A method for attributing regional terrestrial water storage changes based on geographic data modeling

Through geographic data modeling and weighted regression model, the problem of low efficiency in calculating factors affecting land water reserves in the existing technology is solved, and more accurate water reserve changes analysis and data support are achieved, providing valuable reference for environmental resource management. .

CN118503345BActive Publication Date: 2024-11-26WUHAN UNIV
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410686505.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-30
Publication Date
2024-11-26
Estimated Expiration
2044-05-30

AI Technical Summary

Technical Problem

The prior art is difficult to accurately and quickly calculate the impact of environmental factors and human activity factors on land water reserves, resulting in large amounts of calculations and low efficiency.

Method used

Using a geographic data modeling method, by obtaining land water reserve data and driver factor data, pre-processing, trend analysis, correlation screening and principal component analysis are performed, and combined with geographic weighted regression model, a linear regression model is generated to determine the main driver factors. .

Benefits of technology

Improve the understanding of changing trends in land water reserves and the efficiency of data analysis, provide more accurate data to support environmental resource management and climate change response, and help formulate sustainable development and water resource management policies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118503345B_ABST
    Figure CN118503345B_ABST
Patent Text Reader

Abstract

The embodiment of the present application discloses a method, device, equipment and storage medium for attributing changes in regional terrestrial water reserves based on geographic data modeling, and relates to the field of hydrological monitoring technology. The method includes: obtaining a terrestrial water reserve data set and a driving factor data set of a target area within a target period, outputting an image set with a uniform spatiotemporal resolution through preprocessing, and further analyzing the trend analysis results of the terrestrial water reserves in the target area during the target period; screening the driving factors in the image set, eliminating driving factors with multicollinearity, and generating a main driving factor set; combining a principal component analysis algorithm for weighted regression, generating a linear regression model, and determining the main driving factors affecting the change in terrestrial water reserves. The GWR model enhanced by combining the geographic detector method and the principal component analysis method in the present application can better understand the main patterns of data changes and extract the most representative features, thereby more effectively analyzing geographic data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of hydrological monitoring technology, and in particular to a method for attributing changes in regional terrestrial water reserves based on geographic data modeling. Background Art

[0002] Terrestrial water reserves are the sum of water resources on the earth's surface and underground, including lakes, rivers, groundwater, glaciers, snow and soil moisture. Accurately estimating the dynamic changes in terrestrial water reserves will help detect and predict droughts and water resource changes.

[0003] At present, the Gravity Recovery and Climate Experiment (GRACE) satellite can be used to observe the changes in terrestrial water reserves with high precision, and can monitor water resources at different scales such as the world, designated regions, and designated river basins in real time and continuously, and can provide continuous, stable, and high-temporal and spatial resolution terrestrial water reserve observation data. The trend of water reserve changes can then be analyzed based on the observation data, and the degree of influence of environmental, human and other influencing factors on water reserves can be studied through the trend of water reserve changes.

[0004] Related technologies can analyze the degree of influence of influencing factors on water reserves by modeling the changing trends of influencing factors and water reserves. However, due to the large number of influencing factors, including but not limited to environmental factors such as precipitation, river runoff, temperature, humidity, etc., and human activity factors such as cultivated land and population, it is difficult to calculate the impact of each type of influencing factor and the combination of factors on water reserves, resulting in large amount of calculation and low calculation efficiency.

[0005] Therefore, there is currently a lack of a method that can accurately and quickly calculate the impact of environmental factors and human activities on water reserves. Summary of the invention

[0006] The embodiment of the present application provides a method for attributing regional terrestrial water storage changes based on geographic data modeling to solve the defects in the above-mentioned related technologies. The technical solution is as follows:

[0007] In a first aspect, an embodiment of the present application provides a method for attributing changes in regional terrestrial water reserves based on geographic data modeling, comprising:

[0008] Acquire a terrestrial water storage data set of a target area within a target period, and determine a driving factor data set of the target area within the target period;

[0009] Preprocessing the terrestrial water storage data set and the driving factor data set to output a set of images of terrestrial water storage and driving factors with a uniform temporal and spatial resolution for a preset time series;

[0010] Analyze the dynamic changes of terrestrial water reserves based on the image set, and output the trend analysis results of terrestrial water reserves in the target area during the target period;

[0011] The driving factors in the image set are screened by a correlation analysis algorithm, and driving factors with multicollinearity are eliminated to generate a main driving factor set;

[0012] The principal component analysis algorithm and the geographically weighted regression model are combined to perform weighted regression based on the trend analysis results and the set of main driving factors to generate a linear regression model, and the main driving factors affecting the changes in terrestrial water reserves in the corresponding area are determined based on the linear regression model.

