Method and system for evaluating urbanization and ecological quality coupling coordination degree of watery region

Abstract

The invention discloses a method and a system for evaluating urbanization and ecological quality coupling coordination degree of a watery area. The method comprises the following steps: acquiring urbanization level data and ecological quality data of the watery area; an urbanization evaluation index and an ecological quality index are determined based on the obtained data, the weight of each index is calculated, and an ecological quality evaluation index and an urbanization evaluation index are obtained through the weights; constructing a correction coupling coordination degree model, and calculating a coupling coordination level index based on the evaluation index to obtain a watery region urbanization and ecological quality coupling coordination degree evaluation result; according to the method, the coupling degree and the comprehensive development degree of multiple systems under the condition that the coupling coordination degree is consistent can be effectively distinguished, the accuracy and the precision of multi-water urbanization and ecological quality coupling coordination level evaluation are improved, and a scientific support is provided for the human-ground relationship action degree and sustainable development of a multi-water region.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological quality and urbanization evaluation, and in particular to a method and system for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas. Background Art

[0002] With the advent of the era of artificial intelligence, massive geospatial data and socio-economic perception data provide data support for the fine-scale evaluation of ecological quality and urbanization level in water-rich regions. However, as urbanization levels increase, a series of sustainable development issues have also been brought to regional development. Problems such as severe soil erosion, reduced vegetation coverage, deteriorating air quality, and enhanced heat island effects have become increasingly prominent. As ecological and environmental problems deepen, conflicts between humans and the ecological environment have become the fundamental cause of obstacles to regional sustainable development. Therefore, understanding the evolution of the coupling and coordination level between urbanization and ecological quality has extremely important theoretical and practical significance for the realization of regional sustainable development goals, and has become the core content of many United Nations sustainable development goals.

[0003] At present, the research methods of ecological quality evaluation include index evaluation method, fuzzy evaluation method, relative index method and correlation analysis. Among them, index evaluation method is the most widely used and can be divided into single index evaluation method and comprehensive index evaluation method. However, single index evaluation method can only explain one aspect of ecological characteristics, and the ecosystem is composed of multiple interacting subsystems, and the interaction between different indicators comprehensively affects the regional ecosystem, which cannot be separated separately. In comparison, the comprehensive index evaluation method can evaluate the regional ecological quality more comprehensively, especially the remote sensing ecological index, which selects four important indicators closely related to human survival and has been widely used in multi-scale ecological quality evaluation. However, when using remote sensing ecological index to evaluate the region, it is necessary to mask the water body part of the region, so the impact of water body on the overall ecological quality of the region is technically excluded. However, as an important ecological factor, water body is not only the basis for the survival of animals and plants, but also can directly affect the environment, temperature and humidity and other climate factors through evaporation and transpiration. It is also an important part of the ecosystem, especially for multi-water research areas, water body plays an extremely important role in the ecological quality of the region.

[0004] In the field of urbanization research, traditional research mainly focuses on comprehensive measurement of regional urbanization level from the administrative scale, and the statistical yearbook data mainly used are characterized by lag and uncertainty. Therefore, the evaluation results of urbanization level indicators have shortcomings such as poor comparability, weak credibility and low timeliness. Most importantly, the evaluation results of urbanization level are restricted by administrative scale and it is impossible to obtain refined urbanization level data.

[0005] In the study of the relationship between urbanization and ecological quality, conventional techniques mainly conduct a comprehensive analysis of the nonlinear relationship between the two from different perspectives such as measurement analysis, change rules, and mechanism research. The Stillpath model, multi-agent model, fuzzy matter-element model, entropy change equation model, and coupling coordination model are often used to study the coupling characteristics between the two. Among them, the coupling coordination model has been widely used because it can describe the interaction between multiple systems; however, the coupling coordination model also has its shortcomings. The first is how to determine the importance of multiple systems; the second is how to distinguish the coupling degree and comprehensive development degree of multiple systems when the coupling coordination degree is consistent; in addition, although the research on the coupled and coordinated development of urbanization and ecological quality has continued to deepen, it is still mainly focused on temporal changes, and there is little research on the spatial evolution process.

