CN115829351A - Fine-scale population spatialization method fusing geospatial and internet data - Google Patents
Fine-scale population spatialization method fusing geospatial and internet data Download PDFInfo
- Publication number
- CN115829351A CN115829351A CN202211608344.1A CN202211608344A CN115829351A CN 115829351 A CN115829351 A CN 115829351A CN 202211608344 A CN202211608344 A CN 202211608344A CN 115829351 A CN115829351 A CN 115829351A
- Authority
- CN
- China
- Prior art keywords
- population
- residential
- data
- building
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a fine-scale population spatialization method fusing geospatial and internet data. The method comprises the following steps: obtaining residential building base data within the study area; constructing geographic grid data of a research area range, and determining the occupation ratio information of the base area of the residential building in each geographic grid unit; acquiring the floor number of an internet community of a research area, establishing a residential building floor number estimation model, and determining an input initial value of the residential building floor number estimation model; and calculating to obtain the estimated population number of the administrative district, performing error check on the estimated population number of the administrative district and the population number of the corresponding administrative district, iterating according to an error check result, and optimally adjusting the parameters of the residential building layer number estimation model. The invention constructs a population spatialization model by fusing land and building floor numbers of residential buildings covered by the ground surface and internet residential buildings, classifies the population living in cities and towns and villages and estimates the height of the residential building, realizes the spatialization of the fine-scale population and obtains higher precision.
Description
Technical Field
The invention relates to the technical field of demographic data spatialization, in particular to a fine-scale population spatialization method fusing geospatial and internet data.
Background
At present, the population data of China mainly come from census. Census data are typical statistical data, and in practical applications, the population is generally regarded as evenly distributed within the administration unit, the spatial resolution is low, and the administrative boundary is heavily dependent. The population data spatialization is to distribute the demographic data with the minimum unit as an administrative area into a grid with the size smaller than the minimum statistical unit of census according to a certain population spatialization model, and the gridded population density is closer to the real spatial distribution situation of population than the administrative population density. The population distribution information with fine scale is beneficial to evaluating the convenience of public service facilities and the reasonable configuration of public resources, and has important guiding significance for improving population comprehensive management.
Population spatialization accumulates abundant results in the aspects of theory and method, and mainly comprises a soil utilization method, a land utilization density estimation method, an urban area estimation method, a living unit estimation method, a night light index method, a natural and social economic characteristic estimation method and the like. The research results show that the population number has obvious correlation with living space, and the living space is expressed in the form of buildings. Along with the continuous deepening of the novel urbanization process of China, living space is more three-dimensional, and the floor area of a building can not accurately represent urban living space. Researchers usually obtain the building base floor area of the residential area by using remote sensing images, the number of building layers needs to be calculated by adopting a more complex algorithm, and the common methods include a direct method, a shadow method, a height difference method, a projection method and the like. Due to the fact that housing types in China are various, an algorithm for calculating the number of building layers by using a remote sensing method is complex, workload is large, and the method is difficult to be widely applied in a large range. Therefore, a method for quickly and accurately estimating the number of the building layers is lacked at present, and population spatialization in a fine scale is difficult to realize.
Therefore, it is desirable to provide a method for achieving fine-scale population spatialization.
Disclosure of Invention
The invention provides a method for realizing fine-scale population spatialization by fusing geospatial data and internet data, and aims to solve one or more problems.
According to a preferred embodiment of the present invention, there is provided a fine-scale population spatialization method for fusing geospatial and internet data, the method comprising the steps of:
s1, carrying out spatial superposition analysis on residential land data and building area data in a research area to obtain residential building base data in the research area;
s2, constructing a geographical grid unit covering the research area, and determining the occupation ratio information of the base floor area of the residential building in the geographical grid unit;
s3, constructing a residential building floor estimation model, and determining an input initial value of the residential building floor estimation model;
s4, calculating to obtain the population number corresponding to the administrative district based on the residential building floor number estimation model and the determined initial value, and performing error check on the population number corresponding to the administrative district;
and S5, performing parameter optimization adjustment on the residential building floor estimation model by using a result obtained by error detection.
