CN110991497B - BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method - Google Patents

BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method Download PDF

Info

Publication number
CN110991497B
CN110991497B CN201911120007.6A CN201911120007A CN110991497B CN 110991497 B CN110991497 B CN 110991497B CN 201911120007 A CN201911120007 A CN 201911120007A CN 110991497 B CN110991497 B CN 110991497B
Authority
CN
China
Prior art keywords
bsvc
land utilization
representing
model
simulation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911120007.6A
Other languages
Chinese (zh)
Other versions
CN110991497A (en
Inventor
冯永玖
童小华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Priority to CN201911120007.6A priority Critical patent/CN110991497B/en
Publication of CN110991497A publication Critical patent/CN110991497A/en
Application granted granted Critical
Publication of CN110991497B publication Critical patent/CN110991497B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155Bayesian classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/16Real estate
    • G06Q50/165Land development
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/176Urban or other man-made structures

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a BSVC (binary sequence virtual machine) method based urban land utilization change simulation cellular automaton method. Comprising the following steps: 1) Performing supervision classification on the remote sensing images to obtain a classification chart of urban land utilization; 2) Obtaining urban land utilization change driving factor data and preprocessing the data; acquiring effective sample points of a land utilization map and a driving factor by a random hierarchical sampling method; 3) Training the effective sample points by using a Bayes Space Variable Coefficient (BSVC) method to obtain a conversion rule of the cellular automaton; 4) Obtaining urban land utilization conversion probability according to CA conversion rules established by BSVC; 5) Build BSVC-based CA model (CA BSVC ) The method comprises the steps of carrying out a first treatment on the surface of the 6) By CA BSVC The model carries out simulation application and verification analysis on urban land utilization, and realizes evaluation through Overall Accuracy (OA) and figure of merit (FOM); 7) And outputting and storing the simulation result. Compared with the prior art, the invention has higher simulation precision and better urban land utilization change simulation capability.

