A city shrinkage recognition method based on timing population data variable point detection

Abstract

The embodiment of the application discloses a kind of city shrinkage identification methods based on timing population data change point detection, it is related to geographic information technical field, the method comprises: obtaining land use spatial grid data and population spatial grid data;Land use spatial grid data, population spatial grid data are respectively converted into matrix;Determine town land grid based on land use spatial matrix, extract population data from population spatial matrix, construct to obtain one-dimensional population array, obtain smoothed timing data after smoothing processing;Change trend mutation node of population data is identified based on smoothed timing data, each one-dimensional population array is segmented;Population data change trend of the array after identification is segmented, determine city shrinkage grid.The application uses change point detection to automatically divide period, can more objectively identify the start and end time of city shrinkage, can provide data support for future town land evolution simulation and regional development policy formulation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information, and particularly relates to a city shrinkage recognition method based on time-series population data change point detection. BACKGROUND

[0002] City shrinkage is a phenomenon of population decline and economic recession of a city at a certain stage of development, and population decline is still generally regarded as the core symbol of city shrinkage. When the city defined by administrative boundaries is taken as the research object, the use of population decline to describe city shrinkage may include rural population in the analysis, which is easy to lead to result deviation. At present, population decline within the natural city is generally used to depict city shrinkage, and this method still has the following shortcomings:

[0003] (1) The spatial accuracy of city shrinkage recognition is insufficient. As an important field of city research, urban land use evolution simulation usually uses grid or patch as the basic unit to display the spatial city process. However, in the case of identifying city shrinkage based on natural city, the combination of city shrinkage and urban land use evolution spatial display simulation may be limited.

[0004] (2) The division of research period is relatively subjective. At present, most of the related technologies in identifying city shrinkage in a certain period of time will divide the research period into several target periods, and identify the city state in each target period. However, this time division method is usually subjective, and can be divided according to the data availability to set a time interval of five years or ten years. This way is easy to ignore the key time point of the actual occurrence of population change trend, leading to inaccurate identification of city shrinkage period.

[0005] In recent years, with the availability of high-resolution geographic data, some related technologies try to use annual population data or night light data to identify city shrinkage trend, but this method usually only fits the overall population change by a straight line, ignoring the dynamic change of population trend in the research period.

[0006] Therefore, at present, there is a lack of a method which can accurately identify the location and time interval of city shrinkage effect. SUMMARY

[0007] The embodiment of the application provides a city shrinkage identification method based on time-series population data change point detection, to solve the defects in the related art. The application uses annual population grid data, detects change points of time-series data through a Pelt algorithm, divides research periods according to the change points, and judges the change trend of each time period through regression fitting, so as to identify shrinkage grids and the start and end years of shrinkage. The method can more finely understand the spatial imbalance phenomenon in the urban development process, and can provide data support for future urban land evolution simulation and regional development policy making. The technical solution is as follows:

[0008] In a first aspect, the embodiment of the application provides a city shrinkage identification method based on time-series population data change point detection, characterized in that it comprises:

[0009] S1, acquiring land use spatial grid data of a research region in multiple different periods and population spatial grid data corresponding to the periods;

[0010] S2, converting the land use spatial grid data into a land use spatial matrix and converting the population spatial grid data into a population spatial matrix, the matrix elements corresponding to cells, and the matrix space corresponding to cell space;

[0011] S3, determining urban land use grids based on the land use spatial matrix of each period, extracting population data of each urban land use grid in each period from the population spatial matrix, and constructing one-dimensional population arrays of the urban land use grids;

[0012] S4, respectively smoothing each one-dimensional population array to obtain smoothed time-series data;

[0013] S5, identifying change trend mutation nodes of the population data in each one-dimensional population array based on the smoothed time-series data, respectively segmenting each one-dimensional population array based on the change trend mutation nodes, and re-determining the start time node and the end time node of the new one-dimensional population array;

[0014] S6, identifying the change trend of the population data of the segmented new one-dimensional population array, and determining the position of the city shrinkage grid and the corresponding start time node and end time node.

[0015] In an optional solution of the first aspect, step S1 comprises the following steps:

[0016] S101, reclassifying the land use spatial grid data in multiple different periods to determine urban land use grids and other land type grids;

[0017] S102, reprojecting the land use spatial grid data and the population spatial grid data in the same period to make the coordinate projections of the land use spatial grid data and the population spatial grid data consistent.

