Land resource space optimization configuration method applied to land utilization planning
Through the optimization allocation method of land resource space, digital elevation model and deep learning model are used to analyze and predict land use change trends, the problem of failure to consider planning land greening and surrounding land dynamic changes in the existing technology is solved, and land use planning is realized accuracy and coordinated development.
Patent Information
- Application Number
- CN202411105585.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing land use planning fails to fully consider the greening and time utilization effects of planned land and the dynamic changes in surrounding land, resulting in the possible damage to the planned land or inconsistent with surrounding resources.
Adoption of the spatial optimization of land resource allocation methods, including planning land information collection, geographic information system module, surrounding land information comparison module, planning land and surrounding land information combination module and land planning information disclosure module, through digital elevation model, three-dimensional visualization, Pearson Correlation coefficients and deep learning models analyze and predict land use change trends to ensure coordinated development of planning and surrounding land.
It improves the accuracy and diversity of land use planning, ensures that the development of planned land is consistent with surrounding land, and avoids the damage to planned land and resource inconsistency.
Smart Images

Figure CN119026855A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of urban planning, and in particular to a land resource space optimization configuration method applied to the compilation of land use planning. Background Art
[0002] At present, land use planning is the overall strategic layout and overall arrangement of land development, utilization, governance and protection in space and time in a certain area according to the requirements of national social and economic sustainable development and local natural, economic and social conditions. It is based on the overall and long-term interests, takes all the land in the region as the object, and reasonably adjusts the land use structure and layout; takes utilization as the center, and makes overall arrangements and long-term planning for land development, utilization, governance, protection and other aspects.
[0003] The current land use planning is largely based on the surrounding land use planning as the main basis for the preparation of planned land, but it does not fully consider the greening and time utilization effects of the planned land, as well as the previous dynamic changes of the surrounding land. This can easily lead to the planned land being damaged after its preparation, or being inconsistent with the surrounding land resources.
[0004] Therefore, there is an urgent need to apply land resource spatial optimization allocation methods to land use planning to solve existing technical problems. Summary of the invention
[0005] The purpose of the present invention is to provide a method for optimizing the spatial allocation of land resources for use in land use planning, so as to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention aims to provide a land resource spatial optimization configuration method applied to land use planning, including a planning land information collection module, a planning land image collection module, a geographic information system module, a surrounding land information comparison module, a planning land and surrounding land information combination module and a land planning information disclosure module;
[0007] The geographic information system module includes a planned land attribute integration unit and a planned land spatial analysis integration unit. It collects high-definition images of the planned land, analyzes the landform characteristics of the planned land through a digital elevation model, uses query software to obtain soil properties, vegetation coverage, and population density data, and stores the data. Finally, it uses GIS software to integrate soil properties, vegetation coverage, population density data, and landform characteristics data.
[0008] The surrounding land information comparison module includes the surrounding land spatial analysis unit, the surrounding land attribute unit and the surrounding land use change unit. Similarly, the soil properties, vegetation coverage, population density data and land geomorphic feature data obtained by the surrounding land use GIS software are integrated, and the dynamic changes of the surrounding land information are analyzed through time changes and change detection algorithms. As the basis for analysis, it is finally compared with the soil properties, vegetation coverage, population density data and land geomorphic feature data of the planned land, and the correlation between different features and the prediction target is analyzed using statistical methods, and the four feature data of planting, residential, industrial and greening are selected;
[0009] The module for integrating information of planned land and surrounding land includes a land use information prediction unit, a land information collection unit and a land information visualization unit. After comparing the information data of planned land and surrounding land, four characteristic data of planting, residential, industrial and greening are obtained. The area of planned land is planned and analyzed and combined with the relevant information of surrounding land. Through GIS software, the prediction results of the planned land and the adjacent areas of surrounding land are spatially superimposed and visualized, and the spatial correlation and mutual influence of land use changes between regions are analyzed. These characteristic data are used to simulate multiple prediction models, establish a reasonable mathematical model to predict the future trend of land use changes, and compare multiple mathematical models to obtain the optimal mathematical model.