Description

BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method
Technical Field
The invention relates to a method for simulating cellular automata by urban land utilization change, in particular to a method for simulating cellular automata by urban land utilization change based on a BSVC method.
Background
Urban growth reflects the change of natural surface to urban artificial area, and has great influence on human society and ecological environment. In city growth simulation, some models consider spatial non-stationarity, but the existing model methods cannot fully reflect the spatial heterogeneity characteristics of city dynamics.
The geographic Cellular Automaton (CA) is a bottom-up, self-organizing urban simulation model for urban land use history pattern reconstruction and future scene prediction. To define driver-based transformation rules, the CA model typically uses driver factors reflecting the biophysical, socioeconomic, and infrastructure of the urban dynamics. The driving factor based transformation rules are typically constructed using Logistic Regression (LR) which assumes that the impact of each factor on urban space growth is the same. This means that the logistic regression derived parameters have spatial invariance and do not reflect the spatial non-stationarity of the city growth. To solve the problem of spatial instability, some scholars have developed some spatial methods to construct the CA model. For example, partition-based CA modeling divides space into several sub-regions and then uses LR to handle urban growing spatial differences. The K-means and KNN-cluster are adopted for regional division according to the evolution rate, and the performance of the method is superior to that of the traditional CA model. By employing unique transformation rules in each sub-region, the partitioning approach may reflect spatial non-stationarity explicitly and implicitly. Although these methods may represent spatial non-stationarity, they may not adequately represent the spatial non-stationarity of urban growth due to the use of spatially invariant parameters.
The spatial coefficient of variation model (SVCM) can generate transformation rules with spatial non-stationarity by allowing coefficients to vary with spatial and positional changes, thereby defining the spatial non-stationarity of urban growth. In SVCM, geographic Weighted Regression (GWR) is a typical method to incorporate spatial non-stationarity into the parameterization without predefined region classification. GWR is a local statistical model that uses a distance weighted subset of samples to generate regression coefficients for each point that are sensitive to the location of the sample. Recent technology, the combination of GWR and CA models can more accurately simulate urban expansion than traditional CA models. Although this approach may take into account spatial non-stationarity, there are some features that may lead to modeling difficulties. First, since GWR regression depends on the properties of surrounding samples, data set outliers may affect regression coefficients through spatial enclave effects. Second, non-constant variances are widely present in space and may not meet the assumption of normal errors. In contrast, a Bayesian Spatial Variation Coefficient (BSVC) method can detect non-constant variances, detect the effects of outliers, and thereby mitigate the bias of coefficient estimates. Therefore, the BSVC method should be more suitable for city growth simulation in combination with the CA model.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method for simulating cellular automata by urban land utilization change based on a BSVC method.
The aim of the invention can be achieved by the following technical scheme:
a BSVC method-based urban land utilization change simulation cellular automaton method comprises the following steps:
step 1: performing supervision classification on the remote sensing images to obtain land utilization classification diagrams of initial and final years;
step 2: obtaining urban land utilization change driving factor data, and obtaining a land utilization classification chart and effective sample points of the driving factor data after preprocessing;
step 3: training the effective sample points by using a Bayes space coefficient changing method to obtain a conversion rule of the cellular automaton;
step 4: obtaining urban land utilization conversion probability by utilizing conversion rules of cellular automata built according to BSVC training;
step 5: establishing a CA model based on BSVC (binary sequence-based virtual reality) by integrating transformation probability, cell field, random factors and limiting factors, namely CA BSVC A model;
step 6: by CA BSVC The model carries out simulation application and verification analysis on urban land utilization to obtain CA BSVC A model simulation result;
step 7: for CA BSVC And the model and the simulation result thereof respectively carry out precision assessment from two aspects of rule fitting and simulation result, and output and store the simulation result.
Further, the step 1 comprises the following sub-steps:
step 11: acquiring satellite remote sensing image and vector map data required by modeling, and carrying out space reference unification and geometric correction on the satellite remote sensing image and vector map data;
step 12: and acquiring land utilization classification diagrams of cities in the initial year and the ending year based on a spectrum angle supervision classification method by utilizing two-stage satellite remote sensing images.
Further, the step 2 comprises the following sub-steps:
step 21: selecting driving space factor data affecting urban land utilization change, wherein the driving space factor data comprises data of highways, railways, subways, primary highways and elevations and population;
step 22: obtaining variables of distances of expressways, railways, subways and primary roads in ArcGIS by using Euclidean distances through remote sensing image data, administrative division diagrams and road traffic diagrams;
step 23: and sampling the land utilization classification map and the factor graph layer by using a random hierarchical sampling method, and obtaining effective sample points of the land utilization classification map and the driving factor data for providing reliable sample data points for CA rule conversion.