[0018] S103 resampling the land use spatial raster data of each period to make the land use spatial raster data consistent with the raster size of the population spatial raster data.

[0019] In an optional implementation of the first aspect, the step S2 includes the following steps:

[0020] S201 determining the land use type corresponding to each grid in the land use spatial raster data, and assigning values to each land use type respectively to obtain the land use spatial matrix.

[0021] S202 determining the population data corresponding to each grid in the population spatial raster data of each period to obtain the population spatial matrix corresponding to the population spatial raster data of each period, and each element in each population spatial matrix representing the population data of the corresponding grid in the corresponding period.

[0022] In an optional implementation of the first aspect, the step S3 includes the following steps:

[0023] S301 searching for the urban land grid in the land use spatial matrix of each period according to the value corresponding to the urban land type, and determining the duration period of each urban land grid.

[0024] S302 extracting the population data of each urban land grid in the corresponding period from the population spatial matrix corresponding to the duration period, and arranging the population data of each period in chronological order to construct a one-dimensional population array of each urban land grid.

[0025] In an optional implementation of the first aspect, the step S4 includes the following steps:

[0026] Sliding the preset sliding window on the one-dimensional population array, and generating the smoothed time series data based on the population data mean calculated by the preset sliding window in each sliding.

[0027] The population data mean in the preset sliding window is calculated based on the sliding window smoothing method, and the formula is:

[0028]

[0029] Wherein, P(t) is the smoothed population data, g(·) is the population data before smoothing, the size of the preset sliding window is 2n+1, t is the middle point of the preset sliding window, g(t) is the population data corresponding to the middle point, and i is the displacement distance from the middle point.

[0030] In an optional implementation of the first aspect, the step S5 includes the following steps:

[0031] S501 constructing a cost function according to a radial basis function:

[0032] K(y s,t )=exp(-σ||y s -y t || 2 );

[0033]

[0034] wherein K(y s,t ) is the similarity between the data at time s and the data at time t, the value range is [0, 1], ||y s -y t || represents the Euclidean distance between two data points, σ represents the bandwidth, which controls the attenuation speed of the similarity between two data points with the increase of distance; c(y s,t ) is the cost function of the data at time s and the data at time t, b and a are parameters;

[0035] S502 constructing an objective function according to the cost function, the optimization objective is to minimize the objective function, comprising:

[0036] F(t)=Z(s)+c(y s,t )+β;

[0037] wherein F(t) is the objective function when the data point t is the segmentation point, Z(s) is the objective function value when the feasible solution s is the segmentation point, when the feasible solution set is empty, Z(s) is 0; β is a penalty term, which is used to control the number of identified change points;

[0038] S503 in each loop process of solving the objective function, updating the feasible solution set, adding the current time t into the feasible solution set, and filtering out the time s in the feasible solution set which does not satisfy the following condition:

[0039] z(s)+c(y s,t )≤Z(t);

[0040] S504 determining the change trend mutation node of population data according to the solving result of the objective function, segmenting the time series data at each position, segmenting each one-dimensional population array based on the change trend mutation node, and re-determining the starting time node and the ending time node of the new one-dimensional population array.

[0041] In an optional solution of the first aspect, step S6 comprises the following steps:

[0042] Based on the segmented new one-dimensional population array and the starting time node and the ending time node corresponding to the new one-dimensional population array, regression fitting is performed, and the formula is applied:

[0043] P t = kt' + b;

[0044] The urban shrinkage grid is determined based on the following formula:

[0045]

[0046] If the output of f(k, ΔP) is of the type of shrinkage, the corresponding grid is determined as an urban shrinkage grid, and the rest are non-shrinkage grid outputs. The urban shrinkage grid is output.

[0047] where t' is the time, P t is the population data at time t, k is the slope of the fitting straight line, b is the intercept, the population data change trend in the corresponding grid is judged based on the slope k of the fitting straight line: when k > 0, the population in the grid is in an upward trend, and when k < 0, the population in the grid is in a downward trend, and ΔP is the population data change rate.

[0048] In a second aspect, the embodiments of the present application also provide an urban shrinkage identification device based on time sequence population data change point detection, comprising:

[0049] A data acquisition module is configured to acquire land use spatial grid data of a research area at multiple different periods and population spatial grid data corresponding to the periods;

[0050] A data processing module is configured to convert the land use spatial grid data into a land use spatial matrix and convert the population spatial grid data into a population spatial matrix, wherein the matrix elements correspond to cells, and the matrix space corresponds to cell space.

