have：
P(X1,X2,……Xn)=P (X1)P(X2)……P(Xn)；
If known two stochastic variables X and Y, then conditional probability of the X at given Y is：
P (X/Y)=P (X, Y)/P (Y)；
Conditional probability distribution of the stochastic variable Y at condition { X=x } refer to when known X value be some particular value x it
When, the probability distribution of Y.
As preferred embodiment, in order to intuitively show the causal structure of land use and change, the cause and effect to people
Graph model includes the side of relationship between the node of several model variables and several expression model variables.
A kind of corresponding identifying system of recognition methods of land use and change causal structure with Fig. 1, including：
Module is obtained, the data and influence that the land use pattern for obtaining several periods in survey region changes
The data of the factor；
Construct module, the data of data and impact factor for changing using land use pattern are as model variable, structure
Build causal structure network；
Identification module, for obtaining based on the causality between each model variable in PC algorithm identification causal structure network
To carsal graph model.
As preferred embodiment, further include：
Inspection module, for the data of the land use pattern variation to acquisition and the data progress normal state point of impact factor
Cloth is examined, and carries out normal transformation to the data for not meeting normal distribution.
As preferred embodiment, the identification module includes：
Causality judging unit, for determining that any two model becomes in causal structure network by conditional independence tests
It whether there is causality between amount；
Cause and effect direction discernment unit, for there are causal any two model variables by the identification of D law of segregation
Between cause and effect direction.
Present embodiment discloses a kind of identification devices of land use and change causal structure, including：
Memory, for storing program；
Processor executes a kind of knowledge of land use and change causal structure as shown in Figure 1 for loading described program
Other method.
The survey region that the present embodiment is identified using Guangdong Province as land use and change causal structure：
Firstly, setting model is it is assumed that (1) model variable meets normal distribution；(2) it is arranged one to conditional independence tests to show
Work property level value, α<0.05.This shows that a possibility that its model is correct (probability) is 95%.Then, Guangdong province, 2005 is collected
With the delta data of each land use pattern in land system in 2010, land use pattern includes farmland
(Cropland), urban land (Urban land), forest land (Forest), meadow (grassland), water body (Waterbody)
With bare area (Barren land).The data of impact factor are collected, factor data includes：Temperature (SAT), height above sea level (ELE), soil
Policy (policy), gross national product (GDP), social retail product gross sales amount (TRSCG), primary industry gross national product
(GDPP), secondary industry gross national product (GDPS), Gross National Product of Tertiary Industry (GDPT), Engel coefficient (EC),
Cottar's per capita income (TIRI), the density of population (TPOP).Normal distribution-test is carried out to data, to not meeting normal distribution
Data carry out normal transformation.Based on carsal graph model, a complete causal structure network is constructed, carries out Guangdong province, 2005
Causal structure identification between to 2010 between multiple land system variables.With 6 class land use pattern of Guangdong Province and its influence
Factor variations are as carsal graph model variable.
Based on PC algorithm, assume initially that each variable deposits association between any two, the side of every two node is connected with
, it is then deleted according to line between the independence progress variable between conditional independence tests judgement two-by-two variable, to be become
Causality between amount.D law of segregation is reapplied to judge the causal direction that previous step obtains, to determine that who is reason,
Who is as a result, being oriented to remaining line.To the Guangdong province, 2005 that is ultimately oriented to land system between 2010
The causal system diagram of variation.
Wherein, PC algorithm can be completed by R language.
The analysis of this data is to Guangdong province, 2005 to land use pattern delta data and impact factor number between 2010
According to causal structure identification is carried out, Main Analysis situation is as follows：
Fig. 3 result illustrates the causal structure of Guangdong province, 2005 to land use and change between 2010, land use class
Type farmland, urban land and water body variation and impact factor variation present causality, land policy and farmland variation each other because
Fruit；Urban land use change, secondary industry gross national product, gross national product and total volume of retail sales variation are water bodys
The reason of variation；The reason of Gross National Product of Tertiary Industry and Engel coefficient variation are urban land use changes, En Geer system
Several and urban land use change reciprocal causation.Causality is not present in forest land, bare area and grassland change and impact factor variation.
For the step number in above method embodiment, it is arranged only for the purposes of illustrating explanation, between step
Sequence do not do any restriction, the execution of each step in embodiment sequence can according to the understanding of those skilled in the art come into
Row is adaptively adjusted.
It is to be illustrated to preferable implementation of the invention, but the present invention is not limited to the embodiment above, it is ripe
Various equivalent deformation or replacement can also be made on the premise of without prejudice to spirit of the invention by knowing those skilled in the art, this
Equivalent deformation or replacement are all included in the scope defined by the claims of the present application a bit.
