Engineering construction project land argumentation and analysis system based on multi-source data

Abstract

The invention discloses an engineering construction project land argumentation and analysis system based on multi-source data. The engineering construction project land argumentation and analysis system comprises a preprocessing module, a conversion module, a partitioning module and a prediction module, the preprocessing module is used for acquiring construction land resource field survey data and generating standard construction land resource field survey data; the conversion module is used for acquiring multi-source geographic information data and generating multi-source geographic elevation data; the zoning module is used for performing topographic feature analysis on the multi-source geographic elevation data and generating regional zoning land parcels and functional zoning land parcels; the prediction module is used for performing land parcel coincidence marking on the regional partition land parcels and the functional partition land parcels, generating a planning and construction simulation model, and generating a land utilization planning scheme for display according to the planning and construction simulation model; the method and the system are used for solving the technical problem that an existing engineering construction land analysis system lacks comprehensive analysis on land planning, so that the accuracy and the operability of an engineering construction land analysis planning result are insufficient.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of construction project land analysis, and in particular to a construction project land demonstration analysis system based on multi-source data. BACKGROUND

[0002] The popularization and development of remote sensing technology provide more abundant data sources for land use planning. Through satellite and aerial images, planners can obtain large-scale, high-resolution land information, including land cover, vegetation types, land use changes, etc. These data, combined with GIS, provide more accurate basis for planning. In the 21st century, land use planning began to use spatial data mining and model simulation technology. Planners can use these technologies to mine rules from big data and predict the development trend of land use. At the same time, model simulation can help planners evaluate the impact of different planning schemes and provide scientific basis for decision-making.

[0003] Today, with the development of artificial intelligence and big data technology, intelligent engineering construction land use planning analysis systems based on multi-source data are gradually becoming a development trend. These systems can automatically collect, integrate and analyze various data to provide faster and more accurate decision support for engineering construction land planners. At the same time, intelligent analysis systems can also realize dynamic adjustment and optimization of planning schemes to meet the changing development needs of urban engineering construction project land. However, existing engineering construction land analysis systems only plan land use based on single factors such as land use type or terrain, lack comprehensive analysis, and are difficult to accurately divide the utilization potential and characteristics of different plots, resulting in inaccurate and impractical engineering construction land analysis planning results, which leads to insufficient accuracy and operability of engineering construction land use planning results. SUMMARY

[0004] The embodiment of the application provides a construction project land demonstration analysis system based on multi-source data, which is used to solve the technical problem that the existing engineering construction land analysis system lacks comprehensive analysis of land use planning and is difficult to accurately divide the utilization potential and characteristics of different plots, resulting in insufficient accuracy and operability of engineering construction land analysis planning results.

[0005] Therefore, the application provides a construction project land demonstration analysis system based on multi-source data, which comprises a preprocessing module, a conversion module, a partition module and a prediction module.

[0006] The preprocessing module is used to obtain construction land resource field survey data and perform data preprocessing on the construction land resource field survey data to generate standard construction land resource field survey data and send the standard construction land resource field survey data to the partition module.

[0007] The conversion module is configured to acquire multi-source geographic information data, perform terrain data extraction on the multi-source geographic information data, generate a multi-source geographic terrain feature data set, convert the multi-source geographic terrain feature data set, and generate multi-source geographic elevation data and send the multi-source geographic elevation data to the partition module.

[0008] The partition module is configured to perform terrain feature analysis on the multi-source geographic elevation data, perform land cover classification on the standard land resource field survey data, generate land cover classification regions, generate regional partition plots and functional partition plots, and send the regional partition plots and the functional partition plots to the prediction module.

[0009] The prediction module is configured to mark the regional partition plots and the functional partition plots, mark a range plot that overlaps the regional partition plots and the functional partition plots as a composite rich plot, mark a range plot that does not overlap the regional partition plots and the functional partition plots as a single rich plot, generate a plot potential partition map according to the composite rich plot and the single rich plot, generate a planning and construction simulation model according to the plot potential partition map, and generate a land use planning scheme display according to the planning and construction simulation model.

[0010] Optionally, the preprocessing module includes a first data acquisition module, a first data processing module, and a data standardization module.

[0011] The first data acquisition module is configured to acquire the land resource field survey data and send the land resource field survey data to the first data processing module.

[0012] The first data processing module is configured to perform data cleaning on the land resource field survey data to generate land resource field survey cleaning data, perform data missing value detection on the land resource field survey cleaning data to generate land resource field survey missing detection data, and perform missing value filling on the land resource field survey missing detection data to generate land resource field survey filling data and send the land resource field survey filling data to the data standardization module.

[0013] The standardization module is configured to perform data standardization processing on the land resource field survey filling data and generate standard land resource field survey data.

[0014] Optionally, the data conversion module includes a second data acquisition module, a second data processing module, and an elevation conversion module.

[0015] The second data acquisition module is configured to acquire multi-source geographic information data according to satellite images and send the multi-source geographic information data to the second data processing module.

[0016] The second data processing module is configured to perform data cleaning on the multi-source geographic information data to generate multi-source geographic information cleaning data, perform data field unification on the multi-source geographic information cleaning data to generate multi-source geographic information unified data, perform spatial superposition on the multi-source geographic information unified data by using GIS technology to generate multi-source geographic information superposition data, perform terrain data extraction on the multi-source geographic information superposition data to generate a multi-source geographic terrain feature data set, and send the multi-source geographic terrain feature data set to the elevation conversion module.

[0017] The elevation conversion module is configured to perform elevation conversion on the multi-source geographic terrain feature data set to generate multi-source geographic elevation data.

[0018] Optionally, the partition module comprises an analysis module and a classification module.

[0019] The analysis module is configured to project the multi-source geographic elevation data by using a terrain elevation model to generate terrain environment distribution data and water system distribution data, perform slope analysis on the terrain environment distribution data to generate slope fluctuation change data, and integrate terrain feature data according to the slope fluctuation change data and the water system distribution data to generate terrain feature analysis data.

[0020] The classification module is configured to perform land use status analysis on the standard land resource field survey data to generate land use status data, perform land cover classification on the terrain elevation model based on the land use status data to generate land cover classification regions, and perform region feature clustering on the land cover classification regions according to the terrain feature analysis data to generate region partition blocks.

[0021] Optionally, the prediction module comprises a marking module, a calculation module, and a potential prediction module.

[0022] The marking module is configured to mark the region partition blocks and the function partition blocks, mark the range blocks overlapped by the region partition blocks and the function partition blocks as composite rich blocks, and mark the range blocks not overlapped by the region partition blocks and the function partition blocks as single rich blocks.

[0023] The calculation module is configured to perform first block cover complexity calculation on the composite rich blocks to generate composite block cover complexity data, and perform second block cover complexity calculation on the single rich blocks to generate single block cover complexity data.

[0024] The potential prediction module is configured to predict the land use potential according to the composite plot coverage complexity data and the single plot coverage complexity data, generate a plot potential zoning map, simulate planning and construction of the composite rich plot and the single rich plot based on the plot potential zoning map, and generate a planning and construction simulation model.

[0025] Optionally, the step of predicting the land use potential according to the composite plot coverage complexity data and the single plot coverage complexity data, and generating a plot potential zoning map comprises the following steps:

[0026] S61, integrating the composite plot coverage complexity data and the single plot coverage complexity data to generate plot coverage complexity data;

[0027] S62, dividing the plot coverage complexity data into a model training set and a model test set, training a model training set using a support vector machine algorithm to generate a plot potential training model;

[0028] S63, testing the plot potential training model using a model test set, thereby obtaining a plot potential test data, and performing a hollow convolution on the plot potential training model using the plot potential test data to generate a plot potential prediction model;

[0029] S64, importing the plot coverage complexity data into the plot potential prediction model to predict the land use potential, thereby generating plot use potential prediction data; and dividing the plot use potential prediction data into potential grades to generate plot use potential grade data;

[0030] S65, constructing a plot potential zoning map based on the plot use potential grade data and the plot use potential prediction data to generate a plot potential zoning map.

[0031] Optionally, the step of simulating planning and construction of the composite rich plot and the single rich plot based on the plot potential zoning map to generate a planning and construction simulation model comprises the following steps:

[0032] S71, identifying the potential of a plot area of the composite rich plot and the single rich plot based on the plot potential zoning map to generate a plot potential identification area;

[0033] S72, performing resource enrichment analysis on the plot potential identification area to generate resource enrichment analysis data, wherein the resource enrichment analysis data comprises water resource enrichment data and land resource enrichment data;

[0034] S73, discriminant analysis is performed on the aquatic resource enrichment data and the land resource enrichment data, when the aquatic resource enrichment data of the land potential identification area is greater than the land resource enrichment data, then the land potential identification area is subjected to three-dimensional modeling of the agricultural area, and agricultural area modeling data is generated;

[0035] S74, when the land resource enrichment data of the land potential identification area is greater than the aquatic resource enrichment data, then the land potential identification area is subjected to three-dimensional modeling of the industrial area, and industrial area modeling data is generated;

[0036] S75, when the land resource enrichment data of the land potential identification area is equal to the aquatic resource enrichment data, then the land potential identification area is subjected to three-dimensional modeling of the residential area, and residential area modeling data is generated;

[0037] S76, the agricultural area modeling data, the industrial area modeling data and the residential area modeling data are simulated by using laser point cloud technology, and a planning and construction simulation model is generated.

[0038] From the above technical solutions, the embodiments of the present application have the following advantages:

[0039] The land use planning scheme display is generated according to the planning and construction simulation model. The land use planning scheme display can intuitively display the utilization potential of different land blocks, and provide visual reference for land use planning of engineering construction project land. The planning and construction simulation model is generated by simulating the planning and construction of the composite rich land block and the single rich land block according to the land potential zoning map, which helps to analyze and evaluate the feasibility and effect of different engineering construction project land planning schemes, and provides support for decision-making and display of the land use planning scheme of engineering construction project land, thereby improving the accuracy and operability of the land planning result of engineering construction project land. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly express the technical solutions of the embodiments of the present application, the drawings needed for the description of the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0041] Figure 1A system block diagram of an engineering construction project land demonstration analysis system based on multi-source data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0043] For the sake of understanding, please refer to Figure 1 An embodiment of an engineering construction project land demonstration analysis system based on multi-source data provided by the present application comprises a preprocessing module, a conversion module, a partition module and a prediction module; the preprocessing module, the conversion module, the partition module and the prediction module are electrically connected with each other; the preprocessing module is used to obtain construction land resource field survey data and perform data preprocessing on the construction land resource field survey data to generate standard construction land resource field survey data and send the standard construction land resource field survey data to the partition module; the conversion module is used to obtain multi-source geographic information data, perform terrain data extraction on the multi-source geographic information data to generate a multi-source geographic terrain feature data set, convert the multi-source geographic terrain feature data set to generate multi-source geographic elevation data and send the multi-source geographic elevation data to the partition module; the partition module is used to perform terrain feature analysis on the multi-source geographic elevation data and generate terrain feature analysis data, perform land cover classification on the standard land resource field survey data to generate land cover classification regions, perform regional feature clustering according to the land cover classification regions and the terrain feature analysis data to generate regional partition blocks, perform geographic function partitioning according to the regional partition blocks to generate function partition blocks, and send the regional partition blocks and the function partition blocks to the prediction module; the prediction module is used to mark the regional partition blocks and the function partition blocks, mark the range blocks overlapped by the regional partition blocks and the function partition blocks as composite rich blocks, mark the range blocks not overlapped by the regional partition blocks and the function partition blocks as single rich blocks, perform block utilization potential prediction on the composite rich blocks and the single rich blocks to generate a block potential partition map, perform planning and construction simulation on the composite rich blocks and the single rich blocks according to the block potential partition map to generate a planning and construction simulation model, and generate a land use planning scheme display according to the planning and construction simulation model; the system can intuitively display the utilization potential of different blocks and provide visual reference for land use planning of engineering construction project land; the planning and construction simulation model is generated by performing planning and construction simulation on the composite rich blocks and the single rich blocks according to the block potential partition map, which helps to analyze and evaluate the feasibility and effect of different engineering construction project land planning schemes, provides support for decision-making and display of the land use planning scheme of engineering construction project land, and further improves the accuracy and operability of the land planning result of engineering construction project land.

[0044] As a further scheme of the present application, the preprocessing module comprises a first data acquisition module, a first data processing module and a data standardization module; the first data acquisition module is configured to acquire land resource field survey data and send the land resource field survey data to the first data processing module; the first data processing module is configured to perform data cleaning on the land resource field survey data to generate land resource field survey cleaned data, perform data missing value detection on the land resource field survey cleaned data to generate land resource field survey missing detection data, and perform missing value filling on the land resource field survey missing detection data to generate land resource field survey filled data and send the land resource field survey filled data to the data standardization module; and the standardization module is configured to perform data standardization processing on the land resource field survey filled data and generate standard land resource field survey data.

[0045] Specifically, digital land use data and attribute information are acquired through GIS software, high-resolution land image data are acquired using remote sensing technology, field surveys are conducted to collect land attribute information and topographic feature data, data cleaning tools (such as Pandas library in Python) are used to clean the data and handle missing values and outliers, GIS software is used for data integration and conversion to integrate data in different formats and coordinate systems. Spatial data processing tools (such as ArcGIS or QGIS) are used for spatial data processing, such as projection transformation and spatial interpolation, scripts or programs are written to automate the data processing process, improving processing efficiency and ensuring consistency.

[0046] Further, the data conversion module comprises a second data acquisition module, a second data processing module and an elevation conversion module; the second data acquisition module is configured to acquire multi-source geographic information data from satellite images and send the multi-source geographic information data to the second data processing module; the second data processing module is configured to perform data cleaning on the multi-source geographic information data to generate multi-source geographic information cleaned data, perform data field unification on the multi-source geographic information cleaned data to generate multi-source geographic information unified data, perform spatial superposition on the multi-source geographic information unified data using GIS technology to integrate and generate multi-source geographic information superimposed data, perform topographic data extraction on the multi-source geographic information superimposed data to generate a multi-source geographic topographic feature data set, and send the multi-source geographic topographic feature data set to the elevation conversion module; and the elevation conversion module is configured to perform elevation conversion on the multi-source geographic topographic feature data set to generate multi-source geographic elevation data.

[0047] Specifically, high-resolution satellite and aerial image data is obtained from satellite and aerial image service providers, and professional digital map data, such as geographic information data provided by a geographic information system (GIS) platform, is used to ensure reliable data sources and comprehensive coverage. The satellite and aerial image data is processed to generate a high-resolution digital elevation model. Topographic data is extracted using DEM processing software, such as the Spatial Analyst tool in ArcGIS. Topographic features such as terrain undulations, mountains, and plains are extracted to generate a topographic feature dataset. Based on the extracted topographic feature dataset, elevation data is converted and processed using digital map processing software, such as the elevation conversion tool in the Spatial Analyst toolset of ArcGIS. Methods used include elevation interpolation methods (such as Kriging interpolation, triangular mesh interpolation, etc.) to convert the original elevation data into a more smooth and continuous elevation dataset.

[0048] Further, the partition module includes an analysis module and a classification module; the analysis module is used to project the terrain environment distribution of the multi-source geographic elevation data by using the terrain elevation model to generate terrain distribution data and water system distribution data, to perform slope analysis on the terrain distribution data to generate slope undulation change data, and to integrate the terrain feature analysis data according to the slope undulation change data and the water system distribution data; the classification module is used to perform land use status analysis on the standard land resource field investigation data to generate land use status data, to perform land cover classification on the terrain elevation model based on the land use status data to generate land cover classification regions, and to perform regional feature clustering on the land cover classification regions according to the terrain feature analysis data to generate regional partition blocks; and the regional partition blocks are subjected to geographic function partitioning to generate function partition blocks.

[0049] Specifically, by generating multi-source geographic elevation data, various terrain parameters such as slope, slope direction, and elevation are calculated, and terrain analysis tools in GIS software such as the slope and slope direction calculation tools in the Spatial Analyst toolset in ArcGIS are used to extract terrain indices such as terrain humidity index and potential evapotranspiration to reflect the hydrological and climatic characteristics of the terrain. Generate terrain feature analysis data, including datasets of various terrain parameters and terrain indices, and use high-resolution satellite or aerial image data for feature classification and identification. Use remote sensing image processing software such as ENVI or the remote sensing image classification tool in ArcGIS. Set appropriate classification algorithms such as maximum likelihood classification and support vector machine (SVM) to classify the image according to land cover types. According to the field survey data, adjust and verify the classification results to ensure the accuracy of the land cover classification, generate land cover classification regional map, including the distribution range of various land cover types, based on the terrain feature analysis data and the land cover classification regional map, regional feature clustering is carried out. Use clustering algorithms such as K-means clustering to divide the region into clusters with similar terrain features and land cover types, and merge the plots within each cluster to form regional zoning plots. According to the characteristics and clustering results of the plots, the regional zoning plots are divided and named to form the geographical function zoning, and on the GIS platform, the regional zoning plot data and land use planning indicators are used to carry out geographical function zoning. Set planning indicators such as the distribution proportion and range of residential areas, commercial areas, and industrial areas. Use spatial planning models such as planning simulation tools to functionally divide and optimize the layout of each plot, considering urban planning, transportation planning, and other factors to generate the final functional zoning plots to guide land use planning.

[0050] Further, the prediction module includes a marking module, a calculation module, and a potential prediction module; the marking module is used for marking the plot overlap of the regional zoning plots and the functional zoning plots, and marking the range plots overlapped by the regional zoning plots and the functional zoning plots as composite rich plots; at the same time, marking the range plots not overlapped by the regional zoning plots and the functional zoning plots as single rich plots; the calculation module is used for calculating the first plot coverage complexity of the composite rich plots to generate composite plot coverage complexity data; at the same time, calculating the second plot coverage complexity of the single rich plots to generate single plot coverage complexity data; the potential prediction module is used for predicting the plot utilization potential according to the composite plot coverage complexity data and the single plot coverage complexity data to generate a plot potential zoning map, and simulating the planning and construction of the composite rich plots and the single rich plots through the plot potential zoning map to generate a planning and construction simulation model.

[0051] Specifically, the present application divides the land blocks into composite rich land blocks and single rich land blocks by marking the coincidence of the region partition land blocks and the function partition land blocks, which helps to identify important areas in land use, distinguish composite rich land blocks and single rich land blocks, and facilitate subsequent analysis and planning, so as to better utilize land resources. By calculating the coverage complexity data of composite land blocks and single land blocks, the complexity of land use can be quantified to provide data support for subsequent prediction and planning. Based on the coverage complexity data of composite land blocks and single land blocks, land use potential prediction can be carried out to identify potential development trends and key areas of land use, providing guidance for planning. Through land potential zoning map for planning and construction simulation, land use under different planning schemes can be simulated to evaluate the feasibility and effect of the scheme, providing reference for decision-making. The generation of planning and construction simulation model can intuitively show the land use under different planning schemes, which helps to show the planning effect to relevant parties and promote the communication and acceptance of the scheme.

[0052] Further, the land use potential prediction based on the composite land block coverage complexity data and the single land block coverage complexity data to generate the land potential zoning map includes the following steps:

[0053] S61, data integration of the composite land block coverage complexity data and the single land block coverage complexity data to generate land coverage complexity data;

[0054] S62, data set division of the land coverage complexity data to generate model training set and model test set, and then model training of the model training set by using support vector machine algorithm to generate land potential training model;

[0055] S63, model testing of the land potential training model by using the model test set, so as to obtain the land potential test data;

[0056] S64, land use potential prediction by importing the land coverage complexity data into the land potential prediction model, so as to generate land use potential prediction data; potential grade division according to the land use potential prediction data to generate land use potential grade data;

[0057] S65, land potential zoning map construction according to the land use potential grade data and the land use potential prediction data to generate the land potential zoning map.

[0058] Specifically, the coverage complexity of each composite rich patch is calculated by defining a composite richness patch. This can be based on a combination of indicators such as cover species diversity, functional diversity, etc. within the patch. Using patch boundary and attribute information from the patch data, such as land use type, vegetation type, etc., and remote sensing image data, computer vision techniques or geographic information system (GIS) tools are used to analyze the composite rich patch, involving image segmentation, feature extraction, classification algorithms, etc. In the analysis process, clustering analysis, classifier training, etc. can be used to identify the coverage complexity within the patch, such as using the K-means clustering algorithm or support vector machine classifier. Combined with various coverage indicators within the patch, the coverage complexity data of each composite rich patch is calculated. The coverage complexity of single rich patches needs to be calculated using different methods, as these patches only contain a single type of cover, and simplified calculation methods such as land use type diversity index, vegetation structure index, etc. can be used. Similarly, using patch data and remote sensing image data, single rich patches are analyzed without the need for complex image segmentation and classification algorithms as in composite rich patches. According to the characteristics of single patches, the coverage complexity data of each single rich patch is calculated, where the first patch is usually a composite rich patch with multiple different types of cover, such as different land use types, vegetation types, etc. The calculation of the coverage complexity of composite patches needs to consider diversity and functionality, etc. involving more complex image processing and classification algorithms to identify different cover types within the patch and quantify their complexity. In the calculation process, various indicators such as species diversity, ecological function, landscape pattern, etc. need to be considered to comprehensively evaluate the coverage complexity of the patch. The second patch is usually a single rich patch containing only one type of cover, such as a single land use type or vegetation type. The calculation of the coverage complexity of single patches is relatively simple, as only the single type of cover within the patch needs to be considered, without the need for complex image processing and classification algorithms as in composite patches. The calculation method is more direct, involving simplified indicators or methods such as land use type diversity index, vegetation structure index, etc. More specifically, based on landscape ecology indicators such as Landscape Diversity Index (LDI) and Landscape Heterogeneity Index (LHI), the first patch coverage complexity is calculated. Landscape Diversity Index (LDI): LDI = (N / S) x (ln(N) - Σ(ni / S) x ln(ni)). Where N is the number of cover types within the patch, S is the total area of the patch, and ni is the area of each cover type. For the second patch, simplified indicators such as the number or proportion of cover types are used, as the second patch usually only contains a single type of cover, making its complexity assessment simpler.

[0059] Further, the steps of generating the planning and construction simulation model are as follows:

[0060] S71, identifying the potential of the land block region by the land block potential zoning map, and generating a land block potential identification region for the composite rich land block and the single rich land block;

[0061] S72, performing resource enrichment analysis on the land block potential identification region, and generating resource enrichment analysis data, wherein the resource enrichment analysis data includes water resource enrichment data and land resource enrichment data;

[0062] S73, discriminating the water resource enrichment data and the land resource enrichment data, and when the water resource enrichment data of the land block potential identification region is greater than the land resource enrichment data, performing three-dimensional modeling of the agricultural region for the land block potential identification region, and generating agricultural region modeling data;

[0063] S74, when the land resource enrichment data of the land block potential identification region is greater than the water resource enrichment data, performing three-dimensional modeling of the industrial region for the land block potential identification region, and generating industrial region modeling data;

[0064] S75, when the land resource enrichment data of the land block potential identification region is equal to the water resource enrichment data, performing three-dimensional modeling of the residential region for the land block potential identification region, and generating residential region modeling data;

[0065] S76, performing planning and construction simulation on the agricultural region modeling data, the industrial region modeling data and the residential region modeling data by using the laser point cloud technology, and generating a planning and construction simulation model.

[0066] Specifically, the present application identifies the composite rich land and the single rich land through the land potential zoning map, and determines the potential identification area of each land. The purpose of this step is to provide accurate land potential identification area for subsequent analysis and planning, so as to implement different planning measures for different types of land. The resource enrichment analysis of the land potential identification area is carried out, including the enrichment of aquatic resources and land resources. Through the resource enrichment analysis, the resource characteristics of each land can be comprehensively understood, which provides a basis for subsequent planning and construction. According to the enrichment of aquatic resources and land resources, the most suitable utilization mode of the potential identification area of each land is judged. If the enrichment data of aquatic resources is greater than that of land resources, the agricultural area stereoscopic modeling is selected to generate the corresponding agricultural area modeling data; if the enrichment data of land resources is greater than that of aquatic resources, the industrial area stereoscopic modeling is selected to generate the corresponding industrial area modeling data; if both are equal, the residential area stereoscopic modeling is selected to generate the corresponding residential area modeling data. The laser point cloud technology is used to simulate the planning and construction of the agricultural, industrial and residential area modeling data, and the simulation model is generated. The purpose of this step is to show the effect of the land use planning scheme through the simulation model, including the layout, scale and benefit prediction of various areas, so as to provide a visual reference for decision makers and help them to make and implement the land use planning scheme.

[0067] The above-described and above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A land use assessment and analysis system for engineering construction projects based on multi-source data, characterized in that, It includes a preprocessing module, a transformation module, a partitioning module, and a prediction module; The preprocessing module is used to acquire on-site survey data of construction land resources, perform data preprocessing on the on-site survey data of construction land resources, generate standard on-site survey data of construction land resources, and send it to the partitioning module. The conversion module is used to acquire multi-source geographic information data, extract terrain data from the multi-source geographic information data, generate a multi-source geographic terrain feature dataset, and then convert the multi-source geographic terrain feature dataset to generate multi-source geographic elevation data, which is then sent to the partitioning module. The partitioning module is used to perform terrain feature analysis on the multi-source geographic elevation data and to perform land cover classification on the standard land resource field survey data, generate land cover classification areas, generate regional partition plots and functional partition plots, and then send the regional partition plots and the functional partition plots to the prediction module. The prediction module is used to mark overlapping plots in the regional zoning and functional zoning, and to mark the overlapping plots in the regional zoning and functional zoning as composite rich plots, and to mark the non-overlapping plots in the regional zoning and functional zoning as single rich plots. Based on the composite rich plots and the single rich plots, a plot potential zoning map is generated, a planning and construction simulation model is generated based on the plot potential zoning map, and a land use planning scheme display is generated based on the planning and construction simulation model.

2. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 1, characterized in that, The preprocessing module includes a first data acquisition module, a first data processing module, and a data standardization module; The first data acquisition module is used to acquire the land resource field survey data and send the land resource field survey data to the first data processing module; The first data processing module is used to clean the land resource field survey data to generate cleaned land resource field survey data, then perform missing value detection on the cleaned land resource field survey data to generate missing value detection data, and fill in the missing values ​​on the missing value detection data to generate filled land resource field survey data, which is then sent to the data standardization module. The standardization module is used to standardize the data filled in by the land resource field survey and generate standard land resource field survey data.

3. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 1, characterized in that, The data conversion module includes a second data acquisition module, a second data processing module, and an elevation conversion module; The second data acquisition module is used to acquire multi-source geographic information data based on satellite imagery and send the multi-source geographic information data to the second data processing module; The second data processing module is used to clean the multi-source geographic information data to generate multi-source geographic information cleaned data, then unify the data fields of the multi-source geographic information cleaned data to generate multi-source geographic information unified data, then use GIS technology to spatially overlay the multi-source geographic information unified data and integrate it to generate multi-source geographic information overlay data, then extract terrain data from the multi-source geographic information overlay data to generate a multi-source geographic terrain feature dataset, and then send the multi-source geographic terrain feature dataset to the elevation conversion module. The elevation conversion module is used to perform elevation conversion on the multi-source geographic terrain feature dataset and generate multi-source geographic elevation data.

4. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 1, characterized in that, The partitioning module includes an analysis module and a classification module; The analysis module is used to project the terrain environment distribution onto the multi-source geographic elevation data using a terrain elevation model, generate terrain distribution data and water system distribution data, perform slope analysis on the terrain distribution data to generate slope undulation change data, and then integrate the terrain feature data based on the slope undulation change data and the water system distribution data to generate terrain feature analysis data. The classification module is used to analyze the current land use status of standard land resources field survey data, generate current land use status data, classify land cover based on the current land use status data of the topographic elevation model, generate land cover classification areas, and then perform regional feature clustering on the land cover classification areas according to the topographic feature analysis data to generate regional zoning plots. Geographic functional zoning is performed on regional plots to generate functional zoning plots.

5. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 1, characterized in that, The prediction module includes a labeling module, a calculation module, and a potential prediction module; The marking module is used to mark the overlapping plots of the regional partition plots and the functional partition plots, and to mark the overlapping plots of the regional partition plots and the functional partition plots as composite rich plots; at the same time, the non-overlapping plots of the regional partition plots and the functional partition plots are marked as single rich plots. The calculation module is used to perform a first land cover complexity calculation on the composite rich land parcel to generate composite land cover complexity data; at the same time, it performs a second land cover complexity calculation on the single rich land parcel to generate single land cover complexity data. The potential prediction module is used to predict the land use potential based on the complex land cover complexity data and the single land cover complexity data, generate a land potential zoning map, and use the land potential zoning map to simulate the planning and construction of the complex rich land and the single rich land, thereby generating a planning and construction simulation model.

6. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 5, characterized in that, The method for predicting land use potential based on the composite land parcel cover complexity data and the single land parcel cover complexity data, and generating a land parcel potential zoning map, includes the following steps: S61. Integrate the complex land cover complexity data of the composite land parcel and the single land parcel cover complexity data to generate land parcel cover complexity data; S62. Divide the land cover complexity data into datasets to generate a model training set and a model test set. Then, use the support vector machine algorithm to train the model on the model training set to generate a land potential training model. S63. Test the land potential training model using the model test set to obtain the land potential test data. Use the land potential test data to perform dilated convolution on the land potential training model to generate a land potential prediction model. S64. Import the land cover complexity data into the land potential prediction model to predict the land use potential of the land, thereby generating land use potential prediction data; classify the potential levels according to the land use potential prediction data to generate land use potential level data. S65. Based on the land use potential level data and the land use potential prediction data, construct a land potential zoning map to generate a land potential zoning map.

7. The engineering construction project land use demonstration and analysis system based on multi-source data according to claim 6, characterized in that, The step of generating a planning and construction simulation model by simulating the planning and construction of the composite rich land parcel and the single rich land parcel using the land parcel potential zoning map is as follows: S71. Using the land potential zoning map, identify the potential of the composite rich land parcels and the single rich land parcels, and generate land potential identification areas. S72. Perform resource enrichment analysis on the potential identification area of ​​the land parcel to generate resource enrichment analysis data, wherein the resource enrichment analysis data includes aquatic resource enrichment data and land resource enrichment data. S73. The aquatic resource enrichment data and the land resource enrichment data are judged. When the aquatic resource enrichment data of the potential identification area of ​​the land parcel is greater than the land resource enrichment data, the agricultural area three-dimensional modeling is performed on the potential identification area of ​​the land parcel to generate agricultural area modeling data. S74. When the land resource enrichment data of the potential identification area of ​​the land parcel is greater than the aquatic resource enrichment data, then perform three-dimensional industrial area modeling on the potential identification area of ​​the land parcel to generate industrial area modeling data. S75. When the land resource enrichment data of the potential identification area of ​​the land parcel is equal to the aquatic resource enrichment data, a three-dimensional residential area model is performed on the potential identification area of ​​the land parcel to generate residential area modeling data. S76. Using laser point cloud technology, the modeling data of the agricultural area, the industrial area, and the residential area are used to simulate planning and construction, generating a planning and construction simulation model.

Images