[0013] In an optional solution of the first aspect, the preprocessing of the terrestrial water storage dataset and the driving factor dataset to output a set of images of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors includes:

[0014] Performing interpolation processing on the terrestrial water storage dataset and the driving factor dataset to fill in missing data;

[0015] Dividing the target area into a plurality of sub-areas, and resampling the spatial resolution of each sub-area to a preset spatial resolution;

[0016] Aligning the time of the terrestrial water storage dataset and the driving factor dataset corresponding to each of the sub-regions to achieve the unification of the temporal resolution;

[0017] Output an image set of uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors in each sub-region within the target region.

[0018] In an optional solution of the first aspect, the analyzing the dynamic change of the terrestrial water reserve based on the image set and outputting the trend analysis result of the terrestrial water reserve in the target area during the target period includes:

[0019] For each of the sub-areas, dividing the target time period into sub-time periods of predetermined sizes;

[0020] Analyze the trend analysis results of the land water storage over time in each of the sub-periods;

[0021] Output the trend analysis result of the terrestrial water storage in the target area during the target period.

[0022] In an optional solution of the first aspect, the driving factors in the image set are screened by a correlation analysis algorithm, driving factors with multicollinearity are eliminated, and a main driving factor set is generated, including:

[0023] Calculate a first correlation value between every two driving factors based on a correlation analysis algorithm, and retain driving factors whose first correlation values ​​are within a preset correlation threshold range;

[0024] Based on the geographically weighted regression model, a linear regression model is constructed for each of the geographical elements of the sub-region, the variance inflation factor of each driving factor is calculated, and the driving factor whose variance inflation factor is greater than a preset variance inflation factor threshold is deleted;

[0025] A geographic detector analysis is performed on the driving factors of each sub-region to calculate a second correlation value of each driving factor, and the driving factors whose second correlation value is greater than a second correlation value threshold are selected as the main driving factor set of the corresponding sub-region.

[0026] In an optional scheme of the first aspect, the driving factors include hydrological and meteorological related driving factors and human activity related driving factors.

[0027] In an optional solution of the first aspect, the combining of the principal component analysis algorithm and the geographically weighted regression model performs weighted regression based on the trend analysis result and the set of main driving factors to generate a linear regression model, including:

[0028] Standardizing the main driving factors in the main driving factor set, converting each main driving factor into a dimensionless standardized value, constructing a correlation coefficient matrix based on the standardized values ​​of all main driving factors, performing eigenvalue decomposition on the correlation coefficient matrix, and outputting corresponding eigenvectors and eigenvalues ​​corresponding to the eigenvectors;

[0029] Sorting the eigenvalues ​​of the eigenvectors in descending order, and determining the order of the principal components corresponding to the eigenvectors in turn according to the results of the sorting;

[0030] Accumulate the cumulative contribution rates of the principal components starting from the first principal component in the order of the principal components until the value of the cumulative contribution rate is greater than a preset contribution rate threshold, and output the corresponding number of principal components and the principal components with corresponding serial numbers;

[0031] The linear regression model is generated by taking the principal component of the corresponding serial number as the independent variable and the trend analysis result as the dependent variable.

[0032] In a second aspect, the embodiment of the present application further provides a device for attributing regional terrestrial water storage changes based on geographic data modeling, comprising:

[0033] A data acquisition unit, used to obtain a terrestrial water storage data set of a target area within a target period, and determine a driving factor data set of the target area within the target period;

[0034] A data processing unit, used to pre-process the terrestrial water storage data set and the driving factor data set, and output an image set of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors;

[0035] A trend analysis unit, configured to analyze the dynamic changes of the terrestrial water reserves based on the image set, and output a trend analysis result of the terrestrial water reserves in the target area during the target period;

[0036] A driving factor screening unit, used to screen the driving factors in the image set by using a correlation analysis algorithm, remove driving factors with multicollinearity, and generate a main driving factor set;

[0037] The attribution calculation module is used to combine the principal component analysis algorithm and the geographically weighted regression model to perform weighted regression based on the trend analysis results and the set of main driving factors, generate a linear regression model, and determine the main driving factors affecting the changes in terrestrial water reserves in the corresponding area based on the linear regression model.

[0038] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method provided in the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect is implemented.

[0039] In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of the embodiment of the present application or any one of the implementations of the first aspect.

[0040] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0041] The embodiment of the present application provides a method for attributing changes in regional terrestrial water reserves based on geographic data modeling. Through an enhanced geographically weighted regression model, the correlation between the changing trend of terrestrial water reserves and various driving factors is studied in more depth. The GWR model enhanced by combining the geographic detector method and the principal component analysis method provided in the embodiment of the present application can better understand the main patterns of data changes and extract the most representative features, thereby helping to more effectively analyze geographic data, and is expected to provide more accurate data support for fields such as environmental resource management, urban planning, and climate change response, and provide practical reference for the formulation of future sustainable development and water resource management policies. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of a flow chart of a method for attributing changes in regional terrestrial water reserves based on geographic data modeling provided in an embodiment of the present application;

[0044] Figure 2 It is a structural schematic diagram of a regional terrestrial water storage change attribution device based on geographic data modeling provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0048] It should be noted that the terms "first\second" involved in the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those described or illustrated herein.

[0049] Please refer to the following Figure 1 , which is a flow chart of a method for attributing regional terrestrial water storage changes based on geographic data modeling provided by an exemplary embodiment of the present application. Figure 1 As shown, the method comprises the steps of:

[0050] S101, obtaining a terrestrial water storage data set of a target area within a target period, and determining a driving factor data set of the target area within the target period.

[0051] Specifically, the Gravity Recovery and Climate Experiment (GRACE) satellite can be used to conduct high-precision observations of changes in terrestrial water storage, extract image data of the target area, and then easily analyze the terrestrial water storage in the corresponding area.

[0052] Specifically, a preset latitude and longitude range can be selected as the target area, that is, the area to be studied, and can be cropped according to the image data in the original area measured by the satellite. For example, satellite observation data within a certain country can be cropped based on global satellite observation data.

[0053] Specifically, the study area, i.e., the target area, can be photographed periodically by satellite, and observation data for one year can be obtained based on statistics of the periodic photographing results. The observation data for one year can be further processed and arranged by month to obtain monthly time series data. The data can also be arranged by quarter or week to obtain corresponding time series data, which is not limited to the embodiments of the present application.

[0054] Preferably, the terrestrial water storage dataset and driving factor dataset of the target area within the target time period obtained in the embodiment of the present application are monthly time series data in the target area, which can not only reflect the changes in water storage and driving factors in the area, but also reduce the amount of data calculation as much as possible, which is conducive to improving calculation efficiency.

[0055] For example, monthly land water storage data for the Chinese region from 2005 to 2020 can be obtained.

[0056] Specifically, the driving factors may include hydrological and meteorological related driving factors, such as temperature, precipitation, runoff, humidity, etc. The driving factors may also include human activity related driving factors, such as population, cultivated land area, forest land area, etc.

[0057] It can be understood that the driving factor data set can be the change of the characteristic quantity corresponding to each driving factor over time, such as a temperature-time curve, a cultivated land area-time statistical table, etc., which is not limited to this embodiment of the present application.

[0058] S102, preprocessing the terrestrial water storage data set and the driving factor data set, and outputting an image set of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors.

[0059] Specifically, preprocessing may include, but is not limited to, performing difference processing on the terrestrial water storage dataset and the driving factor dataset, cropping the target area, resampling time and space, etc.

[0060] Specifically, the difference processing of the terrestrial water storage dataset and the driving factor dataset can be understood as the measured terrestrial water storage dataset and the driving factor dataset may have missing data at some times and / or in some areas. Interpolation calculations can be performed based on the times and areas of the missing data combined with historical data to generate interpolated values, and the interpolated values ​​can be filled in the times and / or areas where there are missing data.

[0061] Specifically, cropping the target area can immediately divide the target area into multiple sub-areas, and the area of ​​each sub-area can be the same or different. The sub-areas can be divided based on geographical elements such as river basin distribution as sub-areas to be studied. For example, the Yellow River basin, the Yangtze River basin, the Huaihe River basin and other areas can be obtained. This embodiment of the present application is not limited to this.

[0062] Specifically, the spatial resolution of the image data may be set for each sub-region, and the spatial resolution of each region may be unified.

[0063] Specifically, the acquisition times of the acquired terrestrial water storage dataset and the driving factor dataset can be aligned based on the shooting time of the image data, thereby achieving the unification of temporal resolution. For example, the terrestrial water storage dataset and the driving factor dataset can be unified into monthly time series data.

[0064] Specifically, the time series data of each sub-region can be output, that is, a set of images of uniform spatiotemporal resolution of the preset time series of terrestrial water storage and driving factors of each sub-region in the target area is obtained, for example, a set of images of uniform spatiotemporal resolution of monthly scale of terrestrial water storage and driving factors of the Yangtze River Basin in China is obtained. The present application does not limit the time scale of the preset time series.

[0065] It can be understood that the above-mentioned difference processing, cropping of the target area, and resampling of time and space can be completed successively, and the present application does not limit the execution order of the preprocessing steps.

[0066] S103, analyzing the dynamic changes of terrestrial water reserves based on the image set, and outputting trend analysis results of terrestrial water reserves in the target area during the target period.

[0067] Specifically, based on a set of images of uniform spatiotemporal resolution of a preset time series of measured terrestrial water reserves, the Theil–Sen trend test method can be used to perform a trend analysis on the terrestrial water reserves of each sub-region within the preset time series, and the trend analysis results of each target period can be obtained.

[0068] For example, a trend graph of the change of terrestrial water reserves over time in the corresponding area is output with terrestrial water reserves as the vertical axis and time as the horizontal axis.

[0069] It can be understood that the original terrestrial water storage data set is a collection of discrete values ​​of water storage at multiple moments in the corresponding time range of the corresponding region. The Theil–Sen trend test method can be used to integrate the discrete values ​​to obtain a continuous curve of terrestrial water storage in the corresponding time range.

[0070] S104, screening the driving factors in the image set by using a correlation analysis algorithm, eliminating driving factors with multicollinearity, and generating a main driving factor set.

[0071] Understandably, related technologies often encounter multicollinearity problems in multiple linear regression analysis, that is, there is a linear correlation between independent variables, which will lead to an increase in the variance of parameter estimates and a decrease in precision, which in turn makes the significance test of the variables inaccurate and makes it difficult to correctly assess the impact of the explanatory variables on the explained variables. If multicollinearity exists, the results of the global regression model calculated based on such driving factors are often unreliable.

[0072] Based on this, the embodiment of the present application tests the terrestrial water reserves and driving factors of a preset time series through variance inflation factor calculation, Pearson correlation analysis method and GeoDetector method to eliminate driving factors with multicollinearity, and screens out an effective main driving factor data set based on correlation analysis and GeoDetector analysis, and uses the main driving factor data set as the driving factor indicator for subsequent regression model building.

[0073] Specifically, the first correlation value between every two driving factors can be calculated based on the Pearson correlation analysis algorithm, and the driving factors whose absolute values ​​of the correlation values ​​are outside the preset correlation threshold range are deleted, and the driving factors whose absolute values ​​of the first correlation values ​​are within the preset correlation threshold range are retained. The correlation value can be calculated by applying the following formula:

[0074]

[0075] In the formula, is the covariance between the two driving factors X and Y, and are the standard deviations of X and Y respectively.

[0076] The calculated ρ X,YThat is, the first correlation value, which is used to measure the degree of linear correlation between the two driving factors. The value range is (-1,1). When the value approaches 1, it means that the two variables are completely positively correlated; when the value approaches -1, it means that they are completely negatively correlated; when the value is 0, it means that there is no linear correlation between the two.

[0077] Exemplarily, the preset correlation threshold interval may be set to (0.3, 1). If the absolute value of the correlation value is greater than 0.3, the driving factors whose absolute value of the first correlation value falls within (0.3, 1) are retained.

[0078] Understandably, after the Pearson correlation analysis algorithm, the drivers that are significantly correlated with the correlated variables are retained, but further testing is needed to determine if there is multicollinearity between these drivers. If there is a high correlation between multiple drivers, this may lead to an unstable model. Multicollinearity can be detected by calculating the variance inflation factor.

[0079] Specifically, a linear regression model can be constructed for each geographical element of the sub-region based on the geographical weighted regression model. In the process of constructing the linear regression model of the sub-region, the variance inflation factor of each driving factor in the region can be calculated, and the driving factors whose variance inflation factors are greater than a preset variance inflation factor threshold can be deleted.

[0080] Exemplarily, the preset variance inflation factor threshold may be set to 10, and driving factors with variance inflation factors greater than 10 may be eliminated.

[0081] Furthermore, the second correlation value of each driving factor can be calculated by the formula of the geographic detector, and the application formula is as follows:

[0082]

[0083] In the formula, N is the total sample size, N h is the count of each category defined by X, σ 2 and They represent the overall and intra-category variance of Y, respectively. The Q value ranges from 0 to 1, measuring the strength of the relationship, with higher values ​​indicating a more significant impact of X on Y.

[0084] The set of main driving factors for each sub-region in each time period can be calculated based on the Q value.

[0085] Exemplarily, the obtained hydrological and meteorological related driving factors may include temperature TMP, precipitation PRE, runoff RO, evapotranspiration PET, digital elevation DEM, and normalized difference vegetation index NDVI; the human activity related driving factors may include population POP, night lights NL, cultivated land area CPLD, forest area FST, and grassland area GSLD.

[0086] S105, combining the principal component analysis algorithm and the geographically weighted regression model to perform weighted regression based on the trend analysis results and the set of main driving factors, generating a linear regression model, and determining the main driving factors affecting the change of terrestrial water reserves in the corresponding region based on the linear regression model.

[0087] Specifically, the main driving factors in the main driving factor set can be standardized, each main driving factor can be converted into a dimensionless standardized value, a correlation coefficient matrix can be constructed based on the standardized values ​​of all main driving factors, the correlation coefficient matrix can be eigenvalue decomposed, and the corresponding eigenvectors and eigenvalues ​​corresponding to the eigenvectors can be output.

[0088] Furthermore, each eigenvector may be sorted in descending order according to the eigenvalue to obtain a sorting result of the eigenvector, and then the order of the principal components corresponding to the eigenvector may be determined according to the sorting result.

[0089] Exemplarily, the first principal component corresponds to the eigenvector with the largest eigenvalue, the second principal component corresponds to the eigenvector with the second highest eigenvalue, and so on to obtain all principal components and the order of the principal components.

[0090] Furthermore, the cumulative contribution rates of the principal components are accumulated in sequence from the first principal component in the order of the principal components until the value of the cumulative contribution rate is greater than the preset contribution rate threshold, and the corresponding number of principal components and the principal components with corresponding serial numbers are output.

[0091] It can be understood that the contribution rate of each principal component to all principal components can be calculated separately, and the contribution rate can be calculated by applying the formula:

[0092]

[0093] Among them, λ i is the eigenvalue of the i-th principal component, is the sum of the eigenvalues ​​from the first principal component to the pth principal component.

[0094] The contribution rates of the principal components are accumulated according to the order of the principal components to obtain the cumulative contribution rate. The formula is:

[0095]

[0096] The above formula can be used to calculate the sum of the contribution rates from the 1st principal component to the kth principal component, that is, the cumulative contribution rate from the 1st principal component to the kth principal component.

[0097] Furthermore, the cumulative contribution rate is compared with a preset contribution rate threshold. If the value of the cumulative contribution rate is greater than the preset contribution rate threshold, the serial number of the corresponding principal component can be output as the number of principal components.

[0098] For example, if the preset contribution rate threshold is set to 80%, and the cumulative contribution rate of the first principal component to the fourth principal component is calculated to be 83%, it can be determined that four principal components are extracted, and the corresponding principal components are numbered 1-4.

[0099] Specifically, the linear regression model of the corresponding sub-region may be generated by taking the first principal component, the second principal component, the third principal component and the fourth principal component as independent variables and the trend analysis result in the corresponding sub-region as the dependent variable.

[0100] The linear regression model can be constructed based on the following formula:

[0101]

[0102] In the formula, y i is the ith observation of the dependent variable, x ik is the ith observation value of the independent variable k, (u i ,v i ) is the geographic coordinate, indicating the location of the i-th observation point, u i and v i Represent longitude and latitude, or location parameters in other geographic coordinate systems; β0(u i ,v i ) is the same as the geographical location (u i ,v i ) is the intercept coefficient, β k (u i ,v i ) is the same as the geographical location (u i ,v i ) is the coefficient of the independent variable k, p represents the number of independent variables, ∈ i Represents the error term of the i-th observation. This formula describes how the dependent variable y is affected by the independent variable x in the geographically weighted regression model, and takes into account the impact of geographical location on the model coefficients, thereby better adapting to the characteristics of spatial data.

[0103] Furthermore, the linear regression models for each time period and each sub-region can be calculated separately, and then the main driving factors affecting the regional trend of changes in terrestrial water storage in each sub-region in different time periods can be analyzed.

[0104] Furthermore, the contribution rate of each driving factor in the corresponding principal component can be obtained based on the eigenvectors corresponding to the first principal component F1, the second principal component F2, the third principal component F3 and the fourth principal component F4, and the driving factors with the highest contribution rate in each principal component can be selected.

[0105] For example, reference may be made to the contribution of each variable to principal component F1, principal component F2, principal component F3 and principal component F4 in the principal component analysis results from 2005 to 2020 listed in the following table.

[0106] Several driving factors with the highest contribution rate can be selected to determine the corresponding principal components, including:

[0107] In these four years, the first principal component (F1) was mainly determined by precipitation (PRE), potential evapotranspiration (PET), soil moisture (SM), temperature (TMP) and normalized difference vegetation index (NDVI), thus summarizing the impact of environmental and climate conditions on water storage as the principal components. The second principal component (F2) was mainly affected by urban land (IMP), nightlight (NL), runoff (RO), cropland area (CPLD) and forest area (FST), thus summarizing the impact of land use and human activities on water storage as the principal components. The third principal component (F3) is mainly composed of population (POP), night light (NL), height (DEM, Digital Elevation Model) and grassland area (GSLD), which encapsulates the impact of population density and terrain characteristics as principal components on water storage. The fourth principal component (F4) is mainly composed of population POP, urban land IMP and cultivated land area (CPLD, Cropland), representing the difference between urban and rural areas.

[0108]

[0109]

[0110] Then, the main driving factors affecting the terrestrial water reserves in the corresponding region in each year are determined. The above is only an example of the embodiment of the present application and should not be construed as a limitation on the embodiment of the present application.

[0111] The following are device embodiments 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.

[0112] See next Figure 2, is a schematic diagram of the structure of a device for attributing changes in regional terrestrial water reserves based on geographic data modeling provided by an exemplary embodiment of the present application. The device can be implemented as all or part of a terminal through software, hardware, or a combination of both, and can also be integrated on a server as an independent module. The attribution of changes in regional terrestrial water reserves based on geographic data modeling in the embodiment of the present application can be applied to a terminal or a cloud. The device 20 includes a data acquisition unit 210, a data processing unit 220, a trend analysis unit 230, a driving factor screening unit 240, and an attribution calculation module 250, wherein:

[0113] The data acquisition unit 210 is used to obtain a terrestrial water storage data set of a target area within a target period, and determine a driving factor data set of the target area within the target period;

[0114] The data processing unit 220 is used to pre-process the terrestrial water storage data set and the driving factor data set, and output an image set of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors;

[0115] The trend analysis unit 230 is used to analyze the dynamic changes of the terrestrial water storage based on the image set, and output the trend analysis result of the terrestrial water storage in the target area in the target period;

[0116] The driving factor screening unit 240 is used to screen the driving factors in the image set by using a correlation analysis algorithm, remove driving factors with multicollinearity, and generate a main driving factor set;

[0117] The attribution calculation module 250 is used to combine the principal component analysis algorithm and the geographically weighted regression model to perform weighted regression based on the trend analysis results and the set of main driving factors, generate a linear regression model, and determine the main driving factors affecting the changes in terrestrial water reserves in the corresponding area based on the linear regression model.

[0118] It should be noted that the device 20 provided in the above embodiment only uses the division of the above functional modules as an example when executing the regional terrestrial water storage change attribution method based on geographic data modeling. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the embodiment of the regional terrestrial water storage change attribution method based on geographic data modeling belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.

[0119] 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, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the program.

[0120] See also Figure 3 , which is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0121] like Figure 3 As shown, the electronic device 300 includes: a processor 301 and a memory 302 .

[0122] In the embodiment of the present application, the processor 301 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 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0123] The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also called a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0124] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments of the present application, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement the method in the embodiment of the present application.

[0125] In some embodiments, the electronic device 300 further includes: a peripheral device interface 303 and at least one peripheral device. The processor 301, the memory 302 and the peripheral device interface 303 can be connected via a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 303 via a bus, a signal line or a circuit board. Specifically, the peripheral devices include: a display screen 304, a camera 305 and an audio circuit 306. The peripheral device interface 303 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302.

[0126] In some embodiments of the present application, the processor 301, the memory 302, and the peripheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 301, the memory 302, and the peripheral device interface 303 can be implemented on a separate chip or circuit board. This embodiment of the present application does not specifically limit this.

[0127] The display screen 304 is used to display a UI. The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 304 is a touch display screen, the display screen 304 also has the ability to collect touch signals on the surface or above the surface of the display screen 304. The touch signal may be input as a control signal to the processor 301 for processing. At this time, the display screen 304 may also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards.