[0010] As a further improvement of the present technical solution, the planned land information collection module includes soil property units and spatial hierarchy units, and regional divisions are performed according to the soil properties and vegetation coverage of the planned land, as well as the population density distribution.
[0011] As a further improvement of the present technical solution, the planned land image acquisition module includes a land image preprocessing unit and a land image transmission and storage unit, which performs noise and redundancy preprocessing on the images collected by high-definition video of the planned land to obtain clearer images, which are stored in the geographic information system module and compared with soil images of the surrounding land.
[0012] As a further improvement of this technical solution, soil properties, vegetation coverage, and population density data were obtained through the National Soil Information Service app, Green Path app, and GIS software.
[0013] As a further improvement of the technical solution, the change detection algorithm is a change vector analysis method, and the formula of the change vector analysis method is as follows:
[0014] Change vector: x = x1-x2
[0015] Among them, x1 and x2 represent the pictures taken of two surrounding lands under time changes, and the values of the same band at a certain pixel point;
[0016] The intensity of the change (expressed as the Euclidean distance of the change vector):
[0017] Among them, ρ is the change intensity of the two surrounding lands under time change, b represents the number of bands. Here we take dual bands as an example, so the value range of b is 1 to 2, X b Here it refers to the bth component in the change vector x, namely X1 and X2.
[0018] As a further improvement of this technical solution, the statistical method is the Pearson correlation coefficient, which is expressed as follows:
[0019] ρ(X,Y)=cov(X,Y) / (σX*σY)
[0020] in:
[0021] ρ(X,Y): represents the Pearson correlation coefficient between variables X and Y, where variables X and Y are four characteristic data: planting, residential, industrial and green;
[0022] cov(X,Y): represents the covariance of variables X and Y, that is, the average of the product of the difference between the two variables and their respective means;
[0023] σX: represents the standard deviation of variable X, that is, the square root of the average of the squares of the differences between X and its mean;
[0024] σY: represents the standard deviation of variable Y, that is, the square root of the average of the squares of the differences between Y and its mean.
[0025] As a further improvement of the present technical solution, the planning land information disclosure module includes a land information result output unit and a user interaction unit, which obtains the optimal mathematical model and displays it in the form of a map through GIS software. The user interaction unit can also be used to conveniently query, browse and analyze the integrated land information.
[0026] As a further improvement of the present technical solution, the prediction model is a deep learning model that predicts future land use changes through forward propagation, activation function, loss function and back propagation.
[0027] As a further improvement of the present technical solution, the digital elevation model performs three-dimensional visualization of the planned land to obtain the three-dimensional simulated terrain, accurately analyzes the terrain of the planned land, and uses statistical methods to analyze the correlation between different features and prediction targets. The four feature data of planting, residential, industrial and greening are selected, and multiple prediction models are obtained by using a deep learning model to select the four feature data of planting, residential, industrial and greening. The three-dimensional terrain simulation is compared with multiple prediction models, and integrated analysis is performed using GIS software. Finally, the analysis results are output in the form of a map on the interface.
[0028] Compared with the prior art, the present invention has the following beneficial effects:
[0029] 1. This land resource spatial optimization allocation method applied to land use planning can obtain three-dimensional terrain simulation by using digital elevation model to visualize the planned land in three dimensions, so as to better understand the terrain of the planned land. Secondly, feature data of the planned land is extracted from three aspects, such as soil properties, vegetation coverage and population density, and compared with the information data of the surrounding land. The Pearson correlation coefficient is used to analyze the correlation between different features and the prediction target, and four feature data of planting, housing, industry and greening are obtained to improve the accuracy and diversity of the planning of land.