[0006] In order to solve the above problems, it is urgent to propose an evaluation method and system for the coupling and coordination level of urbanization and ecological quality in water-rich areas. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for evaluating the coupling coordination degree of urbanization and ecological quality in water-abundant areas, so as to solve the problem that the evaluation accuracy of ecological quality and urbanization level in traditional water-abundant areas is low and it is difficult to achieve the evaluation of the coupling coordination level on a spatial grid scale.

[0008] In order to solve the above technical problems, the present invention adopts the following technical solution: a method for evaluating the coupling coordination degree between urbanization and ecological quality in water-rich areas, comprising the following steps:

[0009] S1. Acquire urbanization level data and ecological quality data of water-rich areas, the data at least including remote sensing satellite image data of water-rich areas in several seasons; and

[0010] Perform cloud filtering and median synthesis on the remote sensing satellite image data to obtain cloud-free surface reflectance datasets in different seasons;

[0011] S2. Based on the urbanization level data and the ecological quality data, respectively determine the urbanization evaluation index and the ecological quality index, and calculate the weight of each index, and obtain the ecological quality evaluation index and the urbanization evaluation index respectively through the weight;

[0012] S3. Construct a modified coupling coordination model, and calculate the coupling coordination level index based on the ecological quality evaluation index and urbanization evaluation index to obtain the evaluation results of the coupling coordination degree between urbanization and ecological quality in water-rich areas.

[0013] Preferably, in S1, the urbanization level data includes population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU;

[0014] Obtaining population density data to calculate the population urbanization level data PU;

[0015] Obtain nighttime light remote sensing data to calculate economic urbanization level data EU;

[0016] Obtain construction land area ratio data and traffic road network density data to calculate spatial urbanization level data KU;

[0017] Obtain the scientific and educational level density data and medical level density data to calculate the social urbanization level data SU;

[0018] The ecological quality data are calculated using the surface reflectance data set, and the ecological quality data include water abundance index data, normalized latent heat index data, nuclear vegetation index data, normalized building and bare soil index data and surface temperature data.

[0019] Preferably, in S2, the urbanization evaluation index is determined by using data cleaning and kernel density analysis;

[0020] The spatial principal component analysis method is used to obtain the weights of each spatial principal component of all ecological quality indicators, including: constructing a correlation coefficient matrix based on each ecological quality evaluation indicator; calculating the eigenvalue λ and the eigenvector e based on the correlation coefficient matrix; calculating the contribution rate and cumulative contribution rate of each principal component based on the eigenvalue and the eigenvector, and the contribution rate of each principal component is the initial weight of each principal component; and then correcting the initial weight value through the random forest model to construct an ecological quality evaluation index;

[0021] Based on the urbanization evaluation index, the weights of population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU are determined using the hierarchical analysis method to construct an urbanization evaluation index.

[0022] Preferably, the spatial principal component analysis model is:

[0023] PCA i =ω 1i X1+ω 2i X2+ω 3i X3+…+ω ii X i ;

[0024] Among them, PCA i represents the i-th principal component, X1, X2, X3, ..., X i are the original variables, ω1,ω2,ω3,…,ω i is the weight of each variable; and

[0025] The correlation coefficient matrix is:

[0026]

[0027] Among them, r pq represents the correlation coefficient between the pth indicator and the qth indicator;

[0028] Calculate the eigenvalue λ based on the correlation coefficient matrix: Use the Jacobi method to solve the characteristic equation λI-R|=0, where I is the unit matrix and is arranged in order according to the size of the eigenvalue;

[0029] The identity matrix is:

[0030]

[0031] The eigenvector e is calculated as:

[0032]

[0033] Among them, e ij Represents the vector e i The jth component of

[0034] The contribution rate and cumulative contribution rate are calculated as follows:

[0035]

[0036] Preferably, the initial weight value is corrected as follows: constructing a sample training set after Bootstrap sampling based on each spatial principal component data; constructing the best splitting method for each decision tree based on the sample training set; calculating the prediction error value of the sample data not extracted by each Bootstrap sampling; obtaining the final weight of each spatial principal component after correction based on the prediction error value and voting result output by each decision tree; and

[0037] The random forest model is:

[0038]

[0039] Among them, F(X) is the final prediction result of the random forest model for sample X; M is the total number of decision trees in the random forest; f m (X) is the prediction result of the mth decision tree for sample X.