[0128] In some embodiments of the present application, the display screen 304 may be one, which is arranged on the front panel of the electronic device 300; in other embodiments of the present application, the display screen 304 may be at least two, which are arranged on different surfaces of the electronic device 300 or are folded; in still other embodiments of the present application, the display screen 304 may be a flexible display screen, which is arranged on the curved surface or folded surface of the electronic device 300. Even more, the display screen 304 may be arranged in a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 304 may be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode) and the like.

[0129] The camera 305 is used to capture images or videos. Optionally, the camera 305 includes a front camera and a rear camera. Usually, the front camera is arranged on the front panel of the electronic device, and the rear camera is arranged on the back of the electronic device. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments of the present application, the camera 305 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0130] The audio circuit 306 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 301 for processing. For the purpose of stereo sound collection or reduction, there may be multiple microphones, which are respectively arranged at different parts of the electronic device 300. The microphone may also be an array microphone or an omnidirectional collection microphone.

[0131] The power supply 307 is used to power various components in the electronic device 300. The power supply 307 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 307 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0132] The electronic device structure block diagram shown in the embodiment of the present application does not constitute a limitation on the electronic device 300. The electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0133] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method of any of the above embodiments are implemented. The computer-readable storage medium may 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 nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution can be essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for attributing regional terrestrial water storage changes based on geographic data modeling, characterized in that: include: Acquire a terrestrial water storage data set of a target area within a target period, and determine a driving factor data set of the target area within the target period; Preprocessing the terrestrial water storage data set and the driving factor data set to output a set of images of terrestrial water storage and driving factors with a uniform temporal and spatial resolution for a preset time series; Analyze the dynamic changes of terrestrial water reserves based on the image set, and output the trend analysis results of terrestrial water reserves in the target area during the target period; The driving factors in the image set are screened by a correlation analysis algorithm, and driving factors with multicollinearity are eliminated to generate a main driving factor set; Combining the principal component analysis algorithm and the geographically weighted regression model to perform weighted regression based on the trend analysis results and the set of main driving factors, generating a linear regression model, and determining the main driving factors affecting the change of terrestrial water storage in the corresponding region based on the linear regression model; The preprocessing of the terrestrial water storage data set and the driving factor data set to output a set of images of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors includes: Performing interpolation processing on the terrestrial water storage dataset and the driving factor dataset to fill in missing data; Dividing the target area into a plurality of sub-areas, and resampling the spatial resolution of each sub-area to a preset spatial resolution; Aligning the time of the terrestrial water storage dataset and the driving factor dataset corresponding to each of the sub-regions to achieve the unification of the temporal resolution; Outputting a set of images of uniform temporal and spatial resolution of a preset time series of terrestrial water storage and driving factors in each sub-region within the target area; The driving factors in the image set are screened by the correlation analysis algorithm, and driving factors with multicollinearity are eliminated to generate a set of main driving factors, including: Calculate a first correlation value between every two driving factors based on a correlation analysis algorithm, and retain driving factors whose absolute values ​​of the first correlation values ​​are within a preset correlation threshold range; Based on the geographically weighted regression model, a linear regression model is constructed for each of the geographical elements of the sub-region, the variance inflation factor of each driving factor is calculated, and the driving factor whose variance inflation factor is greater than a preset variance inflation factor threshold is deleted; Performing geographic detector analysis on the driving factors of each of the sub-regions, calculating a second correlation value of each driving factor, and selecting the driving factors whose second correlation values ​​are greater than a second correlation value threshold as the main driving factor set of the corresponding sub-region; The combination of principal component analysis algorithm and geographical weighted regression model performs weighted regression based on the trend analysis results and the main driving factor set to generate a linear regression model, including: Standardizing the main driving factors in the main driving factor set, converting each main driving factor into a dimensionless standardized value, constructing a correlation coefficient matrix based on the standardized values ​​of all main driving factors, performing eigenvalue decomposition on the correlation coefficient matrix, and outputting corresponding eigenvectors and eigenvalues ​​corresponding to the eigenvectors; Sorting the eigenvalues ​​of the eigenvectors in descending order, and determining the order of the principal components corresponding to the eigenvectors in turn according to the results of the sorting; Accumulate the cumulative contribution rates of the principal components starting from the first principal component in the order of the principal components until the value of the cumulative contribution rate is greater than a preset contribution rate threshold, and output the corresponding number of principal components and the principal components with corresponding serial numbers; The linear regression model is generated by taking the principal component of the corresponding serial number as the independent variable and the trend analysis result as the dependent variable.