[0030] 2. This method of spatial optimization of land resources used in land use planning uses GIS software to spatially overlay and visualize the prediction results of planned land and surrounding land adjacent areas using four characteristic data of planting, residential, industrial and greening, and uses deep learning models to simulate multiple prediction models. The multiple prediction models of planned land are again predicted and analyzed by GIS software to obtain the optimal mathematical model. At the same time, GIS software also analyzes the dynamic changes of surrounding land information through change vector analysis as one of the analysis bases, and compares it with the optimal mathematical model to achieve the development of the planned land while being consistent with the development direction of the surrounding land. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 A schematic diagram of the module flow of the land resource space optimization configuration method applied to land use planning of the present invention;
[0032] Figure 2 It is a schematic diagram of the flow of the planning land and surrounding land information integration module of the present invention;
[0033] Figure 3 This is a unit flow diagram of the land resource space optimization configuration method applied to land use planning of the present invention. DETAILED DESCRIPTION
[0034] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] Example
[0036] See also Figure 1-Figure 3As shown, the purpose of this embodiment is to provide a land resource space optimization configuration method applied to land use planning, including the following steps:
[0037] S1. First, query the soil properties, vegetation coverage, and population density data of the planned land through the National Soil Information Service App, Green Path App, and GIS software, and divide the planned land into regions based on the soil properties, vegetation coverage, and population density data. After the regional division is completed, further divide the planned land into spatial layers based on the soil properties, vegetation coverage, and population density data;
[0038] S2. Use remote sensing technology to take high-definition pictures of the planned land that has been divided into regions, perform noise and redundancy preprocessing on the pictures collected by the high-definition camera of the planned land, obtain clearer pictures, store them in the geographic information system module, and obtain relevant information of the planned land. Use the digital elevation model to perform three-dimensional visualization through the topography and greening information of the planned land to obtain a three-dimensional terrain simulation, so as to better understand the topography of the planned land and compare it with the soil pictures of the surrounding land;
[0039] S3. Carry out preliminary classification of the images collected by high-definition video cameras of the planned land, analyze the planned land according to the terrain and soil properties, soil utilization status and land utilization value, and systematically analyze the development direction of the entire planned land based on the dynamic development direction of the surrounding land. Finally, use GIS software to integrate the soil properties, vegetation coverage, population density data and landform feature data of the planned land;
[0040] The terrain is divided into mountains, hills and plains. The soil properties are classified by the color and geology of the picture. The planned land is further classified in combination with the terrain and soil properties. The pictures can be annotated through the terrain analysis function and image analysis function of the GIS software, and compared with the terrain and soil properties of the surrounding land, so as to better analyze the development direction of the planned land and the surrounding land;
[0041] S4, the surrounding land information comparison module includes the surrounding land spatial analysis unit, the surrounding land attribute unit and the surrounding land use change unit. Similarly, the soil properties, vegetation coverage and population density data and land geomorphological characteristics data obtained by the surrounding land use GIS software are integrated, and the dynamic changes of the surrounding land information are analyzed through time changes and change detection algorithms. As the basis for analysis, it is finally compared with the soil properties, vegetation coverage, population density data and land geomorphological characteristics data of the planned land, and the correlation between different characteristics and the prediction target is analyzed using statistical methods, and the four characteristic data of planting, residential, industrial and greening are selected;
[0042] The change detection algorithm is the change vector analysis method. The formula of the change vector analysis method is as follows:
[0043] Change vector: x = x1-x2
[0044] Among them, x1 and x2 represent the pictures taken of two surrounding lands under time changes, and the values of the same band at a certain pixel point;
[0045] The intensity of the change (expressed as the Euclidean distance of the change vector):
[0046] Among them, ρ is the change intensity of the two surrounding lands under time change, b represents the number of bands. Here we take dual bands as an example, so the value range of b is 1 to 2, X b Here it refers to the bth component in the change vector x, namely X1 and X2.
[0047] The statistical method is the Pearson correlation coefficient, and the formula is as follows:
[0048] ρ(X,Y)=cov(X,Y) / (σX*σY)
[0049] in:
[0050] ρ(X,Y): represents the Pearson correlation coefficient between variables X and Y, where variables X and Y are four characteristic data: planting, residential, industrial and green;
[0051] cov(X,Y): represents the covariance of variables X and Y, that is, the average of the product of the difference between the two variables and their respective means;
[0052] σX: represents the standard deviation of variable X, that is, the square root of the average of the squares of the differences between X and its mean;
[0053] σY: represents the standard deviation of variable Y, that is, the square root of the average of the squares of the differences between Y and its mean;
[0054] The digital elevation model is used to visualize the planned land in three dimensions and obtain three-dimensional terrain simulation, which can better understand the terrain of the planned land. Secondly, the characteristic data of the planned land is extracted from three aspects: soil properties, vegetation coverage, and population density. The data is compared with the information data of the surrounding land. The Pearson correlation coefficient is used to analyze the correlation between different characteristics and the prediction target. The four characteristic data of planting, residential, industrial and greening are obtained to improve the accuracy and diversity of the compilation of the planned land.
[0055] S5. The module for integrating information of planned land and surrounding land includes a land use information prediction unit, a land information collection unit and a land information visualization unit. After comparing the information data of planned land and surrounding land, four characteristic data of planting, residential, industrial and greening are obtained. The area of planned land is roughly planned and analyzed and combined with the relevant information of surrounding land. Through GIS software, the prediction results of the planned land and the adjacent areas of surrounding land are spatially superimposed and visualized, and the spatial correlation and mutual influence of land use changes between regions are analyzed. These characteristic data are used to simulate multiple prediction models, establish a reasonable mathematical model to predict the future trend of land use changes, and compare multiple mathematical models to obtain the optimal mathematical model;
[0056] GIS software uses four characteristic data, namely planting, residential, industrial and greening, to spatially overlay and visualize the prediction results of planned land and surrounding land adjacent areas, and uses deep learning models to simulate multiple prediction models. The multiple prediction models of planned land are predicted and analyzed again through GIS software to obtain the optimal mathematical model. At the same time, GIS software also analyzes the dynamic changes of surrounding land information through change vector analysis method, and compares it with the optimal mathematical model as one of the analysis bases, so as to achieve the development of planned land itself and keep consistent with the development direction of surrounding land;
[0057] S6. The planning land information disclosure module includes a land information result output unit and a user interaction unit, which displays the optimal mathematical model in the form of a map through GIS software, and the user interaction unit can be used to conveniently query, browse and analyze the integrated land information;
[0058] Through GIS software, the land information data generated by the mathematical model (such as soil properties, vegetation coverage, population density, and landform characteristics) is converted into map layers and displayed in an intuitive graphical form. It supports exporting map data into images, PDF or other file formats for easy storage and sharing;
[0059] The user interaction unit performs statistical analysis on the queried land information, uses historical data to analyze the changing trends of land information, and predicts future development directions.
[0060] In summary, by using the digital elevation model to perform three-dimensional visualization of the planned land and obtain three-dimensional terrain simulation, we can better understand the terrain of the planned land. Secondly, the characteristic data of the planned land are extracted from three aspects, namely soil properties, vegetation coverage, and population density, and compared with the information data of the surrounding land. The Pearson correlation coefficient is used to analyze the correlation between different characteristics and the prediction target, and the four characteristic data of planting, residential, industrial and greening are obtained to improve the accuracy and diversity of the compilation of planned land. GIS software uses the four characteristic data of planting, residential, industrial and greening to spatially superimpose and visualize the prediction results of the planned land and the surrounding land adjacent areas, and uses the deep learning model to simulate multiple prediction models. The multiple prediction models of the planned land are predicted and analyzed again by GIS software to obtain the optimal mathematical model. At the same time, GIS software also analyzes the dynamic changes of the surrounding land information through the change vector analysis method. As one of the analysis bases, it is compared with the optimal mathematical model to achieve the development of the planned land itself while being consistent with the development direction of the surrounding land.
