Carbon emission prediction method and device based on urban spread

Abstract

The invention discloses a carbon emission prediction method and device based on urban spread, and the method comprises the steps: carrying out the measurement of urban spread based on remote sensing satellite data with a preset resolution, and obtaining an index corresponding to urban spread; mining and constructing a mutual relationship between the indexes corresponding to the urban spread and the carbon emission, and obtaining a causal relationship, an interaction parameter and a time influence relationship parameter between the spread elements and the carbon emission; and according to the causal relationship between the spreading element and the carbon emission, the interaction parameter and the time influence relationship parameter, constructing a system dynamics model, predicting the future carbon emission of the city based on a policy scene, and outputting a carbon emission prediction result based on city spreading. According to the method, city spreading is dynamically monitored through remote sensing, future carbon emission is accurately calculated, the carbon emission prediction range and field are widened, and the prediction cost is reduced due to the fact that data are easy to obtain.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission prediction, and in particular to a carbon emission prediction method and device based on urban sprawl. Background Art

[0002] With the continued impact of global climate change, reducing carbon emissions has become an urgent need for the global society. Traditionally, urban carbon emission forecasts rely on statistical data and simple growth models. These methods are difficult to adapt to the rapid changes in urban development and policy changes due to their reliance on past data, resulting in insufficient forecast accuracy and large deviations, which in turn leads to inefficient policy making and resource allocation. With the urgency of the policy environment and the development of technology, society has an increasing demand for high-precision future carbon emission forecasts, especially in the process of rapid urbanization, where traditional forecasting methods are particularly insufficient.

[0003] In order to solve the problems in the existing technology, the existing methods predict future carbon emission data by obtaining time series data of the target location, including carbon emission data, economic data, industrial data, population flow data, and predicted land characteristic data. However, this method requires a huge amount of data, which is difficult to collect, and the data cost and computing resources required for prediction are very large. In addition, there are methods to improve the accuracy and speed of urban transportation carbon emission prediction. Despite this, it still focuses mainly on the transportation field, has limited comprehensive carbon emission prediction capabilities for the entire city, and relies on specific technical implementation.

[0004] Therefore, the prior art needs to be improved. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the defects of the prior art, the present invention provides a carbon emission prediction method and device based on urban sprawl to solve the problems of low prediction accuracy and high cost of the existing carbon emission prediction methods.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows: In a first aspect, the present invention provides a carbon emission prediction method based on urban sprawl, comprising: Urban sprawl is measured based on remote sensing satellite data with preset resolution to obtain indicators corresponding to urban sprawl; Mining and constructing the relationship between the indicators corresponding to the urban sprawl and carbon emissions, and obtaining the causal relationship, interaction parameters and time impact relationship parameters between the sprawl elements and carbon emissions; A system dynamics model is constructed according to the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time impact relationship parameters, and the future carbon emissions of the city are predicted based on policy scenarios, and the carbon emission prediction results based on urban sprawl are output.

[0007] In one implementation, the urban sprawl measurement based on remote sensing satellite data of a preset resolution to obtain indicators corresponding to urban sprawl includes: Select the city to be predicted and the area to which it belongs; Monitoring the selected area by a remote sensing satellite with a preset resolution and performing data preprocessing to obtain the remote sensing satellite data; The remote sensing satellite data is converted into an urban sprawl index through a preset algorithm to obtain an indicator corresponding to the urban sprawl.

[0008] In one implementation, the monitoring of the selected area by a remote sensing satellite of a preset resolution and performing data preprocessing to obtain the remote sensing satellite data includes: Acquiring image data of urban expansion corresponding to the selected area using the remote sensing satellite of the preset resolution; The image data are corrected, classified and analyzed using automated image processing software, and the processed image data are combined with population distribution data and nighttime light data to obtain the remote sensing satellite data.

[0009] In one implementation, converting the remote sensing satellite data into an urban sprawl index by a preset algorithm to obtain an indicator corresponding to the urban sprawl includes: The basic measurement unit is determined according to the accuracy of the remote sensing satellite data, and the proportion of the sprawl elements of the measurement unit in the city is calculated using the following formula: ; in, Indicates the proportion of the measured element in space, represents the spatial weight in the form of , α and β are parameters, α>0; The urban sprawl index is calculated using the following formula to obtain the sprawl expansion of specific sprawl elements in each city: ; in, represents the center point of the city, and n represents all measurement units within the city.

[0010] In one implementation, mining and constructing the relationship between the indicators corresponding to the urban sprawl and carbon emissions to obtain the causal relationship, interaction parameters, and time impact relationship parameters between the sprawl elements and carbon emissions include: Based on the indicators corresponding to the urban sprawl, the panel vector autoregression model is used to identify the impact of multi-dimensional sprawl on carbon emissions, and the causal relationship of each dimension is established according to the Granger causality test method to obtain the causal relationship between the sprawl factors and carbon emissions; The impulse response analysis method and the Akaike information criterion are used to establish the time lag and the persistence of the influence, and the interaction parameters and the time influence relationship parameters are obtained.

[0011] In one implementation, the constructing of a system dynamics model according to the causal relationship between the spreading elements and carbon emissions, the interaction parameters, and the time impact relationship parameters includes: Draw a causal loop diagram based on the causal relationship between the spreading factors and carbon emissions, and establish a flow-stock diagram based on the time impact relationship parameters; The system dynamics model is constructed according to the causal loop diagram, the flow-stock diagram and the interaction parameters, and the model is tested and adjusted using historical data to obtain an adjusted system dynamics model.

[0012] In one implementation, a prediction of future carbon emissions of a city is performed based on a policy scenario, and a carbon emission prediction result based on urban sprawl is output, including: Inputting the urban expansion data into the system dynamics model, and predicting and outputting the carbon emission data of the selected area under the current policy scenario through the system dynamics model; Or different urban development policy scenarios are input into the system dynamics model, and the urban sprawl parameters under the current policy scenario are simulated through scenario simulation related methods. The urban sprawl parameters are input into the system dynamics model to simulate the potential impact of the policy on urban sprawl and carbon emissions under the current policy scenario, and the change data of carbon emissions under different urban sprawl development situations under the current policy control are predicted and output.

[0013] In a second aspect, the present invention provides a carbon emission prediction device based on urban sprawl, comprising: The urban sprawl indicator module is used to measure urban sprawl based on remote sensing satellite data of preset resolution and obtain indicators corresponding to urban sprawl; The module for the relationship between urban sprawl factors and carbon emissions is used to mine and construct the relationship between the indicators corresponding to urban sprawl and carbon emissions, and obtain the causal relationship, interaction parameters and time impact relationship parameters between urban sprawl factors and carbon emissions; The system dynamics module is used to construct a system dynamics model according to the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time impact relationship parameters, and to predict the city's future carbon emissions based on policy scenarios, and output carbon emission prediction results based on urban sprawl.

[0014] In a third aspect, the present invention provides a terminal, comprising: a processor and a memory, wherein the memory stores a carbon emission prediction program based on urban sprawl, and when the carbon emission prediction program based on urban sprawl is executed by the processor, it is used to implement the operation of the carbon emission prediction method based on urban sprawl as described in the first aspect.

[0015] In a fourth aspect, the present invention further provides a medium, which is a computer-readable storage medium, and which stores a carbon emission prediction program based on urban sprawl. When the carbon emission prediction program based on urban sprawl is executed by a processor, it is used to implement the operation of the carbon emission prediction method based on urban sprawl as described in the first aspect.

[0016] The present invention adopts the above technical solution to achieve the following effects: (1) The present invention uses remote sensing images to identify the pattern and process of urban sprawl, converts them into one-dimensional data such as the urban sprawl index through mathematical formulas, and uses a panel vector autoregression model in combination with historical carbon emission data to identify the correlation and causal relationship between sprawl factors and carbon emissions. Based on the identification results, a system dynamics model of urban sprawl is constructed. By inputting the future urban sprawl under the influence of various development policies, the future carbon emissions of the city under the policy can be predicted.

[0017] (2) The present invention improves the accuracy and response speed of urban carbon emission forecasting. By real-time processing of remote sensing monitoring data and analysis of system dynamics models, it can quickly adapt to the impact of urban development or policy changes, thereby achieving more accurate and timely carbon emission forecasts, providing scientific data support for urban planning and environmental policies, and helping policymakers implement effective carbon emission reduction measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the carbon emission prediction method based on urban sprawl in the present invention.

[0020] Figure 2 It is a detailed flow chart of the carbon emission prediction method based on urban sprawl in the present invention.

[0021] Figure 3 It is a functional principle diagram of a terminal in one implementation of the present invention.

[0022] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] Exemplary Methods With the urgency of the policy environment and the development of technology, society has an increasing demand for high-precision predictions of future carbon emissions, especially in the process of rapid urbanization, where traditional prediction methods are particularly insufficient. In order to solve the problems in the existing technology, the existing methods predict future carbon emissions data by obtaining time series data of the target location, including carbon emission data, economic data, industrial data, population flow data, and predicted land characteristics data. However, this method requires a huge amount of data, which is difficult to collect, and the data cost and computing resources required for prediction are very large. In addition, there are methods to improve the accuracy and speed of urban transportation carbon emission prediction. Despite this, it still focuses mainly on the transportation field, has limited ability to predict the comprehensive carbon emissions of the entire city, and relies on specific technical implementation.