Claims (10)
1. a kind of recognition methods of land use and change causal structure, it is characterised in that：Include the following steps：
Obtain the data of the land use pattern variation of several periods in survey region and the data of impact factor；
The data of the data and impact factor that are changed using land use pattern construct causal structure network as model variable；
Based on the causality between each model variable in PC algorithm identification causal structure network, carsal graph model is obtained.
2. a kind of recognition methods of land use and change causal structure according to claim 1, it is characterised in that：Further include
Following steps：
The data of data and impact factor to the variation of the land use pattern of acquisition carry out normal distribution-test, to not meeting just
The data of state distribution carry out normal transformation.
3. a kind of recognition methods of land use and change causal structure according to claim 1, it is characterised in that：The base
Causality in PC algorithm identification causal structure network between each model variable, the step for specifically include：
Determine to whether there is causality in causal structure network between any two model variable by conditional independence tests；
By the identification of D law of segregation, there are the cause and effect directions between causal any two model variable.
4. a kind of recognition methods of land use and change causal structure according to claim 3, it is characterised in that：It is described logical
Conditional independence tests are crossed to determine to whether there is causality in causal structure network between any two model variable, the step for
It specifically includes：
The conditional mutual information value in causal structure network between any two model variable is calculated, judges the conditional mutual information value
Whether given threshold is greater than, if so, determining that there are causalities between two model variables；Conversely, then determining this two
Causality is not present between model variable.
5. a kind of recognition methods of land use and change causal structure according to claim 4, it is characterised in that：The item
The calculation formula of part association relationship is：
Wherein, X, Y and Z are three disjoint variables sets, and I (X, Y | Z) is indicated in the case where specified criteria Z between X and Y
Conditional mutual information value, r, q and s respectively indicate the value number of X, Y and Z, and P () is probability function, xiIndicate i-th of value of X,
yjIndicate j-th of value of Y, zkIndicate k-th of value of Z.
6. a kind of recognition methods of land use and change causal structure according to claim 1-5, feature exist
In：The carsal graph model includes the side of relationship between the node of several model variables and several expression model variables.
7. a kind of identifying system of land use and change causal structure, it is characterised in that：Including：
Module is obtained, for obtaining the data and impact factor that the land use pattern of several periods in survey region changes
Data；
Construct module, the data of data and impact factor for being changed using land use pattern are used as model variable, construct because
Fruit structure network；
Identification module, for based on the causality in PC algorithm identification causal structure network between each model variable, obtain because
Fruit graph model.
8. a kind of identifying system of land use and change causal structure according to claim 7, it is characterised in that：Also wrap
It includes：
Inspection module, for the data of the land use pattern variation to acquisition and the data progress normal distribution inspection of impact factor
It tests, normal transformation is carried out to the data for not meeting normal distribution.
9. a kind of identifying system of land use and change causal structure according to claim 7, it is characterised in that：The knowledge
Other module includes：
Causality judging unit, for by conditional independence tests judgement causal structure network in any two model variable it
Between whether there is causality；
Cause and effect direction discernment unit, for there are between causal any two model variable by the identification of D law of segregation
Cause and effect direction.
10. a kind of identification device of land use and change causal structure, it is characterised in that：Including
Memory, for storing program；
Processor, executed for loading described program a kind of land use and change as claimed in any one of claims 1 to 6 because
The recognition methods of fruit structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810898406.4A CN108876210A (en) | 2018-08-08 | 2018-08-08 | A kind of recognition methods, system and the device of land use and change causal structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810898406.4A CN108876210A (en) | 2018-08-08 | 2018-08-08 | A kind of recognition methods, system and the device of land use and change causal structure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108876210A true CN108876210A (en) | 2018-11-23 |
Family
ID=64317405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810898406.4A Pending CN108876210A (en) | 2018-08-08 | 2018-08-08 | A kind of recognition methods, system and the device of land use and change causal structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876210A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695583A (en) * | 2019-07-18 | 2020-09-22 | 广东电网有限责任公司信息中心 | Feature selection method based on causal network |
| CN118114576A (en) * | 2024-01-19 | 2024-05-31 | 中国民用航空总局第二研究所 | Flight delay figure model detection method based on Nataf transformation independence test |