2. The method for attributing regional terrestrial water storage changes based on geographic data modeling according to claim 1 is characterized in that: The analyzing the dynamic changes of the terrestrial water reserves based on the image set and outputting the trend analysis results of the terrestrial water reserves in the target area during the target period includes: For each of the sub-areas, dividing the target time period into sub-time periods of predetermined sizes; Analyze the trend analysis results of the land water storage over time in each of the sub-periods; Output the trend analysis result of the terrestrial water storage in the target area during the target period.

3. The method for attributing regional terrestrial water storage changes based on geographic data modeling according to claim 1 is characterized in that: The driving factors include hydrological and meteorological related driving factors and human activity related driving factors.

4. A device for attributing regional terrestrial water storage changes based on geographic data modeling, characterized in that: include: A data acquisition unit, used to obtain a terrestrial water storage data set of a target area within a target period, and determine a driving factor data set of the target area within the target period; A data processing unit, used to pre-process the terrestrial water storage data set and the driving factor data set, and output an image set of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors; A trend analysis unit, configured to analyze the dynamic changes of the terrestrial water reserves based on the image set, and output a trend analysis result of the terrestrial water reserves in the target area during the target period; A driving factor screening unit, used to screen the driving factors in the image set by using a correlation analysis algorithm, remove driving factors with multicollinearity, and generate a main driving factor set; An attribution calculation module, used to combine the principal component analysis algorithm and the geographical weighted regression model to perform weighted regression based on the trend analysis results and the set of main driving factors, generate a linear regression model, and determine the main driving factors affecting the change of terrestrial water storage in the corresponding area based on the linear regression model; The preprocessing of the terrestrial water storage data set and the driving factor data set to output a set of images of a uniform spatiotemporal resolution of a preset time series of terrestrial water storage and driving factors includes: Performing interpolation processing on the terrestrial water storage dataset and the driving factor dataset to fill in missing data; Dividing the target area into a plurality of sub-areas, and resampling the spatial resolution of each sub-area to a preset spatial resolution; Aligning the time of the terrestrial water storage dataset and the driving factor dataset corresponding to each of the sub-regions to achieve the unification of the temporal resolution; Outputting a set of images of uniform temporal and spatial resolution of a preset time series of terrestrial water storage and driving factors in each sub-region within the target area; The driving factors in the image set are screened by the correlation analysis algorithm, and driving factors with multicollinearity are eliminated to generate a set of main driving factors, including: Calculate a first correlation value between every two driving factors based on a correlation analysis algorithm, and retain driving factors whose absolute values ​​of the first correlation values ​​are within a preset correlation threshold range; Based on the geographically weighted regression model, a linear regression model is constructed for each of the geographical elements of the sub-region, the variance inflation factor of each driving factor is calculated, and the driving factor whose variance inflation factor is greater than a preset variance inflation factor threshold is deleted; Performing geographic detector analysis on the driving factors of each of the sub-regions, calculating a second correlation value of each driving factor, and selecting the driving factors whose second correlation values ​​are greater than a second correlation value threshold as the main driving factor set of the corresponding sub-region; The combination of principal component analysis algorithm and geographical weighted regression model performs weighted regression based on the trend analysis results and the main driving factor set to generate a linear regression model, including: Standardizing the main driving factors in the main driving factor set, converting each main driving factor into a dimensionless standardized value, constructing a correlation coefficient matrix based on the standardized values ​​of all main driving factors, performing eigenvalue decomposition on the correlation coefficient matrix, and outputting corresponding eigenvectors and eigenvalues ​​corresponding to the eigenvectors; Sorting the eigenvalues ​​of the eigenvectors in descending order, and determining the order of the principal components corresponding to the eigenvectors in turn according to the results of the sorting; Accumulate the cumulative contribution rates of the principal components starting from the first principal component in the order of the principal components until the value of the cumulative contribution rate is greater than a preset contribution rate threshold, and output the corresponding number of principal components and the principal components with corresponding serial numbers; The linear regression model is generated by taking the principal component of the corresponding serial number as the independent variable and the trend analysis result as the dependent variable.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Citation Information

Patent Citations

  • Analysis method for farmland quality influence factors in provincial range

    CN114971159A

  • New crown space-time modeling prediction method based on dynamic population flow matrix space filtering value

    CN115274129A

  • Forest aboveground biomass downscaling method based on multi-scale geographically weighted regression

    CN116091939A

  • Land transfer price prediction method based on neural network and geographically weighted regression

    CN116862616A

  • Regional land water reserve change attribution analysis method based on interpretable deep learning

    CN117132023A