[0025] In response to the above technical problems, an embodiment of the present invention provides a carbon emission prediction method based on urban sprawl. The method measures urban sprawl based on remote sensing satellite data of a preset resolution to obtain indicators corresponding to urban sprawl; mines and constructs the relationship between indicators corresponding to urban sprawl and carbon emissions to obtain the causal relationship, interaction parameters and time influence relationship parameters between sprawl elements and carbon emissions; constructs a system dynamics model based on the causal relationship, interaction parameters and time influence relationship parameters between sprawl elements and carbon emissions, and predicts future carbon emissions of the city based on policy scenarios, and outputs carbon emission prediction results based on urban sprawl.

[0026] Therefore, the embodiments of the present invention not only improve the scope and field of carbon emission prediction by dynamically monitoring urban sprawl and accurately calculating future carbon emissions through remote sensing, but also reduce the prediction cost because of the easy data acquisition; moreover, the embodiments of the present invention improve the accuracy of data support for policy making, help urban planners achieve a more environmentally friendly urban layout, have significant environmental protection and socio-economic benefits, and indicate broad market application prospects.

[0027] like Figure 1 As shown, an embodiment of the present invention provides a carbon emission prediction method based on urban sprawl, comprising the following steps: Step S100, measuring urban sprawl based on remote sensing satellite data of a preset resolution to obtain indicators corresponding to urban sprawl.

[0028] In this embodiment, a carbon emission prediction model based on urban sprawl is designed. This model dynamically monitors urban sprawl and accurately calculates future carbon emissions through remote sensing, which not only improves the scope and field of carbon emission prediction, but also reduces the prediction cost because data is easy to obtain; the basic scheme of this embodiment includes using remote sensing images to identify the pattern and process of urban sprawl, converting it into one-dimensional data such as urban sprawl index through mathematical formulas, and combining historical carbon emission data with panel vector autoregression model to identify the correlation and causal relationship between sprawl elements and carbon emissions, and constructing a system dynamics model of urban sprawl based on the identification results. By inputting the future urban sprawl under the influence of various development policies, the future carbon emissions of the city under the policy can be predicted.

[0029] Specifically, in an implementation of this embodiment, step S100 includes the following steps: Step S101, selecting a city to be predicted and its region.

[0030] In this embodiment, it is necessary to select the city to be predicted and the area to which it belongs; the scope of the prediction object can be a certain city or an area. If the selected object is a county-level city (the smallest unit of a city), it is necessary to include other county-level cities in the county-level city where it is located in the prediction scope, and then allocate the predicted total carbon emissions according to the proportion.

[0031] Step S102, monitoring the selected area by a remote sensing satellite with a preset resolution, and performing data preprocessing to obtain the remote sensing satellite data; Specifically, in one implementation of the present embodiment, the remote sensing satellite data is obtained by monitoring the selected area with a preset resolution remote sensing satellite and performing data preprocessing, including: acquiring image data of urban expansion corresponding to the selected area using the remote sensing satellite with the preset resolution; correcting, classifying and analyzing the image data using automated image processing software, and combining the processed image data with population distribution data and night light data to obtain the remote sensing satellite data.

[0032] In this embodiment, after selecting the city to be predicted and the area to which it belongs, relevant data on urban sprawl are obtained. In this step, high-resolution satellite (i.e., remote sensing satellite with preset resolution) images are used to monitor the urban area. As a complex system, urban sprawl is affected by various factors. Here, the three dimensions of urban land boundaries, urban population distribution, and urban economic vitality are mainly used to identify the urban sprawl in the prediction range.

[0033] In this embodiment, high-resolution satellite images are used to monitor urban areas, and changes in urban artificial surfaces can be identified to obtain relevant data on urban land cover. Urban population data comes from The LandScan Program (a software with high-resolution world population distribution data), and urban economic activity data is represented by night light data. Existing studies have shown that night light data can reflect the economic vitality of a region. The data source is NPP / VIIRS (a remote sensing technology used to monitor night lights on the earth's surface, which obtains night light data by measuring visible light and infrared radiation emitted from the earth's surface). While collecting night light data, carbon emission data is collected.

[0034] As an example, in this embodiment, high-resolution satellites (for example, Landsat series or Sentinel series satellites) are used to obtain image data of urban expansion, and automated image processing software (for example, ERDAS Imagine software or ArcGIS software) is used to pre-process the images. The pre-processing process includes: correction, classification and analysis. After pre-processing, data from different sources are integrated, such as population distribution data provided by LandScan software and night light data from NPP / VIIRS software. The historical data on carbon emissions comes from the existing databases MEIC or EAGER, and the data are superimposed and analyzed through the GIS platform.

[0035] In this embodiment, high-resolution remote sensing satellites are used to monitor urban areas, which directly improves the real-time and accuracy of urban sprawl monitoring. Real-time updated urban boundary and land use change data, as well as nighttime light and population data, enable urban development trends to be captured and analyzed instantly, thereby providing more reliable data to support the correlation study between urban sprawl and carbon emissions. At the same time, since remote sensing image data is relatively simple to obtain, the cost of data acquisition is reduced.

[0036] Step S103: converting the remote sensing satellite data into an urban sprawl index by a preset algorithm to obtain an index corresponding to the urban sprawl.

[0037] Specifically, in an implementation of the present embodiment, the remote sensing satellite data is converted into an urban sprawl index by a preset algorithm to obtain an indicator corresponding to the urban sprawl, including: determining a basic measurement unit according to the accuracy of the remote sensing satellite data, and using a formula to calculate the proportion of sprawl elements of the measurement unit in the city; using a formula to calculate the urban sprawl index to obtain the sprawl expansion of specific sprawl elements of each city.

[0038] In this embodiment, after being processed, the remote sensing image data is converted into an urban sprawl index using a specific mathematical formula while retaining the spatial information of the data. This one-dimensional data simplifies the complex spatial information and facilitates further analysis.

[0039] As an example, this embodiment uses the following method to convert geographic space information (i.e., image data of urban expansion, population distribution data, night light data) into an urban sprawl index: The basic measurement unit is determined according to the accuracy of the remote sensing satellite data, and the proportion of the sprawl elements of the measurement unit in the city is calculated using the following formula: ; in, Indicates the proportion of the measured element in space, represents the spatial weight in the form of , α and β are parameters, α>0; The urban sprawl index is calculated using the following formula to obtain the sprawl expansion of specific sprawl elements in each city: ; in, represents the center point of the city, and n represents all measurement units within the city.

[0040] In this embodiment, the specific parameters of the calculation process of the indicator corresponding to urban sprawl are set as follows: Set the parameters α and β in the influence function, where α is set to the exponent of the maximum distance observed for any city , and β is set to 0. This setting helps the model better reflect the different contributions of distance from the central point to urban sprawl. In order to maintain consistency and reduce the impact of center point movement caused by annual factor changes, the fixed administrative center set by the Statistics Bureau is selected as the center point. This method simplifies the application of the model and ensures that the comparison between different factors is comparable.

[0041] In this embodiment, a more comprehensive picture of urban development is provided by integrating multi-source data, making the analysis of urban sprawl more comprehensive and in-depth. This multi-dimensional data integration enhances the model's ability to predict urban sprawl and its impact on carbon emissions, making the prediction more comprehensive and accurate.

[0042] The uniqueness of this embodiment is that it systematically analyzes and predicts urban carbon emissions specifically from the perspective of urban sprawl. This method provides a new perspective to understand and manage urban carbon footprint by directly linking the geographic, demographic and economic factors of urban expansion with carbon emission data. Compared with existing carbon emission prediction technologies, most of which focus on carbon emission prediction from the perspectives of industrial activities, energy consumption, etc., the present invention provides a more comprehensive carbon management strategy by focusing on urban expansion itself, an area that is directly affected by policies and closely related to a variety of socio-economic factors. This method can reveal the direct connection between urban size growth and carbon emissions, providing more targeted data support for urban planning and environmental policies.

[0043] This embodiment uses a new mathematical formula that can retain spatial information to the maximum extent when converting the geographic spatial information of urban sprawl into one-dimensional data. Compared with traditional methods, this method reduces the loss of spatial information when processing urban remote sensing data. Traditional methods usually ignore or simplify the complexity of spatial structure during the conversion process, resulting in the loss of important spatial information in the sprawl index. The mathematical method used in this embodiment can identify the changes in spatial distribution during urban sprawl, improve the accuracy of data conversion and information retention, and lay the foundation for predicting carbon emissions through urban sprawl.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a carbon emission prediction method based on urban sprawl, comprising the following steps: Step S200 , mining and constructing the correlation between the indicators corresponding to the urban sprawl and the carbon emissions, and obtaining the causal relationship, interaction parameters and time impact relationship parameters between the sprawl elements and the carbon emissions.