[0040] Preferably, a hierarchical structure model is established based on the population urbanization level data PU, the economic urbanization level data EU, the spatial urbanization level data KU and the social urbanization level data SU; and a judgment matrix is ​​constructed based on the hierarchical structure model;

[0041] Calculate the consistency index CI and consistency ratio CR of each judgment matrix; when the consistency ratio is lower than the preset consistency ratio, solve the eigenvector of each judgment matrix as the weight of the ecological indicator of each urbanization sub-indicator; otherwise, reconstruct the judgment matrix;

[0042] The urbanization evaluation index is constructed based on the weights:

[0043] UEI=ω1×PU+ω2×EU+ω3×KU+ω4×SU;

[0044] Among them, ω1, ω2, ω3 and ω4 are the weight values ​​of PU, EU, KU and SU determined by the hierarchical analysis method, and satisfy ω1+ω2+ω3+ω4=1.

[0045] Preferably, the judgment matrix is:

[0046]

[0047] Among them, b ij is a judgment value of the relative importance of element i to element j, and the judgment values ​​include at least 1, 3, 5, 7 and 9, where: 1 indicates that element i and element j are equally important, and 3 to 9 indicate that the importance of element i is increasing compared to element j; and

[0048] The calculation of consistency index CI is:

[0049]

[0050] Among them, λ max is the maximum eigenvalue of the judgment matrix B, and n represents the order of the judgment matrix.

[0051] Preferably, in S3, the evaluation model of the coupling coordination level of ecological quality and urbanization based on the modified coupling coordination degree model is expressed as:

[0052]

[0053] T = α × U + β × E;

[0054]

[0055] Among them, U and E are the urbanization evaluation index and ecological quality evaluation index; C refers to the coupling value; T refers to the comprehensive development index; MCCD is the improved coupling coordination index value.

[0056] Preferably, based on the coupling coordination evaluation results, the coupling coordination value level is divided using the mean average method:

[0057] The present invention also discloses a coupling coordination evaluation system for urbanization and ecological quality in water-rich areas, including:

[0058] Data acquisition module: obtain urbanization level data and ecological quality data in water-rich areas;

[0059] Data preprocessing and analysis module: Based on the cloud processing platform, cloud filtering and median synthesis processing are performed on remote sensing satellite image data of water-rich areas. At the same time, the weights of urbanization evaluation indicators and ecological quality indicators are determined and analyzed based on spatial principal component analysis, random forest method and hierarchical analysis method respectively;

[0060] Model building module: construct an urbanization level evaluation index model based on urbanization level data and urbanization evaluation index weights; construct an ecological quality evaluation index model based on ecological quality data and ecological quality indicators; and construct a modified coupling coordination degree model at the same time;

[0061] Index calculation module: The ecological quality evaluation index and urbanization evaluation index are calculated through the urbanization level index model and the ecological quality index model respectively, and the coupling coordination level index is calculated based on the ecological quality evaluation index and the urbanization evaluation index using the modified coupling coordination degree model;

[0062] Coupling coordination level grading module: The coupling coordination value levels are graded using the coupling coordination level index and grading standards.

[0063] Beneficial effects: The present invention can effectively improve the problem of incomplete ecological quality evaluation results in a single season by using a long-term series of cloud-free surface reflectance datasets in different seasons in multi-water-type regions, thereby improving the accuracy of the calculation results of various ecological indicators;

[0064] In addition, the principal component analysis results of all ecological indicators were objectively determined spatially through the spatial principal component analysis method; the random forest model was used to further correct the initial spatial principal component weights, thereby improving the objectivity of the spatial principal component weights; multi-source spatial data products were used to establish urbanization evaluation indicators that consider population, space, economy and society, thereby ensuring the rationality and accuracy of the spatial evaluation results of urbanization levels; the hierarchical analysis method was used to determine the weights of population, space, economy and social urbanization, taking into account the relative importance of different sub-urbanization indicators, thereby ensuring the scientific nature of the weight allocation process.

[0065] In the present invention, a modified coupling coordination model is constructed to calculate the coupling coordination level index, thereby solving the problem that the traditional coupling coordination model cannot scientifically determine the importance of multiple systems. At the same time, it can effectively distinguish the coupling degree and comprehensive development degree of multiple systems when the coupling coordination degree is consistent.