Further, the step 4 specifically includes: the method for acquiring the transformation probability of the land by utilizing the transformation rule of the cellular automaton established according to BSVC training to acquire the transformation probability distribution of the land under the influence of the space variable under the set space resolution comprises the following steps:
assuming that s represents whether the cell state transitions from non-urban to urban from time t to t+1, then y is denoted as 1; s is marked as 0 when the state of the cell is unchanged from time t to t+1;
and calculating the conversion probability of the land by using the acquired space variable data.
Further, CA in the step 5 BSVC The core problem of the model is to determine whether to switch a cell from one state to another in the next step, and the corresponding description formula is:
Figure BDA0002275188510000031
in the method, in the process of the invention,
Figure BDA0002275188510000032
indicates the state of the cell at time t+1, < >>
Figure BDA0002275188510000037
Representing the cell state at time t, f representing the calculated total transition probability P g Is a comprehensive transfer rule of (1),P d Representing land use conversion probability based on driving factors, < ->
Figure BDA0002275188510000038
Representing the impact of the domain, con represents the spatial suppression function.
Further, CA in the step 5 BSVC The land utilization conversion probability and the total conversion probability of the model based on the driving factors are calculated as follows:
Figure BDA0002275188510000035
Figure BDA0002275188510000036
wherein a is i Representing the weight, x, of the ith driving factor i Represents the ith driving factor, ε represents the fit residual, TIP represents the time delta parameter, and LAP represents the local adjustment parameter.
Further, CA in the step 5 BSVC The field of the model adopts Moore field, and the description formula is as follows:
Figure BDA0002275188510000041
in the method, in the process of the invention,
Figure BDA0002275188510000042
the total number of urban cells in the m.times.m domain is represented, and (j. Noteq.i) indicates that the central cell i does not participate in the calculation.
Further, the weight of the ith driving factor is calculated as:
Figure BDA0002275188510000043
in which W is ij Representing a row normalization matrix, I k A standard matrix representing k rows and k columns, u i Representing random disturbance, beta i Representing the matrix of model coefficients, σ, at position i 2 Representing variance, delta 2 Representing a scale factor controlling the smoothing effect, W i The (n×n) space matrix in the position i is represented, and X represents the dependent variable matrix (n×k).
Further, the step 6 specifically includes: CA implementation using UrbanCA software and MTALAB language BSVC And (3) a simulation and prediction process of the model is performed by using the CA model for M times by taking the land utilization pattern of a certain year as an initial state, wherein M represents the year difference between the initial and the end, and a simulation and prediction result of land utilization change is obtained.
Further, the step 7 includes the following sub-steps:
step 71: by comparison with the land utilization pattern of remote sensing classification, CA BSVC And (3) carrying out precision calculation and evaluation on the model simulation result, wherein the precision calculation indexes comprise: figure of merit FOM and overall accuracy OA;
step 72: CA will be CEO Superposing and evaluating the model simulation result and the remote sensing classification result, wherein the superposed result comprises the following steps: the actual and simulation are city Hit, non-city simulation is city False, city simulation is non-city Miss, non-city CR and Water;
step 73: and outputting and storing the simulation result in GIS software.
Compared with the prior art, the invention has the following advantages:
(1) The invention considers the Bayesian space variable coefficient and constructs a CA model CA based on the Bayesian Space Variable Coefficient (BSVC) BSVC And is applied to simulation of urban land use variation. CA model CA by regressing the model with Geographic Weighting (GWR) GWR And (3) comparing the simulation results of the test pieces. CA (CA) BSVC Is superior to CA in terms of overall accuracy and graphics goodness GWR . The urban land utilization change model simulation method based on the cellular automata and the Bayesian space variable coefficients can better simulate and predict urban land utilization change dynamics.
(2) The invention relates to a BSVC-method-based urban land utilization change simulation cellular automaton method, which adopts influence factors mainly including space distance variables, natural factors and socioeconomic factor variables, and adopts a Bayesian space change coefficient CA model (CA BSVC ) The modeling effect of the model is superior to that of the geo-weighted regression CA model (CA GWR ) The simulation of urban land utilization change can be well completed.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of an example study area;
FIG. 3 is a diagram of urban land use driving factors;
FIG. 4 shows the actual urban land use variation and CA BSVC 、CA GWR Conversion probability maps of the two models;
FIG. 5 is a real urban land distribution and CA BSVC 、CA GWR Two models simulate urban land distribution maps.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The invention can be realized by the following technical scheme:
as shown in fig. 1, the overall flow of the method for simulating cellular automata by urban land utilization change based on a Bayesian Space Variable Coefficient (BSVC) method of the invention comprises the following steps:
1) Performing supervision classification on the remote sensing images by utilizing a spectrum angle method to obtain urban land utilization classification diagrams of initial and final years;
2) Obtaining urban land utilization change driving factor data and preprocessing; acquiring effective sample points of a land utilization map and a driving factor by a random hierarchical sampling method;