[0045] In this embodiment, the panel vector autoregression method is used to explore the impact relationship between multi-dimensional sprawl and carbon emissions, including establishing the causal relationship, interaction relationship, stock and flow required for system dynamics, determining model parameters, and constructing an urban sprawl model to predict future urban carbon emissions.

[0046] Specifically, in an implementation of this embodiment, step S200 includes the following steps: Step S201, based on the indicators corresponding to the urban sprawl, a panel vector autoregression model is used to identify the impact relationship of multi-dimensional sprawl on carbon emissions, and the causal relationship of each dimension is established according to the Granger causality test method to obtain the causal relationship between the sprawl factor and carbon emissions; Step S202, using the impulse response analysis method and the Akaike information criterion to establish the time lag and the persistence of the influence, and obtain the interaction parameter and the time influence relationship parameter.

[0047] In this embodiment, a panel vector autoregression (PVAR) or model is used to identify the impact relationship of multi-dimensional contagion on carbon emissions, and the causal relationship of each dimension is established based on the Granger causality test. The impulse response analysis (IRF) and Akaike information criterion (AIC) are used to establish the time lag and impact persistence, and the corresponding impact parameters are obtained.

[0048] As an example, in this embodiment, a statistical software package (eg, Stata software package or R software package) is used to construct a panel vector autoregression model to analyze the dynamic relationship between urban sprawl and carbon emissions.

[0049] By applying the panel vector autoregression model in this embodiment, this embodiment can accurately identify and quantify the direct and indirect effects of urban sprawl on carbon emissions, thereby accurately capturing the complex interactions between urban sprawl and carbon emissions.

[0050] like Figure 1 As shown, an embodiment of the present invention provides a carbon emission prediction method based on urban sprawl, comprising the following steps: Step S300, constructing a system dynamics model according to the causal relationship between the sprawl factor and carbon emissions, the interaction parameters and the time impact relationship parameters, and predicting the city's future carbon emissions based on policy scenarios, and outputting carbon emission prediction results based on urban sprawl.

[0051] In this embodiment, the establishment of a system dynamics model provides a platform to simulate and predict the future trend of urban sprawl and carbon emissions under different policy interventions. By using a panel vector autoregression model and a system dynamics model, the understanding of the causal relationship between urban expansion and carbon emissions is improved, allowing the direct and indirect effects of various urban development measures on carbon emissions to be accurately identified and quantified. Based on the identified impact relationships, a system dynamics model can be constructed to handle the complex impact relationships between different system elements, and improve the accuracy and reliability of the prediction model.

[0052] Specifically, in an implementation of this embodiment, building the system dynamics model in step S300 includes the following steps: Step S301, drawing a causal loop diagram according to the causal relationship between the diffusion factor and carbon emissions, and establishing a flow stock diagram according to the time impact relationship parameters; Step S302: construct the system dynamics model according to the causal loop diagram, the flow-stock diagram and the interaction parameters, and use historical data to test and adjust the model to obtain an adjusted system dynamics model.

[0053] In this embodiment, based on the results of the panel vector autoregression model, a system dynamics model of urban sprawl is constructed, which can simulate the dynamic relationship between urban development and carbon emissions. The specific steps include: drawing a causal loop diagram based on the results of the Granger causality test, establishing a flow-stock diagram based on the results of the impulse response analysis, establishing a system dynamics model based on the panel vector autoregression related results, and then using historical data to test and adjust the model.

[0054] As an example, in this embodiment, software (eg, Vensim software or Stella software) is used to construct and simulate a system dynamics model, and policy analysis and prediction are performed based on the model results.

[0055] Specifically, in one implementation of this embodiment, the prediction of future carbon emissions of the city in step S300 includes the following steps: Step S303, inputting the urban expansion data into the system dynamics model, and predicting and outputting the carbon emission data of the selected area under the current policy scenario through the system dynamics model; Step S304, or input different urban development policy scenarios into the system dynamics model, simulate the urban sprawl parameters under the current policy scenario through scenario simulation related methods, and input the urban sprawl parameters into the system dynamics model to simulate the potential impact of the policy on urban sprawl and carbon emissions under the current policy scenario, and predict and output the change data of carbon emissions under different urban sprawl development situations under the current policy control.

[0056] In this example, different urban development policy scenarios are designed, including but not limited to land use change, transportation system improvement, industrial zone layout adjustment, etc. Each scenario is based on a certain development policy and corresponds to specific urban sprawl performance, such as increasing the proportion of green space, improving public transportation coverage, and urban population expansion.

[0057] As an example, in this embodiment, by presetting various scenarios corresponding to urban development policies, a dedicated Python or R software package is developed to automatically process and simulate urban sprawl and carbon emission forecasts under different policy scenarios. These software packages will have built-in model parameters and algorithms, and users only need to simplify the input parameters to quickly obtain simulation results.

[0058] The scenario simulation method of this embodiment allows the present invention to explore various possible future development scenarios by setting different assumptions. This method combines the outputs of the system dynamics model and the panel vector autoregression model to form a detailed forecast of the impact of urban sprawl and policy changes on carbon emissions. The use of this method allows the impact of urban policies to be directly visualized, providing decision makers with forecast results under different scenarios. The scenario simulation method enhances the flexibility and foresight of policy making. Decision makers can evaluate the long-term impact of different policy options based on the simulation results and choose the strategy that best promotes sustainable development and carbon emission reduction.

[0059] In this embodiment, after simulating different urban development policy scenarios, by inputting urban expansion data into the system dynamics model, the model can predict the carbon emission data of the city under this scenario; or by inputting different urban development policy scenarios into the model, such as land use changes, traffic policy adjustments, etc., the performance of urban sprawl under this scenario is simulated through scenario simulation related methods, and the urban sprawl parameters under the influence of policies are input to simulate the potential impact of these policies on urban sprawl and carbon emissions, so as to predict the changes in carbon emissions under different urban sprawl development situations under policy control.

[0060] This embodiment combines urban development policies with scenario simulation to predict their impact on urban sprawl and future carbon emissions. This method allows users to evaluate the environmental impact of different development strategies through preset or customized policy variables, providing scientific decision support for urban planning and environmental policies.

[0061] This embodiment builds a complete system flow from collecting remote sensing data to predicting urban carbon emissions. This flow forms a comprehensive urban sprawl monitoring and carbon emission prediction framework by integrating data collection, data processing algorithms, statistical models and system dynamics models.

[0062] As an example, Figure 2 As shown, Figure 2 A detailed flow chart of the carbon emission prediction method based on urban sprawl in the present invention includes the following steps: Step S11, determining the range of the prediction object; Step S12, capturing remote sensing data and carbon emission data; Step S13, converting into urban sprawl indicators; The above steps S11 to S13 are the data collection and sorting process of the carbon emission prediction method based on urban sprawl. The specific process may refer to the data processing process of steps S101 to S103 in the above embodiment.

[0063] Step S14, determining the influence relationship; Step S15, determining the system dynamics model parameters and composition; Step S16, constructing a system dynamics model simulation; The above steps S14 to S16 are the model building process of the carbon emission prediction method based on urban sprawl. The specific process can refer to the system dynamics model building process of steps S201 to 202 and steps S301 to 302 in the above embodiments.

[0064] Step S17, policy scenario construction; Step S18, clarify the changes in urban sprawl under the policy scenario; Step S19, predicting carbon emissions at this time; The above steps S17 to S19 are a scenario simulation and carbon emission prediction process based on the carbon emission prediction method of urban sprawl. The specific process can refer to the carbon emission prediction process under the policy scenario of steps S304 to S305 in the above embodiment.

[0065] It is worth mentioning that, as an alternative to the above solution in this embodiment, for the data integration method, an automated system can be developed based on the above data acquisition method to regularly collect the latest data from the above data sources and automatically update the database to ensure that the data used by the model is always the latest, thereby improving the accuracy of the model prediction.

[0066] For the implementation variation of the panel vector autoregression model and the system dynamics model, the model calculation and data processing tasks can be migrated to cloud platforms, such as AWS (Amazon Web Services) or Azure (Azure), or relevant parameters can be obtained using machine learning methods, such as using genetic algorithms to obtain the optimal parameters of the model.

[0067] This embodiment achieves the following technical effects through the above technical solution: (1) This embodiment uses remote sensing images to identify the pattern and process of urban sprawl, converts them into one-dimensional data such as the urban sprawl index through mathematical formulas, and uses a panel vector autoregression model in combination with historical carbon emission data to identify the correlation and causal relationship between sprawl factors and carbon emissions. Based on the identification results, a system dynamics model of urban sprawl is constructed. By inputting the future urban sprawl under the influence of various development policies, the future carbon emissions of the city under the policy can be predicted.

[0068] (2) This embodiment improves the accuracy and response speed of urban carbon emission forecasting. By processing remote sensing monitoring data and analyzing system dynamics models in real time, it can quickly adapt to the impact of urban development or policy changes, thereby achieving more accurate and timely carbon emission forecasting, providing scientific data support for urban planning and environmental policies, and helping policymakers implement effective carbon emission reduction measures.