[0066] In addition, the present invention divides the coupling coordination level on the spatial grid scale through a grading standard, making the coupling coordination level evaluation result more intuitive. It improves the accuracy and rationality of the evaluation of ecological quality and urbanization level in water-rich areas, realizes the evaluation of coupling coordination level on the grid scale, and provides scientific and powerful support for the identification of the degree of human-land relationship and sustainable development in water-rich areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0068] In the attached picture:

[0069] Figure 1 It is the overall flow chart of the evaluation method of the present invention;

[0070] Figure 2 is a technical flow chart of the evaluation method of the present invention;

[0071] Figure 3 Schematic diagram of the system structure of the evaluation system of the present invention. DETAILED DESCRIPTION

[0072] The embodiments of the present invention are described below in conjunction with the drawings in the embodiments of the present invention. The terms used in the implementation mode of the present invention are only used to explain the specific embodiments of the present invention, and are not intended to limit the present invention. The embodiments of the present application are described below in conjunction with the drawings.

[0073] Example: Figure 1-Figure 2 As shown, the present invention provides a method for evaluating the coupling coordination degree between urbanization and ecological quality in water-rich areas; comprising:

[0074] S1. Acquire urbanization level data and ecological quality data of water-rich areas, wherein the data at least include remote sensing satellite image data of water-rich areas in several seasons;

[0075] The urbanization level data include population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU;

[0076] Obtaining population density data to calculate the population urbanization level data PU;

[0077] PU=P i / P max ;

[0078] Where P i is the value of cell i in population density data; P max Represents the maximum value of all cell networks in the region;

[0079] Obtain nighttime light remote sensing data to calculate economic urbanization level data EU;

[0080] EU=E i / E max ;

[0081] Where E i is the grid value of the i-th unit in the nighttime light remote sensing data; E max Represents the maximum value of all cell networks in the region;

[0082] Obtain construction land area ratio data and traffic road network density data to calculate spatial urbanization level data KU;

[0083]

[0084] Among them A i is the area of ​​construction land in the unit land use data; A is the area of ​​unit land use data; R i Represents the grid value of unit i in the traffic network density data; R max Represents the maximum value of all cell networks in the region;

[0085] Obtain the scientific and educational level density data and medical level density data to calculate the social urbanization level data SU;

[0086]

[0087] Among them, H i is the sum kernel density result value of the i unit in the medical level density data; H max Represents the maximum kernel density value of all cell networks in the region; S i represents the kernel density result value of unit i in the density data of science and education level; S max Represents the maximum value of all cell networks in the region;

[0088] The ecological quality data are calculated using the surface reflectance dataset, which includes the water body abundance index data (SPWI), the normalized latent heat index data (NDLI), the nuclear vegetation index data (kNDVI), the normalized building and bare soil index data (NDBSI) and the land surface temperature data (LST);

[0089] The calculation model of water abundance index is expressed as:

[0090]

[0091] Among them, ρ blue , nir and ρ swir2It indicates the true reflectance of the surface of the blue band, near infrared band and short infrared band 2 of the remote sensing image;

[0092] The normalized latent heat index calculation model is:

[0093]

[0094] Among them, ρ green , red and ρ swir1 Indicates the true surface reflectance of the green band, red band and short infrared band 1 of the remote sensing image;

[0095] The calculation model of the kernel vegetation index is:

[0096]

[0097] Among them, ρ nir and ρ red represents the true reflectance of the surface in the near-infrared band and the red band of the remote sensing image. σ is the length scale parameter specified in each specific application, which represents the sensitivity of the exponential model to sparse / dense vegetation areas. A reasonable choice is to take the average value, that is, σ = 0.5 (ρ nir +ρ red );

[0098] The calculation model of normalized building and bare soil index is:

[0099]

[0100] NDBSI=(SI+IBI) / 2;

[0101] Among them, ρ green , red , swir1 , blue and ρ nir Indicates the true surface reflectance of the green band, red band, short infrared band 1, blue band and near infrared band of remote sensing images;

[0102] The surface temperature calculation model is:

[0103]