[0061] Example:
[0062] Assuming that a city plans to develop a new piece of land, it will first query the soil properties, vegetation coverage, and population density data of the planned land through the National Soil Information Service app, Green Path app, and GIS software, and divide the planned land into regions based on the soil properties, vegetation coverage, and population density data. After the regional division is completed, the planned land will be further divided into spatial layers based on the soil properties, vegetation coverage, and population density data, and the areas suitable for planting, residential, industrial, and green areas will be effectively distinguished and marked;
[0063] Then, high-definition pictures of the planned land that have been divided into regions are taken through remote sensing technology. The pictures collected by the high-definition camera of the planned land are pre-processed for noise and redundancy to obtain clearer pictures, which are stored in the geographic information system module to obtain the topography and greening information of the planned land. The digital elevation model is used to perform three-dimensional visualization through the topography and greening information of the planned land to obtain a three-dimensional terrain simulation, which can better understand the topography of the planned land and compare the information with the soil pictures of the surrounding land. The Pearson correlation coefficient is used to analyze the correlation between different features and the prediction target, and the four feature data of planting, housing, industry and greening are obtained. For example, the characteristics with strong correlation in several divided areas of the planned land are planting, housing and greening, while the characteristics with strong correlation in the surrounding land are housing and industry.
[0064] The change vector analysis method is used to analyze the temporal dynamic changes of the planned land information for the four characteristic data of planting, housing, industry and greening, and the prediction analysis is carried out through GIS software, which can evaluate the use and development trend of the planned land, spatially superimpose and visualize the prediction results of the planned land and the surrounding land adjacent areas, analyze the spatial correlation and mutual influence of land use changes between regions, use these characteristic data to simulate multiple prediction models, establish a reasonable mathematical model to predict the future land use change trend, and compare multiple mathematical models to obtain the optimal mathematical model. The characteristics with strong correlation in several divided areas of planned land are planting, housing and greening, and the characteristics with strong correlation with surrounding land are housing and industry. The prediction results analyzed by GIS software and change vector analysis method are spatially superimposed and visualized, and finally the optimal mathematical model is obtained for housing and greening;
[0065] Once again, the dynamic changes of the surrounding land information are analyzed by the change vector analysis method through GIS software. As one of the analysis bases, it is compared with the optimal mathematical model, and finally a mathematical model that conforms to the planned land development itself and is consistent with the development direction of the surrounding land is obtained. The land information data generated by the mathematical model (such as soil properties, vegetation coverage, population density, and landform characteristics) are converted into map layers using GIS software, and displayed in an intuitive graphical form. It also supports exporting map data as pictures, PDF or other file formats for easy storage and sharing. The dynamic changes of the surrounding land information are predicted using the change vector analysis method, and the main feature is residential. Therefore, compared with the optimal mathematical model with residential and greening, it is a mathematical model that conforms to the planned land development itself and is consistent with the development direction of the surrounding land, and the mathematical model is displayed through GIS software for reference;
[0066] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A method for optimizing the spatial allocation of land resources used in land use planning, characterized by: It includes a planning land information collection module, a planning land image acquisition module, a geographic information system module, a surrounding land information comparison module, a planning land and surrounding land information combination module and a land planning information disclosure module; The geographic information system module includes a planned land attribute integration unit and a planned land spatial analysis integration unit, which collects high-definition video of the planned land, analyzes the landform characteristics of the planned land through a digital elevation model, uses query software to obtain soil properties, vegetation coverage, and population density data, and stores the data, and finally uses GIS software to integrate the soil properties, vegetation coverage, population density data and landform characteristics data; The surrounding land information comparison module includes a surrounding land spatial analysis unit, a surrounding land attribute unit and a surrounding land use change unit. Similarly, the soil properties, vegetation coverage, population density data and land geomorphic feature data obtained by the surrounding land use GIS software are integrated, and the dynamic changes of the surrounding land information are analyzed through time changes and change detection algorithms. As the basis for analysis, the surrounding land information is compared with the soil properties, vegetation coverage, population density data and land geomorphic feature data of the planned land, and the correlation between different features and the prediction target is analyzed by using statistical methods, and the four feature data of planting, residential, industrial and greening are selected; The planned land and surrounding land information integration module includes a land use information prediction unit, a land information collection unit and a land information visualization unit. After comparing the information data of the planned land and the surrounding land, four characteristic data of planting, residential, industrial and greening are obtained, the area of the planned land is planned and analyzed and combined with the relevant information of the surrounding land. Through GIS software, the prediction results of the planned land and the adjacent areas of the surrounding land are spatially superimposed and visualized, the spatial correlation and mutual influence of land use changes between regions are analyzed, and multiple prediction models are simulated using these characteristic data. A reasonable mathematical model is established to predict the future trend of land use changes, and multiple mathematical models are compared to obtain the optimal mathematical model.
2. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1 is characterized in that: The planned land information collection module includes a soil property unit and a spatial hierarchy unit, and performs regional division according to the soil property and vegetation coverage rate of the planned land, as well as the population density distribution.
3. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1 is characterized in that: The planned land image acquisition module includes a land image preprocessing unit and a land image transmission and storage unit, which performs noise and redundancy preprocessing on the images collected by high-definition video of the planned land to obtain clearer images, which are stored in the geographic information system module and compared with soil images of surrounding land.
4. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1 is characterized in that: The soil properties, vegetation coverage, and population density data were obtained through the National Soil Information Service app, Green Path app, and GIS software.
5. The method for optimizing spatial allocation of land resources for land use planning according to claim 1, characterized in that: The change detection algorithm is a change vector analysis method, and the formula of the change vector analysis method is as follows: Change vector: x = x1-x2 Among them, x1 and x2 represent the pictures taken of two surrounding lands under time changes, and the values of the same band at a certain pixel point; The intensity of the change (expressed as the Euclidean distance of the change vector): Among them, ρ is the change intensity of the two surrounding lands under time change, b represents the number of bands. Here we take dual bands as an example, so the value range of b is 1 to 2, X b Here it refers to the bth component in the change vector x, namely X1 and X2.
6. The method for optimizing spatial allocation of land resources for land use planning according to claim 1, characterized in that: The statistical method is the Pearson correlation coefficient, which is expressed as follows: ρ(X,Y)=cov(X,Y) / (σX*σY) in: ρ(X,Y): represents the Pearson correlation coefficient between variables X and Y, where variables X and Y are four characteristic data: planting, residential, industrial and green; cov(X,Y): represents the covariance of variables X and Y, that is, the average of the product of the difference between the two variables and their respective means; σX: represents the standard deviation of variable X, that is, the square root of the average of the squares of the differences between X and its mean; σY: represents the standard deviation of variable Y, that is, the square root of the average of the squares of the differences between Y and its mean.
7. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1, characterized in that: The planned land information disclosure module includes a land information result output unit and a user interaction unit. The optimal mathematical model obtained is displayed in the form of a map through GIS software, and the user interaction unit can be used to conveniently query, browse and analyze the integrated land information.
8. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1 is characterized by: The prediction model is a deep learning model that predicts future land use changes through forward propagation, activation function, loss function and back propagation.
9. The method for optimizing the spatial allocation of land resources for land use planning according to claim 1, characterized in that: The digital elevation model performs three-dimensional visualization of the planned land to obtain a three-dimensional simulated terrain, accurately analyzes the terrain of the planned land, and uses statistical methods to analyze the correlation between different features and prediction targets, selects four feature data of planting, residential, industrial and greening, and obtains multiple prediction models for the four feature data of planting, residential, industrial and greening by using a deep learning model. The three-dimensional terrain simulation is compared with the multiple prediction models, and integrated analysis is performed using GIS software. Finally, the analysis results are output in the form of a map on the interface.
Citation Information
Patent Citations
Land resource utilization change dynamic prediction model based on GIS (Geographic Information System) and using method of dynamic prediction model
CN102750732A
Geographic information system and method for land planning
CN117036112A
Land space information construction method and system, electronic equipment and medium
CN117391305A
Land utilization planning method and system based on data analysis
CN118094196A
Method and system for acquiring land utilization change information based on resource data
CN118152501A