3) Training effective sample points by using a Bayes Space Variable Coefficient (BSVC) method to obtain a conversion rule of a Cellular Automaton (CA);
4) Obtaining urban land utilization conversion probability according to CA conversion rules established by BSVC;
5) Establishing a CA model (CA) based on BSVC by integrating transformation probability, cell neighborhood, random factors and limiting factors BSVC );
6) By CA BSVC The model carries out simulation application and verification analysis on urban land utilization, and realizes evaluation through Overall Accuracy (OA) and figure of merit (FOM);
7) And outputting and storing the simulation result.
The step 1) specifically comprises the following steps:
8) Acquiring satellite remote sensing image and vector map data required by modeling, and carrying out space reference unification and geometric correction on the satellite remote sensing image and vector map data;
9) Acquiring urban land utilization classification diagrams of the initial year and the final year based on a spectrum angle supervision classification method by utilizing two-stage satellite remote sensing images;
the step 2) specifically comprises the following steps:
10 Firstly, selecting space factors which influence urban land utilization change, including data of expressways, railways, subways, primary highways, elevations and population;
11 The variables of the distances of the expressway, the railway, the subway and the primary road are obtained in the ArcGIS by using Euclidean distances through remote sensing image data, administrative division diagrams and road traffic diagrams.
The step 3) is specifically as follows:
12 Firstly, sampling a land utilization map and a factor map layer by using a random hierarchical sampling method, and providing reliable sample point data for CA rule conversion;
the step 4) is specifically as follows;
13 Training CA conversion rules on the obtained effective sampling point data by using Bayesian Space Variable Coefficients (BSVC);
14 Using established CA transformation rules, the transformation probability distribution under the influence of the spatial variable is obtained at a spatial resolution of 30 m. The method for obtaining the land transition probability data comprises the following steps:
assuming that s represents whether the cell state transitions from Non-Urban (Non-uban) to Urban (Urban) from time t to t+1, s is denoted as 1; s is marked as 0 if the state of the cell has not changed from time t to t+1. And calculating the land transition probability by using the acquired space variable data.
The step 5) is specifically as follows;
15 Based on the data of step 14), establishing a geographic CA model based on BSVC and GWR, specifically comprising the following steps: the CA model determines whether to next transition a unit from one state to another, the cell state at time t+1 can be expressed as:
Figure BDA0002275188510000071
in the method, in the process of the invention,
Figure BDA0002275188510000072
indicates the state of the cell at time t+1, < >>
Figure BDA0002275188510000073
Representing the cell state at time t, f representing the calculated total transition probability P g Comprehensive transfer rules of P d Representing land use conversion probability based on driving factors, < ->
Figure BDA0002275188510000074
Representing the impact of the domain, con represents the spatial suppression function.
The Time Increment Parameter (TIP) is utilized to counteract the decay of the transition probability based on the driving factor, and the Local Adjustment Parameter (LAP) is utilized to counteract the increase in the neighborhood impact. Thus, the transition probability and the total transition probability based on the driving factor can be given by the following formulas:
Figure BDA0002275188510000075
Figure BDA0002275188510000076
wherein a is i Representing the weight, x, of the ith driving factor i The i-th driving factor is represented, epsilon represents the fitting residual error, TIP represents the time increment parameter, the value range of which is 0.0-0.1, LAP represents the local adjustment parameter, and the value range of which is 0.5-1.
For evaluation of the influence of the neighborhood, the CA model is more of a regular neighborhood of square or circle, such as the Moore neighborhood of m can be expressed as:
Figure BDA0002275188510000077
in the method, in the process of the invention,
Figure BDA0002275188510000078
representing the total number of urban cells in the m×m domain, (j+.i) representing that the central cell i does not participate in the calculation, the invention selects Moore5×5 as the cell neighborhood.
The limiting factor Con indicates that the cells are subject to some limitation including large-area water bodies, basic farms, ecological protection areas, parks, greenbelts, etc., and cannot develop and transform into urban cells. Con can be expressed as:
Con=Bin(cell i (t)~available)
wherein Con is 0 or 1,0 indicates that the cell cannot be developed as a city cell, and 1 indicates that the cell can be developed as a city cell.
The random factor R is used to simulate a cell state transition caused by an uncertain factor, such as a cell that has no urban cell nearby, and the random factor increases the probability of development, and the cell is converted from a non-urban state to a urban state. The random factor R is expressed as:
R=1+(lnr) a
wherein R represents a random number between 0 and 1, a represents a control parameter of a random factor R, and the value is an integer between 0 and 10.
Driving factor based land utilization conversion probability P determined by space variable d Is the core of the transformation rules, which represents the impact of these factors on land utilization and affects the cell state at the next moment by way of probability. If a Geographic Weighted Regression (GWR) is used to obtain the CA parameter, the weight a of the ith driving factor i The inner can be calculated by the following formula:
W i Y=W iii
in which W is i Representing an (n) spatial matrix in position i; y is an explanatory variable vector (n×1); x is a dependent variable matrix (n X k); beta i Representing a matrix of model coefficients at location i; epsilon i Representing random errors.
