Urban area energy information identification method based on remote sensing data

Abstract

The invention discloses an urban area energy information identification method based on remote sensing data. The method comprises the following steps: acquiring data information; analyzing and processing the data information; performing clustering analysis on the data information; calculating the data comparability of the four class clusters; the four indexes and the relation between the four indexes and the comprehensive energy indexes; a long-term change mode of energy utilization conditions; according to the method, the data information of the urban built-up area in the aspect of sustainable energy utilization is collected through the remote sensing technology, the data information is divided into four index data through clustering analysis, and the four indexes can be clearly displayed through score processing, so that the method is convenient and fast to operate. Analyzing the relation between the four indexes and the comprehensive index through a nonparametric Spearman rank correlation coefficient, analyzing the reliability measurement of the nonlinear monotonic relation between the four indexes and the comprehensive index, analyzing the long-term change processing of the energy utilization condition through time trend analysis, and analyzing the energy utilization condition through clustering analysis. And analyzing the internal structure of sustainable utilization of energy.

Description

Technical Field

[0001] The present invention relates to the technical field of urban area energy information identification, and in particular to an urban area energy information identification method based on remote sensing data. Background Art

[0002] The main contradictions in society are constantly changing. With the advancement of industrialization, the problems of material scarcity and energy shortage have been basically solved. However, excessive emissions of greenhouse gases such as carbon dioxide have gradually made climate and environmental issues the main contradictions affecting human survival. Huge economic losses have been caused in various places. Global climate change has become a major challenge on the road to sustainable development for mankind.

[0003] As the main area of ​​economic innovation output and energy consumption, sustainable energy utilization in urban built-up areas is crucial to achieving global sustainable development goals. However, as a non-administrative unit, urban built-up areas lack effective energy statistics.

[0004] Promoting sustainable utilization of energy in urban built-up areas (SUEUBA) is key to achieving global sustainable development goals. Globally, cities, which account for less than 3% of the land area, account for about 55% of the population, consume about 78% of the world's energy, and contribute more than 80% of the world's GDP. With the acceleration of urbanization, energy demand has also increased dramatically. However, energy utilization information in urban built-up areas (UBA) is often difficult to obtain and use due to the complexity and opacity of data, resulting in unclear sustainable energy utilization in UBA.

[0005] Satellite observations provide an accurate and efficient solution for SUEUBA situation identification, and provide support for obtaining information such as energy utilization intensity, efficiency, and changes. Many scholars use remote sensing data with high spatial resolution and temporal frequency to evaluate the feasibility of power generation, heating, and lighting on building roofs and exterior walls. However, this kind of energy consumption measurement at the community scale or in a single building cannot meet the needs of overall UBA energy mapping. Although remote sensing mapping research has also been conducted on energy consumption in urban transportation, industrial activities, and infrastructure, these studies have difficulty in forming a grid distribution of energy consumption utilization that is consistent in time and space, and lack a basis for evaluating regional energy utilization in UBA.

[0006] Global mapping and monitoring of electricity consumption and carbon dioxide emissions can provide continuous data in time and space, providing new opportunities for comprehensive identification of UBA to optimize and reduce emissions. Combined with socioeconomic data such as population and GDP, efficiency and structural analysis can be further conducted to comprehensively evaluate the sustainability of urban energy use. For example, by combining electricity consumption and carbon dioxide emissions with GDP and population data, electricity consumption and carbon dioxide emissions per unit of GDP and per capita can be calculated, the energy efficiency of different regions can be evaluated, and the energy utilization structure of urban built-up areas can be analyzed to optimize energy efficiency and structure. However, existing research lacks spatial evaluation and analysis of UBA energy utilization efficiency and structure.