| CN118114576B (en) * | 2024-01-19 | 2024-07-09 | 中国民用航空总局第二研究所 | Flight delay figure model detection method based on Nataf transformation independence test |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050091012A1 (en) * | 2003-10-23 | 2005-04-28 | Przytula Krzysztof W. | Evaluation of bayesian network models for decision support |
| CN1987906A (en) * | 2005-12-22 | 2007-06-27 | 中国煤炭地质总局航测遥感局 | Method for dynamicaly predicting land use change |
| US20090094076A1 (en) * | 2007-10-05 | 2009-04-09 | Reddy Sudhakar Y | Method and system using linear programming for estimating test costs for bayesian diagnostic models |
| CN101604326A (en) * | 2009-07-16 | 2009-12-16 | 浙江大学 | Land use data based on event semantics upgrades and analytical approach |
| CN103514366A (en) * | 2013-09-13 | 2014-01-15 | 中南大学 | Urban air quality concentration monitoring missing data recovering method |
| CN105718717A (en) * | 2016-01-12 | 2016-06-29 | 叶翔 | Method and device for establishing boiler combustion process model by utilizing Bayesian network algorithm |
| CN107563596A (en) * | 2017-08-03 | 2018-01-09 | 清华大学 | A kind of evaluation index equilibrium state analysis method based on Bayes's causal network |
-
2018
- 2018-08-08 CN CN201810898406.4A patent/CN108876210A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050091012A1 (en) * | 2003-10-23 | 2005-04-28 | Przytula Krzysztof W. | Evaluation of bayesian network models for decision support |
| CN1987906A (en) * | 2005-12-22 | 2007-06-27 | 中国煤炭地质总局航测遥感局 | Method for dynamicaly predicting land use change |
| US20090094076A1 (en) * | 2007-10-05 | 2009-04-09 | Reddy Sudhakar Y | Method and system using linear programming for estimating test costs for bayesian diagnostic models |
| CN101604326A (en) * | 2009-07-16 | 2009-12-16 | 浙江大学 | Land use data based on event semantics upgrades and analytical approach |
| CN103514366A (en) * | 2013-09-13 | 2014-01-15 | 中南大学 | Urban air quality concentration monitoring missing data recovering method |
| CN105718717A (en) * | 2016-01-12 | 2016-06-29 | 叶翔 | Method and device for establishing boiler combustion process model by utilizing Bayesian network algorithm |
| CN107563596A (en) * | 2017-08-03 | 2018-01-09 | 清华大学 | A kind of evaluation index equilibrium state analysis method based on Bayes's causal network |
Non-Patent Citations (2)
| Title |
|---|
| 张浩等: "基于互信息的适用于高维数据的因果推断算法", 《计算机应用研究》 * |
| 易三莉等: "基于PC-Simple算法的医院病案首页数据挖掘", 《软件导刊》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695583A (en) * | 2019-07-18 | 2020-09-22 | 广东电网有限责任公司信息中心 | Feature selection method based on causal network |
| CN118114576A (en) * | 2024-01-19 | 2024-05-31 | 中国民用航空总局第二研究所 | Flight delay figure model detection method based on Nataf transformation independence test |
| CN118114576B (en) * | 2024-01-19 | 2024-07-09 | 中国民用航空总局第二研究所 | Flight delay figure model detection method based on Nataf transformation independence test |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106781489B (en) | A kind of road network trend prediction method based on recurrent neural network | |
| Brown et al. | Path dependence and the validation of agent‐based spatial models of land use | |
| CN107644279A (en) | The modeling method and device of evaluation model | |
| CN109766454A (en) | A kind of investor's classification method, device, equipment and medium | |
| CN101478534B (en) | Network exception detecting method based on artificial immunity principle | |
| CN103577876B (en) | Based on feedforward neural network credible with insincere user identification method | |
| Gong et al. | Small-world particle swarm optimization with topology adaptation | |
| CN111767517A (en) | BiGRU multi-step prediction method and system applied to flood prediction and storage medium | |
| Dai et al. | Agent-based model of land system: Theory, application and modelling framework | |
| Alibrandi et al. | A decision support tool for sustainable and resilient building design | |
| Xiao et al. | Incentive mechanism design for federated learning: A two-stage stackelberg game approach | |
| CN115203496A (en) | Project intelligent prediction and evaluation method and system based on big data and readable storage medium | |
| Li et al. | An Integrated Artificial Neural Network-based Precipitation Revision Model. | |
| CN108876210A (en) | A kind of recognition methods, system and the device of land use and change causal structure | |
| Yamanishi et al. | 8. functional data analysis geographically weighted functional multiple regression analysis: A numerical investigation | |
| CN105955814A (en) | Event priority scheduling-based complex event detection method | |
| Papageorgiou et al. | Soft computing technique of fuzzy cognitive maps to connect yield defining parameters with yield in cotton crop production in central Greece as a basis for a decision support system for precision agriculture application | |
| CN117522652A (en) | Human living environment vulnerability evaluation method, system, intelligent terminal and storage medium | |
| CN111914465A (en) | Data-free regional hydrological parameter calibration method based on clustering and particle swarm optimization | |
| CN109978138A (en) | The structural reliability methods of sampling based on deeply study | |
| Yan et al. | Toward databases mining: Pre-processing collected data | |
| CN111144243A (en) | Household pattern recognition method and device based on counterstudy | |
| Quinn | Computational techniques for crop disease monitoring in the developing world | |
| Carmel et al. | Performance of a spatio-temporal error model for raster datasets under complex error patterns | |
| CN113392934A (en) | Bias data balancing method and device for deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |