Fine-scale population spatialization method fusing geospatial and internet data

Abstract

This invention provides a fine-scale population spatialization method that integrates geospatial and internet data. The method includes: obtaining residential building footprint data within the study area; constructing geographic grid data for the study area and determining the proportion of residential building footprint area in each geographic grid unit; obtaining the number of floors in internet-connected buildings within the study area, establishing a residential building floor estimation model, and determining the initial input values ​​for the residential building floor estimation model; calculating the estimated population for each administrative region, performing error verification with the corresponding administrative region's population statistics, iterating based on the error verification results, and optimizing and adjusting the parameters of the residential building floor estimation model. This invention constructs a population spatialization model by integrating land use (residential land), surface-covered building areas, and the number of floors in internet-connected buildings, classifying the population living in urban and rural areas to estimate the floor height of residential buildings, achieving fine-scale population spatialization with high accuracy.

Description

Technical Field

[0001] This invention relates to the field of population data spatialization technology, and in particular to a fine-scale population spatialization method that integrates geospatial and internet data. Background Technology

[0002] Currently, my country's population data primarily comes from population censuses. Census data is a typical statistical data source. In practical applications, it typically treats the population as evenly distributed within administrative units, resulting in low spatial resolution and heavy reliance on administrative boundaries. Population spatialization involves allocating population statistics, with the smallest unit being administrative regions, into a grid smaller than the smallest statistical unit in the census, according to a specific population spatialization model. The population density in this grid is closer to the true spatial distribution of the population than that in administrative units. Fine-scale population distribution information helps evaluate the convenience of public service facilities and the rational allocation of public resources, providing important guidance for improving comprehensive population management.

[0003] The spatialization of population has accumulated rich theoretical and methodological achievements, mainly including land use methods, land use density estimation methods, urban area estimation methods, residential unit estimation methods, nighttime light index-based methods, and estimation methods based on natural and socio-economic characteristics. These research results indicate a significant correlation between population size and residential space, which is expressed in the form of buildings. With the deepening of my country's new urbanization process, residential space is becoming more three-dimensional, and building footprint area can no longer accurately represent urban residential space. Researchers typically use remote sensing imagery to obtain the building footprint area of ​​residential land, while the number of building stories requires more complex algorithms for estimation. Commonly used methods include the direct method, the shadow method, the elevation difference method, and the projection method. Due to the diverse housing types in my country, the algorithms for estimating the number of building stories using remote sensing methods are complex and labor-intensive, making widespread application difficult. Therefore, there is currently a lack of a fast and accurate method for estimating the number of building stories, hindering the realization of fine-scale population spatialization.

[0004] Therefore, there is an urgent need to provide a method for achieving precise population spatialization. Summary of the Invention

[0005] This invention provides a fine-scale population spatialization method that integrates geospatial and internet data, aiming to solve one or more of the above-mentioned problems.

[0006] According to a preferred embodiment of the present invention, a fine-scale population spatialization method that integrates geospatial and internet data is provided, the method comprising the following steps:

[0007] S1. Perform spatial overlay analysis on the residential land data and building area data in the study area to obtain the residential building footprint data in the study area;

[0008] S2. Construct a geographic grid cell covering the study area and determine the proportion of residential building footprint area in the geographic grid cell;

[0009] S3. Construct a residential building floor number estimation model and determine the initial input values ​​for the residential building floor number estimation model;

[0010] S4. Based on the residential building floor estimation model and the determined initial value, calculate the population corresponding to the administrative region, and perform error verification on the population corresponding to the administrative region;

[0011] S5. Using the results obtained from the error test, optimize and adjust the parameters of the residential building floor estimation model.

[0012] Preferably, the spatial overlay analysis of residential land data and building area data within the study area specifically includes:

[0013] Using the spatial selection module of the ArcGIS system, data on building areas whose spatial locations fall within the residential land area are selected. The results are used as residential building base data. Based on the residential land attributes, the residential building base data are divided into two categories: urban residential building base data and rural residential building base data.

[0014] Preferably, step S2 specifically includes the following sub-steps:

[0015] S21. Construct a geographic grid cell covering the study area, wherein the geographic grid cells have the same area;

[0016] S22. Perform spatial overlay analysis on the residential building base data and the geographic grid unit, and calculate the residential building base area in the geographic grid unit for the geographic grid unit;

[0017] S23. Summarize and statistically analyze the building footprint areas of the residential buildings in the geographic grid unit according to the geographic grid unit index number to obtain the sum of the building footprint areas of the residential buildings in the geographic grid unit;

[0018] S24. For the geographic grid cell, divide the sum of the residential building footprint areas of the geographic grid cell by the area of ​​the geographic grid cell to obtain the percentage information of the residential building footprint area in the geographic grid cell.

[0019] Preferably, in step S3, the initial input values ​​of the model are determined through the following steps:

[0020] S31. Obtain residential community data and building floor count data for the study area;

[0021] S32. Add the building floor number attribute data to the residential community data and the residential building foundation data respectively;

[0022] S33. Perform spatial overlay analysis on the residential community data and the residential building base data, which have already had the building floor number attribute data added, to obtain the building floor number corresponding to the classification code of the building area;

[0023] S34. Summarize and statistically analyze the number of building floors corresponding to the obtained classification codes according to the classification codes, and obtain the average number of building floors corresponding to the classification codes. Use the average value as the initial input value of the residential building floor estimation model.

[0024] Preferably, the residential building floor number estimation model is a calculation formula relating population size to the number of residential building floors, and the model expression is:

[0025]

[0026] Among them, P i Let ∑CIT represent the population corresponding to geographic grid cell i (where i is the index number of the geographic grid cell). i ∑COU represents the total building volume of residential buildings within urban residential land in geographic grid cell i. i P represents the total building volume of houses within a rural homestead in geographic grid cell i. CIT P represents the total population residing in the town / town. COU A1-A9 represent the total population residing in rural areas, and A1-A9 represent the building footprint area corresponding to the nine types of houses within the urban residential land area. A1 -F A9 This indicates the number of floors for the nine types of buildings within urban residential land, and B1-B9 indicate the building footprint area for the nine types of buildings within rural homestead land. B1 -F B9 This indicates the number of floors corresponding to the nine types of houses within the rural homestead area.

[0027] Preferably, step S4 includes: inputting the initial value into the residential building floor estimation model, calculating the population corresponding to geographic grid unit i, summarizing the population corresponding to all geographic grid units within the administrative region to obtain the population corresponding to the administrative region, and performing error verification on the population corresponding to the administrative region.

[0028] The error test formula is as follows:

[0029]

[0030] Among them, E j For the spatial estimation error of the population of administrative region j, P j Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

[0031] Preferably, step S5 includes the following steps:

[0032] S51. Using the population estimation errors of each administrative region, calculate the sum of the population estimation errors of all administrative regions, denoted as E, and take the maximum absolute value of the population estimation errors of all administrative regions, denoted as E0. MAX ;

[0033] S52. If the population estimation error and E≥0, E MAX If F ≥ 0, then F A1 -F A9 and F B1 -F B9 Within their respective value ranges, the values ​​are iteratively increased or decreased in steps of 0.5.

[0034] S53. If the population estimation error and E < 0, E MAX <0, then F A1 -F A9 and F B1 -F B9 Within their respective value ranges, the values ​​are iteratively increased or decreased in steps of 0.5.

[0035] S54. Calculate the square root error of the population Q according to the following formula:

[0036]

[0037] Among them, P j Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

[0038] S55. Repeat steps S3 and S4, in F A1 -F A9 and F B1 -F B9 The iteration is performed within the range of values ​​until the square root error of the population Q reaches its minimum value, and at the same time, F is obtained. A1 -F A9 and F B1 -F B9 The optimal solution.

[0039] Preferably, the method further includes: S6. Calculating the spatialized population estimation error.

[0040] The present invention also provides an electronic device, the electronic device comprising:

[0041] One or more processors;

[0042] Memory, used to store one or more programs;

[0043] When the one or more programs are executed by the one or more processors, the one or more processors perform the method as described above.

[0044] The present invention also provides a computer-readable storage medium on which a program is stored, which, when executed by a processor, implements the method described above.

[0045] This invention constructs a spatial model by integrating land use (residential land), surface cover (building areas), and the number of floors in internet-connected communities. It then classifies the population residing in towns and villages to estimate the floor height of residential buildings, achieving fine-scale population spatialization with high accuracy. Attached Figure Description

[0046] Figure 1 This is a flowchart of a fine-scale population spatialization method that integrates geospatial and internet data according to an embodiment of the present invention. Detailed Implementation

[0047] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0048] like Figure 1 As shown, the present invention provides a fine-scale population spatialization method that integrates geospatial and internet data, which mainly includes the following steps:

[0049] S1. Perform spatial overlay analysis on the residential land data and building area data within the study area to obtain the residential building footprint data within the study area. The study area in step S1 can refer to an administrative region, such as Beijing.

[0050] Specifically, land use status data and land cover data for the study area are pre-stored. Residential land data is extracted from the land use status data, and building area data is extracted from the land cover data. Detailed classifications and corresponding data contents of the extracted residential land data and building area data are shown in Table 1.

[0051]

[0052] Table 1. Classification Codes and Data Contents for Residential Land and Surface Cover

[0053] According to a preferred embodiment of the present invention, the spatial overlay analysis of residential land data and building area data within the study area specifically includes:

[0054] Using the spatial selection module of the ArcGIS system, data on building areas whose spatial locations fall within the residential land area are selected. The results are used as residential building base data. Based on the residential land attributes, the residential building base data are divided into two categories: urban residential building base data and rural residential building base data.

[0055] S2. Construct multiple geographic grid cells covering the study area and determine the proportion of residential building footprint area in each geographic grid cell.

[0056] According to a preferred embodiment of the present invention, step S2 specifically includes the following sub-steps:

[0057] S21. Construct a geographic grid cell covering the study area, wherein the geographic grid cells have the same area.

[0058] According to a preferred embodiment of the present invention, geographic grid cells covering the study area are constructed using geographic grid creation units in the ArcGIS system (e.g., the Fishnet function module). Preferably, the area of ​​each geographic grid cell is 0.5 km * 0.5 km, but the present invention does not specifically limit the size of the geographic grid cells and can set it according to the specific conditions of the study area.

[0059] S22. Perform spatial overlay analysis on the residential building base data and each of the geographic grid cells, and calculate the base area of ​​at least one residential building in each geographic grid cell.

[0060] According to a preferred embodiment of the present invention, the spatial overlay analysis module (i.e., the Intersect function module) of the ArcGIS system is used to perform spatial overlay analysis on the residential building base data and the geographic grid cells.

[0061] S23. Summarize and statistically analyze the base area of ​​at least one residential building in each geographic grid cell according to the geographic grid cell index number to obtain the sum of the base areas of residential buildings in each geographic grid cell.

[0062] According to a preferred embodiment of the present invention, the statistical function module (i.e., the Frequency function module) of the ArcGIS system is used to summarize and statistically analyze the residential building footprint area in each geographic grid cell to obtain the sum of the residential building footprint areas in each geographic grid cell.

[0063] S24. For each of the geographic grid cells, the sum of the residential building footprint areas of the geographic grid cells is divided by the area of ​​the geographic grid cell to obtain the percentage information of the residential building footprint area in the geographic grid cell.

[0064] S3. Construct a residential building floor number estimation model and determine the initial input values ​​for the residential building floor number estimation model.

[0065] Specifically, the residential building floor number estimation model is a calculation formula relating population size to the number of residential building floors. The model expression is as follows:

[0066]

[0067] Among them, P i Let ∑CIT represent the population corresponding to geographic grid cell i (where i is the index number of the geographic grid cell). i ∑COU represents the total building volume of residential buildings within urban residential land in geographic grid cell i. i P represents the total building volume of houses within a rural homestead in geographic grid cell i. CIT P represents the total population residing in the town / town. COU F represents the total population residing in rural areas (total population refers to the total population of the study area, sourced from population census or statistical yearbooks), A1-A9 represent the building footprint area corresponding to nine types of buildings within the urban residential land area (see Table 1 for the nine types of buildings, the same below), and F A1 -F A9 This indicates the number of floors for the nine types of buildings within urban residential land, and B1-B9 indicate the building footprint area for the nine types of buildings within rural homestead land. B1 -F B9 This indicates the number of stories corresponding to nine types of houses within the rural homestead area. Specifically, A1-A9, B1-B9, and F... A1 -F A9 F B1 -F B9 It refers to data within the study area.

[0068] It should be noted that A1-A9 and B1-B9 are obtained from step 23 above;

[0069] ∑CIT i =A 1i *FA1 +A 2i *F A2 +…+A 9i *F A9

[0070] ∑COU i =B 1i *F B1 +B 2i *F B2 +…+B 9i *F B9

[0071] Among them, A 1i –A 9i B refers to the building footprint area corresponding to nine types of buildings within the urban residential land area of ​​geographic grid unit i. 1i –B 9i This refers to the building footprint area corresponding to the nine types of houses within the rural residential land area of ​​geographic grid unit i.

[0072] The initial input value of the model in step S3 mentioned above refers to F. A1 -F A9 F B1 -F B9 Specifically, the initial input values ​​for the model are determined through the following steps:

[0073] S31. Obtain residential community data and building floor count data for the study area;

[0074] According to a preferred embodiment of the present invention, the residential community data is derived from the geographic national conditions monitoring data of residential communities; the building floor number attribute data of the residential community is obtained by crawling the name of the residential community and the corresponding building floor number information from Lianjia.com or other real estate agency-related web pages using a Python crawling algorithm.

[0075] S32. Add the building floor number attribute data to the residential community data and the residential building foundation data respectively.

[0076] Specifically, the name of the residential community is used as the attribute association field, and the building floor number attribute data with the same name as the residential community is assigned to the spatial range floor number attribute item of the corresponding residential community.

[0077] S33. Perform spatial overlay analysis on the residential community data and the residential building base data, which have already had the building floor number attribute data added, to obtain the building floor number corresponding to the classification codes of the buildings and building areas.

[0078] According to a preferred embodiment of the present invention, the spatial overlay analysis module (i.e., the Intersect function module) of the ArcGIS system is used to perform spatial overlay analysis on the residential community data and the residential building base data, which have been supplemented with the building floor number attribute data.

[0079] S34. Summarize and statistically analyze the number of building floors corresponding to the obtained classification codes according to the classification codes, and obtain the average number of building floors corresponding to the classification codes. Use the average value as the initial input value of the residential building floor estimation model.

[0080] It should be noted that the average number of building floors is calculated as the initial value for the model, which will be used for the next step of iterative optimization.

[0081] According to a preferred embodiment of the present invention, the statistical function module (i.e., the frequency function module) of the ArcGIS system is used to summarize and statistically analyze the number of building floors corresponding to the classification code, and the average number of building floors for each type is obtained by dividing the total number of building floors for each type by the number of corresponding buildings.

[0082] The average number of building floors corresponding to the classification codes obtained in step S34 is used as the initial input value for the residential building floor estimation model. It should be noted that the initial value is calculated based on existing data and has a high correlation with the actual value, effectively improving iteration efficiency.

[0083] S4. Based on the residential building floor estimation model and the determined initial value, calculate the population corresponding to the administrative region, and perform error verification on the population corresponding to the administrative region.

[0084] Specifically, step S4 includes: inputting the initial value into the residential building floor estimation model to calculate the population corresponding to geographic grid cell i; and summing up the population corresponding to all geographic grid cells within the administrative region to obtain the population corresponding to the administrative region, i.e., P in the formula below. j And perform error verification on the population corresponding to the administrative region.

[0085] The error test formula is as follows:

[0086]

[0087] Among them, E j For the spatial estimation error of the population of administrative region j, P j Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

[0088] S5. Using the results obtained from the error test, optimize and adjust the parameters of the residential building floor estimation model.

[0089] The parameter optimization and adjustment method in step S5 mainly includes the following steps:

[0090] S51. Using the population estimation errors of each administrative region, calculate the sum of the population estimation errors of all administrative regions, denoted as E, and take the maximum absolute value of the population estimation errors of all administrative regions, denoted as E0. MAX ;

[0091] S52. If the population estimation error and E≥0, E MAX If F ≥ 0, then F A1 -F A9 and F B1 -F B9 Iteratively increase or decrease within their respective value ranges in steps of 0.5.

[0092] S53. If the population estimation error and E < 0, E MAX <0, then F A1 -F A9 and F B1 -F B9 Within their respective value ranges, the values ​​are iteratively increased or decreased in steps of 0.5.

[0093] S54. Calculate the square root error of the population Q according to the following formula:

[0094]

[0095] Among them, P j Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

[0096] It should be noted that Q refers to the square root error of the smallest statistical unit of population statistics, which is determined based on the available population statistics data. In this embodiment, it refers to the square root error of the population of the district / county unit.

[0097] S55. Repeat steps S3 and S4, in F A1 -F A9 and F B1 -F B9 The iteration is performed within the range of values ​​until the square root error of the population Q reaches its minimum value, and at the same time, F is obtained. A1 -F A9 and F B1 -F B9 The optimal solution.

[0098] F A1 -F A9 and F B1 -F B9 Please refer to Table 2 for the range of values.

[0099]

[0100]

[0101] Table 2 Range of Model Variable Values

[0102] According to a preferred embodiment of the present invention, the present invention may further include step S6, to calculate the error of the model results. Specifically,

[0103] S6. Calculate the spatialized population estimation error, specifically including the following steps:

[0104] 1) Input the information on the proportion of residential building area of ​​the geographic grid obtained in step S2 and the number of building floors of the building type obtained in step S5 into the population estimation model formula in step S3 to calculate the population corresponding to each geographic grid.

[0105] 2) Estimate the population by the smallest statistical unit of population data, compare it with the actual population in the population statistics, and evaluate the estimation error of the model of this invention. The calculation method is as follows:

[0106]

[0107] Among them, P j Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

[0108] The following section uses Beijing as an example to explain in detail the fine-scale population spatialization method for estimating building floors by integrating geospatial data and internet data proposed in this invention.

[0109] my country is currently in a stage of population concentration in large cities, which face "big city problems" such as traffic congestion, overcrowded living spaces, and insufficient ecological space. Detailed population distribution information at the urban scale helps evaluate the convenience of public service facilities and the rational allocation of public resources, and is of great guiding significance for improving comprehensive population management. Beijing, as the capital of China, is a typical example of a megacity. Therefore, this embodiment selects Beijing as an example, which administers 16 districts.

[0110] In step S1, residential land data and building area data of Beijing are extracted and spatially overlaid to obtain the residential building footprint data within the study area. This specifically includes the following sub-steps:

[0111] 1) Extract residential land data for Beijing based on land use data, including urban residential land and rural homesteads;

[0112] 2) Extract building (district) data for Beijing based on land cover data;

[0113] 3) Input two layers of Beijing residential land data and building (district) data for spatial overlay analysis, and output the building footprint data of residential buildings;

[0114] 4) Input residential building footprint data and Beijing municipal county-level administrative division data for spatial overlay analysis to prepare for subsequent verification of spatial population accuracy.

[0115] In step S2, multiple geographic grid cells covering Beijing are constructed, and the proportion of the residential building footprint area in each geographic grid cell is determined.

[0116] Specifically, it includes the following sub-steps:

[0117] 1) Using the fishnet function module of ArcGIS 10.7 system, generate a geographic grid covering the entire area of ​​Beijing, 500m*500m.

[0118] 2) Perform spatial overlay analysis on the residential building foundation data obtained in step S1 and the 500m geographic grid data of Beijing.

[0119] 3) Using the spatial overlay analysis results obtained in the previous step, the building footprint area of ​​residential buildings is statistically summarized according to the geographic grid index, and the proportion of residential building area in each geographic grid is calculated accordingly.

[0120] In step S3, the data on the number of floors in residential buildings in Beijing is obtained, which specifically includes the following sub-steps:

[0121] 1) Use Python web scraping algorithms to crawl Lianjia.com or other real estate agency-related web pages to obtain the names of all residential communities in Beijing and their corresponding building floors;

[0122] 2) Obtain spatial range data of residential communities in Beijing;

[0123] 3) Using the name of the residential community as the attribute association field, assign the number of building floors with the same name to the corresponding number of floors in the spatial range of the residential community.

[0124] Determine the initial input values ​​for the residential building floor estimation model, which includes the following sub-steps:

[0125] 1) Based on the obtained residential community spatial data with assigned building height attribute values, select the building foundation data of residential buildings;

[0126] 2) Based on the residential land use attributes of urban residential land and rural homesteads, the average building height corresponding to various types of building data is calculated separately, and this value is used as the initial value.

[0127] The residential building floor estimation model constructed in step S3 and its calculation are as described above, and will not be repeated here.

[0128] In step S4, the spatialized population estimation error is calculated using the residential building area ratio information obtained in step S2 and the initial value calculated in step S3 as input parameters, as shown in the following formula:

[0129]

[0130] In the formula, P j Population estimation data for administrative district j; This is the actual population statistics for administrative district j, which are derived from the population bulletins of the Seventh National Population Census of each district in Beijing.

[0131] The optimal solution is obtained by iteratively solving the model in step S4. The optimal solutions for different building types in the model are shown in Table 3.

[0132]

[0133]

[0134] Table 3 Optimal Solution of Model Variables

[0135] Step 8: Calculate the spatialized population estimation error, which includes the following steps:

[0136] 1) Input the information on the proportion of residential building area of ​​the geographic grid obtained in step S2 and the number of building floors of the building type calculated in step 7 into the model formula in step 5 to calculate the population corresponding to each geographic grid.

[0137] 2) Population estimates were compiled and statistically analyzed for each district under the jurisdiction of Beijing. The spatial estimation error of the population is shown in Table 4.

[0138]

[0139] Table 4 Error Table for Spatial Estimation of Beijing's Population

[0140] The present invention also provides an electronic device comprising: one or more processors; a memory for storing one or more programs; wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the various method steps of the above embodiments.

[0141] The present invention also provides a computer-readable storage medium storing a program that, when executed by a processor, implements the various method steps of the method embodiments described above. The computer-readable storage medium may be, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0142] Furthermore, it should be noted that in the apparatus and method of this application, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of this application. Moreover, the steps performing the above series of processes can naturally be executed in the order described or in chronological order, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of this application can be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices.

[0143] Although the present invention has been described in detail above with general descriptions, specific embodiments, and experiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A fine-scale population spatialization method that integrates geospatial and internet data, characterized in that, The method includes the following steps: S1. Perform spatial overlay analysis on residential land data and building area data in the study area to obtain residential building footprint data in the study area, including urban residential building footprint data and rural residential building footprint data. S2. Construct a geographic grid cell covering the study area and determine the proportion of residential building footprint area in the geographic grid cell; S3. Construct a residential building floor number estimation model and determine the initial input value of the residential building floor number estimation model; wherein, the community name and corresponding building floor information are obtained by crawling Lianjia.com or other real estate agency related web pages through Python web crawling algorithm, and the average building floor height corresponding to various types of housing building data is statistically calculated according to the residential land use attributes of urban residential land and rural homestead, and this value is used as the initial value; The residential building floor number estimation model is a calculation formula relating population size to the number of residential building floors. The model expression is: ； Among them, P i Let ∑CIT represent the population corresponding to geographic grid cell i (where i is the index number of the geographic grid cell). i ∑COU represents the total building volume of residential buildings within urban residential land in geographic grid cell i. i P represents the total building volume of houses within a rural homestead in geographic grid cell i. CIT P represents the total population residing in the town / town. COU A1-A9 represent the total population residing in rural areas, and A1-A9 represent the building footprint area corresponding to the nine types of houses within the urban residential land area. A1 -F A9 This indicates the number of floors for the nine types of buildings within urban residential land, and B1-B9 indicate the building footprint area for the nine types of buildings within rural homestead land. B1 -F B9 This indicates the number of floors corresponding to the nine types of houses within the rural homestead area; S4. Based on the residential building floor estimation model and the determined initial value, calculate the population corresponding to the administrative region, and perform error verification on the population corresponding to the administrative region; S5. Using the results obtained from the error test, optimize and adjust the parameters of the residential building floor estimation model; Step S5 includes the following steps: S51. Using the population estimation errors of each administrative region, calculate the sum of the population estimation errors of all administrative regions, denoted as E, and take the maximum absolute value of the population estimation errors of all administrative regions, denoted as E0. MAX ; S52. If the population estimation error and E≥0, E MAX If F ≥ 0, then F A1 -F A9 and F B1 -F B9 Within their respective value ranges, the values ​​are iteratively increased or decreased in steps of 0.

5. S53. If the population estimation error and E < 0, E MAX <0, then F A1 -F A9 and F B1 -F B9 Within their respective value ranges, the values ​​are iteratively increased or decreased in steps of 0.

5. S54. Calculate the square root error of the population Q according to the following formula: ； in, Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j. S55. Repeat steps S3 and S4, in F A1 -F A9 and F B1 -F B9 The iteration is performed within the range of values ​​until the square root error of the population Q reaches its minimum value, and at the same time, F is obtained. A1 -F A9 and F B1 -F B9 The optimal solution.

2. The method according to claim 1, characterized in that, The spatial overlay analysis of residential land data and building area data within the study area specifically includes: Using the spatial selection module of the ArcGIS system, data on building areas whose spatial locations fall within the residential land area are selected. The results are used as residential building base data. Based on the residential land attributes, the residential building base data are divided into two categories: urban residential building base data and rural residential building base data.

3. The method according to claim 1, characterized in that, Step S2 specifically includes the following sub-steps: S21. Construct a geographic grid cell covering the study area, wherein each geographic grid cell has the same area; S22. Perform spatial overlay analysis on the residential building footprint data and the geographic grid cell, and calculate the residential building footprint area in the geographic grid cell for each geographic grid cell; S23. Summarize and statistically analyze the building footprint area of ​​each residential building in each geographic grid cell according to the geographic grid cell index number to obtain the sum of the building footprint areas of the residential buildings in the geographic grid cell; S24. For the geographic grid cell, divide the sum of the residential building footprint areas of the geographic grid cell by the area of ​​the geographic grid cell to obtain the percentage information of the residential building footprint area in the geographic grid cell.

4. The method according to claim 1, characterized in that, In step S3, the initial input values ​​of the model are determined through the following steps: S31. Obtain residential community data and building floor count data for the study area; S32. Add the building floor number attribute data to the residential community data and the residential building foundation data respectively; S33. Perform spatial overlay analysis on the residential community data and the residential building base data that have been added with the building floor number attribute data to obtain the building floor number corresponding to the classification code of the building and the building area; S34. Summarize and statistically analyze the number of building floors corresponding to the obtained classification codes according to the classification codes, and obtain the average number of building floors corresponding to the classification codes. Use the average value as the initial input value of the residential building floor estimation model.

5. The method according to claim 1, characterized in that, Step S4 includes: inputting the initial value into the residential building floor estimation model, calculating the population corresponding to geographic grid cell i, summarizing the population corresponding to all geographic grid cells within the administrative region to obtain the population corresponding to the administrative region, and performing error verification on the population corresponding to the administrative region. The error test formula is as follows: ； Among them, E j To estimate the spatial population error of administrative region j, Population estimation data for administrative district j. This refers to the actual population statistics for administrative region j.

6. The method according to claim 1, characterized in that, The method further includes: S6. Calculate the spatialized population estimation error.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

8. A computer-readable storage medium having a program stored thereon, the program being executed by a processor to implement the method as described in any one of claims 1-6.

Images