CN114417724A - Simulation method for land use evolution of mountain city - Google Patents
Simulation method for land use evolution of mountain city Download PDFInfo
- Publication number
- CN114417724A CN114417724A CN202210069578.7A CN202210069578A CN114417724A CN 114417724 A CN114417724 A CN 114417724A CN 202210069578 A CN202210069578 A CN 202210069578A CN 114417724 A CN114417724 A CN 114417724A
- Authority
- CN
- China
- Prior art keywords
- simulation
- land
- mountain
- data
- land use
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for simulating land use evolution of mountain cities, which comprises the following specific steps of: s1, preprocessing data: acquiring mountain city remote sensing image data, preprocessing the data, S2, determining a driving factor, and analyzing contribution: selecting the city driving factor data, performing factor contribution analysis on different land utilization types, and simulating a model in S3: simulating the land utilization condition by determining parameters such as conversion rules, neighborhood weights and the like, and S4, precision evaluation: and comparing the simulation result with the real land utilization data, and verifying the precision through a Kappa coefficient and a FoM index. According to the method, simulation is performed on the basis of an improved CA model-PLUS model, a new conversion rule data mining framework in the model can be used for identifying rules of land utilization change, the advantages of a conversion analysis strategy and a pattern analysis strategy are combined, the contribution degree of each factor is distinguished by adding special driving factors of the mountain cities, the land utilization simulation precision of the mountain cities is improved, and therefore the driving factors of land utilization evolution of the mountain cities are accurately analyzed, and the land utilization change is accurately simulated.
Description
Technical Field
The invention relates to the technical field of geographic information, in particular to a method for simulating land use evolution of a mountain city.
Background
At present, the existing land utilization simulation model adopts a cellular automata model and a series of derived improved models, in order to improve the simulation precision and the operation speed, the improved cellular automata model technology is gradually developed, for example, in the Chinese patent 'a method for simulating urban extension of a cellular automata based on random forest', with the application number of 201410409993.8, a random forest-cellular automata model is proposed;
however, in the current simulation of urban land use evolution, the simulation of special cities such as mountains is less, the distribution of land use types of mountain cities is obviously influenced by terrain due to high terrain, large fall and large gradient, and the arrangement of construction lands such as road networks communicated among towns and groups is also influenced deeply due to the terrain and the obstruction of mountains, so the simulation analysis of the land use of the mountain cities is particularly important.
Disclosure of Invention
The invention provides a method for simulating land use evolution of mountain cities, which can effectively solve the problems that the simulation of special cities such as mountains is less, the distribution of land use types of the mountain cities is obviously influenced by the terrain due to higher terrain, larger fall and large gradient of the mountain cities, and the arrangement of construction land such as road networks communicated among towns and groups is also deeply influenced due to the terrain and the blockage of the mountains in the conventional simulation of the land use evolution of the cities, and the like.
In order to achieve the purpose, the invention provides the following technical scheme: a simulation method for land utilization evolution of mountain cities comprises the following specific steps:
s1, preprocessing data: acquiring mountain city remote sensing image data and preprocessing the data;
s2, determining a driving factor, and analyzing the contribution: selecting the city driving factor data, and performing factor contribution analysis on different land utilization types;
s3, model simulation: simulating the land utilization condition by determining parameters such as a conversion rule, neighborhood weight and the like;
s4, precision evaluation: and comparing the simulation result with the real land utilization data, and verifying the precision through a Kappa coefficient and a FoM index.
According to the technical scheme, in the step S2, the contributions of the factors to the change of different land utilization types are analyzed, and the importance of the independent variable to the change of the dependent variable is calculated by adopting the root mean square error and the specific detection value of the root mean square error outside the bag of the random forest;
random sampling is carried out on each land class by adopting a random forest method, and the method can be used for outputting the growth probability of the land utilization type k of the i grid
The formula is as follows:
in the formula (1), d ═ 1 indicates that there is conversion from another site type to a k type, and the rest indicates d ═ 0;
x represents a drive factor vector;
the I (-) function is about a set of decision trees in a random forest;
hn(x) Representing the prediction type of the vector x under the nth decision tree;
m is the number of all decision trees;
and reasonably configuring the pixel space distribution of each land utilization type in the future by combining the development probability, the neighborhood weight, the conversion rule and the region constraint condition of each land utilization type.
According to the technical scheme, in the step S3, a PLUS model is used for simulation, the number of the metamorphic cells is changed during simulation, and neighborhood weight parameters in the model need to be repeatedly debugged during simulation until the simulation precision meets the requirement.
According to the technical scheme, in the S4, the Kappa coefficient integrates two parameters of user precision and drawing precision to check the grid land utilization type space precision, and the calculation formula is as follows:
in the formula (2), Ps is the proportion of the actual land use type consistent with the simulated land use type, namely the simulation accuracy;
pr is the expected accuracy under random conditions;
the value range of the Kappa coefficient is between 0 and 1, the closer the Kappa coefficient is to 1, the better the description consistency is, and the closer the simulated soil utilization map is to the actual soil utilization map.
The FoM index measures the consistency between the actual observed conversion number and the simulation prediction conversion, and the specific calculation formula is as follows:
in the formula (3), NAThe number of pixels which are converted in actual observation and are not converted in the simulation process is represented;
NBrepresenting the conversion in actual observation and simulating the correct pixel number;
NCthe number of pixels which are changed in actual observation and converted in the simulation process but have wrong conversion types is represented;
NDindicating the number of pixels that were not converted in the actual observation but were converted in the simulation.
According to the technical scheme, in the step S1, the remote sensing images of the beginning and the ending years are obtained and preprocessed, and land utilization classification is carried out according to the actual land utilization/coverage conditions of local mountain cities.
According to the technical scheme, in the step S2, original data of mountain city driving factors are screened, elevation, gradient and multi-level road network data are added in addition to general GDP and population density driving factors, and Euclidean distance measurement is carried out.
Compared with the prior art, the invention has the beneficial effects that:
1. by simulating on the basis of the improved CA model-PLUS model, a new conversion rule data mining framework in the model can be used for identifying rules of land utilization change, the advantages of a conversion analysis strategy and a pattern analysis strategy are combined, the contribution degree of each factor is distinguished by adding special driving factors of the mountain cities, and the land utilization simulation precision of the mountain cities is improved, so that the driving factors of land utilization evolution of the mountain cities are accurately analyzed, and the land utilization change is accurately simulated.
2. The method has the advantages that the characteristics of elevation and roads of the mountain cities are considered, the improved cellular automata PLUS model is adopted, conversion rule mining is carried out based on a land expansion analysis strategy, multi-level road networks, elevation and gradient factors are added in simulation, simulation precision is improved, contributions of the elevation, the gradient and the multi-level road networks and other driving factors of the mountain cities are well analyzed and identified, a foundation is laid for subsequent technical improvement and scientific research, and meanwhile, an actual decision basis is provided for the land utilization layout and development of the mountain cities for the country.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
In the drawings:
FIG. 1 is a diagram of the simulation steps for the land use evolution of the mountain city of the present invention;
FIG. 2 is a technical flow diagram of the present invention;
FIG. 3 is a graph of land use type development probabilities of the present invention;
FIG. 4 is a plot of land use expansion factor contribution for each land use type of the present invention;
FIG. 5 is a training accuracy for each land use type of the present invention;
FIG. 6 is a graph showing the variation of the number of cells in the simulation of the present invention;
fig. 7 shows the simulation result of the land utilization in 2015 of the new area of the two rivers.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1:
as shown in fig. 1-2, the invention provides a technical solution, a method for simulating land use evolution in mountain cities, comprising the following specific steps:
s1, preprocessing data: acquiring mountain city remote sensing image data and preprocessing the data;
s2, determining a driving factor, and analyzing the contribution: selecting different types of plots and driving factors of the city, and performing contribution analysis;
s3, model simulation: inputting parameters in the model, and debugging the parameters to simulate the land utilization condition;
s4, precision evaluation: and comparing the simulation result with real land utilization data, and measuring and calculating the simulation precision through a Kappa coefficient and a FoM index.
According to the technical scheme, in S2, the contributions of the factors to the change of different land utilization types are analyzed, and the importance of independent variables to the change of dependent variables is calculated by adopting the root mean square error and the specific detection value of the root mean square error outside the bag of the random forest;
random sampling is carried out on each land class by adopting a random forest method, and the method can be used for outputting the growth probability of the land utilization type k of the i grid
The formula is as follows:
in the formula (1), d ═ 1 indicates that there is conversion from another site type to a k type, and the rest indicates d ═ 0;
x represents a drive factor vector;
the I (-) function is about a set of decision trees in a random forest;
hn(x) Representing the prediction type of the vector x under the nth decision tree;
m is the number of all decision trees;
and reasonably configuring the pixel space distribution of each land utilization type in the future by combining the development probability, the neighborhood weight, the conversion rule and the region constraint condition of each land utilization type.
According to the technical scheme, in S3, a PLUS model is used for simulation, the number of time cells is simulated to change, and neighborhood weight parameters in the model need to be repeatedly debugged during simulation until the simulation precision meets the requirement.
According to the technical scheme, in S4, the Kappa coefficient integrates two parameters of user precision and drawing precision to check the grid land utilization type space precision, and the calculation formula is as follows:
in the formula (2), Ps is the proportion of the actual land use type consistent with the simulated land use type, namely the simulation accuracy;
pr is the expected accuracy under random conditions;
the value range of the Kappa coefficient is between 0 and 1, the closer the Kappa coefficient is to 1, the better the description consistency is, and the closer the simulated soil utilization map is to the actual soil utilization map.
The FoM index measures the consistency between the actual observed conversion number and the simulation prediction conversion, and the specific calculation formula is as follows:
in the formula (3), NAThe number of pixels which are converted in actual observation and are not converted in the simulation process is represented;
NBrepresenting the conversion in actual observation and simulating the correct pixel number;
NCthe number of pixels which are changed in actual observation and converted in the simulation process but have wrong conversion types is represented;
NDindicating the number of pixels that were not converted in the actual observation but were converted in the simulation.
According to the technical scheme, in S1, the remote sensing images of the beginning and the ending years are obtained and preprocessed, and land utilization classification is carried out according to the actual land utilization/coverage conditions of local mountain cities.
According to the technical scheme, in S2, original data of mountain city driving factors are screened, elevation, gradient and multi-level road network data are added in addition to general GDP and population density driving factors, and Euclidean distance measurement is carried out.
Example 2:
taking the two river new districts in Chongqing city as an example, the implementation steps are as follows:
the method comprises the following steps: preprocessing data
The method comprises the steps of acquiring remote sensing images of two-stage two-river new regions on a Google Earth Engine platform, classifying the images by visual explanation by combining Google Earth high-definition images, acquiring land utilization data of a starting year and a terminating year, and dividing a classification system by combining local mountain city specific conditions: the construction land mainly comprises urban industrial and mining land, urban residential land and transportation and water conservancy land, vegetation mainly comprises various forest vegetation of trees and shrubs, bare land mainly comprises unused land and water mainly comprises rivers, lakes and reservoirs.
Basic driving factor data are obtained on an OpenStreetMap platform, a Chinese academy of resource and environment science and data center, a Chongqing city geographic information center and a geospatial data cloud platform, and ArcGIS is used for calculating the spatial distance between grid points and each element in two river new areas to obtain the data in the table 1.
TABLE 1 two river New zone drive factor selection and its implications
Step two: determining a driving factor, contribution analysis
As shown in fig. 3, four types of land use types, namely vegetation, construction land, water and bare land, are sampled in a random sampling manner, the sampling rate is set to 0.01, the number of decision trees is set to 12, and finally the development probability of the land use type on each pixel and the contribution degree of each driving factor in the new region 2015 of the two rivers are obtained.
As shown in fig. 4, from the contribution results of the land utilization type land expansion factors, the factors influencing the vegetation distribution in the new regions of the two rivers mainly include the distance to the railway station, the distance to the secondary road, the GDP and the local GDP which are obviously positively correlated, the vegetation distribution is obviously negatively correlated with the distance to the railway station and the distance to the secondary road, and the importance of the vegetation distribution is greater than 0.11. The construction land is mostly distributed in flat areas with convenient traffic, places with high elevation and large gradient are not beneficial to building construction, the construction land usually considers the comfort of living, so the construction land is consistent with the fact that the construction land is built at a certain distance from the road, and the secondary road has great influence on the production and life of local residents. The water body distribution is mainly negatively correlated with the elevation, and the importance of the elevation driving force factor is as high as 0.502, which indicates that the water bodies in the two river new areas are mainly distributed in the regions with low terrain. Factors influencing the bare land distribution mainly comprise factors of the distance to a secondary road, the distance to a railway and the distance to a primary road, and are in negative correlation.
