CN114818517A - Land use change simulation method based on NSGA-II self-correcting cellular automaton - Google Patents

Land use change simulation method based on NSGA-II self-correcting cellular automaton Download PDF

Info

Publication number
CN114818517A
CN114818517A CN202210737915.5A CN202210737915A CN114818517A CN 114818517 A CN114818517 A CN 114818517A CN 202210737915 A CN202210737915 A CN 202210737915A CN 114818517 A CN114818517 A CN 114818517A
Authority
CN
China
Prior art keywords
land use
land
nsga
correcting
self
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
Application number
CN202210737915.5A
Other languages
Chinese (zh)
Other versions
CN114818517B (en
Inventor
杜志强
李柏延
王超
李沐春
王伟
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.)
Nanjing Weiguang Intelligent Information Technology Co ltd
Original Assignee
Nanjing Beidou Innovation And Application Technology Research Institute Co ltd
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 Nanjing Beidou Innovation And Application Technology Research Institute Co ltd filed Critical Nanjing Beidou Innovation And Application Technology Research Institute Co ltd
Priority to CN202210737915.5A priority Critical patent/CN114818517B/en
Publication of CN114818517A publication Critical patent/CN114818517A/en
Application granted granted Critical
Publication of CN114818517B publication Critical patent/CN114818517B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling

Abstract

The invention discloses a land use change simulation method based on an NSGA-II self-correcting cellular automaton, which relates to the technical field of land use change simulation application, can solve the problem that the switching rule of the cellular automaton is automatically corrected by utilizing an NSGA-II algorithm, improves the reliability and the expansibility of a land use change simulation model, and through simulation research, the invention fits on the basis of a Gaussian function by utilizing the NSGA-II around the neighborhood transition potential of the switching rule of the cellular automaton, overcomes the defects that the traditional method needs to adopt an enrichment index to describe the neighborhood effect, neglects the influence of distance factors on the acting force between the land, improves the reliability and the expansibility of the land use change simulation model, and is an established land use change simulation method of the self-correcting cellular automaton, the method plays an important role in simulating the land utilization evolution characteristics of a long time sequence, promoting the reasonable utilization of regional resources and ecological sustainable development.

Description

Land use change simulation method based on NSGA-II self-correcting cellular automaton
Technical Field
The invention relates to the technical field of land use change simulation application, in particular to a land use change simulation method based on an NSGA-II self-correcting cellular automaton.
Background
Land-Use/Cover Change (LUCC) is a remarkable representation form of applying influence on Land Use on different space-time scales of local, urban and even global human activities, is an integral part of global environmental Change and sustainable development research, and in recent decades, along with the aggravation of human activities, the Land Use pattern is also changed violently, urbanization is one of the most typical forms of Land Use Change, brings human benefits, and also causes social and ecological problems such as ecological damage, resource waste, climate abnormity, grain safety and the like, so that a Land Use Change model is constructed, Land Use evolution characteristics under the background of urbanization are simulated, the model is important for sustainable development, the LUCC model is used as an important tool for space decision of Land Use Change, and the interpretability and reliability of the simulation result are influenced by related scholars, The general focus of practitioners and decision makers.
However, since land use changes have a path-dependent characteristic, the calibration process of the LUCC model is very complex, and in addition, the existing model calibration method is mainly based on expert experience and manual calibration, which causes the model to have a certain limitation in describing the land use complexity, and it is difficult to meet the requirements of spatial decision on the objectivity and repeatability of the simulation result.
Disclosure of Invention
In order to solve the technical problems, the invention provides a land use change simulation method based on an NSGA-II self-correcting cellular automaton, which comprises the following steps:
s1, according to the land use space-time evolution characteristics of the research area, selecting land use change driving factors and two-stage land use current situation data of the research area, and constructing a land use change simulation research data set;
s2, calculating land use change data based on the current land use data of the two periods, inputting the land use change data and land use change driving factors into a random forest, acquiring the expansion probability of each land class, and primarily constructing a cellular automata conversion rule;
s3, correcting neighborhood transition potential parameters of the cellular automata conversion rule by adopting an NSGA-II algorithm;
s4, establishing a land use evolution self-correcting cellular automata model based on NSGA-II;
s5, simulating space-time land utilization evolution through the NSGA-II-based land utilization evolution self-correcting cellular automata model, and verifying the simulation precision of the model.
The technical scheme of the invention is further defined as follows:
further, in step S1, the method for constructing the land use change simulation research data set includes the following steps:
s1.1, performing projection coordinate system conversion on the land utilization status grid data, the road vector data and the driving factor grid data to ensure that the spatial reference and the resolution of the three data are consistent;
s1.2, performing reachability calculation on road vector data by using Euclidean distance to obtain a road reachability data driving factor in a grid format;
and S1.3, normalizing all driving factors of the road accessibility data.
In the foregoing land use change simulation method based on the NSGA-II self-calibrated cellular automata, in step S2, the land use change data calculation method includes the following steps:
s2.1, superposing the current land utilization state data based on the two stages to obtain land utilization change data;
s2.2, randomly sampling the land use change data and the land use change driving factors, wherein the data of various driving factors of sampling points are independent variables, whether the land use changes into dependent variables or not is judged, the point with the changed land use is marked as 1, and the point without the changed land use is marked as 0;
s2.3, excavating expansion probabilities of various types of land under the influence of various land utilization change driving factors by utilizing random forests;
s2.4, constructing a cellular automaton conversion rule based on the expansion probability of each category, the neighborhood effect and the influence of random factors, wherein the calculation formula is as follows:
Figure DEST_PATH_IMAGE002
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE004
representing the probability of the conversion from the cell land type i to the land type j;
Figure DEST_PATH_IMAGE006
represents the expansion probability of the land use type j calculated by the step S3.3;
Figure DEST_PATH_IMAGE008
representing the neighborhood transition potential with the land type i;
Figure DEST_PATH_IMAGE010
representing a spatial constraint;
Figure DEST_PATH_IMAGE012
representing a random factor;
Figure 417566DEST_PATH_IMAGE008
the neighborhood transition potential with the land type i is represented, and the calculation formula is as follows:
Figure DEST_PATH_IMAGE014
in the formula (I), the compound is shown in the specification,
Figure 742369DEST_PATH_IMAGE008
representing the neighborhood transition potential of the cell i converted from the current land type to the land type j;
Figure DEST_PATH_IMAGE016
representing the set of all cells in the spatial neighborhood with i as the core;
Figure DEST_PATH_IMAGE018
representing any cell in the return spatial neighborhood
Figure DEST_PATH_IMAGE020
The current land use status;
Figure DEST_PATH_IMAGE022
representing any cell in the return spatial neighborhood
Figure 236804DEST_PATH_IMAGE020
Current land use state of
Figure DEST_PATH_IMAGE023
The effort of type j is converted for potential land use,
Figure DEST_PATH_IMAGE025
represents the distance between two cells; finally, the neighborhood transition potential is equal to the sum of the forces of other cells which are d away from the central cell in the neighborhood space;
Figure DEST_PATH_IMAGE027
representing the space constraint, the calculation formula is:
Figure DEST_PATH_IMAGE029
in the formula (I), the compound is shown in the specification,
Figure 441914DEST_PATH_IMAGE027
representing spatial constraints, whether land-use conditions can occurThe limiting factor of the conversion.
In the foregoing land use change simulation method based on the NSGA-II self-correcting cellular automata, in step S3, the method for correcting the neighborhood transition potential parameter of the cellular automata conversion rule includes the following steps:
s3.1, determining decision variables for correcting the cellular automata conversion rule, wherein the decision variables are used for correcting neighborhood transition potentials in the cellular automata conversion rule; based on the step S2, the acting force of the land type to the potential land use conversion type j is assumed, and the distance between two cells
Figure DEST_PATH_IMAGE025A
The Gaussian function is satisfied, and the calculation formula is as follows:
Figure DEST_PATH_IMAGE031
wherein a, b and c represent decision variables which need to be corrected in NSGA-II;
s3.2, determining a target function for evaluating the quality of the correction result; constructing a target function based on Kappa and FoM indexes as NSGA-II;
s3.3, randomly generating an initial population S based on an NSGA-II algorithm, wherein the initial population S comprises N individuals, namely the population scale is N, each individual is a decision vector, and calculating the individual fitness;
s3.4, generating a new population;
and S3.5, repeatedly executing the step S3.4 until the algorithm termination condition is met, and selecting the individuals with the fitness in the range of-50 to 50 as the final solution of the neighborhood transition potential correction of the cellular automaton.
The land use evolution self-correcting cellular automata model based on the NSGA-II self-correcting cellular automata in the step S4 is obtained by adopting the relevant parameters of the conversion rule corrected in the step S3 to be brought into the cellular automata model and then carrying out land use change simulation and iteration, wherein the maximum iteration time is set to be 500 times, and the land use conversion total probability of the self-correcting cellular automata model based on the NSGA-II in the step S4 has the calculation formula as follows:
Figure DEST_PATH_IMAGE033
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE035
the overall probability of ground-based conversion of the NSGA-II based self-correcting cellular automaton model is shown.
The land use change simulation method based on the NSGA-II self-correcting cellular automata comprises the following steps of S5:
s5.1, evaluating a land use change simulation result of the self-correcting cellular automata model based on the NSGA-II algorithm by using overall accuracy OA, FoM and Kappa indexes;
and S5.2, outputting and storing the simulation result in the geographic information software environment.
In the aforementioned land use change simulation method based on the NSGA-II self-correcting cellular automata, in step S3.4, the method for generating the new population comprises the following steps:
s3.4.1, selecting M individuals from the current population;
s3.4.2, intersecting the decision vectors of the selected M individuals;
s3.4.3, carrying out mutation operation on the crossed individuals, and using the mutation operation to make elements in the decision vector mutate;
s3.4.4, calculating the fitness of the newly generated individual;
s3.4.5, selecting individuals with fitness ranging from-50 to 50 from excellent parents and children of the current population to generate a new population.
The invention has the beneficial effects that:
the method can automatically correct the conversion rule of the cellular automata by using an NSGA-II algorithm, improves the reliability and expansibility of a land use change simulation model, and by simulation research, the method surrounds the neighborhood transition potential of the conversion rule of the cellular automata, uses NSGA-II to fit on the basis of a Gaussian function, overcomes the defects that the traditional method needs to adopt an enrichment index to describe the neighborhood effect, neglects the influence of the acting force between the land used by distance factors, and improves the reliability and expansibility of the land use change simulation model.
Drawings
FIG. 1 shows the current land utilization in the test areas in year 2000 and 2010 according to the embodiment of the invention;
FIG. 2 is a test area land use change driver dataset in an embodiment of the present invention;
FIG. 3 is a method block diagram of the present invention;
FIG. 4 is a flow chart of method steps of the present invention.
Detailed Description
In order to facilitate the understanding and implementation of the present invention by those of ordinary skill in the art, the present invention will be further described in detail by taking the land use variation of 20 km around the three gorges dam in 2000-2010 extracted by using Landsat data of Google Earth Engine as an example.
The land use change simulation method based on the NSGA-II self-correcting cellular automata provided by the embodiment, as shown in fig. 3 to 4, includes the following steps:
s1, according to the land use space-time evolution characteristics of the research area, selecting land use change driving factors and two-stage land use current situation data of the research area, and constructing a land use change simulation research data set: performing projection coordinate system conversion on the land utilization status grid data, the road vector data and the driving factor grid data to ensure that the spatial reference and the resolution of the three data are kept consistent; performing reachability calculation on the road vector data by using the Euclidean distance to obtain a road reachability data driving factor in a grid format; all of the road reachability data drivers are normalized.
This step resulted in the present land use data for the 20 km range around the three gorges dam in 2000 and 2010, and all available land use variation driver data sets, as shown in figures 1-2.
S2, constructing land utilization change data based on the current land utilization data of the two phases, and respectively acquiring areas converted into cultivated land, woodland, grassland, water body and construction land based on the current land utilization data of the two phases in 2000 and 2010 through superposition analysis to obtain expansion maps of the lands;
inputting the land use change data and the land use change driving factors into a random forest, acquiring the expansion probability of each land class, and initially constructing a cellular automata conversion rule: in the area shown in fig. 1, randomly sampling land use change data and land use change driving factors, wherein the data of various driving factors of sampling points are independent variables, whether land use changes into dependent variables or not is judged, the point with the changed land use is marked as 1, and the point without the changed land use is marked as 0; utilizing random forest to excavate the expansion probability of each land under the influence of various land utilization change driving factors; based on the expansion probability of each category, neighborhood effect and the influence of random factors, a cellular automata conversion rule is constructed, and the calculation formula is as follows:
Figure DEST_PATH_IMAGE002A
in the formula (I), the compound is shown in the specification,
Figure 301285DEST_PATH_IMAGE004
representing the probability of the conversion from the cell land type i to the land type j;
Figure 97072DEST_PATH_IMAGE006
represents the expansion probability of the land use type j calculated by the step S3.3;
Figure 270564DEST_PATH_IMAGE008
representing the neighborhood transition potential with the land type i;
Figure 281245DEST_PATH_IMAGE010
representing a spatial constraint;
Figure 186885DEST_PATH_IMAGE012
representing a random factor;
Figure 283017DEST_PATH_IMAGE008
the neighborhood transition potential with the land type i is represented, and the calculation formula is as follows:
Figure 994621DEST_PATH_IMAGE014
in the formula (I), the compound is shown in the specification,
Figure 37970DEST_PATH_IMAGE008
representing the neighborhood transition potential of the cell i converted from the current land type to the land type j;
Figure DEST_PATH_IMAGE036
representing the set of all cells in the spatial neighborhood with i as the core;
Figure 176827DEST_PATH_IMAGE018
representing any cell in the return spatial neighborhood
Figure 697939DEST_PATH_IMAGE020
The current land use status;
Figure 947654DEST_PATH_IMAGE022
representing any cell in the return spatial neighborhood
Figure 932928DEST_PATH_IMAGE020
Current land use state of
Figure 429637DEST_PATH_IMAGE023
The effort of type j is converted for potential land use,
Figure DEST_PATH_IMAGE025AA
represents the distance between two cells; finally, the neighborhood transition potential, i.e., the neighborhood effect, is equal to the force of the other cells in the neighborhood space from the central cell by dThe sum of (a);
Figure 438044DEST_PATH_IMAGE027
representing the space constraint, the calculation formula is:
Figure DEST_PATH_IMAGE029A
in the formula (I), the compound is shown in the specification,
Figure 678402DEST_PATH_IMAGE027
the space constraint is represented as a limiting factor of whether the land state can be converted or not.
S3, correcting neighborhood transition potential parameters of the cellular automata conversion rule by adopting an NSGA-II algorithm, and determining decision variables corrected by the cellular automata conversion rule for correcting the neighborhood transition potential in the cellular automata conversion rule; based on step S2, assuming the acting force of the land type on the potential land use conversion type j and the distance between two cells
Figure DEST_PATH_IMAGE025AAA
The Gaussian function is satisfied, and the calculation formula is as follows:
Figure DEST_PATH_IMAGE031A
wherein a, b and c represent decision variables which need to be corrected in NSGA-II;
for evaluating the quality of the correction result; constructing a target function based on Kappa and FoM indexes as NSGA-II; randomly generating an initial population S based on an NSGA-II algorithm, wherein the initial population S comprises N individuals, namely the population scale is N, each individual is a decision vector, and the individual fitness is calculated; selecting M individuals from the current population; intersecting the decision vectors of the selected M individuals; carrying out mutation operation on the crossed individuals for mutating elements in the decision vector; calculating the fitness of the newly generated individual; selecting individuals with fitness ranging from-50 to 50 from excellent parent individuals and offspring individuals of the current population to generate a new population; and repeating iteration until the algorithm termination condition is met, namely computing resource limit is met or the algorithm is converged and an optimal solution is found, and selecting an individual with fitness in the range of-50 to 50 as a final solution of neighborhood transition potential correction of the cellular automaton.
S4, establishing a land use evolution self-correcting cellular automata model based on NSGA-II: substituting the relevant parameters of the conversion rule corrected in the step S3 into the cellular automata model, and then performing land use change simulation and iteration to obtain the land use change model, wherein the maximum iteration number is set to be 500, and the total land use conversion probability of the self-correcting cellular automata model based on NSGA-II in the step S4 has the calculation formula as follows:
Figure 642816DEST_PATH_IMAGE033
in the formula (I), the compound is shown in the specification,
Figure 123475DEST_PATH_IMAGE035
the overall probability of ground-based conversion of the NSGA-II based self-correcting cellular automaton model is shown.
S5, simulating space-time land utilization evolution through a land utilization evolution self-correcting cellular automata model based on NSGA-II, and verifying the simulation precision of the model: evaluating a land use change simulation result of the self-correcting cellular automata model based on the NSGA-II algorithm by using the OA, FoM and Kappa indexes of the overall precision; and finally, outputting and storing the simulation result in a geographic information software environment.
In addition to the above embodiments, the present invention may have other embodiments. All technical solutions formed by adopting equivalent substitutions or equivalent transformations fall within the protection scope of the claims of the present invention.