[0007] To this end, the present invention provides a method for identifying urban area energy information based on remote sensing data. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies in the prior art, the present invention provides an urban energy information identification method based on remote sensing data, which collects data information on sustainable energy utilization in urban built-up areas through remote sensing technology, and classifies the data information through cluster analysis, so that the data information can be divided into four indicator data, and through data comparability processing of four clusters and score processing, it is convenient to process the four indicators and realize clear display of the four indicators, and analyzes the relationship between the four indicators and the comprehensive indicator through the non-parametric Spearman rank correlation coefficient, analyzes the reliable measurement of the nonlinear monotonic relationship between the four indicators and the comprehensive indicator, and for the indicators after analysis and processing, predicts the long-term change processing of energy utilization through time trend analysis, and analyzes the internal structure of sustainable energy utilization through cluster analysis, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A method for identifying urban energy information based on remote sensing data, comprising:

[0013] Collect data information, collect data information on sustainable energy utilization in urban built-up areas through remote sensing technology, and select energy-related indicators from sustainable development goals, selecting a total of four indicators to measure energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions;

[0014] Analyze and process data information, including receiving, converting, filtering, gaining and cleaning data information collected by remote sensing technology on sustainable energy utilization in urban built-up areas;

[0015] The data information is clustered and divided into four clusters to measure energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions. The algorithm of cluster analysis is as follows:

[0016]

[0017] Among them, F is the outlier factor, D is the data information on sustainable energy utilization in urban built-up areas collected by remote sensing technology, |z j | is the number of samples in the jth cluster group, d(p,z j ) is the distance between sample p and the jth cluster center, and z j is the jth cluster center, and the value of j is 4;

[0018] To calculate the data comparability of the four clusters, the indicators of the four clusters were adjusted from 0 to 100, where 0 represents the worst performance and 100 represents the best performance. The adjustment formula is as follows:

[0019] ,

[0020] Among them, x 0 is the standardized value of the indicator, x is the original value of the indicator, and x max and x min Provide upper and lower limits of indicators respectively;

[0021] The four indicators and their relationship with the comprehensive energy indicators are analyzed using the non-parametric Spearman rank correlation coefficient to analyze the relationship between the four indicators and the comprehensive indicators. It is a reliable measure of the nonlinear monotonic relationship between the four indicators and the comprehensive indicators, and is less affected by outliers. When p-value<0.05, ρ>0, it means that the sub-indicator promotes the overall indicator. On the contrary, when p-value<0.05, ρ<0, it means that the sub-indicator has a negative effect on the overall indicator.

[0022] Long-term change patterns of energy utilization,Time trend analysis calculates the long-term change patterns of energy utilization, and through cluster analysis of unsupervised learning methods, the internal structure of sustainable energy utilization in built-up areas.

[0023] Furthermore, energy intensity refers to the energy intensity measured in terms of primary energy and gross domestic product, expressed as the ratio of electricity consumption to real GDP; the lower the ratio, the better, indicating that the economy consumes less energy while producing the same or more GDP;

[0024] Carbon intensity indicates the amount of carbon dioxide emissions per unit of added value, expressed as the ratio of carbon dioxide emissions to real GDP, indicating the amount of carbon dioxide released when producing each unit of economic output. The lower the ratio, the better.

[0025] The carbon emission intensity of power generation is defined as the carbon dioxide emissions generated when producing a unit of electricity, that is, the ratio of carbon dioxide emissions to electricity consumption. A low ratio indicates that the process of electricity generation is cleaner and more efficient, reflecting the use of more renewable energy or more efficient fossil fuels in the process of electricity generation.

[0026] The reduction in annual per capita carbon dioxide emissions indicates more efficient energy use and wider utilization of clean energy.

[0027] Furthermore, the data information analysis and processing includes an acquisition module for receiving the data information, an analog-to-digital conversion for converting the data information, a filtering module for filtering out clutter from the data information, a gain module for amplifying the data information, and a cleaning module for removing abnormalities from the data information;

[0028] The filtering module filters the data information through the following formula;

[0029]

[0030] in, Identifies the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set, and the movement unit each time is 1.

[0031] Furthermore, the cleaning module uses the following formula to clean the data information: X is the input value of the data, Y is the output of the data,

[0032] Y i =α+βX i +ε i ;

[0033] Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient, which is also the slope of the overall regression line. When the data information is far from the regression line, the data information is judged to be an abnormal signal, and the distance is determined by calculating the cluster center.