[0104] Where ρ is a constant, and its value is 1.438×10 -2 mK; T is the temperature at the sensor; L is the reflectivity of the thermal infrared band after the remote sensing image is calibrated by radiation; φ is the central wavelength of the thermal infrared band; ε is the surface emissivity; K1 and K2 are constants, and their values ​​are 774.89Wm -2 sr -1 μm -1 and 1321.08K;

[0105] Wherein: In a specific embodiment, data acquisition includes: obtaining regional remote sensing satellite image data of the four seasons of spring, summer, autumn and winter in the water-rich area from 2000 to 2024, wherein March to May is spring, June to August is summer, September to November is autumn, and December to February of the following year is winter, and the data spatial resolution is 30 meters; obtaining NPP / VIIRS-like night light remote sensing data from 2000 to 2024, and the data spatial resolution is 500 meters; obtaining WorldPop population density data from 2000 to 2024, and the data spatial resolution is 100 meters; obtaining land use data from 2000 to 2024, and the data spatial resolution is 30 meters, and the land use types include six types: forest land, grassland, construction land, water body, bare land and garden land; obtaining traffic road network vector data from 2000 to 2024; obtaining point of interest data in the water-rich area from 2000 to 2024;

[0106] Perform cloud filtering and median synthesis on the remote sensing satellite image data to obtain cloud-free surface reflectance datasets in different seasons;

[0107] S2. Based on the urbanization level data and the ecological quality data, respectively determine the urbanization evaluation index and the ecological quality index, and calculate the weight of each index, and obtain the ecological quality evaluation index and the urbanization evaluation index respectively through the weight;

[0108] Determine urbanization evaluation indicators using data cleaning and kernel density analysis;

[0109] In a specific embodiment, based on the acquired point of interest data, after data cleaning, that is, screening the point of interest data, when processing the point of interest data in the social urbanization level data, the number, location and name of schools, research institutes, pharmacies, hospitals and health centers at all levels in the point of interest are obtained, and the spatial distribution location, establishment time and operation status of regional scientific and educational level institutions and medical level institutions are obtained.

[0110] Based on the point of interest data of scientific and educational level and medical level institutions after data cleaning, the density data of scientific and educational level and medical level are calculated using the kernel density method.

[0111] The kernel density method is:

[0112]

[0113] Where h=1,…,k are the input points and Rd is the radius distance. Points are only included in the sum if they are within the radius distance of the (x,y) position. ph is the population field value of the h point, which is an optional parameter. disth is the distance between point h and the (x,y) position.

[0114] The spatial principal component analysis method is used to obtain the weights of each spatial principal component of all ecological quality indicators, including: constructing a correlation coefficient matrix based on each ecological quality evaluation indicator; calculating the eigenvalue λ and the eigenvector e based on the correlation coefficient matrix;

[0115] The correlation coefficient matrix is:

[0116]

[0117] Among them, r pq represents the correlation coefficient between the pth indicator and the qth indicator;

[0118] Calculate the eigenvalue λ based on the correlation coefficient matrix: Use the Jacobi method to solve the characteristic equation λI-R|=0, where I refers to the identity matrix and is arranged in order according to the size of the eigenvalue;

[0119] The identity matrix is:

[0120]

[0121] The eigenvector e is calculated as:

[0122]

[0123] Among them, e ij Represents the vector e i The jth component of

[0124] The contribution rate and cumulative contribution rate are calculated as follows:

[0125]

[0126] The contribution rate and cumulative contribution rate of each principal component are calculated based on the eigenvalue and eigenvector. The contribution rate of each principal component is the initial weight of each principal component.

[0127] The spatial principal component analysis model is:

[0128] PCA i =ω 1i X1+ω 2i X2+ω 3i X3+…+ω ii X i ;

[0129] Among them, PCA i represents the i-th principal component, X1, X2, X3, ..., X i are the original variables, ω1,ω2,ω3,…,ω i is the weight of each variable;

[0130] Then the initial weight value is corrected through the random forest model;

[0131] Based on the data of each spatial principal component, a sample training set after Bootstrap sampling is constructed; based on the sample training set, the best splitting method for each decision tree is constructed; the prediction error value of the sample data not drawn by each Bootstrap sampling is calculated; based on the prediction error value and voting results output by each decision tree, the final weight of each spatial principal component after correction is obtained; and

[0132] The random forest model is:

[0133]