[0069] Exemplary Devices Based on the above embodiments, the present invention further provides a carbon emission prediction device based on urban sprawl, comprising: The urban sprawl indicator module is used to measure urban sprawl based on remote sensing satellite data of preset resolution and obtain indicators corresponding to urban sprawl; The module for the relationship between urban sprawl factors and carbon emissions is used to mine and construct the relationship between the indicators corresponding to urban sprawl and carbon emissions, and obtain the causal relationship, interaction parameters and time impact relationship parameters between urban sprawl factors and carbon emissions; The system dynamics module is used to construct a system dynamics model according to the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time impact relationship parameters, and to predict the city's future carbon emissions based on policy scenarios, and output carbon emission prediction results based on urban sprawl.

[0070] This embodiment achieves the following technical effects through the above technical solution: (1) This embodiment uses remote sensing images to identify the pattern and process of urban sprawl, converts them into one-dimensional data such as the urban sprawl index through mathematical formulas, and uses a panel vector autoregression model in combination with historical carbon emission data to identify the correlation and causal relationship between sprawl factors and carbon emissions. Based on the identification results, a system dynamics model of urban sprawl is constructed. By inputting the future urban sprawl under the influence of various development policies, the future carbon emissions of the city under the policy can be predicted.

[0071] (2) This embodiment improves the accuracy and response speed of urban carbon emission forecasting. By processing remote sensing monitoring data and analyzing system dynamics models in real time, it can quickly adapt to the impact of urban development or policy changes, thereby achieving more accurate and timely carbon emission forecasting, providing scientific data support for urban planning and environmental policies, and helping policymakers implement effective carbon emission reduction measures.

[0072] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be as follows: Figure 3 shown.

[0073] The terminal includes: a processor, a memory, an interface, a display screen and a communication module connected through a system bus; wherein the processor of the terminal is used to provide computing and control capabilities; the memory of the terminal includes a storage medium and an internal memory; the storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and the computer program in the storage medium; the interface is used to connect to external devices; the display screen is used to display corresponding information; and the communication module is used to communicate with a cloud server or other devices.

[0074] When the computer program is executed by a processor, it is used to implement the operation of the carbon emission prediction method based on urban sprawl.

[0075] It can be understood by those skilled in the art that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] In one embodiment, a terminal is provided, which includes: a processor and a memory, wherein the memory stores a carbon emission prediction program based on urban sprawl, and the carbon emission prediction program based on urban sprawl is used to implement the operations of the above carbon emission prediction method based on urban sprawl when executed by the processor.

[0077] In one embodiment, a storage medium is provided, wherein the storage medium stores a carbon emission prediction program based on urban sprawl, and when the carbon emission prediction program based on urban sprawl is executed by a processor, it is used to implement the operations of the above carbon emission prediction method based on urban sprawl.

[0078] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and volatile memory.

[0079] In summary, the present invention provides a method and device for predicting carbon emissions based on urban sprawl, including: measuring urban sprawl based on remote sensing satellite data of preset resolution to obtain indicators corresponding to urban sprawl; mining and constructing the relationship between the indicators corresponding to urban sprawl and carbon emissions to obtain the causal relationship, interaction parameters and time influence relationship parameters between the sprawl elements and carbon emissions; constructing a system dynamics model based on the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time influence relationship parameters, and predicting future carbon emissions of the city based on policy scenarios, and outputting carbon emission prediction results based on urban sprawl. The present invention not only improves the scope and field of carbon emission prediction by dynamically monitoring urban sprawl and accurately calculating future carbon emissions through remote sensing, but also reduces prediction costs because data is easy to obtain.

[0080] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A carbon emission prediction method based on urban sprawl, characterized in that: include: Urban sprawl is measured based on remote sensing satellite data with preset resolution to obtain indicators corresponding to urban sprawl; Mining and constructing the relationship between the indicators corresponding to the urban sprawl and carbon emissions, and obtaining the causal relationship, interaction parameters and time impact relationship parameters between the sprawl elements and carbon emissions; A system dynamics model is constructed according to the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time impact relationship parameters, and the future carbon emissions of the city are predicted based on policy scenarios, and the carbon emission prediction results based on urban sprawl are output.

2. The carbon emission prediction method based on urban sprawl according to claim 1, characterized in that: The urban sprawl measurement based on remote sensing satellite data with a preset resolution is performed to obtain indicators corresponding to urban sprawl, including: Select the city to be predicted and the area to which it belongs; Monitoring the selected area by a remote sensing satellite with a preset resolution and performing data preprocessing to obtain the remote sensing satellite data; The remote sensing satellite data is converted into an urban sprawl index through a preset algorithm to obtain an indicator corresponding to the urban sprawl.

