CN109508360A - A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata - Google Patents
A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata Download PDFInfo
- Publication number
- CN109508360A CN109508360A CN201811318953.7A CN201811318953A CN109508360A CN 109508360 A CN109508360 A CN 109508360A CN 201811318953 A CN201811318953 A CN 201811318953A CN 109508360 A CN109508360 A CN 109508360A
- Authority
- CN
- China
- Prior art keywords
- cellular
- time
- space
- data
- flow data
- 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.)
- Granted
Links
- 230000001413 cellular effect Effects 0.000 title claims abstract description 117
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 230000002123 temporal effect Effects 0.000 claims abstract description 9
- 239000000284 extract Substances 0.000 claims abstract description 6
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000009028 cell transition Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000013499 data model Methods 0.000 abstract description 2
- 230000008520 organization Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- PLXMOAALOJOTIY-FPTXNFDTSA-N Aesculin Natural products OC[C@@H]1[C@@H](O)[C@H](O)[C@@H](O)[C@H](O)[C@H]1Oc2cc3C=CC(=O)Oc3cc2O PLXMOAALOJOTIY-FPTXNFDTSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Complex Calculations (AREA)
- Traffic Control Systems (AREA)
Abstract
The polynary flow data space-time autocorrelation analysis method of geography based on cellular automata that the present invention provides a kind of, it is expressed using spatiotemporal and complexity of the improved cellular automata dynamic model to geodata, and the special heterogeneity of cellular (geographic area) transformation rule and asynchronous evolution is considered, it can more precisely analyze the geographical polynary flow data of the nonlinear organization based on complex network.Analysis of the present invention to cellular unit, extracts a variety of impact factors, can more accurately obtain cellular Automation Model parameter, accurate and high-efficient;The transformation rule obtained using ANN algorithm, the transformation rule fixed compared to entire model are had dynamic, can more describe and meet the real transform situation of cellular;The correlation between cellular is indicated according to Moran ' s I, more preferably, more clearly reacts the spatial and temporal distributions situation of geodata, so that subsequent Spatio-Temporal Data Model for Spatial simulation and prediction are more easily carried out, so that simulation is higher with precision of prediction.
Description
Technical field
The invention belongs to geographical space statistical analysis techniques, and in particular to cellular automata, geographical Multi-flow data processing,
The fields such as geographical space correlation analysis.
Background technique
Continuous development and universal, band recently as geographical information technology, remote sensing technology, Internet of Things and mobile terminal
There is the polynary geodata of georeferencing, by the rapid development of decades, forms the polynary flow data of geography of magnanimity.These
Flow data has the characteristics that sequence, largely, rapidly, continuously reaches, and can be aggregated as one and continue at any time and increase without limitation
Dynamic data set can also be referred to as space-time flow data, such as traffic data, temperature Real-time Monitoring Data.
At present spatial autocorrelation analysis technology can preferably disclose in research object spatial character, be widely applied
In the spatial distribution characteristic for analyzing, monitoring environment, disaster.But it can be found that geographical more from the document that scholars study
The model of first flow data is mainly based upon time series models building, only considered time autocorrelation, does not account for geographical sky
Between correlation between heterogeneous and polytomy variable.As in relevant document, Langchao Co., Ltd. is in patent of invention " one
Kind uses distribution 3D dynamic space data analysing method " number of patent application: CN201410529971.5 publication number:
In CN104298743A, in certain time period, the spatial data of dynamic body is collected, sometime with specified time interval storage
The data information of point can be used for behavioural analysis, the behavior judgement of dynamic body;Beijing Jiaotong University is in a kind of patent of invention " society
Correlation analysis between event and passenger traffic demand " number of patent application: CN201711403609.3 publication number:
In CN108133291A, using machine learning algorithm, for different type event, construction merges mould respectively on the attribute of design
Type predicts the variable quantity of the transport need as caused by event.Spatial autocorrelation analysis method is mainly used in discrete space-time
Space-time data is split as spatial data and time series data by data, is individually carried out correlation analysis to two kinds of data, is ignored
The interaction of the time and space.