[0051] The data processing module is further configured to determine a town land grid based on the land use spatial matrix of each period, extract population data of each town land grid at each period from the population spatial matrix, and construct a one-dimensional population array of each town land grid.

[0052] The data processing module is further configured to perform smoothing processing on each one-dimensional population array to obtain smoothed time sequence data.

[0053] A calculation module is configured to identify a change trend mutation node of population data in each one-dimensional population array based on the smoothed time sequence data, segment each one-dimensional population array based on the change trend mutation node, and determine a starting time node and an ending time node of a new one-dimensional population array.

[0054] The calculation module is further configured to identify a population data change trend of the segmented new one-dimensional population array, and determine a position of an urban shrinkage grid and corresponding starting time node and ending time node.

[0055] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method provided by the first aspect or any one of the implementation manners of the first aspect when executing the program.

[0056] In a fourth aspect, a non-transitory computer-readable storage medium is provided, which stores a computer program, and the computer program is executable on a processor to implement the method provided by the first aspect or any one of the implementation manners of the first aspect.

[0057] The technical scheme provided by some embodiments of the present application has at least the following beneficial effects:

[0058] Compared with the prior art, the method for identifying urban shrinkage based on time-series population data change point detection provided by the embodiments of the present application has the following advantages and beneficial effects:

[0059] (1) The present application selects population decline as the core index to ensure that the spatial and temporal resolution of the data is fine enough, the spatial resolution of the population spatial grid data can match the basic unit of urban expansion simulation, and the data is easy to obtain year by year. The results of identification can be better combined with urban expansion simulation research.

[0060] (2) The present application uses change point detection to automatically divide the period, more objectively identifies the start and end time of urban shrinkage, determines the node of period division by searching for the mutation point in the time-series population data, identifies the population change trend in each period after division, and then obtains the start and end time of the urban shrinkage grid appearing urban shrinkage phenomenon. It provides support for more finely understanding the spatial imbalance phenomenon in the process of urban development, and provides reliable data support for future urban land evolution simulation and regional development policy making. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical schemes in the present application or related art, the following will briefly introduce the drawings needed to be used in the embodiments or related art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0062] Figure 1 is a flowchart of a method for identifying urban shrinkage based on time-series population data change point detection provided by the embodiments of the present application;

[0063] Figure 2is a window size influence schematic diagram in data smoothing provided by an embodiment of the application based on time sequence population data change point detection;

[0064] Figure 3 is a city shrinkage grid proportion situation schematic diagram of a city shrinkage identification method based on time sequence population data change point detection provided by an embodiment of the application;

[0065] Figure 4 is a city development state schematic diagram of a city shrinkage identification method based on time sequence population data change point detection provided by an embodiment of the application;

[0066] Figure 5 is a structure schematic diagram of a city shrinkage identification device based on time sequence population data change point detection provided by an embodiment of the application;

[0067] Figure 6 is a structure schematic diagram of an electronic device provided by an embodiment of the application. DETAILED DESCRIPTION

[0068] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0069] The terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above-described drawings are intended to cover the non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but can optionally include other steps or modules not listed or can optionally include other steps or modules inherent to the process, method, product or device.

[0070] It should be noted that the terms "first" and "second" involved in the present application are only to distinguish similar objects, and do not represent a specific order of the objects. Understandably, "first" and "second" can be interchanged in a specific order or sequence as allowed. It should be understood that the objects distinguished by "first" and "second" can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those described or illustrated herein.

[0071] The present application will be described in detail below with reference to specific embodiments.

[0072] Next, the present application will be described in detail below with reference to specific embodiments. Figure 1, and introduce a city shrinkage recognition method based on time-series population data change point detection provided by the embodiment of the application. For details, please refer to Figure 1 , Figure 1 A flowchart of a city shrinkage recognition method based on time-series population data change point detection provided by the embodiment of the application is shown. As shown in Figure 1 , the method comprises the following steps:

[0073] S1 obtaining land use spatial raster data of a research area in multiple different periods and population spatial raster data corresponding to the periods;

[0074] S2 converting the land use spatial raster data into a land use spatial matrix and converting the population spatial raster data into a population spatial matrix, the elements of the matrix corresponding to cells, and the matrix space corresponding to the cell space;

[0075] S3 determining a town land use grid based on the land use spatial matrix of each period, extracting population data of each town land use grid in each period from the population spatial matrix, and constructing a one-dimensional population array of each town land use grid;

[0076] S4 performing smoothing processing on each one-dimensional population array to obtain smoothed time-series data;

[0077] S5 identifying a change trend mutation node of the population data in each one-dimensional population array based on the smoothed time-series data, segmenting each one-dimensional population array based on the change trend mutation node, and re-determining a starting time node and an ending time node of a new one-dimensional population array;

[0078] S6 identifying a population data change trend of the segmented new one-dimensional population array, and determining a position of a city shrinkage grid and corresponding starting time node and ending time node.

[0079] Specifically, step S1 comprises the following steps:

[0080] S101 reclassifying the land use spatial raster data in multiple different periods to determine town land use grids and other land type grids;

[0081] S102 reprojecting the land use spatial raster data and the population spatial raster data in the same period to make the coordinate projections of the land use spatial raster data and the population spatial raster data consistent;

[0082] S103 resampling the land use spatial raster data of each period to make the grid sizes of the land use spatial raster data and the population spatial raster data consistent.

[0083] Specifically, the city shrinkage in the Beijing-Tianjin-Hebei region can be identified. Land use spatial grid data and population spatial grid data in 2000, 2005, 2010, 2015, 2020 and 2022 are selected. Each grid in the land use spatial grid data corresponds to the land use type in the corresponding year, such as urban land, expandable land and water area. Each grid in the population spatial grid data corresponds to the population data in the corresponding year.

[0084] In some embodiments, step S2 comprises the following steps:

[0085] S201 determines the land use type corresponding to each grid in the land use spatial grid data, and assigns a value to each land use type to obtain the land use spatial matrix.

[0086] For example, the element value of the matrix includes: urban land is 1, expandable land is 0, and water area is 2. The value of each element reflects the corresponding land use type. The embodiments of the present application are not limited thereto.

[0087] S202 determines the population data corresponding to each grid in the population spatial grid data in each period to obtain the population spatial matrix corresponding to the population spatial grid data in each period. Each element in each population spatial matrix represents the population data of the corresponding grid in the corresponding period.

[0088] For example, the population spatial grid data in each period can be converted into a series of population quantity matrices A, B, C, …, N, etc. The element value in each matrix A, B, C, …, N represents the population quantity in each grid unit in a specific period.

[0089] In some embodiments, step S3 comprises the following steps:

[0090] S301 searches for urban land grids in the land use spatial matrix in each period according to the value corresponding to the urban land type, and determines the duration period of each urban land grid.

[0091] S302 extracts the population data of each urban land grid in the corresponding period from the population spatial matrix corresponding to the duration period, arranges the population data in each period in chronological order, and constructs a one-dimensional population array of each urban land grid.

[0092] Specifically, since the grid size and the coordinate projection are consistent in step S1, the land use spatial matrix and the population spatial matrix can be stacked into a high-dimensional tensor in the spatial dimension. Specifically, the population data of each town land grid can be extracted by searching for the spatial coordinates (x, y) of the town land type corresponding value in the land use state matrix, for example, the town land type corresponding value is 1, and the population data of the same position grid in the population spatial matrix of each period can be correspondingly obtained, so as to realize the extraction of the population data of each town land grid.

[0093] Further, according to the advancement of time, the town land grid can be updated according to the land use spatial matrix of the next period. For the newly added town land position, the starting time of the conversion to town land can be determined, and the ending time of the conversion of part of the town land to other land types in the previous period can also be determined, so that the duration of each town land grid can be determined, and the population data at the corresponding time point can be extracted from the population spatial matrix of the corresponding period, so as to continuously update the one-dimensional population array of each town land grid.

[0094] For example, a grid is a town land grid from 2000 to 2022, and the population data corresponding to the grid during 2000-2022 is extracted, and each data is arranged in chronological order, so that a one-dimensional population array corresponding to the grid is obtained. At this time, the one-dimensional population array includes 23 population data, and the data length of the array at this time can be recorded as 23.

[0095] In some embodiments, step S4 includes the following steps:

[0096] Based on the preset sliding window sliding on the one-dimensional population array, the population data mean calculated by the preset sliding window at each sliding is used to generate smoothed time series data;

[0097] The population data mean in the preset sliding window is calculated based on the sliding window smoothing method, and the formula is:

[0098]

[0099] Wherein, P(t) is the smoothed population data, g(·) is the population data before smoothing, the size of the preset sliding window is 2n+1, t is the middle point of the preset sliding window, g(t) is the population data corresponding to the middle point, and i is the displacement distance from the middle point.

[0100] It should be noted that sensitivity analysis can be performed on different window sizes, such as Figure 2As shown, in the present embodiment, when the size of the preset sliding window is 3, the key changes can be retained while effectively reducing the interference of noise on the detection of mutation points; when the size of the window is 5, the key changes can also be retained, but data will be lost, which will make the time series data with a data length of 8 unreliable; when the size of the window is 7, more data will be lost, and the characteristics of the key changes are not well retained. Therefore, the size of the preset sliding window can be preferably 3.

[0101] In some embodiments, step S5 comprises the following steps:

[0102] S501 constructing a cost function according to a radial basis function:

[0103] K(y s,t )=exp(-σ||y s -y t || 2 );

[0104]

[0105] wherein K(y s,t ) is the similarity between the data at time s and the data at time t, and the value range is [0, 1], ||y s -y t || represents the Euclidean distance between two data points, and σ represents the bandwidth, which controls the decay speed of the similarity between two data points as the distance increases; c(y s,t ) is the cost function of the data at time s and the data at time t, and b and a are parameters for evaluating the consistency within a period; the cost function ensures the comparability of the cost functions between different lengths of periods by introducing the (b-a) term and multiplying the sum of the similarities of the points within a period by a normalization term 1 / (b-a).

[0106] S502 constructing an objective function according to the cost function, and the optimization objective is to minimize the objective function, comprising:

[0107] F(t)=Z(s)+c(y s,t )+β;

[0108] wherein F(t) is the objective function when the data point t is the segmentation point, Z(s) is the objective function value when the feasible solution s is the segmentation point, and Z(s) is 0 when the feasible solution set is empty; β is a penalty term for controlling the number of identified change points;

[0109] S503 in each loop process of solving the objective function, updating the feasible solution set, adding the current time t into the feasible solution set, and filtering out the time s in the feasible solution set that does not satisfy the following conditions:

[0110] Z(s) + c(y s,t )≤Z(r);

[0111] S504 According to the solving result of the target function, a change trend mutation node of population data is determined, time series data at each position is segmented, each one-dimensional population array is segmented based on the change trend mutation node, and a starting time node and an ending time node of a new one-dimensional population array are re-determined.

[0112] In some embodiments, step S6 includes the following steps:

[0113] Based on the segmented new one-dimensional population array and the starting time node and the ending time node corresponding to the new one-dimensional population array, regression fitting is performed, and the formula is applied:

[0114] P t =kt′+b;

[0115] The urban shrinkage grid is determined based on the following formula:

[0116]

[0117] If the output type of f(k, ΔP) is shrinkage, it is determined that the corresponding grid is an urban shrinkage grid, and the rest are non-shrinkage grid. The urban shrinkage grid is output.

[0118] Where t' is the time, P t is the population data at time t, k is the slope of the fitting straight line, b is the intercept, the slope k of the fitting straight line is used to judge the population data change trend in the corresponding grid: when k>0, the population in the grid is in an upward trend, and when k<0, the population in the grid is in a downward trend, and ΔP is the population data change rate.

[0119] In some embodiments, after S4, the data length of each one-dimensional population array can be determined. If the data length of the one-dimensional population array is greater than a preset threshold, the step of S5 is performed to segment the one-dimensional population array, and the step of S6 is performed based on the segmented one-dimensional population array to perform regression fitting. Otherwise, the step of S6 is directly performed based on the unsegmented one-dimensional population array to perform regression fitting.

[0120] In one specific embodiment, the data used in the present application includes population data and land use data. The population data of the Beijing-Tianjin-Hebei region from 2000 to 2022 is used to determine the population change trend and identify urban shrinkage. The land use data of the Beijing-Tianjin-Hebei region from 2000 to 2020 is used to determine the range of urban land. The specific circumstances of these two types of data are as follows:

[0121] The population data used in the embodiments of the present application can be obtained from the LandScan population dataset. To further ensure the accuracy and representativeness of this dataset, the embodiments of the present application can aggregate the population data of 2010 and 2020 to the city scale, and verify it with the statistical results of the census to determine whether it is reliable to use the LandScan population data to identify urban shrinkage.

[0122] The land use data used in the embodiments of the present application can be obtained from the Resource and Environment Data Center of the Chinese Academy of Sciences. This dataset is based on Landsat remote sensing image data and is built by combining field surveys, including 6 first-level classes and 25 second-level classes, with a resolution of 30m. The embodiments of the present application select land use data from 2000 to 2020 at intervals of 5 years according to the availability of data and the research period, and regard the urban land in the second-level class as urban land.

[0123] Since the projection coordinate systems and resolutions of the population data and the land use data are not the same, the embodiments of the present application also perform re-projection and resampling operations on the population data and the land use data. First, the population data is re-projected to the same as the land use data, and then the land use data is resampled to the resolution consistent with the re-projected population data. Cities have the characteristics of high population density, and in the grid with both urban land and non-urban land, urban land often contributes more population, so the resampling principle of the embodiments is that as long as there is urban land in the grid, the attribute of the grid is urban land.

[0124] All data preprocessing, data smoothing, change trend mutation node detection and shrinkage identification algorithms of the embodiments of the present application can be implemented in the Python 3.11 environment, and can use Python libraries such as Numpy, Geopandas and Gdal.

[0125] The embodiments of the present application identify the urban shrinkage of the Jing-Jin-Ji region at the grid scale from 2000 to 2022, and preliminarily count these grids. Figure 3 The proportion of the number of grids in shrinkage state since 2000 to the number of urban land in 2000 is shown. As shown in the figure, more than 20% of the urban land of all cities in the Jing-Jin-Ji region appeared shrinkage phenomenon in 2000, and the shrinkage area of Tangshan and Handan even exceeded 40%. By 2022, the proportion of shrinkage area of all cities has decreased, and only 4 cities have a shrinkage area ratio of more than 30%, among which Handan has the largest decline, and the shrinkage area ratio of Qinhuangdao has decreased to less than 20%.

[0126] The embodiments of the present application identify the contraction and growth patterns of cities at intervals of 5 years, identify the contraction and growth patterns of each city in four periods from 2000 to 2020, as shown in Figure 4 The four contraction and growth patterns in the Beijing-Tianjin-Hebei region from 2000 to 2020 are densification (increase in urban population density), contraction (decrease in urban population density and decrease in total urban population), sprawl (decrease in urban population density but increase or no change in total urban population), and reasonable growth (no change in urban population density but increase in total urban population).

[0127] From Figure 4 It can be seen that from 2000 to 2005, the cities in the Beijing-Tianjin-Hebei region were mainly of sprawl and contraction types, and only Shijiazhuang was of densification type; from 2005 to 2010, most cities were of sprawl type, only Baoding was of reasonable growth type, and Cangzhou was of densification type; from 2010 to 2015, the cities were mainly of densification and sprawl types; from 2015 to 2020, there were mainly sprawl and contraction types, and only Hengshui was of reasonable growth type. Among the four periods, the cities in the Beijing-Tianjin-Hebei region were mainly of sprawl, contraction and densification types, and reasonable growth appeared less frequently. Most cities experienced a densification process from 2010 to 2015, indicating that the phenomenon of faster urban land expansion than population growth in this period was effectively curbed.

[0128] The following is a device embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0129] Next, please refer to Figure 5 , a structural schematic diagram of a city contraction identification device based on time-series population data change point detection provided by an exemplary embodiment of the present application. The device can be realized by software, hardware or a combination of the two to become all or part of the terminal, and can also be integrated as an independent module on the server. The device 50 includes a data acquisition module 501, a data processing module 502 and a calculation module 503, wherein:

[0130] The data acquisition module 501 is configured to acquire land use spatial raster data of a research region in multiple different periods and population spatial raster data corresponding to the periods;

[0131] The data processing module 502 is configured to convert the land use spatial raster data into a land use spatial matrix and convert the population spatial raster data into a population spatial matrix, the elements of the matrix corresponding to cells, and the matrix space corresponding to the cell space;

[0132] The data processing module 502 is further configured to determine urban land grids based on the land use spatial matrix of each period, extract the population data of each urban land grid in each period from the population spatial matrix, and construct a one-dimensional population array of each urban land grid;

[0133] The data processing module 502 is further configured to perform smoothing on each one-dimensional population array to obtain smoothed time series data;

[0134] The calculation module 503 is used to identify the mutation nodes of the population data change trend in each one-dimensional population array based on the smoothed time series data, segment each one-dimensional population array based on the mutation nodes, and re-determine the start time node and end time node of the new one-dimensional population array;

[0135] The calculation module 503 is further used to identify the population data change trend of the segmented new one-dimensional population array, and determine the position of the urban shrinkage grid and the corresponding start time node and end time node.

[0136] It should be noted that the device 50 provided in the above embodiment, when implementing the urban shrinkage identification method based on change point detection in time-series population data, is merely illustrated by the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the device provided in the above embodiment and the embodiment of the urban shrinkage identification method based on change point detection in time-series population data are based on the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0137] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method of any of the above embodiments are implemented.

[0138] See Figure 6 , is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0139] like Figure 6 As shown, the electronic device 600 includes a processor 601 and a memory 602 .

[0140] In the embodiments of the present application, the processor 601 is the control center of the computer system, which can be a processor of a physical machine or a processor of a virtual machine. The processor 601 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 601 can be implemented in at least one of the hardware forms of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array).

[0141] The processor 601 can also include a main processor and a coprocessor. The main processor is a processor for processing data in a wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state.

[0142] The memory 602 can include one or more computer-readable storage media, which can be non-transitory. The memory 602 can also include a high-speed random access memory, and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments of the present application, the non-transitory computer-readable storage medium in the memory 602 is used to store at least one instruction for being executed by the processor 601 to implement the method in the embodiments of the present application.

[0143] In some embodiments, the electronic device 600 further includes a peripheral device interface 603 and at least one peripheral device 604. The processor 601, the memory 602, and the peripheral device interface 603 can be connected through a bus or a signal line. Each peripheral device 604 can be connected to the peripheral device interface 603 through a bus, a signal line, or a circuit board. Specifically, the peripheral device interface 603 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 601 and the memory 602.

[0144] In some embodiments of the present application, the processor 601, the memory 602, and the peripheral device interface 603 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 601, the memory 602, and the peripheral device interface 603 can be implemented on a separate chip or circuit board. The embodiments of the present application do not make specific limitations in this regard.

[0145] The electronic device structure block diagram shown in the embodiments of the present application does not constitute a limitation on the electronic device 600, and the electronic device 600 can include more or fewer components than shown, or combine certain components, or use a different arrangement of components.

[0146] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps of the method of any of the preceding embodiments. The computer readable storage medium can include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nano system (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0147] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course can also be implemented by hardware. Based on such an understanding, the above technical solutions, essentially or in other words, the part that contributes to the related art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some part of the embodiments.

[0148] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some 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 method for identifying urban shrinkage based on timing population data change point detection, characterized in that, The method comprises the following steps: S1: acquiring land use spatial raster data of a research area in multiple different periods and population spatial raster data corresponding to the periods; S2: converting the land use spatial raster data into a land use spatial matrix and converting the population spatial raster data into a population spatial matrix, wherein elements of the matrix correspond to cells and matrix spaces correspond to cell spaces; S3: determining urban land use grids based on the land use spatial matrix of each period, extracting population data of each urban land use grid in each period from the population spatial matrix, and constructing a one-dimensional population array of each urban land use grid; S4: performing smoothing processing on each one-dimensional population array to obtain smoothed time series data; S5: identifying change trend mutation nodes of the population data in each one-dimensional population array based on the smoothed time series data, segmenting each one-dimensional population array based on the change trend mutation nodes, and re-determining starting time nodes and ending time nodes of new one-dimensional population arrays; S6: identifying population data change trends of the segmented new one-dimensional population arrays and determining positions of urban shrinkage grids and corresponding starting time nodes and ending time nodes. 2.The urban shrinkage identification method based on timing population data change point detection according to claim 1, characterized in that, Step S1 comprises the following steps: S101: reclassifying the land use spatial raster data in multiple different periods to determine urban land use grids and other land type grids; S102: reprojecting the land use spatial raster data and the population spatial raster data in the same period to make the coordinate projections of the land use spatial raster data and the population spatial raster data consistent; S103: resampling the land use spatial raster data in each period to make the grid sizes of the land use spatial raster data and the population spatial raster data consistent. 3.The urban shrinkage identification method based on timing population data change point detection according to claim 2, characterized in that, Step S2 comprises the following steps: S201: determining land use types corresponding to each grid in the land use spatial raster data, assigning values to each land use type, and obtaining the land use spatial matrix; S202: determining population data corresponding to each grid in the population spatial raster data in each period, obtaining population spatial matrices corresponding to the population spatial raster data in each period, and representing population data of corresponding grids in corresponding periods by each element in each population spatial matrix.

4. The urban shrinkage identification method based on timing population data change point detection according to claim 3, characterized in that, Step S3 comprises the following steps: S301: searching for urban land use grids in the land use spatial matrix of each period according to values corresponding to urban land types and determining duration periods of each urban land use grid; S302: extracting population data of each urban land use grid in corresponding periods from the population spatial matrix corresponding to the duration period, arranging the population data of each period in chronological order, and constructing a one-dimensional population array of each urban land use grid. 5.The urban shrinkage identification method based on timing population data change point detection according to claim 1, wherein, Step S4 comprises the following steps: Sliding a preset sliding window on the one-dimensional population array, and generating smoothed time series data based on population data mean values calculated by the preset sliding window in each sliding; The population data mean values in the preset sliding window are calculated based on the sliding window smoothing method and the formula is: ； wherein, is the smoothed population data, is the smoothed population data, the size of the preset sliding window is 2n+1, and t is the middle point of the preset sliding window, is the population data corresponding to the middle point, and i is the displacement from the middle point.

6. The urban shrinkage identification method based on timing population data change point detection according to claim 5, characterized in that, Step S5 comprises the following steps: S501: constructing a cost function according to a radial basis function: ； ; wherein, is the similarity between data at time s and data at time t, and the value range is [0, 1], denotes the Euclidean distance between two data points, and σ denotes the bandwidth, which controls the attenuation speed of the similarity between two data points with the increase of the distance; is the cost function of data at time s and data at time t, and b and a are parameters; S502 constructing an objective function according to the cost function, and optimizing an objective to minimize the objective function, including: ; wherein, is the objective function with data point t as the split point, is the objective function value with feasible solution s as the split point, when the feasible solution set is empty, is 0; β is a penalty term for controlling the number of identified change points; S503 in each loop process of solving the objective function, updating a feasible solution set, adding a current time t into the feasible solution set, and filtering out a time s in the feasible solution set that does not satisfy the following condition: ; S504 determining a change trend mutation node of population data according to a solving result of the objective function, segmenting time series data at each position, segmenting each one-dimensional population array based on the change trend mutation node, and re-determining a start time node and an end time node of a new one-dimensional population array.

7. The urban shrinkage identification method based on timing population data change point detection according to claim 6, characterized in that, Step S6 includes the following steps: Based on the segmented new one-dimensional population array and the start time node and the end time node corresponding to the new one-dimensional population array, regression fitting is performed, and the formula is applied: ； Based on the following formula, the urban shrinkage grid is determined: ； If the type of output is contraction, then determine that the corresponding grid is a city contraction grid, and the rest are non-contraction grid output the city contraction grid; wherein, is the time, is the population data at t is the population data at the time, k is the slope of the fitted line, b is the intercept, based on the slope of the fitted line k determines the trend of the population data within the corresponding grid: k > 0, the population within the grid is in an upward trend, k < 0, the population within the grid is in a downward trend, is the rate of change of the population data.

8. An urban shrinkage recognition device based on timing population data change point detection, characterized in that, Comprising: A data acquisition module configured to acquire land use spatial grid data of a research area at multiple different time periods and population spatial grid data corresponding to the time periods; A data processing module configured to convert the land use spatial grid data into a land use spatial matrix and convert the population spatial grid data into a population spatial matrix, wherein elements of the matrix correspond to cells, and matrix spaces correspond to cell spaces; The data processing module is further configured to determine a town land grid based on the land use spatial matrix of each time period, extract population data of each town land grid at each time period from the population spatial matrix, and construct a one-dimensional population array of each town land grid; The data processing module is further configured to perform smoothing processing on each one-dimensional population array to obtain smoothed time series data; A calculation module is configured to identify a change trend mutation node of population data in each one-dimensional population array based on the smoothed time series data, segment each one-dimensional population array based on the change trend mutation node, and re-determine a start time node and an end time node of a new one-dimensional population array. The calculation module is further configured to identify a population data change trend of the segmented new one-dimensional population array, and determine a position of an urban shrinkage grid and corresponding start time node and end time node.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the method of any one of claims 1 to 7 when executing the program.

10. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the method of any one of claims 1 to 7 when executed by the processor.

Images