If CA parameters are obtained by using Bayesian space-variant coefficients (BSVC), the weight a of the ith driving factor i The method can be modified as follows:
Figure BDA0002275188510000081
in which W is ij Representing a row normalization matrix, I k A standard matrix representing k rows and k columns, u i Representing random disturbance, beta i Representing the matrix of model coefficients, σ, at position i 2 Representing variance, delta 2 Representing a scale factor controlling the smoothing effect, W i The (n×n) space matrix in the position i is represented, and X represents the dependent variable matrix (n×k).
The total conversion probability P of land utilization is calculated according to the above formula g . In actual calculation, the MTALAB language is utilized to complete the parameter calculation of GWR and BSVC, and the calculation result and the set threshold value P are used thd A comparison is made to determine if the cell will be transformed at one time. Probability of transition P when cell i gi,t Greater than the set threshold P thd Converting into city type, otherwise, maintaining the state of the cell unchanged, and correspondingly describing the formula as follows:
Figure BDA0002275188510000082
the step 6) is specifically as follows;
16 CA implementation using urbanaca software and MTALAB language BSVC And (3) selecting a land utilization pattern of a certain year as an initial state, and operating the CA model for M times (the initial and ending years are different) to obtain a simulation and prediction result of land utilization change.
17 A land use change result based on the two model simulations and predictions is output.
The step 7) is specifically as follows;
18 For CA) BSVC Land utilization results of model simulation are evaluated in terms of simulation accuracy from two aspects of rule fitting accuracy and simulation result respectively
Firstly, comparing the simulation result with the land utilization pattern of remote sensing classification, and calculating the accuracy of the simulation result, wherein the main indexes include graphic goodness (FOM) and Overall Accuracy (OA). Decomposing the overall accuracy into two types, namely a city (Hit) and a non-City (CR), and decomposing errors into two types, namely ignorance (Misses) and substitution (False), wherein the ignorance errors refer to urban cells which are actually cities but are simulated to be non-cities, namely, the CA model cannot capture; an alternative error refers to a city cell that is actually non-city but modeled as a city, i.e., the CA model erroneously increases.
Superposing the simulation result and the remote sensing classification result, wherein the superposition result comprises 5 types: the actual and simulated are city (Hit), actual non-city simulated as city (False), actual city simulated as non-city (Miss), actual and simulated are non-City (CR), and Water (Water). Based on visual discrimination display, contrast CA BSVC The simulation result of the model differs from the actual classification result.
The step 8) specifically comprises the following steps:
19 Outputting and storing the simulation result in GIS software.
The practical embodiment of the invention is as follows:
taking the land utilization of the combined fertilizer city in 2008-2018 as a case, the regional position of the case is shown in figure 2. For testingSyndrome CA BSVC The effectiveness of the model in land use change simulation, in which case the CA model (CA GWR ) As a comparison object, the change process of the synchronous urban land utilization is simulated, and the result shows that CA BSVC Is superior to CA in simulation effect GWR And (5) a model. A method for simulating cellular automata based on the urban land utilization change of Bayesian space variable coefficients comprises the following steps:
1) Firstly, remote sensing image data of the combined fertilizer city 2008 and 2018, administrative division diagrams and road traffic diagrams are selected to be used as basic data for training CA rule conversion and obtaining land transition probability;
2) Sampling the values of the space variables, the initial year and the end year state values of land use according to remote sensing image data by using a random hierarchical sampling method;
3) Calculating the distance, elevation and population data (table 1) from the expressway, the railway, the subway and the primary road by using the remote sensing images of each year, the administrative division layer and the road traffic layer and using Euclidean distance;
4) The method is used for supervising and classifying the fertilizer combination remote sensing image by utilizing a spectrum angle method, so that land utilization patterns are interpreted;
5) And realizing Bayesian Space Variable Coefficients (BSVC) and Geographic Weighted Regression (GWR) by using the effective sample points and the space variable values obtained by using a random hierarchical sampling method in actual calculation by using MATLAB language. Table 1 shows goodness of fit for the two models, indicating CA BSVC The model is better; table 2 shows transformation rule parameters for both models and fig. 3 shows urban land transformation for both models;
6) Using the obtained land transition probability and CA conversion rule (FIG. 4), a geographic CA model CA based on BSVC and GWR is established BSVC And CA GWR
7) With 2008 state as initial value, CA is used respectively BSVC And CA GWR The model was run 10 times to predict 2018 land use change (fig. 5);
8) Comparing the simulated and predicted result with the real city growth, and analyzing the change of the Overall Accuracy (OA) and the figure of merit (FOM); table 2 shows that the overall accuracy of the invention is improved by 0.5% and the figure of merit for the change of interest is improved by 23.5% compared to the GWR based CA model;
9) And outputting and storing the visualized result.
Table 1 CA GWR And CA BSVC Model parameter comprehensive statistics
Figure BDA0002275188510000101
Table 2 CA GWR And CA BSVC Accuracy result analysis of (a)
Figure BDA0002275188510000102
Note that: variation= (BSVC-GWR)/gwr×100
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (4)