Therefore, the present invention innovatively proposes the space-time of polynary flow data of geography based on cellular automata a kind of from phase
The solution for closing analysis carries out table using spatiotemporal and complexity of the improved cellular automata dynamic model to geodata
It reaches, and considers the special heterogeneity of cellular (geographic area) transformation rule and asynchronous evolution, can more precisely analyze base
In the geographical polynary flow data of the nonlinear organization of complex network.
Summary of the invention
The purpose of the present invention is realize geographical polynary flow data space-time autocorrelation analysis.There is time dimension for data
And the characteristic continuously reached, the geographical Multi-flow data representation model based on cellular automata is constructed, one kind is proposed and changes
Into the space-time autocorrelation analysis method of Moran ' s I index.The Spatio-temporal Evolution that the present invention can disclose geographical polynary flow data is special
Sign provides one kind and takes the continuous table of time and space dimension into account for the forecast analysis of temperature real-time monitoring, Traffic monitoring etc.
The solution reached, is of great significance to Geoprocessing.
The invention mainly includes steps:
Step 1, classify for original geographical Multi-flow data, obtain the raster data containing plurality of classes;
Step 2, cellular Automation Model is improved, a kind of cellular automata mould for meeting geographical multi-source flow data characteristic is established
Type;
Step 3, it is a cellular unit by each mesh definition in raster data, extracts shadow in each cellular unit
Ring the factor;
Step 4, the neighborhood relationships between the state status and cellular of cellular are determined;
Step 5, the attribute data in several cellulars is randomly selected as training data from the sample survey;
Step 6, consider the diversities of data with it is spatiotemporal, using the ANN algorithm in machine learning to training data from the sample survey
Repetition training is carried out, until obtaining optimal solution, and using obtained output result as ginseng required in cellular Automation Model
Number;
Step 7, using the impact factor of extraction as input layer, the result obtained using training is as initial weight value, benefit
The transformation rule in each cellular is excavated with ANN algorithm, it is general to obtain the initial conversion that the cellular class switch is another classification
Rate;
Step 8, the output layer data i.e. transition probability data obtained using training are extracted maximum value, determine subsequent time
Whether cellular classification changes, and determines the trend for being converted to which kind of classification;
Step 9, using mole neighborhood mode of cellular models, the Temporal Weight value between cellular is calculated;
Step 10, according to the continuation property of geographical Multi-flow data, and in three spatial position, attribute, time levels
On model tormulation form, improve space-time Moran ' s I situational variables space-time structure;
Step 11, take the correlation between cellular into account, the Temporal Weight matrix that step 9 is calculated with it is improved in step 10
Moran ' s I index carries out sunykatuib analysis and prediction, shape in conjunction with the cellular Automation Model established based on geographical polynary flow data
At built-up pattern on the basis of cellular Automation Model with space-time autocorrelation analytic function.
Further, a kind of cellular Automation Model definition meeting geographical multi-source flow data characteristic described in step 2
It is as follows,
A={ F, L, G, S, N, R } formula (2)
In above-mentioned formula, F={ f } expression can be with the data of attribute information of quantitative expression;L={ l } indicates point of geographical phenomenon
Cloth;G is that the cellular of geographical space divides;N={ c1,c2,...,cnIt is cellular neighbours;S={ sc, indicate that the state of cellular becomes
Amount;R={ r } indicates rule set, or referred to as evolution collection of functions.
Further, it is standardized in step 5 using maxima and minima, so that obtained training data from the sample survey is all
Between 0 to 1.
Further, determine whether subsequent time cellular classification changes in step 8, which kind of classification determination is converted to
The calculation formula of trend is as follows,
pt(i, j)=(1+ (- ln γ)a)×pg×con(St(i,j))×Ωt(i, j) formula (5)
In formula, pt(i, j) is the transition probability of classification represented by a certain cellular;1+(-lnγ)aRandom entry is indicated, so that mould
Quasi- result is more in line with actual conditions;pgFor global transformation probability;con(St(i, j))) indicate cellular unit restrictive condition;
Ωt(i, j) indicates neighborhood function, indicates influence of the neighborhood to cellular transition probability.