As shown in fig. 5, the most common root mean square error and the specific out-of-bag root mean square error detection value of the random forest are adopted to perform precision evaluation on the prediction result, in the training result, the water body has the smallest error in the four land utilizations, and through inspection, the precision of the land utilization training in 2015 years of the two rivers new region is higher and the error is within the allowable range.
Step three: model simulation
During simulation, neighborhood weight parameters in the model need to be debugged repeatedly until simulation precision meets requirements, and finally, each weight factor is set as: 0.35 of vegetation, 0.95 of construction land, 0.4 of water and 0.2 of bare land;
considering that Yangtze river and Jialin river in the two new river areas are the most important river water areas in Chongqing, and the Yangtze river water areas are not only water source guarantees of local and downstream residents, but also water transportation main roads, so that the types of water bodies in the researched areas are limited and represented by a binary grid diagram, wherein the value of the area where the water bodies are not allowed to change is set to be 0, and the value of the area where the water bodies are allowed to change is set to be 1;
as shown in fig. 6, the simulation was performed using the PLUS model, simulating the change in the number of neurons;
as shown in fig. 7, the results of the land use simulation in 2015.
Step four: evaluation of accuracy
Comparing the simulation graph in 2015 with the actual land utilization graph by using a grid calculator to obtain a simulation correct value of 1, counting to find that the number of simulation correct pixels is 1077694, and the actual total pixels is 1310414, so that the simulation precision is 82%, the simulation rate is correct 1 in an ideal state, and calculating according to a formula to obtain a Kappa index of 0.73 and a FoM index of 0.263 of the simulation graph in 2015 in the two river new area, which indicates that the simulation effect is feasible.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A simulation method for land use evolution of mountain cities is characterized by comprising the following steps: the method comprises the following specific steps:
s1, preprocessing data: acquiring mountain city remote sensing image data and preprocessing the data;
s2, determining a driving factor, and analyzing the contribution: selecting the city driving factor data, and performing factor contribution analysis on different land utilization types;
s3, model simulation: simulating the land utilization condition by determining parameters such as a conversion rule, neighborhood weight and the like;
s4, precision evaluation: and comparing the simulation result with the real land utilization data, and verifying the precision through a Kappa coefficient and a FoM index.
2. The method for simulating land use evolution of mountain cities as claimed in claim 1, wherein in S2, the contribution of each factor to different land use type changes is analyzed, and the detected values of root mean square error and random forest specific root mean square error are used to calculate the importance of independent variable to dependent variable change;
random sampling is carried out on each land class by adopting a random forest method, and the method can be used for outputting the growth probability of the land utilization type k of the i grid
The formula is as follows:
in the formula (1), d ═ 1 indicates that there is conversion from another site type to a k type, and the rest indicates d ═ 0;
x represents a drive factor vector;
the I (-) function is about a set of decision trees in a random forest;
hn(x) Representing the prediction type of the vector x under the nth decision tree;
m is the number of all decision trees;
and reasonably configuring the pixel space distribution of each land utilization type in the future by combining the development probability, the neighborhood weight, the conversion rule and the region constraint condition of each land utilization type.
3. The method for simulating land use evolution in mountain cities as claimed in claim 1, wherein in S3, the simulation is performed using a PLUS model, the number of time cells is changed, and neighborhood weight parameters in the model need to be adjusted repeatedly during the simulation until the simulation precision meets the requirement.
4. The method for simulating land use evolution in mountainous regions and cities as claimed in claim 1, wherein in S4, Kappa coefficient combines two parameters of user precision and drawing precision to check spatial precision of grid land use type, and the calculation formula is:
in the formula (2), Ps is the proportion of the actual land use type consistent with the simulated land use type, namely the simulation accuracy;
pr is the expected accuracy under random conditions;
the value range of the Kappa coefficient is between 0 and 1, the closer the Kappa coefficient is to 1, the better the description consistency is, and the closer the simulated soil utilization map is to the actual soil utilization map.
The FoM index measures the consistency between the actual observed conversion number and the simulation prediction conversion, and the specific calculation formula is as follows:
in the formula (3), NAThe number of pixels which are converted in actual observation and are not converted in the simulation process is represented;
NBrepresenting the conversion in actual observation and simulating the correct pixel number;
NCthe number of pixels which are changed in actual observation and converted in the simulation process but have wrong conversion types is represented;
NDindicating the number of pixels that were not converted in the actual observation but were converted in the simulation.