1. A BSVC method-based urban land utilization change simulation cellular automaton method is characterized by comprising the following steps:
step 1: performing supervision classification on the remote sensing images to obtain land utilization classification diagrams of initial and final years;
step 2: obtaining urban land utilization change driving factor data, and obtaining a land utilization classification chart and effective sample points of the driving factor data after preprocessing;
step 3: training the effective sample points by using a Bayes space coefficient changing method to obtain a conversion rule of the cellular automaton;
step 4: obtaining urban land utilization conversion probability by utilizing conversion rules of cellular automata built according to BSVC training;
step 5: establishing a CA model based on BSVC (binary sequence-based virtual reality) by integrating transformation probability, cell field, random factors and limiting factors, namely CA BSVC A model;
step 6: by CA BSVC The model carries out simulation application and verification analysis on urban land utilization to obtain CA BSVC A model simulation result;
step 7: for CA BSVC The model and the simulation result thereof are respectively subjected to precision assessment from two aspects of rule fitting and simulation result, and the simulation result is output and stored;
the step 2 comprises the following sub-steps:
step 21: selecting driving space factor data affecting urban land utilization change, wherein the driving space factor data comprises data of highways, railways, subways, primary highways and elevations and population;
step 22: obtaining variables of distances of expressways, railways, subways and primary roads in ArcGIS by using Euclidean distances through remote sensing image data, administrative division diagrams and road traffic diagrams;
step 23: sampling the land utilization classification map and the factor graph layer by using a random hierarchical sampling method to obtain effective sample points of the land utilization classification map and the driving factor data for providing reliable sample data points for CA rule conversion;
the step 4 specifically includes: the method for acquiring the transformation probability of the land by utilizing the transformation rule of the cellular automaton established according to BSVC training to acquire the transformation probability distribution of the land under the influence of the space variable under the set space resolution comprises the following steps:
assuming that s represents whether the cell state transitions from non-urban to urban from time t to t+1, then y is denoted as 1; s is marked as 0 when the state of the cell is unchanged from time t to t+1;
calculating the conversion probability of the land by using the acquired space variable data;
CA in the step 5 BSVC The core problem of the model is to determine whether to switch a cell from one state to another in the next step, and the corresponding description formula is:
Figure FDA0004092735420000021
in the method, in the process of the invention,
Figure FDA0004092735420000022
indicates the state of the cell at time t+1, < >>
Figure FDA0004092735420000023
Representing the cell state at time t, f representing the calculated total transition probability P g Comprehensive transfer rules of P d Representing land utilization conversion probability based on driving factors, Ω i t represents the influence of the domain, con represents the spatial suppression function;
CA in the step 5 BSVC The land utilization conversion probability and the total conversion probability of the model based on the driving factors are calculated as follows:
Figure FDA0004092735420000024
Figure FDA0004092735420000025
wherein a is i Representing the weight, x, of the ith driving factor i Representing the ith driving factor, epsilon representing the fitting residual, TIP representing the time increment parameter, LAP representing the local adjustment parameter;
CA in the step 5 BSVC The field of the model adopts Moore field, and the description formula is as follows:
Figure FDA0004092735420000026
in the method, in the process of the invention,
Figure FDA0004092735420000027
representing the total number of urban cells in the m×m domain, (j+.i) representing that the central cell i does not participate in the calculation;
the weight of the ith driving factor is calculated as follows:
Figure FDA0004092735420000028
in which W is ij Representing a row normalization matrix, I k A standard matrix representing k rows and k columns, u i Representing random disturbance, beta i Representing the matrix of model coefficients, σ, at position i 2 Representing variance, delta 2 Representing a scale factor controlling the smoothing effect, W i The (n×n) space matrix in the position i is represented, and X represents the dependent variable matrix (n×k).
2. The method for simulating cellular automata for urban land use change based on BSVC method according to claim 1, wherein said step 1 comprises the following sub-steps:
step 11: acquiring satellite remote sensing image and vector map data required by modeling, and carrying out space reference unification and geometric correction on the satellite remote sensing image and vector map data;
step 12: and acquiring land utilization classification diagrams of cities in the initial year and the ending year based on a spectrum angle supervision classification method by utilizing two-stage satellite remote sensing images.
3. The method for simulating cellular automata for urban land use variation based on BSVC method according to claim 1, wherein said step 6 specifically comprises: CA implementation using UrbanCA software and MTALAB language BSVC The simulation and prediction flow of the model selects the land utilization pattern of a certain year as an initial state and utilizes the CA model to run M times, wherein M represents the year difference between the initial and the end to obtain the landUsing varying simulations and predictions.
4. The method for simulating cellular automata for urban land use change based on BSVC method according to claim 1, wherein said step 7 comprises the following sub-steps:
step 71: by comparison with the land utilization pattern of remote sensing classification, CA BSVC And (3) carrying out precision calculation and evaluation on the model simulation result, wherein the precision calculation indexes comprise: figure of merit FOM and overall accuracy OA;
step 72: CA will be CEO Superposing and evaluating the model simulation result and the remote sensing classification result, wherein the superposed result comprises the following steps: the actual and simulation are city Hit, non-city simulation is city False, city simulation is non-city Miss, non-city CR and Water;
step 73: and outputting and storing the simulation result in GIS software.
CN201911120007.6A 2019-11-15 2019-11-15 BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method Active CN110991497B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911120007.6A CN110991497B (en) 2019-11-15 2019-11-15 BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911120007.6A CN110991497B (en) 2019-11-15 2019-11-15 BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method

Publications (2)

Publication Number Publication Date
CN110991497A CN110991497A (en) 2020-04-10
CN110991497B true CN110991497B (en) 2023-05-02

Family

ID=70084419

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911120007.6A Active CN110991497B (en) 2019-11-15 2019-11-15 BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method

Country Status (1)

Country Link
CN (1) CN110991497B (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111680576A (en) * 2020-05-20 2020-09-18 中国地质大学(武汉) LULC prediction method based on self-adaptive cellular algorithm
CN112163367B (en) * 2020-08-20 2023-02-07 同济大学 Firefly algorithm and cellular automaton fused city expansion simulation prediction method
CN112131731B (en) * 2020-09-15 2022-06-14 同济大学 Urban growth cellular simulation method based on spatial feature vector filtering
CN112487724B (en) * 2020-12-11 2022-09-23 重庆邮电大学 Urban dynamic expansion simulation method based on partition and improved CNN-CA model
CN112597948B (en) * 2020-12-29 2023-03-28 同济大学 Urban land utilization change prediction method
CN112651661B (en) * 2021-01-11 2024-06-18 中国科学院空天信息创新研究院 Village and town aggregation digital simulation method and system based on road and land interaction
CN112818447A (en) * 2021-01-29 2021-05-18 中国地质大学(武汉) Urban space structure analysis method
CN113505948B (en) * 2021-09-13 2021-11-19 四川师范大学 Future ecological security pattern prediction and optimization method based on Bayesian network
CN115238572B (en) * 2022-06-29 2024-08-27 北京师范大学 Urban expansion simulation method and device based on neural network
CN116453583B (en) * 2023-03-16 2024-05-31 宁夏蓝怡生物工程有限公司 Method for simulating change of nuclear protein algae corrected by LUCC cellular automaton
CN116976526B (en) * 2023-09-20 2023-12-15 北京师范大学 Land utilization change prediction method coupling ViViViT and ANN

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102222313A (en) * 2010-04-14 2011-10-19 同济大学 Urban evolution simulation structure cell model processing method based on kernel principal component analysis (KPCA)
CN105512759A (en) * 2015-12-01 2016-04-20 武汉大学 Urban CA model parameter optimization method based on biogeographic optimization algorithm
CN106021751A (en) * 2016-05-26 2016-10-12 上海海洋大学 Land utilization change simulation method for coastal zone based on CA and SAR
CN108376183A (en) * 2017-12-29 2018-08-07 武汉大学 A kind of city CA model construction method based on principle of maximum entropy

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9147132B2 (en) * 2013-09-11 2015-09-29 Digitalglobe, Inc. Classification of land based on analysis of remotely-sensed earth images
EP3151169A3 (en) * 2015-09-30 2017-07-05 Tata Consultancy Services Limited Methods and systems for optimizing hidden markov model based land change prediction

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102222313A (en) * 2010-04-14 2011-10-19 同济大学 Urban evolution simulation structure cell model processing method based on kernel principal component analysis (KPCA)
CN105512759A (en) * 2015-12-01 2016-04-20 武汉大学 Urban CA model parameter optimization method based on biogeographic optimization algorithm
CN106021751A (en) * 2016-05-26 2016-10-12 上海海洋大学 Land utilization change simulation method for coastal zone based on CA and SAR
CN108376183A (en) * 2017-12-29 2018-08-07 武汉大学 A kind of city CA model construction method based on principle of maximum entropy

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Xiaohua Tong等.A review of assessment methods for cellular automata models of land-use change and urban growth.International Journal of Geographical Information Science .2019,866-898. *
冯永玖等.基于空间自回归CA模型的城市土地利用变化模拟与预测.地理与地理信息科学.2016,第32卷(第05期),37-44,127. *

Also Published As

Publication number Publication date
CN110991497A (en) 2020-04-10

Similar Documents

Publication Publication Date Title
CN110991497B (en) BSVC (binary sequence video coding) -method-based urban land utilization change simulation cellular automaton method
Feng et al. Modeling urban growth with GIS based cellular automata and least squares SVM rules: a case study in Qingpu–Songjiang area of Shanghai, China
CN110991262B (en) Multi-bandwidth geographic weighted regression cellular automaton method for ecological service value prediction
CN111598101B (en) Urban area intelligent extraction method, system and equipment based on remote sensing image scene segmentation
CN109359166B (en) Space growth dynamic simulation and driving force factor contribution degree synchronous calculation method
CN102222313B (en) Urban evolution simulation structure cell model processing method based on kernel principal component analysis (KPCA)
CN106021751A (en) Land utilization change simulation method for coastal zone based on CA and SAR
Du et al. A case-based reasoning approach for land use change prediction
Li et al. Multiple land use change simulation with Monte Carlo approach and CA-ANN model, a case study in Shenzhen, China
CN110909924A (en) City expansion multi-scenario simulation cellular automata method based on cross entropy optimizer
CN110766038A (en) Unsupervised landform classification model training and landform image construction method
CN108376183B (en) City CA model construction method based on maximum entropy principle
Li et al. Firefly algorithm-based cellular automata for reproducing urban growth and predicting future scenarios
Chettry et al. Delineating urban growth boundary using remote sensing, ANN-MLP and CA model: a case study of Thiruvananthapuram urban agglomeration, India
Wang et al. Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture
Moradi et al. Projection of future land use/cover change in the Izeh-Pyon Plain of Iran using CA-Markov model
Chen et al. A cellular automata approach of urban sprawl simulation with Bayesian spatially-varying transformation rules
CN201716727U (en) Geographical simulation system based on remote sensing and GIS
CN117827863B (en) Atmospheric environment monitoring and analyzing method and system based on CLDAS database
Wang et al. A comparison of proximity and accessibility drivers in simulating dynamic urban growth
CN116976526B (en) Land utilization change prediction method coupling ViViViT and ANN
Goldberg et al. Toward quantitative geocode accuracy metrics
CN116167661A (en) Land utilization change simulation credibility assessment method based on space dislocation
Simpson et al. An open-source automatic survey of green roofs in London using segmentation of aerial imagery
Tayyebi et al. Monitoring land use change by multi-temporal Landsat remote sensing imagery

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