[0034] Furthermore, for the distance away from the cluster center, it is set to average the distance from the center of the data information, and calculate the data results processed by the cluster analysis algorithm, that is, If the distance of the data information is greater than 2d, the data signal is determined to be abnormal data information.

[0035] Furthermore, when calculating the comparability of the data of the four clusters, x max and x min The 97.5th percentile and 2.5th percentile of the indicator value distribution were taken. The value of the indicator exceeding the upper limit was scored as 100, and the value below the lower limit was scored as 0. The average value of the four indicators was taken as the comprehensive representation of SUEUBA, and the median value of the indicator was selected as the scale statistical unit value.

[0036] Furthermore, the calculation formula of the nonparametric Spearman rank correlation coefficient is as follows:

[0037]

[0038] Where d is the rank difference between X and Y, n is the number of data points, and this formula is used to calculate the Spearman rank correlation coefficient, which represents the degree of rank correlation between X and Y, where X and Y represent the four indicators and their correlation with the comprehensive energy indicator, respectively.

[0039] Furthermore, the four indicators and their comprehensive energy indicators X and Y are sorted according to size and assigned corresponding ranks:

[0040] Then, calculate the rank difference between X and Y:

[0041] Then the rank difference is calculated as d = X i -Y i , where i represents the location of the data, X and Y represent the four indicators and their relationship with the comprehensive energy indicator,

[0042] Substituting these differences into Calculate the Spearman correlation coefficient.

[0043] Furthermore, the time trend analysis calculation formula is as follows:

[0044] φ p (B)Φ P (B S )(1-B S ) d (1-B S ) D x t =θ q (B)Θ Q (B S )εt ;

[0045] Among them, B is the difference operator, B S is the time difference operator, x t is the observed value at time point t, ε t is the error term;

[0046] The nonparametric Mann-Kendall (MK) test evaluates the presence of a significant trend in the evapotranspiration time series data by testing the Z value of the statistic:

[0047]

[0048] S is the Kendall rank statistic, x i ,y j is the current calculated value that can effectively evaluate the change trend of SUEUBA corresponding to the i-th and j-th, as well as the predicted value that is certain in the prediction time; n is the amount of calculated data;

[0049] At a specific α significance level, the bilateral trend test is also used. At a given significance level, the critical value Z is found in the normal distribution table. 1-α / 2 ; When |Z|≤Z 1-α / 2 When |Z|>Z 1-α / 2 , then reject the predicted value;

[0050] Used to reflect the long-term changing patterns of energy utilization and further reveal the effects of policy and technological interventions.

[0051] Furthermore, in the cluster analysis of the unsupervised learning method, the input data information is the data information collected by the data query, which is set as x.

[0052] but, Among them, x i is the data information of the i-th input, u jn Represented as the center of the j-cluster classification;

[0053] When new data information is included in the corresponding cluster, the center of the cluster is updated:

[0054] Among them, C j Clusters represented as categories;

[0055] The silhouette coefficient was used to evaluate the clustering effect. By comparing the silhouette coefficients under different cluster numbers (k values ​​ranged from 2 to 10), the k value with the highest score was selected as the optimal cluster number. The silhouette coefficient measures the compactness and separation of clusters. The higher the value, the better the clustering effect.

[0056] The silhouette coefficient evaluates the clustering effect:

[0057]

[0058] Among them, a represents the average distance of this sample in the same category;

[0059] b represents the average distance of this sample in the other class closest to it.

[0060] (III) Beneficial effects

[0061] The present invention provides a method for identifying urban energy information based on remote sensing data, which has the following beneficial effects:

[0062] When the present invention is used, data information on sustainable energy utilization in urban built-up areas is collected through remote sensing technology, and the data information is classified and processed through cluster analysis, so that the data information can be divided into four indicator data, namely energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions.

[0063] And through the data comparability processing of the four clusters and the processing of the scores, it is convenient to process the four indicators and realize the clear display of the four indicators. The non-parametric Spearman rank correlation coefficient is used to analyze the relationship between the four indicators and the comprehensive indicator, and the reliable measurement of the nonlinear monotonic relationship between the four indicators and the comprehensive indicator is analyzed. For the indicators after analysis, the contribution of the four sub-indicators of different countries to SUEUBA, the SUEUBA trend and the clustering pattern are analyzed, which provides a new perspective for the spatial measurement and analysis of SUEUBA to support the optimization of urban energy utilization efficiency and structure in various countries.

[0064] By predicting the long-term changes in energy utilization through time trend analysis and analyzing the internal structure of sustainable energy utilization through cluster analysis, we can deepen our understanding of the sustainable development performance of energy in urban built-up areas. In addition to revealing the performance of cities in various countries in reducing energy consumption and carbon emissions, we can also show the differences in energy sustainability practices in urban built-up areas of different countries, thereby identifying which countries' policies and technological innovations are most effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of the steps of the urban energy information identification method based on remote sensing data of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] See also Figure 1 The present invention provides a method for identifying urban energy information based on remote sensing data, comprising:

[0068] Collect data information, collect data information on sustainable energy utilization in urban built-up areas through remote sensing technology, and select energy-related indicators from sustainable development goals, selecting a total of four indicators to measure energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions;

[0069] Analyze and process data information, including receiving, converting, filtering, gaining and cleaning data information collected by remote sensing technology on sustainable energy utilization in urban built-up areas;

[0070] The data information is clustered and divided into four clusters to measure energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions. The algorithm of cluster analysis is as follows:

[0071]

[0072] Among them, F is the outlier factor, D is the data information on sustainable energy utilization in urban built-up areas collected by remote sensing technology, |z j | is the number of samples in the jth cluster group, d(p,z j ) is the distance between sample p and the jth cluster center, and z j is the jth cluster center, and the value of j is 4;

[0073] To calculate the data comparability of the four clusters, the indicators of the four clusters were adjusted from 0 to 100, where 0 represents the worst performance and 100 represents the best performance. The adjustment formula is as follows:

[0074]

[0075] Among them, x 0 is the standardized value of the indicator, x is the original value of the indicator, and x max and x min Provide upper and lower limits of indicators respectively;

[0076] The four indicators and their relationship with the comprehensive energy indicators are analyzed using the non-parametric Spearman rank correlation coefficient to analyze the relationship between the four indicators and the comprehensive indicators. It is a reliable measure of the nonlinear monotonic relationship between the four indicators and the comprehensive indicators, and is less affected by outliers. When p-value<0.05, ρ>0, it means that the sub-indicator promotes the overall indicator. On the contrary, when p-value<0.05, ρ<0, it means that the sub-indicator has a negative effect on the overall indicator.

[0077] Long-term change patterns of energy utilization,Time trend analysis calculates the long-term change patterns of energy utilization, and through cluster analysis of unsupervised learning methods, the internal structure of sustainable energy utilization in built-up areas.

[0078] In order to classify and process the data information collected by remote sensing technology on sustainable energy utilization in urban built-up areas, and to classify the data information into different representation directions, in this embodiment, preferably, energy intensity refers to energy intensity measured by primary energy and gross domestic product, and is represented by the ratio of electricity consumption to actual GDP; the lower the ratio, the better, indicating that the economy consumes less energy when generating the same or more GDP;

[0079] Carbon intensity indicates the amount of carbon dioxide emissions per unit of added value, expressed as the ratio of carbon dioxide emissions to real GDP, indicating the amount of carbon dioxide released when producing each unit of economic output. The lower the ratio, the better.

[0080] The carbon emission intensity of power generation is defined as the carbon dioxide emissions generated when producing a unit of electricity, that is, the ratio of carbon dioxide emissions to electricity consumption. A low ratio indicates that the process of electricity generation is cleaner and more efficient, reflecting the use of more renewable energy or more efficient fossil fuels in the process of electricity generation.

[0081] The reduction in annual per capita carbon dioxide emissions indicates more efficient energy use and wider utilization of clean energy.