3. The carbon emission prediction method based on urban sprawl according to claim 2 is characterized in that: The remote sensing satellite data is obtained by monitoring the selected area with a preset resolution and performing data preprocessing, including: Acquiring image data of urban expansion corresponding to the selected area using the remote sensing satellite of the preset resolution; The image data are corrected, classified and analyzed using automated image processing software, and the processed image data are combined with population distribution data and nighttime light data to obtain the remote sensing satellite data.

4. The carbon emission prediction method based on urban sprawl according to claim 2, characterized in that: The converting the remote sensing satellite data into an urban sprawl index by a preset algorithm to obtain an index corresponding to the urban sprawl includes: The basic measurement unit is determined according to the accuracy of the remote sensing satellite data, and the proportion of the sprawl elements of the measurement unit in the city is calculated using the following formula: ； in, Indicates the proportion of the measured element in space, represents the spatial weight in the form of , α and β are parameters, α>0; The urban sprawl index is calculated using the following formula to obtain the sprawl expansion of specific sprawl elements in each city: ； in, represents the center point of the city, and n represents all measurement units within the city.

5. The carbon emission prediction method based on urban sprawl according to claim 1, characterized in that: The mining and construction of the relationship between the indicators corresponding to the urban sprawl and the carbon emissions, obtaining the causal relationship, interaction parameters and time impact relationship parameters between the sprawl elements and the carbon emissions, includes: Based on the indicators corresponding to the urban sprawl, the panel vector autoregression model is used to identify the impact of multi-dimensional sprawl on carbon emissions, and the causal relationship of each dimension is established according to the Granger causality test method to obtain the causal relationship between the sprawl factors and carbon emissions; The impulse response analysis method and the Akaike information criterion are used to establish the time lag and the persistence of the influence, and the interaction parameters and the time influence relationship parameters are obtained.

6. The carbon emission prediction method based on urban sprawl according to claim 1, characterized in that: The system dynamics model is constructed according to the causal relationship between the spreading elements and carbon emissions, the interaction parameters and the time impact relationship parameters, including: Draw a causal loop diagram based on the causal relationship between the spreading factors and carbon emissions, and establish a flow-stock diagram based on the time impact relationship parameters; The system dynamics model is constructed according to the causal loop diagram, the flow-stock diagram and the interaction parameters, and the model is tested and adjusted using historical data to obtain an adjusted system dynamics model.

7. The carbon emission prediction method based on urban sprawl according to claim 1, characterized in that: Based on the policy scenarios, the city's future carbon emissions are predicted, and the carbon emissions prediction results based on urban sprawl are output, including: Inputting the urban expansion data into the system dynamics model, and predicting and outputting the carbon emission data of the selected area under the current policy scenario through the system dynamics model; Or different urban development policy scenarios are input into the system dynamics model, and the urban sprawl parameters under the current policy scenario are simulated through scenario simulation related methods. The urban sprawl parameters are input into the system dynamics model to simulate the potential impact of the policy on urban sprawl and carbon emissions under the current policy scenario, and the change data of carbon emissions under different urban sprawl development situations under the current policy control are predicted and output.

8. A carbon emission prediction device based on urban sprawl, characterized in that: include: The urban sprawl indicator module is used to measure urban sprawl based on remote sensing satellite data of preset resolution and obtain indicators corresponding to urban sprawl; The module for the relationship between urban sprawl factors and carbon emissions is used to mine and construct the relationship between the indicators corresponding to urban sprawl and carbon emissions, and obtain the causal relationship, interaction parameters and time impact relationship parameters between urban sprawl factors and carbon emissions; The system dynamics module is used to construct a system dynamics model according to the causal relationship between the sprawl elements and carbon emissions, the interaction parameters and the time impact relationship parameters, and to predict the city's future carbon emissions based on policy scenarios, and output carbon emission prediction results based on urban sprawl.

9. A terminal, characterized in that: include: A processor and a memory, wherein the memory stores a carbon emission prediction program based on urban sprawl, and when the carbon emission prediction program based on urban sprawl is executed by the processor, it is used to implement the operation of the carbon emission prediction method based on urban sprawl as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a carbon emission prediction program based on urban sprawl, and when the carbon emission prediction program based on urban sprawl is executed by a processor, it is used to implement the operation of the carbon emission prediction method based on urban sprawl as claimed in any one of claims 1 to 7.

Images