Further, there are two types of expression ways for improved Moran ' s I index in step 10, and expression is as follows,
Moran ' the s I index OSTI of global space-time manifold formulakWith Moran ' the s I index of local space time manifold formula
PSTIk,
In formula, n is cellular number of unit, wt-k,tFor the time weighting value at t-k moment to t moment;wi,jFor space weight square
An element of battle array W, W is capable standardized Spatial weight matrix, for quantifying the proximity between peripheral region;Ai,t-kFor
Standardized nature value of the cellular unit i at the t-k moment;For all cellular units the t-k moment standardized nature value
Average value;Aj,tFor cellular unit j t moment standardized nature value;For all cellular units t moment standardization category
The average value of property value;Moran ' s I index OSTI based on geographical polynary flow datakWith PSTIkVariation range be (- 1,1).
It further, further include obtaining OSTI in step 10kWith PSTIkOn the basis of value, construct Normal Distribution when
Empty statistic Z, the conspicuousness of space-time autocorrelation is examined with this, and space-time statistic Z is indicated are as follows:
Or
Wherein:
Beneficial effects of the present invention: a variety of impact factors are extracted in the analysis to cellular unit, can more accurately obtain member
Cellular automaton model parameter, the parameter error more determining than manually is smaller in use, accurate and high-efficient;It is obtained using ANN algorithm
Transformation rule, the transformation rule fixed compared to entire model have dynamic, can more describe and meet the real transform of cellular
Situation;The correlation between cellular is indicated according to Moran ' s I, more preferably, more clearly reacts the spatial and temporal distributions feelings of geodata
Condition, so that subsequent Spatio-Temporal Data Model for Spatial simulation and prediction are more easily carried out, so that simulation is higher with precision of prediction.
Detailed description of the invention
Fig. 1 is standard CA modular concept figure.
Fig. 2 is specific embodiment flow chart.
Tri- kinds of cellular neighborhood relationships mode figures of Fig. 3.
Fig. 4 neural metwork training obtains model parameter schematic diagram.
Specific embodiment
Technical solution of the present invention can be run by those skilled in the art using computer software technology when being embodied.This hair
Bright specific embodiment is described by conjunction with attached drawing 2, providing present example specific steps by taking land use data as an example
It is as follows:
(1) diversity and space-time characterisation of data are analyzed using geographical polynary flow data, the data that this example uses for
More period land use change survey remote sensing image datas;
(2) for initial data carry out pretreatment operation, using ArcGIS software carry out image classification, contained there are many
The raster data of ground class, such as urban land, forest land, meadow, field, wetland, water body ground class, untapped land used;
(3) cellular Automation Model is constructed, in conjunction with instance data, cellular Automation Model is improved, establishes one kind and meet ground
Manage the cellular Automation Model of multi-source flow data characteristic.Standard CA be one by (cellular, cellular state, neighborhood and
State update rule) constitute four-tuple (such as Fig. 1), can be indicated with mathematic sign are as follows:
A={ L, d, S, N, f } formula (1)
The expressed intact and description of geographical polynary flow data, need to meet has abundant accurately semanteme, traditional cellular automatic
Machine has ignored the special heterogeneity of transformation rule and different cellulars (geographic area) asynchronous evolution.By improving cellular automata mould
Type constructs the cellular Automation Model based on geographical polynary flow data, the geographical letter for expressing complicated, dynamic, connecting each other
Cease primitive.Improved model is defined as follows:
A={ F, L, G, S, N, R } formula (2)
In above-mentioned formula, F={ f } expression can be with the data of attribute information of quantitative expression;L={ l } indicates point of geographical phenomenon
Cloth is unable to quantitative expression;G is that the cellular of geographical space divides;N={ c1,c2,...,cnIt is cellular neighbours;S={ sc, it indicates
The state variable of cellular;R={ r } indicates rule set, or referred to as evolution collection of functions.