5. The method for simulating land use evolution of mountain cities as claimed in claim 1, wherein in S1, remote sensing images of the beginning and ending years are obtained and preprocessed, and land use classification is performed in combination with the actual land use/cover situation of the local mountain cities.
6. The method for simulating land use evolution of mountain cities as claimed in claim 1, wherein in S2, the mountain city driving factor raw data are screened, and in addition to general GDP and population density driving factor, elevation, gradient and multi-level road network data are added and euclidean distance estimation is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210069578.7A CN114417724A (en) | 2022-01-20 | 2022-01-20 | Simulation method for land use evolution of mountain city |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210069578.7A CN114417724A (en) | 2022-01-20 | 2022-01-20 | Simulation method for land use evolution of mountain city |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114417724A true CN114417724A (en) | 2022-04-29 |
Family
ID=81275555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210069578.7A Pending CN114417724A (en) | 2022-01-20 | 2022-01-20 | Simulation method for land use evolution of mountain city |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114417724A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114861277A (en) * | 2022-05-23 | 2022-08-05 | 中国科学院地理科学与资源研究所 | Long-time-sequence national soil space function and structure simulation method |
| CN115600075A (en) * | 2022-12-12 | 2023-01-13 | 深圳市城市规划设计研究院有限公司（Cn） | Landscape plaque change measuring method and device, electronic equipment and storage medium |
-
2022
- 2022-01-20 CN CN202210069578.7A patent/CN114417724A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114861277A (en) * | 2022-05-23 | 2022-08-05 | 中国科学院地理科学与资源研究所 | Long-time-sequence national soil space function and structure simulation method |
| CN115600075A (en) * | 2022-12-12 | 2023-01-13 | 深圳市城市规划设计研究院有限公司（Cn） | Landscape plaque change measuring method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liping et al. | Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—A case study of a hilly area, Jiangle, China | |
| CN110472882B (en) | Urban development land suitability evaluation method based on principal component analysis | |
| Liao et al. | Urban sprawl scenario simulations based on cellular automata and ordered weighted averaging ecological constraints | |
| Lin et al. | Comparison of multimodel simulations of land use and land cover change considering integrated constraints-A case study of the Fuxian Lake basin | |
| CN116070918B (en) | Urban flood safety assessment and flood disaster prevention and control method | |
| Degerli et al. | Using the remote sensing method to simulate the land change in the year 2030 | |
| CN109359166B (en) | Space growth dynamic simulation and driving force factor contribution degree synchronous calculation method | |
| CN114417724A (en) | Simulation method for land use evolution of mountain city | |
| CN104298841A (en) | Flood forecasting method and system based on historical data | |
| CN106650618A (en) | Random forest model-based population data spatialization method | |
| Hakim et al. | Spatial dynamic prediction of landuse/landcover change (case study: tamalanrea sub-district, makassar city) | |
| CN107480808B (en) | Method for planning diversion project line in high-altitude mountain area | |
| Li et al. | Firefly algorithm-based cellular automata for reproducing urban growth and predicting future scenarios | |
| CN109933901B (en) | MCR city expansion simulation method for optimizing service value of ecosystem | |
| CN112784503B (en) | Gate dam dispatching launching bird habitat suitability calculation method and device | |
| Moradi et al. | Projection of future land use/cover change in the Izeh-Pyon Plain of Iran using CA-Markov model | |
| CN110175370A (en) | A kind of REGION OF WATER INJECTION OILFIELD recognition methods of city charge for remittance | |
| Yang et al. | A multitarget land use change simulation model based on cellular automata and its application | |
| CN113743659B (en) | Urban layout prediction method based on component method and Markov cellular automaton and application | |
| CN113011720B (en) | CA model-based incremental decrement town development boundary defining method | |
| KR101313822B1 (en) | Wind power density prediction method using neural network technique | |
| Bowman et al. | Landscape connectivity in the Great Lakes basin | |
| CN114372652A (en) | Urban ecological capacity assessment and development boundary simulation method | |
| Maithani et al. | An artificial neural network based approach for modelling urban spatial growth | |
| Zhang et al. | GRIDDED POPULATION DISTRIBUTION MAP FOR THE HEBEI PROVINCE OF CHINA. |
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 |