[0134] Among them, F(X) is the final prediction result of the random forest model for sample X; M is the total number of decision trees in the random forest; f m (X) is the prediction result of the mth decision tree for sample X;

[0135] Constructing an ecological quality evaluation index:

[0136] EQI=ω1×PC1+ω2×PC2+ω3×PC3+ω4×PC4+ω5×PC5;

[0137] Among them, ω1, ω2, ω3, ω4 and ω5 are the weight values ​​of PC1, PC2, PC3, PC4 and PC5 after spatial principal component analysis and random forest correction, and satisfy ω1+ω2+ω3+ω4+ω5=1;

[0138] Based on the urbanization evaluation index, the weights of population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU are determined by using the hierarchical analysis method;

[0139] A hierarchical model is established based on population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU; a judgment matrix is ​​constructed based on the hierarchical model, and a hierarchical single ranking is established based on the judgment matrix; a hierarchical total ranking is established based on the hierarchical single ranking; and the weights of population urbanization, economic urbanization, spatial urbanization and social urbanization are calculated based on the hierarchical total ranking;

[0140] Calculate the consistency index CI and consistency ratio CR of each judgment matrix; when the consistency ratio is lower than the preset consistency ratio, solve the eigenvector of each judgment matrix as the weight of the ecological indicator of each urbanization sub-indicator; otherwise, reconstruct the judgment matrix; in a specific embodiment, if CR is less than 0.1, it is considered that the judgment matrix has satisfactory consistency, otherwise it is considered that the judgment matrix is ​​inconsistent and needs to be adjusted;

[0141] The judgment matrix is:

[0142]

[0143] Among them, b ij is the judgment value of the relative importance of element i to element j. The judgment value includes at least 5 scales: 1, 3, 5, 7 and 9, where: 1 means that element i and element j are equally important, 3 to 9 respectively mean that the importance of element i is increasing compared to element j, that is, 3 means that element i is a little more important than element j; 5 means that element i is much more important than element j; 7 means that element i is more important than element j; 9 means that element i is extremely more important than element j; and 2, 4, 6, and 8 represent the median of adjacent judgments. When 5 levels are not enough, these numbers can be used.

[0144] The value of the judgment matrix can be obtained after comprehensive consideration of data, expert opinions, and analyst cognition. The judgment matrix satisfies:

[0145]

[0146] Hierarchical single sorting is the result obtained after solving the characteristic roots and eigenvectors of the judgment matrix, expressed as:

[0147] BW=λ max W;

[0148] Among them, λ max is the maximum eigenvalue of the judgment matrix B, W is the normalized eigenvector corresponding to , and the component W of W i It is the weight value corresponding to the single sorting of elements;

[0149] The calculation of consistency index CI is:

[0150]

[0151] Among them, λ max is the maximum characteristic root of the judgment matrix B, n represents the order of the judgment matrix, that is, the number of evaluation indicators at a certain level;

[0152] Constructing urbanization evaluation index;

[0153] UEI=ω1×PU+ω2×EU+ω3×KU+ω4×SU;

[0154] Wherein, ω1, ω2, ω3 and ω4 are the weight values ​​of PU, EU, KU and SU determined by the hierarchical analysis method, and satisfy ω1+ω2+ω3+ω4=1;

[0155] S3. Construct a modified coupling coordination model, and calculate the coupling coordination level index based on the ecological quality evaluation index and urbanization evaluation index to obtain the evaluation results of the coupling coordination degree between urbanization and ecological quality in water-rich areas;

[0156] The evaluation model of the coupling coordination level between ecological quality and urbanization based on the modified coupling coordination degree model is expressed as follows:

[0157]

[0158] T = α × U + β × E;

[0159] The traditional coupling coordination index CCD is:

[0160]

[0161] It cannot distinguish between situations where the coupling degree and comprehensive development index values ​​are different but the coupling coordination degree values ​​are the same.

[0162] The specific circumstances are as follows:

[0163] (1) When C = 0.9, T = 0.1, CCD is equal to 0.3;

[0164] (2) When C and T are both equal to 0.3, CCD is still equal to 0.3.