According to time series models principle, state of the cellular m at the t+k moment is determined by cellular t moment state and cellular neighbours
Fixed, then iterative process indicates are as follows:
st+k=r (Nm,st) formula (3)
(4) cellular unit is defined, is a cellular unit by each mesh definition in raster data;
(5) sky in ArcGIS software is utilized there are a variety of attributive character (i.e. impact factor) in each cellular unit
Between analysis tool extract a variety of impact factor (xt,1,xt,2......,xt,Q), wherein Q is impact factor quantity, for soil benefit
With data, what impact factor mainly extracted have distance apart from the city core data, from road distance data, various ground class with neighborhood window
The statistic unit quantity etc. that form is extracted;
(6) state status for determining cellular indicates land type with the state that cellular is in.In image classification, adopt
Different land types are indicated with polychrome rendering, it can with clearly understanding soil class distribution situation;
(7) neighborhood relationships between cellular are determined, the neighborhood relationships model of mainstream mainly has von Neumann type, rubs at present
Your type, Ma Gelesi type etc., according to instance data, using a mole neighborhood relationships model (such as Fig. 3);
(8) attribute data in several cellulars is randomly selected as training data from the sample survey.Training data is mainly random
Extract each grid data and a variety of impact factor data therein.In view of the training data of acquisition is not of uniform size, between
Numerical value differ greatly, be standardized using maxima and minima so that obtained training data from the sample survey all 0 to 1 it
Between;
(9) diversity of data and spatiotemporal is considered, using the ANN algorithm in machine learning to training data from the sample survey progress
Repetition training, until obtaining optimal solution, and (such as using obtained output result as parameter required in cellular Automation Model
Fig. 4);
(10) by the impact factor (x of extractiont,1,xt,2......,xt,Q) it is used as input layer, the result obtained using training
As initial weight value;
(11) it carries out excavating the transformation rule in each cellular using identical ANN algorithm again, passes through the letter of input layer
Breath and weighted value, into hidden layer, by activating the processing of Sigmoid function, class is converted to another ground with obtaining the cellular
The initial transition probability of class chooses certain threshold value, returns to input layer and carries out repetition training, until obtaining optimum translation probability
Just stop.The activation Sigmoid function chosen in ANN algorithm are as follows:
In formula, wp,qIndicate the weighted value between neuron p and q;xt,qIndicate q-th of neuron of t moment (i.e. influence because
Son) standardization after attribute value.
(12) the output layer data i.e. transition probability data obtained using training extract maximum value, determine subsequent time member
Born of the same parents class whether change, determine the trend for being converted to which kind of ground class, calculation is as follows:
pt(i, j)=(1+ (- ln γ)a)×pg×con(St(i,j))×Ωt(i, j) formula (5)
In formula, pt(i, j) is the transition probability of a certain cellular represented ground class;1+(-lnγ)aRandom entry is indicated, so that mould
Quasi- result is more in line with actual conditions;pgFor global transformation probability;con(St(i, j))) indicate cellular unit restrictive condition;
Ωt(i, j) indicates neighborhood function, indicates influence of the neighborhood to cellular transition probability.
(13) mole neighborhood mode for using cellular models, calculates the Temporal Weight value w between cellulart-k,t, wi,j。wt-k,t
For the time weighting value at t-k moment to t moment;wi,jFor an element of Spatial weight matrix W.W is capable standardized space right
Weight matrix, for quantifying the proximity between peripheral region.
(14) according to the continuation property of geographical Multi-flow data, and on three spatial position, attribute, time levels
Model tormulation form, improve Wartenberg scholar propose space-time Moran ' s I (Spatio-Temporal Moran ' s I,
STIk) situational variables space-time structure, carry out the space-time autocorrelation analysis to geographical Multi-flow data.Consider area, overall situation and partial situation
When domain is analyzed, there are temporal-spatial heterogeneities, then there are two types of expression ways: Moran ' the s I index of global space-time manifold formula
OSTIkWith Moran ' the s I indices P STI of local space time manifold formulak.Moran ' the s I index OSTI of space-time manifold formulakWith
PSTIkExpression formula is as follows:
In formula: n is cellular number of unit;Ai,t-kFor cellular unit i the t-k moment standardized nature value;For institute
There is cellular unit in the average value of the standardized nature value at t-k moment;Aj,tFor cellular unit j t moment standardized nature
Value;For all cellular units the standardized nature value of t moment average value.