Claims (7)

1. A land use change simulation method based on an NSGA-II self-correcting cellular automaton is characterized by comprising the following steps: the method comprises the following steps:
s1, according to the land use space-time evolution characteristics of the research area, selecting land use change driving factors and two-stage land use current situation data of the research area, and constructing a land use change simulation research data set;
s2, calculating land use change data based on the current land use data of the two periods, inputting the land use change data and land use change driving factors into a random forest, acquiring the expansion probability of each land class, and primarily constructing a cellular automata conversion rule;
s3, correcting neighborhood transition potential parameters of the cellular automata conversion rule by adopting an NSGA-II algorithm;
s4, establishing a land use evolution self-correcting cellular automata model based on NSGA-II;
s5, simulating space-time land utilization evolution through the NSGA-II-based land utilization evolution self-correcting cellular automata model, and verifying the simulation precision of the model.
2. The land use change simulation method based on the NSGA-II self-correcting cellular automata according to claim 1, wherein: in step S1, the method for constructing the land use change simulation research data set includes the following steps:
s1.1, performing projection coordinate system conversion on the land utilization status grid data, the road vector data and the driving factor grid data to ensure that the spatial reference and the resolution of the three data are consistent;
s1.2, performing reachability calculation on road vector data by using Euclidean distance to obtain a road reachability data driving factor in a grid format;
and S1.3, normalizing all driving factors of the road accessibility data.
3. The land use change simulation method based on the NSGA-II self-correcting cellular automata according to claim 1, wherein: in step S2, the method for calculating land use change data includes the following steps:
s2.1, superposing the current land utilization state data based on the two stages to obtain land utilization change data;
s2.2, randomly sampling the land use change data and the land use change driving factors, wherein the data of various driving factors of sampling points are independent variables, whether the land use changes into dependent variables or not is judged, the point with the changed land use is marked as 1, and the point without the changed land use is marked as 0;
s2.3, excavating expansion probabilities of various types of land under the influence of various land utilization change driving factors by utilizing random forests;
s2.4, constructing a cellular automata conversion rule according to the expansion probability of each region, the neighborhood effect and the influence of random factors, wherein the calculation formula is as follows:
Figure 894228DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 973043DEST_PATH_IMAGE002
representing the probability of the conversion from the cell land type i to the land type j;
Figure 657971DEST_PATH_IMAGE003
represents the expansion probability of the land use type j calculated by the step S3.3;
Figure 429618DEST_PATH_IMAGE004
representing the neighborhood transition potential with the land type i;
Figure 380256DEST_PATH_IMAGE005
representing a spatial constraint;
Figure 200445DEST_PATH_IMAGE006
representing a random factor;
Figure 552929DEST_PATH_IMAGE004
the neighborhood transition potential with the land type i is represented, and the calculation formula is as follows:
Figure 685357DEST_PATH_IMAGE007
in the formula (I), the compound is shown in the specification,
Figure 123292DEST_PATH_IMAGE004
representing the neighborhood transition potential of the cell i converted from the current land type to the land type j;
Figure 543909DEST_PATH_IMAGE008
representing the set of all cells in the spatial neighborhood with i as the core;
Figure 954162DEST_PATH_IMAGE009
representing any cell in the return spatial neighborhood
Figure 67611DEST_PATH_IMAGE010
The current land use status;
Figure 992842DEST_PATH_IMAGE011
representing any cell in the return spatial neighborhood
Figure 404100DEST_PATH_IMAGE010
Current land use state of
Figure 465597DEST_PATH_IMAGE009
The effort of type j is converted for potential land use,
Figure 687631DEST_PATH_IMAGE012
represents the distance between two cells; finally, the neighborhood transition potential is equal to the sum of the forces of other cells which are d away from the central cell in the neighborhood space;
Figure 100158DEST_PATH_IMAGE013
representing the space constraint, the calculation formula is:
Figure 128157DEST_PATH_IMAGE014
in the formula (I), the compound is shown in the specification,
Figure 496690DEST_PATH_IMAGE015
representing spatial constraints, which are limiting factors for whether a transition can occur with the land state.
4. The land use change simulation method based on the NSGA-II self-correcting cellular automata according to claim 1, wherein: in step S3, the method for correcting the neighborhood transition potential parameter of the cellular automata conversion rule includes the following steps:
s3.1, determining decision variables for correcting the cellular automata conversion rule, wherein the decision variables are used for correcting neighborhood transition potentials in the cellular automata conversion rule; based on step S2, assuming the acting force of the land type on the potential land use conversion type j and the distance between two cells
Figure 686363DEST_PATH_IMAGE012
The Gaussian function is satisfied, and the calculation formula is as follows:
Figure 586186DEST_PATH_IMAGE016
wherein a, b and c represent decision variables which need to be corrected in NSGA-II;
s3.2, determining a target function for evaluating the quality of the correction result; constructing a target function based on Kappa and FoM indexes as NSGA-II;
s3.3, randomly generating an initial population S based on an NSGA-II algorithm, wherein the initial population S comprises N individuals, namely the population scale is N, each individual is a decision vector, and calculating the individual fitness;
s3.4, generating a new population;
and S3.5, repeatedly executing the step S3.4 until the algorithm termination condition is met, and selecting the individuals with the fitness in the range of-50 to 50 as the final solution of the neighborhood transition potential correction of the cellular automaton.
5. The land use change simulation method based on the NSGA-II self-correcting cellular automata according to claim 1, wherein: the NSGA-II-based land use evolution self-correcting cellular automata model in the step S4 is obtained by substituting the relevant parameters of the conversion rule corrected in the step S3 into the cellular automata model, then performing land use change simulation and iteration, wherein the maximum iteration frequency is set to be 500 times, and the total land use conversion probability of the NSGA-II-based self-correcting cellular automata model in the step S4 is calculated by the following formula:
Figure 89980DEST_PATH_IMAGE017
in the formula (I), the compound is shown in the specification,
Figure 391648DEST_PATH_IMAGE018
the overall probability of ground-based conversion of the NSGA-II based self-correcting cellular automaton model is shown.
6. The land use change simulation method based on the NSGA-II self-correcting cellular automata according to claim 1, wherein: the step S5 includes the steps of:
s5.1, evaluating a land use change simulation result of the self-correcting cellular automata model based on the NSGA-II algorithm by using overall accuracy OA, FoM and Kappa indexes;
and S5.2, outputting and storing the simulation result in the geographic information software environment.
7. The land use change simulation method based on the NSGA-II self-correcting cellular automata as claimed in claim 4, wherein: in step S3.4, the method of generating a new population comprises the steps of:
s3.4.1, selecting M individuals from the current population;
s3.4.2, intersecting the decision vectors of the selected M individuals;
s3.4.3, carrying out mutation operation on the crossed individuals, and using the mutation operation to make elements in the decision vector mutate;
s3.4.4, calculating the fitness of the newly generated individual;
s3.4.5, selecting individuals with fitness ranging from-50 to 50 from excellent parents and children of the current population to generate a new population.
CN202210737915.5A 2022-06-28 2022-06-28 Land use change simulation method based on NSGA-II self-correcting cellular automaton Active CN114818517B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210737915.5A CN114818517B (en) 2022-06-28 2022-06-28 Land use change simulation method based on NSGA-II self-correcting cellular automaton