[0165] CCD cannot distinguish which of the two situations is better;

[0166] In the present invention, the traditional coupling coordination index CCD is improved to obtain:

[0167]

[0168] Among them, U and E are the urbanization evaluation index and ecological quality evaluation index; C refers to the coupling value; T refers to the comprehensive development index; MCCD refers to the improved coupling coordination index value; MCCD is equal to 0.14 and 0.30 in the above two cases respectively, which can clearly distinguish the cases with different C and T values ​​and the same coupling coordination values.

[0169] Based on the coupling coordination evaluation results, the coupling coordination value level is divided using the mean average method:

[0170]

[0171] The present invention also discloses a coupling coordination evaluation system for urbanization and ecological quality in water-rich areas, comprising:

[0172] Data acquisition module: obtain urbanization level data and ecological quality data in water-rich areas;

[0173] Data preprocessing and analysis module: Based on the cloud processing platform, cloud filtering and median synthesis processing are performed on remote sensing satellite image data of water-rich areas. At the same time, the weights of urbanization evaluation indicators and ecological quality indicators are determined and analyzed based on spatial principal component analysis, random forest method and hierarchical analysis method respectively;

[0174] Model building module: construct an urbanization level evaluation index model based on urbanization level data and urbanization evaluation index weights; construct an ecological quality evaluation index model based on ecological quality data and ecological quality indicators; and construct a modified coupling coordination degree model at the same time;

[0175] Index calculation module: The ecological quality evaluation index and urbanization evaluation index are calculated through the urbanization level index model and the ecological quality index model respectively, and the coupling coordination level index is calculated based on the ecological quality evaluation index and the urbanization evaluation index using the modified coupling coordination degree model;

[0176] Coupling coordination level grading module: The coupling coordination value levels are graded using the coupling coordination level index and grading standards.

[0177] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the modules described above can refer to the corresponding process in the aforementioned method implementation, and will not be repeated here.

[0179] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present implementation scheme.

[0180] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0181] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for a computer system (which can be a personal computer, a server, or a network system, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0182] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned implementation modes, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation modes, 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 various implementation modes of the present application.

Claims

1. The evaluation method of coupling coordination degree between urbanization and ecological quality in water-rich areas is characterized by: The steps include: S1. Acquire urbanization level data and ecological quality data of water-rich areas, wherein the data at least include remote sensing satellite image data of water-rich areas in several seasons; as well as Performing cloud filtering and median synthesis on the remote sensing satellite image data; Obtain cloud-free surface reflectance datasets in different seasons; S2. Based on the urbanization level data and the ecological quality data, respectively determine the urbanization evaluation index and the ecological quality index, and calculate the weight of each index, and obtain the ecological quality evaluation index and the urbanization evaluation index respectively through the weight; S3. Construct a modified coupling coordination model, and calculate the coupling coordination level index based on the ecological quality evaluation index and urbanization evaluation index to obtain the evaluation results of the coupling coordination degree between urbanization and ecological quality in water-rich areas.

2. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 1 is characterized by: In S1, the urbanization level data includes population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU; Obtaining population density data to calculate the population urbanization level data PU; Obtain nighttime light remote sensing data to calculate economic urbanization level data EU; Obtain construction land area ratio data and traffic road network density data to calculate spatial urbanization level data KU; Obtain the scientific and educational level density data and medical level density data to calculate the social urbanization level data SU; The ecological quality data are calculated using the surface reflectance data set, and the ecological quality data include water abundance index data, normalized latent heat index data, nuclear vegetation index data, normalized building and bare soil index data and surface temperature data.

3. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 2 is characterized by: In S2, data cleaning and kernel density analysis were used to determine urbanization evaluation indicators; The spatial principal component analysis method is used to obtain the weights of each spatial principal component of all ecological quality indicators, including: constructing a correlation coefficient matrix based on each ecological quality evaluation indicator; calculating the eigenvalue λ and the eigenvector e based on the correlation coefficient matrix; calculating the contribution rate and cumulative contribution rate of each principal component based on the eigenvalue and the eigenvector, and the contribution rate of each principal component is the initial weight of each principal component; and then correcting the initial weight value through the random forest model to construct an ecological quality evaluation index; Based on the urbanization evaluation index, the weights of population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU are determined using the hierarchical analysis method to construct an urbanization evaluation index.

4. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 3 is characterized by: The spatial principal component analysis model is: PCA i =ω 1i X1+ω 2i X2+ω 3i X3+…+ω ii X i ; Among them, PCA i represents the i-th principal component, X1, X2, X3, ..., X i are the original variables, ω1,ω2,ω3,…,ω i is the weight of each variable; and The correlation coefficient matrix is: Among them, r pq represents the correlation coefficient between the pth indicator and the qth indicator; Calculate the eigenvalue λ based on the correlation coefficient matrix: Use the Jacobi method to solve the characteristic equation λI-R=0, where I is the unit matrix and the eigenvalues ​​are arranged in order; The identity matrix is: The eigenvector e is calculated as: Among them, e ij Represents the vector e i The jth component of The contribution rate and cumulative contribution rate are calculated as follows:

5. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 3 is characterized by: The initial weight values ​​are corrected as follows: constructing a sample training set after Bootstrap sampling based on the data of each spatial principal component; constructing the best splitting method for each decision tree based on the sample training set; calculating the prediction error value of the sample data not drawn by each Bootstrap sampling; obtaining the final weight of each spatial principal component after correction based on the prediction error value and voting results output by each decision tree; and The random forest model is: Among them, FX is the final prediction result of the random forest model for sample X; M is the total number of decision trees in the random forest; f m X is the prediction result of the mth decision tree for sample X.

6. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 3 is characterized by: A hierarchical model is established based on population urbanization level data PU, economic urbanization level data EU, spatial urbanization level data KU and social urbanization level data SU; a judgment matrix is ​​constructed based on the hierarchical model; Calculate the consistency index CI and consistency ratio CR of each judgment matrix; when the consistency ratio is lower than the preset consistency ratio, solve the eigenvector of each judgment matrix as the weight of the ecological indicator of each urbanization sub-indicator; otherwise, reconstruct the judgment matrix; The urbanization evaluation index is constructed based on the weights: UEI=ω1×PU+ω2×EU+ω3×KU+ω4×SU; Among them, ω1, ω2, ω3 and ω4 are the weight values ​​of PU, EU, KU and SU determined by the hierarchical analysis method, and satisfy ω1+ω2+ω3+ω4=1.

7. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 6 is characterized by: The judgment matrix is: Among them, b ij is a judgment value of the relative importance of element i to element j, and the judgment values ​​include at least 1, 3, 5, 7 and 9, where: 1 indicates that element i and element j are equally important, and 3 to 9 indicate that the importance of element i is increasing compared to element j; and The calculation of consistency index CI is: Among them, λ max is the maximum eigenvalue of the judgment matrix B, and n represents the order of the judgment matrix.

8. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 3 is characterized by: In S3, the evaluation model of the coupling coordination level between ecological quality and urbanization based on the modified coupling coordination degree model is expressed as: T = α × U + β × E; Among them, U and E are the urbanization evaluation index and ecological quality evaluation index; C refers to the coupling value; T refers to the comprehensive development index; MCCD is the improved coupling coordination index value.

9. The method for evaluating the coupling coordination degree of urbanization and ecological quality in water-rich areas according to claim 1 is characterized by: Based on the coupling coordination evaluation results, the coupling coordination value level is divided using the mean average method:

10. The evaluation system of coupling coordination degree between urbanization and ecological quality in water-rich areas is characterized by: include: Data acquisition module: obtain urbanization level data and ecological quality data in water-rich areas; Data preprocessing and analysis module: Based on the cloud processing platform, cloud filtering and median synthesis processing are performed on remote sensing satellite image data of water-rich areas. At the same time, the weights of urbanization evaluation indicators and ecological quality indicators are determined and analyzed based on spatial principal component analysis, random forest method and hierarchical analysis method respectively; Model building module: construct an urbanization level evaluation index model based on urbanization level data and urbanization evaluation index weights; construct an ecological quality evaluation index model based on ecological quality data and ecological quality indicators; and construct a modified coupling coordination degree model at the same time; Index calculation module: The ecological quality evaluation index and urbanization evaluation index are calculated through the urbanization level index model and the ecological quality index model respectively, and the coupling coordination level index is calculated based on the ecological quality evaluation index and the urbanization evaluation index using the modified coupling coordination degree model; Coupling coordination level grading module: The coupling coordination value levels are graded using the coupling coordination level index and grading standards.

Images