Moran ' s I index OSTI based on geographical polynary flow datakWith PSTIkVariation range be (- 1,1).If
When aerial two cellular units it is uncorrelated, then STIk(OSTIkWith PSTIk) expectation close to 0, work as STIk(OSTIkWith PSTIk)
Value when taking negative value, typically represent space-time negative autocorrelation, i.e. the temporal correlation of future time ground class variation is weak;Work as STIk
(OSTIkWith PSTIk) value when taking positive value, typically represent the positive autocorrelation of space-time, i.e. the when Kongxiang of future time ground class variation
Guan Xingqiang.
Obtaining theory STIkOn the basis of value, the space-time statistic Z of Normal Distribution can be constructed, space-time is examined certainly with this
The conspicuousness (p < 0.05) of correlation.Space-time statistic Z is indicated are as follows:
Wherein:
Similarly, OSTIkWith PSTIkThe conspicuousness of space-time autocorrelation can also be examined by formula 7 and 8.
(15) finally, taking the correlation between cellular into account, Temporal Weight matrix W and (14) step that (13) step is calculated
Space-time Moran ' s I index OSTIkOr PSTIk, mould is carried out in conjunction with the cellular Automation Model established based on land use data
Quasi- analysis and prediction are formed in the built-up pattern with space-time autocorrelation analytic function on the basis of cellular Automation Model.Point
Prediction result is analysed, non-urban land (meadow, forest land, water body etc.) is transformed into urban land with the time, can be with statistics variations face
Product has subsequent relevant departments in Urban Expansion or expansion construction using forecast land use change situation and refers to well
Lead meaning.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (6)
1. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata, which is characterized in that including such as
Lower step:
Step 1, classify for original geographical Multi-flow data, obtain the raster data containing plurality of classes;
Step 2, cellular Automation Model is improved, a kind of cellular Automation Model for meeting geographical multi-source flow data characteristic is established;
Step 3, by each mesh definition in raster data be a cellular unit, in each cellular unit extract influence because
Son;
Step 4, the neighborhood relationships between the state status and cellular of cellular are determined;
Step 5, the attribute data in several cellulars is randomly selected as training data from the sample survey;
Step 6, consider the diversities of data with it is spatiotemporal, training data from the sample survey is carried out using the ANN algorithm in machine learning
Repetition training, until obtaining optimal solution, and using obtained output result as parameter required in cellular Automation Model;
Step 7, using the impact factor of extraction as input layer, the result obtained using training utilizes ANN as initial weight value
Algorithm excavates the transformation rule in each cellular, obtains the initial transition probability that the cellular class switch is another classification;
Step 8, the output layer data i.e. transition probability data obtained using training are extracted maximum value, determine subsequent time cellular
Whether classification changes, and determines the trend for being converted to which kind of classification;
Step 9, using mole neighborhood mode of cellular models, the Temporal Weight value between cellular is calculated;
Step 10, according to the continuation property of geographical Multi-flow data, and on three spatial position, attribute, time levels
Model tormulation form improves the space-time structure of space-time Moran ' s I situational variables;
Step 11, take the correlation between cellular into account, the Temporal Weight matrix that step 9 is calculated with it is improved in step 10
Moran ' s I index carries out sunykatuib analysis and prediction, shape in conjunction with the cellular Automation Model established based on geographical polynary flow data
At built-up pattern on the basis of cellular Automation Model with space-time autocorrelation analytic function.
2. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata as described in claim 1,
It is characterized by: a kind of cellular Automation Model for meeting geographical multi-source flow data characteristic described in step 2 is defined as follows,
A={ F, L, G, S, N, R } formula (2)
In above-mentioned formula, F={ f } expression can be with the data of attribute information of quantitative expression;The distribution of L={ l } expression geographical phenomenon;G
It is the cellular division of geographical space;N={ c1,c2,...,cnIt is cellular neighbours;S={ sc, indicate the state variable of cellular;R
={ r } indicates rule set, or referred to as evolution collection of functions.
3. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata as described in claim 1,
It is characterized by: being standardized in step 5 using maxima and minima, so that obtained training data from the sample survey is all 0 to 1
Between.
4. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata as described in claim 1,
It is characterized by: determining whether subsequent time cellular classification changes in step 8, the trend for being converted to which kind of classification is determined
Calculation formula is as follows,
pt(i, j)=(1+ (- ln γ)a)×pg×con(St(i,j))×Ωt(i, j) formula (5)
In formula, pt(i, j) is the transition probability of classification represented by a certain cellular;1+(-lnγ)aRandom entry is indicated, so that simulation knot
Fruit is more in line with actual conditions;pgFor global transformation probability;con(St(i, j))) indicate cellular unit restrictive condition;Ωt
(i, j) indicates neighborhood function, indicates influence of the neighborhood to cellular transition probability.
5. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata as described in claim 1,
It is characterized by: there are two types of expression ways for improved Moran ' s I index in step 10, expression is as follows,
Moran ' the s I index OSTI of global space-time manifold formulakWith Moran ' the s I indices P STI of local space time manifold formulak,
In formula, n is cellular number of unit, wt-k,tFor the time weighting value at t-k moment to t moment;wi,jFor Spatial weight matrix W
An element, W is capable standardized Spatial weight matrix, for quantifying the proximity between peripheral region;Ai,t-kFor member
Standardized nature value of born of the same parents' unit i at the t-k moment;For all cellular units the t-k moment standardized nature value it is flat
Mean value;Aj,tFor cellular unit j t moment standardized nature value;For all cellular units t moment standardized nature
The average value of value;Moran ' s I index OSTI based on geographical polynary flow datakWith PSTIkVariation range be (- 1,1).
6. a kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata as claimed in claim 5,
It is characterized by: further including obtaining OSTI in step 10kWith PSTIkOn the basis of value, the space-time system of Normal Distribution is constructed
Z is measured, the conspicuousness of space-time autocorrelation is examined with this, space-time statistic Z is indicated are as follows:
Or
Wherein:
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811318953.7A CN109508360B (en) | 2018-11-07 | 2018-11-07 | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton |
AU2018101946A AU2018101946A4 (en) | 2018-11-07 | 2018-12-04 | Geographical multivariate flow data spatio-temporal autocorrelation analysis method based on cellular automaton |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811318953.7A CN109508360B (en) | 2018-11-07 | 2018-11-07 | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109508360A true CN109508360A (en) | 2019-03-22 |
CN109508360B CN109508360B (en) | 2021-03-16 |
Family
ID=65009405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811318953.7A Active CN109508360B (en) | 2018-11-07 | 2018-11-07 | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109508360B (en) |
AU (1) | AU2018101946A4 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110909924A (en) * | 2019-11-12 | 2020-03-24 | 同济大学 | City expansion multi-scenario simulation cellular automata method based on cross entropy optimizer |
CN112396231A (en) * | 2020-11-18 | 2021-02-23 | 京东数字科技控股股份有限公司 | Modeling method and device for spatio-temporal data, electronic equipment and readable medium |
CN113297174A (en) * | 2021-05-24 | 2021-08-24 | 中南大学 | Land use change simulation method based on deep learning |
CN114611188A (en) * | 2022-03-09 | 2022-06-10 | 生态环境部卫星环境应用中心 | Cellular automata-based tailing pond dam break leakage simulation analysis method and system |
CN115271221A (en) * | 2022-08-04 | 2022-11-01 | 中南大学 | City expansion prediction method, device, medium and equipment |
CN116451873A (en) * | 2023-06-12 | 2023-07-18 | 中国科学技术大学 | Wind power generation power prediction method and system based on multi-scale double space-time network area |