[0082] In order to realize the preprocessing of the data information on sustainable energy utilization in urban built-up areas collected by remote sensing technology, so that the data information is convenient for subsequent calculation and processing, in this embodiment, preferably, the analysis and processing of the data information includes an acquisition module for receiving the data information, an analog-to-digital conversion for converting the data information, a filtering module for filtering out clutter from the data information, a gain module for amplifying the data information, and a cleaning module for removing abnormalities from the data information;

[0083] The filtering module filters the data information through the following formula;

[0084]

[0085] in, Identifies the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set, and the movement unit each time is 1.

[0086] In order to realize the calculation and analysis of the erroneous and abnormal data in the data information, in this embodiment, preferably, the cleaning module uses the following formula to clean the data information: X is the input value of the data, Y is the output of the data,

[0087] Y i =α+βX i +ε i ;

[0088] Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient, which is also the slope of the overall regression line. When the data information is far from the regression line, the data information is judged to be an abnormal signal, and the distance is determined by calculating the cluster center.

[0089] In order to determine whether the abnormal data obtained by calculation and analysis is abnormal error data information, a judgment standard is set. In this embodiment, preferably, for the distance away from the cluster center, it is set to average the distance center position of the data information, and calculate the data results processed by the cluster analysis algorithm, that is, If the distance of the data information is greater than 2d, the data signal is determined to be abnormal data information.

[0090] In order to achieve the index setting of the calculation result of the data comparability of the four clusters, in this embodiment, preferably, when calculating the data comparability of the four clusters, x max and x min The 97.5th percentile and 2.5th percentile of the indicator value distribution were taken. The value of the indicator exceeding the upper limit was scored as 100, and the value below the lower limit was scored as 0. The average value of the four indicators was taken as the comprehensive representation of SUEUBA, and the median value of the indicator was selected as the scale statistical unit value.

[0091] In order to analyze the relationship between the four indicators and the comprehensive indicator, the nonlinear monotonic relationship between the four indicators and the comprehensive indicator can be effectively analyzed. In this embodiment, preferably, the calculation formula of the non-parametric Spearman rank correlation coefficient is as follows:

[0092]

[0093] Where d is the rank difference between X and Y, n is the number of data points, and this formula is used to calculate the Spearman rank correlation coefficient, which represents the degree of rank correlation between X and Y, where X and Y represent the four indicators and their correlation with the comprehensive energy indicator, respectively.

[0094] In order to calculate the rank differences between the four indicators and the comprehensive energy indicators, in this embodiment, preferably, the four indicators and the comprehensive energy indicators X and Y are sorted according to size and assigned corresponding ranks:

[0095] Then, calculate the rank difference between X and Y:

[0096] Then the rank difference is calculated as d = X i -Y i , where i represents the location of the data, X and Y represent the four indicators and their relationship with the comprehensive energy indicator,

[0097] Substituting these differences into Calculate the Spearman correlation coefficient.

[0098] In order to analyze the time trend of the SUEUBA indicator, reflect the long-term change pattern of urban energy utilization, and further reveal the effect of policy and technical intervention, in this embodiment, preferably, the time trend analysis calculation formula is as follows:

[0099] φ p (B)Φ P (B S )(1-B S ) d (1-B S ) D x t =θ q (B)Θ Q (B S )ε t ;

[0100] Among them, B is the difference operator, B S is the time difference operator, x t is the observed value at time point t, ε t is the error term;

[0101] The nonparametric Mann-Kendall (MK) test evaluates the presence of a significant trend in the evapotranspiration time series data by testing the Z value of the statistic:

[0102]

[0103] S is the Kendall rank statistic, xi ,y j is the current calculated value that can effectively evaluate the change trend of SUEUBA corresponding to the i-th and j-th, as well as the predicted value that is certain in the prediction time; n is the amount of calculated data;

[0104] At a specific α significance level, the bilateral trend test is also used. At a given significance level, the critical value Z is found in the normal distribution table. 1-α / 2 ; When |Z|≤Z 1-α / 2 When |Z|>Z 1-α / 2 , then reject the predicted value;

[0105] Used to reflect the long-term changing patterns of energy utilization and further reveal the effects of policy and technological interventions.