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210737915.5A CN114818517B (en) 2022-06-28 2022-06-28 Land use change simulation method based on NSGA-II self-correcting cellular automaton

Publications (2)

Publication Number Publication Date
CN114818517A true CN114818517A (en) 2022-07-29
CN114818517B CN114818517B (en) 2022-09-30

Family

ID=82522520

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210737915.5A Active CN114818517B (en) 2022-06-28 2022-06-28 Land use change simulation method based on NSGA-II self-correcting cellular automaton

Country Status (1)

Country Link
CN (1) CN114818517B (en)

Citations (3)

* Cited by examiner, † Cited by third party
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
CN105512759A (en) * 2015-12-01 2016-04-20 武汉大学 Urban CA model parameter optimization method based on biogeographic optimization algorithm
CN107480885A (en) * 2017-08-14 2017-12-15 国家电网公司 Distributed power source based on non-dominated ranking differential evolution algorithm is layouted planing method

Patent Citations (3)

* Cited by examiner, † Cited by third party
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
CN105512759A (en) * 2015-12-01 2016-04-20 武汉大学 Urban CA model parameter optimization method based on biogeographic optimization algorithm
CN107480885A (en) * 2017-08-14 2017-12-15 国家电网公司 Distributed power source based on non-dominated ranking differential evolution algorithm is layouted planing method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
柯新利等: "内嵌空间聚类算法的分区地理元胞自动机建模与应用", 《地球信息科学学报》 *

Also Published As

Publication number Publication date
CN114818517B (en) 2022-09-30

Similar Documents

Publication Publication Date Title
CN111080070B (en) Urban land utilization cellular automaton simulation method based on space errors
Sahin et al. A spatial temporal decision framework for adaptation to sea level rise
CN112884226A (en) Multi-agent algorithm-based territorial spatial pattern simulation planning method and system
CN108376183B (en) City CA model construction method based on maximum entropy principle
CN114501530B (en) Method and device for determining antenna parameters based on deep reinforcement learning
Zhang et al. TrafficGAN: Off-deployment traffic estimation with traffic generative adversarial networks
CN110909447B (en) High-precision short-term prediction method for ionization layer region
CN110826244A (en) Conjugate gradient cellular automata method for simulating influence of rail transit on urban growth
CN115544889A (en) Numerical mode precipitation deviation correction method based on deep learning
CN115032720A (en) Application of multi-mode integrated forecast based on random forest in ground air temperature forecast
CN109033181B (en) Wind field geographic numerical simulation method for complex terrain area
CN114818517B (en) Land use change simulation method based on NSGA-II self-correcting cellular automaton
CN109636194B (en) Multi-source cooperative detection method and system for major change of power transmission and transformation project
Mondal et al. Cellular automata (CA) contiguity filters impacts on ca Markov modeling of land use land cover change predictions results
Zhao et al. Examining Land-Use Change Trends in Yucheng District, Ya’an City, China, Using ANN-CA Modeling
CN112684519A (en) Weather forecasting method and device, computer equipment and storage medium
CN118051845A (en) Geospatial full coverage data generation method and device based on space variable parameter machine learning
CN115328373B (en) Deterministic coefficient calculation method and system
Sanjuan Gómez et al. A recursive LMI-based algorithm for efficient vertex reduction in LPV systems
CN112633559B (en) Social relationship prediction method and system based on dynamic graph convolutional neural network
CN111815194B (en) Index management method, system and storage medium based on big data
CN117541272B (en) Method, system, equipment and storage medium for determining digital engineering carbon emission data
CN117633964A (en) Urban open space automatic design method and system based on multiple intelligent agents
Shokouhifar et al. DSSA: Direct Simplified Symbolic analysis using metaheuristic-driven circuit modelling
Cao et al. Modeling conversion of rural-urban land use based on cellular automa and genetic algorithm

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
TR01 Transfer of patent right

Effective date of registration: 20230113

Address after: 210000 8 Huyue East Road, Longchi street, Liuhe District, Nanjing City, Jiangsu Province

Patentee after: Nanjing Weiguang Intelligent Information Technology Co.,Ltd.

Address before: 211599 No.8, Huyue East Road, Longchi street, Liuhe District, Nanjing City, Jiangsu Province

Patentee before: Nanjing Beidou innovation and Application Technology Research Institute Co.,Ltd.

TR01 Transfer of patent right