CN116955335A (en) * | 2023-07-21 | 2023-10-27 | 北京国信达数据技术有限公司 | Address data management method and system based on big data model algorithm |
CN117057674A (en) * | 2023-10-11 | 2023-11-14 | 晨达(广州)网络科技有限公司 | Discrete model-based information technology service quality assessment method and system |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111080070B (en) * | 2019-11-19 | 2023-05-02 | 同济大学 | Urban land utilization cellular automaton simulation method based on space errors |
CN111428405B (en) * | 2020-03-20 | 2023-07-07 | 北京百分点科技集团股份有限公司 | Fine particulate matter concentration simulation method and device, storage medium and electronic equipment |
CN111797523B (en) * | 2020-06-30 | 2024-03-22 | 南京图申图信息科技有限公司 | Land utilization change-oriented multi-level vector cellular automaton modeling method |
CN112116160B (en) * | 2020-09-25 | 2024-07-02 | 国网新疆电力有限公司电力科学研究院 | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network |
CN113032510B (en) * | 2021-04-02 | 2023-06-02 | 中国人民解放军国防科技大学 | LBGM method initial value disturbance generation method based on Gaussian weight |
CN113255221B (en) * | 2021-05-28 | 2022-11-25 | 中国石油大学(华东) | Inter-well connectivity analysis method and device based on cellular automata deduction |
CN113742925B (en) * | 2021-09-06 | 2023-09-29 | 吉林大学 | Signal control intersection pedestrian flow simulation method |
CN113793376B (en) * | 2021-09-14 | 2023-12-05 | 安徽理工大学 | Irrigation water body extraction method |
CN116976526B (en) * | 2023-09-20 | 2023-12-15 | 北京师范大学 | Land utilization change prediction method coupling ViViViT and ANN |
Citations (5)
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 |
US20130117000A1 (en) * | 2007-09-22 | 2013-05-09 | Chaitanya N. Hiremath | Method for predicting ADMET properties using Abbreviated Profile of Drugs (A-POD) |
CN104732279A (en) * | 2015-03-25 | 2015-06-24 | 武汉大学 | Improved cellular automaton traffic flow simulation analysis method based on geographic information system |
CN106780089A (en) * | 2016-12-27 | 2017-05-31 | 广州蓝图地理信息技术有限公司 | Permanent basic farmland demarcation method based on neutral net cellular Automation Model |
CN107194504A (en) * | 2017-05-09 | 2017-09-22 | 云南师范大学 | Forecasting Methodology, the device and system of land use state |
-
2018
- 2018-11-07 CN CN201811318953.7A patent/CN109508360B/en active Active
- 2018-12-04 AU AU2018101946A patent/AU2018101946A4/en not_active Ceased
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130117000A1 (en) * | 2007-09-22 | 2013-05-09 | Chaitanya N. Hiremath | Method for predicting ADMET properties using Abbreviated Profile of Drugs (A-POD) |
CN102184328A (en) * | 2011-05-10 | 2011-09-14 | 南京大学 | Method for optimizing land use evolution CA model transformation rules |
CN104732279A (en) * | 2015-03-25 | 2015-06-24 | 武汉大学 | Improved cellular automaton traffic flow simulation analysis method based on geographic information system |
CN106780089A (en) * | 2016-12-27 | 2017-05-31 | 广州蓝图地理信息技术有限公司 | Permanent basic farmland demarcation method based on neutral net cellular Automation Model |
CN107194504A (en) * | 2017-05-09 | 2017-09-22 | 云南师范大学 | Forecasting Methodology, the device and system of land use state |
Non-Patent Citations (1)
Title |
---|
赵占轻: "基于GIS和元胞自动机的女儿寨小流域植被动态模拟研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110909924B (en) * | 2019-11-12 | 2023-05-02 | 同济大学 | Urban expansion multi-scenario simulation cellular automaton method based on cross entropy optimizer |
CN110909924A (en) * | 2019-11-12 | 2020-03-24 | 同济大学 | City expansion multi-scenario simulation cellular automata method based on cross entropy optimizer |
CN112396231A (en) * | 2020-11-18 | 2021-02-23 | 京东数字科技控股股份有限公司 | Modeling method and device for spatio-temporal data, electronic equipment and readable medium |
CN112396231B (en) * | 2020-11-18 | 2023-09-29 | 京东科技控股股份有限公司 | Modeling method and device for space-time data, electronic equipment and readable medium |
CN113297174B (en) * | 2021-05-24 | 2023-10-13 | 中南大学 | Land utilization change simulation method based on deep learning |
CN113297174A (en) * | 2021-05-24 | 2021-08-24 | 中南大学 | Land use change simulation method based on deep learning |
CN114611188B (en) * | 2022-03-09 | 2022-09-02 | 生态环境部卫星环境应用中心 | Cellular automata-based tailing pond dam break leakage simulation analysis method and system |