[0106] In order to help different countries to understand the internal structure of sustainable energy utilization in urban built-up areas, similar countries are classified into the same group, which is more conducive to data analysis and understanding and exploring hidden patterns. In this embodiment, the cluster analysis of the unsupervised learning method is preferred. The input data information is the data information collected by the data query, which is set as x.

[0107] but, Among them, x i is the data information of the i-th input, u jn Represented as the center of the j-cluster classification;

[0108] When new data information is included in the corresponding cluster, the center of the cluster is updated:

[0109] Among them, C j Clusters represented as categories;

[0110] The silhouette coefficient was used to evaluate the clustering effect. By comparing the silhouette coefficients under different cluster numbers (k values ​​ranged from 2 to 10), the k value with the highest score was selected as the optimal cluster number. The silhouette coefficient measures the compactness and separation of clusters. The higher the value, the better the clustering effect.

[0111] The silhouette coefficient evaluates the clustering effect:

[0112]

[0113] Among them, a represents the average distance of this sample in the same category;

[0114] b represents the average distance of this sample in the other class closest to it.

[0115] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for identifying urban energy information based on remote sensing data, characterized in that: Included are: Collect data information, collect data information on sustainable energy utilization in urban built-up areas through remote sensing technology, and select energy-related indicators from sustainable development goals, selecting a total of four indicators to measure energy intensity, carbon intensity, carbon emission intensity of power generation and annual per capita carbon dioxide emissions; Analyze and process data information, including receiving, converting, filtering, gaining and cleaning data information collected by remote sensing technology on sustainable energy utilization in urban built-up areas; The data information is clustered and divided into four clusters to measure energy intensity, carbon intensity, power generation carbon emission intensity and annual per capita carbon dioxide emissions. The algorithm of cluster analysis is as follows: Among them, F is the outlier factor, D is the data information on sustainable energy utilization in urban built-up areas collected by remote sensing technology, |zj| is the number of samples in the jth cluster group, d(p,z j ) is the distance between sample p and the jth cluster center, and z j is the jth cluster center, and the value of j is 4; To calculate the data comparability of the four clusters, the indicators of the four clusters were adjusted from 0 to 100, where 0 represents the worst performance and 100 represents the best performance. The adjustment formula is as follows: Among them, x0 is the standardized value of the indicator, x is the original value of the indicator, and x max and x min Provide upper and lower limits of indicators respectively; The four indicators and their relationship with the comprehensive energy indicators are analyzed using the non-parametric Spearman rank correlation coefficient to analyze the relationship between the four indicators and the comprehensive indicators. It is a reliable measure of the nonlinear monotonic relationship between the four indicators and the comprehensive indicators, and is less affected by outliers. When p-value<0.05, ρ>0, it means that the sub-indicator promotes the overall indicator. On the contrary, when p-value<0.05, ρ<0, it means that the sub-indicator has a negative effect on the overall indicator. Long-term change patterns of energy utilization,Time trend analysis calculates the long-term change patterns of energy utilization, and through cluster analysis of unsupervised learning methods, the internal structure of sustainable energy utilization in built-up areas.

2. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: Energy intensity refers to the energy intensity measured in terms of primary energy and gross domestic product, expressed as the ratio of electricity consumption to real GDP; the lower the ratio, the better, indicating that the economy consumes less energy while producing the same or more GDP; Carbon intensity indicates the amount of carbon dioxide emissions per unit of added value, expressed as the ratio of carbon dioxide emissions to real GDP, indicating the amount of carbon dioxide released when producing each unit of economic output, the lower the ratio, the better; The carbon emission intensity of power generation is defined as the carbon dioxide emissions generated when producing a unit of electricity, that is, the ratio of carbon dioxide emissions to electricity consumption. A low ratio indicates that the process of electricity generation is cleaner and more efficient, reflecting the use of more renewable energy or more efficient fossil fuels in the process of electricity generation. The reduction in annual per capita carbon dioxide emissions indicates more efficient energy use and wider utilization of clean energy.

3. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: The data information analysis and processing includes an acquisition module for receiving the data information, an analog-to-digital conversion for converting the data information, a filtering module for filtering out clutter from the data information, a gain module for amplifying the data information, and a cleaning module for removing abnormalities from the data information; The filtering module filters the data information through the following formula; in, Identifies the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set, and the movement unit each time is 1.

4. The method for identifying urban energy information based on remote sensing data according to claim 3 is characterized in that: The cleaning module uses the following formula to clean the data information: X is the input value of the data, Y is the output of the data, Y i =α+βX i +e i ; Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient, which is also the slope of the overall regression line. When the data information is far from the regression line, the data information is judged to be an abnormal signal, and the distance is determined by calculating the cluster center.

5. The method for identifying urban energy information based on remote sensing data according to claim 4, characterized in that: For the distance away from the cluster center, it is set to average the distance from the center of the data information, and the data results processed by the cluster analysis algorithm are calculated, that is, If the distance of the data information is greater than 2d, the data signal is determined to be abnormal data information.

6. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: When calculating the comparability of the data of the four clusters, the 97.5th x of the indicator value distribution is taken. max x min Percentile and 2.5th percentile, the value of the indicator exceeding the upper limit is scored as 100, and the value below the lower limit is scored as 0. The average value of the four indicators is taken as the comprehensive representation of SUEUBA, and the median value of the indicator is selected as the scale statistical unit value.

7. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: The calculation formula of the nonparametric Spearman rank correlation coefficient is as follows: Where d is the rank difference between X and Y, n is the number of data points, and this formula is used to calculate the Spearman rank correlation coefficient, which represents the degree of rank correlation between X and Y, where X and Y represent the four indicators and their correlation with the comprehensive energy indicator, respectively.

8. The method for identifying urban energy information based on remote sensing data according to claim 7, characterized in that: Sort the four indicators and their comprehensive energy indicators X and Y by size and assign corresponding ranks: Then, calculate the rank difference between X and Y: Then the rank difference is calculated as d = X i -Y i , where i represents the location of the data, X and Y represent the four indicators and their relationship with the comprehensive energy indicator, Substituting these differences into Calculate the Spearman correlation coefficient.

9. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: The calculation formula for time trend analysis is as follows: f p (B)F P (B S )(1-B S ) d (1-B S ) D x t =θ q (B)I Q (B S )e t ; Among them, B is the difference operator, B S is the time difference operator, x t is the observed value at time point t, ε t is the error term; The nonparametric Mann-Kendall (MK) test evaluates the presence of a significant trend in the evapotranspiration time series data by testing the Z value of the statistic: S is the Kendall rank statistic, x i ,y j is the current calculated value that can effectively evaluate the change trend of SUEUBA corresponding to the i-th and j-th, as well as the predicted value that is certain in the prediction time; n is the amount of calculated data; At a specific α significance level, the bilateral trend test is also used. At a given significance level, the critical value Z is found in the normal distribution table. 1-α / 2 ; When |Z|≤Z 1-α / 2 When |Z|>Z 1-α / 2 , then reject the predicted value; Used to reflect the long-term changing patterns of energy utilization and further reveal the effects of policy and technological interventions.

10. The method for identifying urban energy information based on remote sensing data according to claim 1, characterized in that: Cluster analysis of unsupervised learning methods, the input data information is the data information collected by data query, set as x, but, Among them, x i is the data information of the i-th input, u jn Represented as the center of the j-cluster classification; When new data information is included in the corresponding cluster, the center of the cluster is updated: Among them, C j Clusters represented as categories; The silhouette coefficient was used to evaluate the clustering effect. By comparing the silhouette coefficients under different cluster numbers (k values ​​ranged from 2 to 10), the k value with the highest score was selected as the optimal cluster number. The silhouette coefficient measures the compactness and separation of clusters. The higher the value, the better the clustering effect. The silhouette coefficient evaluates the clustering effect: Among them, a represents the average distance of this sample in the same category; b represents the average distance of this sample in the other class closest to it.

Images