Preferably, the performing spatial stacking analysis on residential land data and building block data in the research area specifically includes:
and selecting the data of the building area with the space position falling in the residential land range by using a space selection module of the ArcGIS system, taking the data as residential building base data, and dividing the residential building base data into two types according to the residential land attribute, namely urban residential building base data and rural residential building base data.
Preferably, step S2 specifically includes the following sub-steps:
s21, constructing geographical grid units covering the research area, wherein the areas of the geographical grid units are the same;
s22, carrying out spatial superposition analysis on the residential building base data and the geographic grid units, and calculating to obtain the residential building base area in the geographic grid units aiming at the geographic grid units;
s23, summarizing and counting the base areas of the residential buildings in the geographic grid units according to the index numbers of the geographic grid units to obtain the sum of the base areas of the residential buildings in the geographic grid units;
and S24, aiming at the geographic grid unit, dividing the sum of the base areas of the residential buildings of the geographic grid unit by the area of the geographic grid unit to obtain the ratio information of the base areas of the residential buildings in the geographic grid unit.
Preferably, in step S3, the input initial value of the model is determined by:
s31, acquiring residential community data and residential community building floor attribute data of the research area;
s32, adding the building floor attribute data to the residential community data and the residential building base data respectively;
s33, performing space superposition analysis on the residential community data and the residential building base data added with the building floor attribute data to obtain building floors corresponding to the classification codes of the building areas;
and S34, summarizing and counting the building floor number corresponding to the obtained classification code according to the classification code to obtain an average value of the building floor number corresponding to the classification code, and taking the average value as an input initial value of the residential building floor number estimation model.
Preferably, the residential building floor number estimation model is a calculation formula in which the population number is related to the number of residential building floors, and the expression of the model is as follows:
wherein, P i Represents a geographic grid cell i (whichWhere i is the index number of the geographic grid cell), sigma CIT i Represents the total volume of the housing construction in the urban residential land in the geographic grid unit i, sigma COU i Represents the total building volume P of the house in the rural homestead in the geographic grid unit i CIT Representing the general population living in a town, P COU Representing the general population living in the countryside, A 1 -A 9 Representing the base floor area of nine types of buildings corresponding to the area of the urban housing, F A1 -F A9 Indicating the number of floors corresponding to nine types of buildings in the area of urban housing, B 1 -B 9 Representing the base area of the building corresponding to nine types of house buildings in the range of rural homesteads, F B1 -F B9 The corresponding floor number of nine types of house buildings in the range of the rural homesteads is shown.
Preferably, step S4 includes: inputting the initial value into the residential building floor number estimation model, calculating to obtain the population number corresponding to the geographic grid unit i, summarizing the population numbers corresponding to all the geographic grid units in the administrative area to obtain the population number corresponding to the administrative area, and performing error check on the population number corresponding to the administrative area.
Wherein, the error checking formula is as follows:
wherein E is j Estimating error, P, for administrative district j population spatialization j The data is estimated for the population of administrative area j,
is the actual demographic data for administrative area j.
Preferably, step S5 includes the steps of:
s51, calculating population estimation errors of all administrative districts by using population estimation errors of all administrative districts, recording the population estimation errors as E, and taking the maximum value of the absolute values of the population estimation errors of all the administrative districts as E MAX ；
S52If the population estimation error sum E is not less than 0,E MAX Greater than or equal to 0, then F A1 -F A9 And F B1 -F B9 Iteratively increasing or decreasing in steps of 0.5 within their respective range of values;
s53, if population estimation error sum E<0，E MAX <0, then F A1 -F A9 And F B1 -F B9 Iteratively increasing or decreasing in steps of 0.5 over their respective range;
s54, calculating population square root error Q according to the following formula:
wherein, P j The data is estimated for the population of administrative area j,
actual demographic data for administrative district j;
s55, repeating the steps S3 and S4, at F A1 -F A9 And F B1 -F B9 Until the square root error Q of the population takes the minimum value, and simultaneously, F is obtained A1 -F A9 And F B1 -F B9 The optimal solution of (1).
Preferably, the method further comprises: and S6, calculating a spatialization population estimation error.
The present invention also provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method as described above.
The invention also provides a computer readable storage medium having a program stored thereon, which when executed by a processor implements a method as described above.
The invention constructs a spatial model by fusing land and building floor numbers of residential areas, ground surface covering building areas and internet residential areas, classifies the population living in cities and towns and villages to estimate the height of the residential building floor, realizes the spatialization of fine-scale population and obtains higher precision. .
Drawings
FIG. 1 is a flow diagram of a method of fine-scale demographics fusing geospatial and Internet data, according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
As shown in fig. 1, the fine-scale population spatialization method for fusing geospatial and internet data provided by the invention mainly includes the following steps:
s1, performing spatial superposition analysis on residential land data and building area data in a research area to obtain residential building base data in the research area. The research area in step S1 may refer to an administrative area, for example, beijing.
Specifically, the present land use data and the surface coverage data of the research area are stored in advance, wherein the residential land data is extracted from the present land use data, the housing construction area data is extracted from the surface coverage data, and the detailed classification and the corresponding data content of the extracted residential land data and the housing construction area data are shown in table 1:
TABLE 1 residential land, earth surface coverage Classification code and data content
According to a preferred embodiment of the present invention, the spatially superimposed analysis of the residential site data and the building block data in the study area specifically comprises:
and selecting the data of the housing building area with the space position falling in the housing land range by using a space selection module of the ArcGIS system, taking the data as housing building base data, and dividing the housing building base data into two types according to the housing land attribute, namely town housing building base data and rural housing building base data.
S2, constructing a plurality of geographic grid units covering the research area, and determining the occupation ratio information of the base area of the residential building in each geographic grid unit.
According to a preferred embodiment of the invention, step S2 comprises in particular the following sub-steps:
s21, constructing geographic grid units covering the research area, wherein the areas of the geographic grid units are the same.
According to a preferred embodiment of the invention, the geographical grid unit covering the investigation region is built by a geographical grid creation unit (e.g. a fishernet function module) of the ArcGIS system. Preferably, the area of each geographic grid cell is 0.5 km by 0.5 km, but the size of the geographic grid cell is not particularly limited by the present invention and may be set according to the specific condition of the study area.
And S22, carrying out spatial superposition analysis on the residential building base data and each geographic grid unit, and calculating to obtain the base area of at least one residential building in the geographic grid units aiming at each geographic grid unit.
According to a preferred embodiment of the present invention, the residential building base data and the geographic grid cells are spatially superposed and analyzed by using a spatial superposition analysis module (i.e., intercept function module) of the ArcGIS system.
S23, summarizing and counting the base area of the at least one residential building in each geographic grid unit according to the index number of the geographic grid unit to obtain the sum of the base areas of the residential buildings in each geographic grid unit.
According to the preferred embodiment of the present invention, the residential building base area in each geographic grid cell is summarized and counted by using a statistical function module (i.e., frequency function module) of the ArcGIS system, so as to obtain the sum of the residential building base area of each geographic grid cell.
And S24, dividing the sum of the base areas of the residential buildings of the geographic grid units by the area of the geographic grid units to obtain the ratio information of the base areas of the residential buildings in the geographic grid units.
And S3, constructing a residential building floor estimation model, and determining an input initial value of the residential building floor estimation model.
Specifically, the residential building floor number estimation model is a calculation formula of the correlation between the population number and the number of the residential building floors, and the expression of the model is as follows:
wherein, P i Represents the population number, sigma CIT, corresponding to the geographic grid unit i (wherein i is the index number of the geographic grid unit) i Represents the total building volume of the residential buildings in the urban residential land in the geographic grid unit i, sigma COU i Represents the total building volume P of the house in the rural homestead in the geographic grid unit i CIT Representing the general population living in a town, P COU Representing the total population living in the countryside (the total population refers to the total population in the research area and is derived from census or yearbook of statistics), A 1 -A 9 Shows the base floor area of nine types of house buildings (see Table 1 for nine types of house buildings, the same below) in the area of the urban house A1 -F A9 Indicating the number of floors corresponding to nine types of buildings in the area of urban housing, B 1 -B 9 Representing the base area of the building corresponding to nine types of house buildings in the range of rural homesteads, F B1 -F B9 The number of floors corresponding to nine types of house buildings in the range of the rural homesteads is represented. Wherein A is 1 -A 9 ，B 1 -B 9 ，F A1 -F A9 ，F B1 -F B9 Is directed to the study ofData within the zone.
In addition, A is 1 -A 9 ，B 1 -B 9 Obtained by the above step 23;
∑CIT i ＝A 1i *F A1 +A 2i *F A2 +…+A 9i *F A9
∑COU i ＝B 1i *F B1 +B 2i *F B2 +…+B 9i *F B9
wherein A is 1i –A 9i Is the corresponding building base floor area of nine types of house buildings in the town residence land range aiming at the geographic grid unit i, B 1i –B 9i The area of the building base corresponding to nine types of house buildings in the rural residential land range for the geographic grid unit i is referred to.
The input initial value of the model in the above-described step S3 means F A1 -F A9 ，F B1 -F B9 . Specifically, the input initial value of the model is determined by the following steps:
s31, acquiring residential community data and residential community building floor attribute data of the research area;
according to the preferred embodiment of the present invention, the residential quarter data is derived from geographical national condition monitoring residential quarter data; the residential community building floor number attribute data is obtained by crawling on a chain home network or other house intermediary related web pages through a Python crawler algorithm, and the residential community name and the corresponding building floor number information are obtained.
And S32, adding the building floor attribute data to the residential community data and the residential building base data respectively.
The residential cell name is used as an attribute association field, and the building floor attribute data with consistent residential cell names are assigned to the space range floor attribute item of the corresponding residential cell.
And S33, performing space superposition analysis on the residential community data and the residential building base data added with the building floor attribute data to obtain building floors corresponding to the classification codes of the house buildings and the house building areas.
According to a preferred embodiment of the present invention, the residential cell data and the residential building base data, to which the building floor number attribute data has been added, are subjected to spatial overlay analysis using a spatial overlay analysis module (i.e., an Intersect function module) of the ArcGIS system.
And S34, summarizing and counting the building floor number corresponding to the obtained classification code according to the classification code to obtain an average value of the building floor number corresponding to the classification code, and taking the average value as an input initial value of the residential building floor number estimation model.
It should be noted that the average value of the number of building layers is calculated to be used as an initial value of the model, and the next iterative optimization is performed.
According to the preferred embodiment of the invention, the number of the building layers corresponding to the classification codes is summarized and counted by utilizing a counting function module (namely, a Frequency function module) of the ArcGIS system, and the average value of the number of the building layers of each type is obtained by dividing the total number of the building layers of each type by the number of the corresponding building.
The average value of the building floor numbers corresponding to the classification code obtained in step S34 is used as an input initial value of the residential building floor number estimation model. It should be noted that the initial value is obtained based on the existing data calculation, and has a high correlation with the true value, so that the iteration efficiency can be effectively improved.
And S4, calculating to obtain the population number corresponding to the administrative area based on the residential building floor number estimation model and the determined initial value, and performing error check on the population number corresponding to the administrative area.
Specifically, step S4 includes: inputting the initial value into the residential building floor number estimation model, calculating to obtain the population number corresponding to the geographic grid unit i, and summarizing the population numbers corresponding to all the geographic grid units in the administrative district to obtain the population number corresponding to the administrative district, namely P in the following formula j And carrying out error check on the population number corresponding to the administrative district.
Wherein, the error checking formula is as follows:
wherein E is j Estimating error, P, for administrative district j population spatialization j The data is estimated for the population of administrative area j,
is the actual demographic data for administrative area j.
And S5, performing parameter optimization adjustment on the residential building floor estimation model by using a result obtained by error detection.
The parameter optimization and adjustment method in step S5 mainly includes the following steps:
s51, calculating population estimation errors of all administrative districts by using population estimation errors of all administrative districts, recording the population estimation errors as E, and taking the maximum value of the absolute values of the population estimation errors of all the administrative districts as E MAX ；
S52, if the population estimation error sum E is more than or equal to 0,E MAX Greater than or equal to 0, then F A1 -F A9 And F B1 -F B9 The iterative increase or decrease is performed in steps of 0.5 over their respective ranges.
S53, if the population estimation error is equal to E<0，E MAX <0, then F A1 -F A9 And F B1 -F B9 The iterative increase or decrease is performed in steps of 0.5 over their respective ranges.
S54, calculating population square root error Q according to the following formula:
wherein, P j The data is estimated for the population of administrative area j,
is the actual demographic data for administrative area j.
It should be noted that Q refers to the square root error of the smallest statistical unit of the demographic data, which is determined according to the available demographic data, and in this embodiment refers to the square root error of the county unit.
S55, repeating the steps S3 and S4, at F A1 -F A9 And F B1 -F B9 Until the square root error Q of the population takes the minimum value, and simultaneously, F is obtained A1 -F A9 And F B1 -F B9 The optimal solution of (1).
F A1 -F A9 And F B1 -F B9 See table 2 for the value ranges of (a).
TABLE 2 model variable value Range
According to a preferred embodiment of the present invention, the present invention may further include a step S6 to calculate an error of the model result. In particular, the method comprises the following steps of,
s6, calculating a spatialization population estimation error, and specifically comprising the following steps:
1) Inputting the building area ratio information of the residential building of the geographic grid obtained in the step S2 and the building type number of the building obtained in the step S5 into the population estimation model formula in the step S3, and calculating the population number corresponding to each geographic grid;
2) And (3) carrying out estimation population summary according to the minimum statistical unit of the population data, comparing with the actual population of the population statistics, and estimating the estimation error of the model, wherein the calculation method comprises the following steps:
wherein, P j The data is estimated for the population of administrative area j,
demographics for administrative district j.
The fine-scale population spatialization method for estimating the number of building layers by fusing geospatial data and internet data, which is provided by the invention, is explained in detail by taking Beijing as an example.
At present, china is in a development stage that population is gathered to a large city, the large city faces the problems of traffic jam, crowded living space, insufficient ecological space and the like, and the fine-scale population distribution information of the city is beneficial to evaluating the convenience of public service facilities and the reasonable allocation of public resources, and has important guiding significance for improving population comprehensive management. The Beijing city, the capital of China, is a typical representative super-large city. Therefore, in this embodiment, beijing is taken as an example, and 16 prefectures in Beijing are managed.
In step S1, residential land data and housing building district data of beijing are extracted for spatial overlay analysis to obtain residential building base data within the research district. The method specifically comprises the following substeps:
1) Extracting Beijing city residential land data including urban residential land and rural residential base based on the land utilization data;
2) Extracting building construction (district) data of Beijing city based on the surface coverage data;
3) Inputting two image layers of Beijing residential land data and house building (district) data to perform space superposition analysis, and outputting the two image layers as the base data of the residential house building;
4) Inputting the building base data of the residential buildings and the administrative district data of Beijing city and county level to carry out space superposition analysis, and preparing for the inspection of the subsequent spatialization population precision.
In step S2, a plurality of geographic grid cells covering beijing city are constructed, and proportion information of the base area of the residential building in each of the geographic grid cells is determined.
The method specifically comprises the following substeps:
1) Generating a geographical grid covering 500m × 500m of the universe of Beijing city by using a fishernet function module of an ArcGIIS10.7 system;
2) Performing spatial superposition analysis on the residential building base data obtained in the step S1 and 500m geographic grid data in Beijing City;
3) And utilizing the space superposition analysis result obtained in the previous step to count and summarize the base area of the residential building according to the geographic grid index, and calculating the residential building area ratio information of each geographic grid according to the statistical summary.
In step S3, acquiring building floor number data of residential cells in beijing city, specifically including the following substeps:
1) Crawling on a link home network or other house intermediary related web pages through a Python crawler algorithm to obtain the names of city cells in Beijing city and corresponding building layer number information;
2) Acquiring space range data of residential communities in Beijing city;
3) And assigning the building floor number attribute with consistent residential cell names to the floor number attribute item of the space range of the corresponding residential cell by using the residential cell names as the attribute associated fields.
Determining an input initial value of the residential building floor estimation model, specifically comprising the following substeps:
1) Selecting residential building base data based on the obtained residential community space data with the assigned building layer height attribute value;
2) And respectively counting the average building floor height values corresponding to various building data according to the residential land attribute town residential land and rural residential base, wherein the values are used as initial values.
The estimation model of the number of floors of the residential building constructed in the step S3 and the calculation thereof are as described above, and are not described herein again.
In step S4, the spatialization population estimation error is calculated by using the geographical grid residential building area ratio information obtained in step S2 and the initial value input obtained in step S3 as input parameters, and the formula is as follows:
in the formula, P j Estimating data for a population of administrative district j;
is actual statistical data of the population of the administrative district j, and the data is derived from seven-common population publications of all jurisdictions in Beijing.
And (5) iterating the model in the step (S4) to obtain an optimal solution, and calculating to obtain optimal solutions corresponding to different building types in the model, as shown in a table 3.
TABLE 3 model variable optimal solution
And 8: calculating a spatialization population estimation error, specifically comprising the following steps:
1) Inputting the building area ratio information of the residential building of the geographic grid obtained in the step S2 and the building floor number of the building type obtained by calculation in the step 7 into a model formula in the step 5, and calculating the population number corresponding to each geographic grid;
2) And (3) performing estimation population summary statistics according to the prefectures of various cities in Beijing, wherein the population spatialization estimation error is shown in a table 4.
TABLE 4 error table for spatialization estimation of Beijing market population
The present invention also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement the various method steps of the embodiments described above.
The invention also provides a computer-readable storage medium, on which a program is stored which, when being executed by a processor, carries out the individual method steps of the method embodiments described above. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
Furthermore, it should be noted that in the apparatus and method of the present application, it is apparent that the components or steps may be disassembled and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application. Also, the steps of performing the above-described series of processes may naturally be performed in the order described or in chronological order, but need not necessarily be performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be understood by those of ordinary skill in the art that all or any of the steps or elements of the methods and apparatus of the present application may be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or any combination thereof.
Although the invention has been described in detail hereinabove by way of general description, specific embodiments and experiments, it will be apparent to those skilled in the art that many modifications and improvements can be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A method of fine-scale population spatialization fusing geospatial and internet data, the method comprising the steps of:
s1, performing space superposition analysis on residential land data and building area data in a research area to obtain residential building base data in the research area;
s2, constructing a geographical grid unit covering the research area, and determining the occupation ratio information of the base floor area of the residential building in the geographical grid unit;
s3, constructing a residential building floor estimation model, and determining an input initial value of the residential building floor estimation model;
s4, calculating to obtain the population number corresponding to the administrative district based on the residential building floor number estimation model and the determined initial value, and performing error check on the population number corresponding to the administrative district;
and S5, performing parameter optimization adjustment on the residential building floor estimation model by using a result obtained by error detection.
2. The method of claim 1, wherein the spatially superimposed analysis of residential site data and residential building area data in the study area specifically comprises:
and selecting the data of the housing building area with the space position falling in the housing land range by using a space selection module of the ArcGIS system, taking the data as housing building base data, and dividing the housing building base data into two types according to the housing land attribute, namely town housing building base data and rural housing building base data.
3. The method according to claim 1, characterized in that step S2 comprises in particular the following sub-steps:
s21, constructing geographical grid units covering the research area, wherein the area of each geographical grid unit is the same;
s22, carrying out spatial superposition analysis on the residential building base data and the geographic grid units, and calculating to obtain the residential building base area in the geographic grid units aiming at each geographic grid unit;
s23, summarizing and counting the base areas of the residential buildings in each geographic grid unit according to the index number of the geographic grid unit to obtain the sum of the base areas of the residential buildings in the geographic grid unit;
and S24, aiming at the geographic grid unit, dividing the sum of the base areas of the residential buildings of the geographic grid unit by the area of the geographic grid unit to obtain the ratio information of the base areas of the residential buildings in the geographic grid unit.
4. The method according to claim 1, characterized in that in step S3 the input initial value of the model is determined by:
s31, acquiring residential community data and residential community building floor attribute data of the research area;
s32, adding the building floor attribute data to the residential community data and the residential building base data respectively;
s33, performing space superposition analysis on the residential community data and the residential building base data which are added with the building floor attribute data to obtain building floors corresponding to the classification codes of the house buildings and the house building areas;
and S34, summarizing and counting the building floor number corresponding to the obtained classification code according to the classification code to obtain an average value of the building floor number corresponding to the classification code, and taking the average value as an input initial value of the residential building floor number estimation model.
5. The method of claim 1 or 4, wherein the residential building number estimation model is a calculation formula of the population number and the residential building number, and the expression of the model is as follows:
wherein, P i Represents the population number, sigma CIT, corresponding to the geographic grid unit i (wherein i is the index number of the geographic grid unit) i Represents the total building volume of the residential buildings in the urban residential land in the geographic grid unit i, sigma COU i Represents the total building volume P of the house in the rural homestead in the geographic grid unit i CIT Representing the general population living in towns, P COU Representing the general population living in the countryside, A 1 -A 9 Building corresponding to nine types of house buildings within range of urban housingBase area, F A1 -F A9 Indicating the number of floors corresponding to nine types of buildings in the area of urban housing, B 1 -B 9 Representing the base area of the building corresponding to nine types of house buildings in the range of rural homesteads, F B1 -F B9 The number of floors corresponding to nine types of house buildings in the range of the rural homesteads is represented.
6. The method of claim 1,
step S4 comprises the following steps: and inputting the initial value into the residential building floor estimation model, calculating to obtain the population number corresponding to the geographic grid unit i, summarizing the population numbers corresponding to all the geographic grid units in the administrative area to obtain the population number corresponding to the administrative area, and performing error check on the population number corresponding to the administrative area.
Wherein, the error checking formula is as follows:
wherein E is j Estimating error, P, for administrative district j population spatialization j The data is estimated for the population of administrative area j,
is the actual demographic data for administrative area j.
7. The method according to claim 1, wherein step S5 comprises the steps of:
s51, calculating population estimation errors of all administrative districts by using population estimation errors of all administrative districts, recording the population estimation errors as E, and taking the maximum value of the absolute values of the population estimation errors of all the administrative districts as E MAX ；
S52, if the population estimation error sum E is more than or equal to 0,E MAX Greater than or equal to 0, then F A1 -F A9 And F B1 -F B9 Iteratively increasing or decreasing in steps of 0.5 over their respective range;
s53, if the population estimation error is equal to E<0，E MAX <0, then F A1 -F A9 And F B1 -F B9 Iteratively increasing or decreasing in steps of 0.5 within their respective range of values;
s54, calculating population square root error Q according to the following formula:
wherein, P j The data is estimated for the population of administrative area j,
actual demographic data for administrative district j;
s55, repeating the steps S3 and S4, at F A1 -F A9 And F B1 -F B9 Until the square root error Q of the population takes the minimum value, and simultaneously, F is obtained A1 -F A9 And F B1 -F B9 The optimal solution of (a).
8. The method of claim 1, further comprising:
and S6, calculating a spatialization population estimation error.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, having a program stored thereon, which when executed by a processor, implements the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211608344.1A CN115829351A (en) | 2022-12-14 | 2022-12-14 | Fine-scale population spatialization method fusing geospatial and internet data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211608344.1A CN115829351A (en) | 2022-12-14 | 2022-12-14 | Fine-scale population spatialization method fusing geospatial and internet data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115829351A true CN115829351A (en) | 2023-03-21 |
Family
ID=85545693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211608344.1A Pending CN115829351A (en) | 2022-12-14 | 2022-12-14 | Fine-scale population spatialization method fusing geospatial and internet data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829351A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746271A (en) * | 2023-12-29 | 2024-03-22 | 西南石油大学 | Intelligent recognition method for high-consequence area of gas transmission pipeline based on unmanned aerial vehicle image |
-
2022
- 2022-12-14 CN CN202211608344.1A patent/CN115829351A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746271A (en) * | 2023-12-29 | 2024-03-22 | 西南石油大学 | Intelligent recognition method for high-consequence area of gas transmission pipeline based on unmanned aerial vehicle image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Boeing | Street network models and indicators for every urban area in the world | |
| CN111932036B (en) | Fine spatio-temporal scale dynamic population prediction method and system based on position big data | |
| Arbia et al. | Error propagation modelling in raster GIS: overlay operations | |
| CN108804551B (en) | Spatial interest point recommendation method considering diversity and individuation | |
| CN105188030B (en) | A kind of method that mobile network data carries out geographical grid mapping | |
| CN110956412B (en) | Flood dynamic assessment method, device, medium and equipment based on real-scene model | |
| CN112085250B (en) | Population space distribution simulation method, terminal equipment and storage medium | |
| CN112954623B (en) | Resident occupancy rate estimation method based on mobile phone signaling big data | |
| WO2021248335A1 (en) | Method and system for measuring urban poverty spaces based on street view images and machine learning | |
| CN112508332B (en) | Gradual rural settlement renovation partitioning method considering multidimensional characteristics | |
| CN111986215A (en) | Population calculation method and system based on high-precision building data | |
| CN115829351A (en) | Fine-scale population spatialization method fusing geospatial and internet data | |
| Calka et al. | Redistribution population data across a regular spatial grid according to buildings characteristics | |
| Hu et al. | Incorporating spatial autocorrelation into house sale price prediction using random forest model | |
| CN116522272A (en) | Multi-source space-time data transparent fusion method based on urban information unit | |
| CN110716998B (en) | Fine scale population data spatialization method | |
| CN115129802A (en) | Population spatialization method based on multi-source data and ensemble learning | |
| Gao et al. | Improving the accuracy of extant gridded population maps using multisource map fusion | |
| Hsu et al. | Sample strategies for bias correction of regional LiDAR-assisted forest inventory estimates on small woodlots | |
| Zhao et al. | Urban spatial structure analysis: quantitative identification of urban social functions using building footprints | |
| CN114138926B (en) | Method and system for determining size of population distribution grid | |
| Ehlschlaeger et al. | Mapping neighborhood scale survey responses with uncertainty metrics | |
| CN103309980A (en) | Method, device and system for processing performance data | |
| Köhler et al. | Determination of household area and number of occupants for residential buildings based on census data and 3D CityGML building models for entire municipalities in Germany | |
| CN113191553A (en) | Population space distribution estimation method and system based on building scale |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: No.28 Lianhuachi West Road, Haidian District, Beijing 100080 Applicant after: NATIONAL GEOMATICS CENTER OF CHINA Address before: 100830 courtyard 28, Lianhuachi West Road, Haidian District, Beijing Applicant before: NATIONAL GEOMATICS CENTER OF CHINA |
|
| CB02 | Change of applicant information |