CN114611188A (en) * | 2022-03-09 | 2022-06-10 | 生态环境部卫星环境应用中心 | Cellular automata-based tailing pond dam break leakage simulation analysis method and system |
CN115271221A (en) * | 2022-08-04 | 2022-11-01 | 中南大学 | City expansion prediction method, device, medium and equipment |
CN116451873A (en) * | 2023-06-12 | 2023-07-18 | 中国科学技术大学 | Wind power generation power prediction method and system based on multi-scale double space-time network area |
CN116451873B (en) * | 2023-06-12 | 2023-10-20 | 中国科学技术大学 | Wind power generation power prediction method and system based on multi-scale double space-time network area |
CN116955335A (en) * | 2023-07-21 | 2023-10-27 | 北京国信达数据技术有限公司 | Address data management method and system based on big data model algorithm |
CN117057674A (en) * | 2023-10-11 | 2023-11-14 | 晨达(广州)网络科技有限公司 | Discrete model-based information technology service quality assessment method and system |
CN117057674B (en) * | 2023-10-11 | 2024-09-10 | 晨达(广州)网络科技有限公司 | Discrete model-based information technology service quality assessment method and system |
Also Published As
Publication number | Publication date |
---|---|
AU2018101946A4 (en) | 2019-01-17 |
CN109508360B (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109508360A (en) | A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata | |
CN107818302A (en) | Non-rigid multi-scale object detection method based on convolutional neural network | |
CN109902885A (en) | Typhoon prediction method based on deep learning mixed CNN-LSTM model | |
CN103268495B (en) | Human body behavior modeling recognition methods based on priori knowledge cluster in computer system | |
CN109117864A (en) | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion | |
CN108805070A (en) | A kind of deep learning pedestrian detection method based on built-in terminal | |
Zhang et al. | Unsupervised difference representation learning for detecting multiple types of changes in multitemporal remote sensing images | |
CN114519302B (en) | Highway traffic situation simulation method based on digital twinning | |
CN114842208B (en) | Deep learning-based power grid harmful bird species target detection method | |
CN106909938B (en) | Visual angle independence behavior identification method based on deep learning network | |
CN110212528A (en) | Reconstructing method is lacked based on the power distribution network metric data for generating confrontation and dual Semantic Aware | |
CN112950780B (en) | Intelligent network map generation method and system based on remote sensing image | |
CN110135502A (en) | A kind of image fine granularity recognition methods based on intensified learning strategy | |
CN114092697B (en) | Building facade semantic segmentation method with attention fused with global and local depth features | |
CN113887517B (en) | Crop remote sensing image semantic segmentation method based on parallel attention mechanism | |
Chen et al. | Agricultural remote sensing image cultivated land extraction technology based on deep learning | |
CN109903339A (en) | A kind of video group personage's position finding and detection method based on multidimensional fusion feature | |
CN110008853A (en) | Pedestrian detection network and model training method, detection method, medium, equipment | |
Zhang et al. | Urban spatial risk prediction and optimization analysis of POI based on deep learning from the perspective of an epidemic | |
CN113033321A (en) | Training method of target pedestrian attribute identification model and pedestrian attribute identification method | |
CN110502989A (en) | A kind of small sample EO-1 hyperion face identification method and system | |
Sun et al. | GAN-based LUCC prediction via the combination of prior city planning information and land-use probability | |
Lin et al. | Optimal CNN-based semantic segmentation model of cutting slope images | |
CN113616209B (en) | Method for screening schizophrenic patients based on space-time attention mechanism | |
Rui et al. | Remote sensing imaging analysis and ubiquitous cloud-based mobile edge computing based intelligent forecast of forest tourism demand |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |