Carbon emission prediction method and device based on urban system model, electronic equipment and storage medium

Abstract

The invention provides a carbon emission prediction method and device based on an urban system model, electronic equipment and a storage medium. The method comprises the steps that a target grid map of a target area and historical data of the target area are acquired; performing evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain target land utilization distribution data and target traffic flow distribution data of the target area; determining carbon sink prediction data, industrial carbon emission prediction data and building carbon emission prediction data of each grid unit according to the target land utilization distribution data and the target grid map; determining traffic carbon emission prediction data of each grid unit according to the target traffic flow distribution data and the target grid map; and calculating carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data and the traffic carbon emission prediction data of each grid unit. According to the invention, the accuracy and reliability of urban carbon emission prediction can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of carbon emissions, and in particular, to a carbon emission prediction method and device, an electronic device, and a storage medium based on an urban system model. Background Art

[0002] As the main gathering place of population and economic activities, the carbon emissions of cities have a significant impact on the total global greenhouse gas emissions. Accurately simulating and predicting urban carbon emissions is crucial for formulating effective emission reduction strategies and achieving low-carbon development goals. Urban carbon emissions are affected by various factors, including land use patterns, population distribution, transportation, industrial structure, energy consumption, etc. These factors interact and influence each other, constituting a complex urban system.

[0003] In related technologies, existing urban carbon emission prediction technologies often have difficulty fully considering the complexity and dynamic changes of the urban system, lack in-depth analysis of the micro-mechanisms of carbon emissions, and often rely on artificially set parameters during prediction, resulting in low accuracy and reliability of prediction results. Summary of the Invention

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a carbon emission prediction method and device, an electronic device, and a storage medium based on an urban system model, which can improve the accuracy and reliability of urban carbon emission prediction.

[0005] To achieve the above object, a first aspect of the embodiments of the present application proposes a carbon emission prediction method based on an urban system model, the method including: Obtain a target grid map of a target area and historical data of the target area; Perform evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain target land use distribution data and target traffic flow distribution data of the target area; According to the target land use distribution data and the target grid map, determine carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid unit; According to the target traffic flow distribution data and the target grid map, determine traffic carbon emission prediction data corresponding to each grid unit; Calculate the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data, and the traffic carbon emission prediction data corresponding to each grid unit.

[0006] In some embodiments, the target land use distribution data includes carbon sink land use distribution data, industrial land use distribution data, and construction land use distribution data. Determining the carbon sink prediction data, industrial carbon emission prediction data, and construction carbon emission prediction data corresponding to each grid cell according to the target land use distribution data and the target grid map includes: Determine the carbon sink land area, industrial land area, and construction land area of each grid cell in the target grid map according to the carbon sink land use distribution data, the industrial land use distribution data, and the construction land use distribution data; For each grid cell, calculate the carbon sink prediction data in the grid cell according to the carbon sink land area and a preset carbon absorption factor; For each grid cell, calculate the industrial carbon emission prediction data in the grid cell according to the industrial land area and a preset industrial carbon emission factor; For each grid cell, calculate the construction carbon emission prediction data in the grid cell according to the construction land area and a preset construction carbon emission factor.

[0007] In some embodiments, for each grid cell, calculating the industrial carbon emission prediction data in the grid cell according to the industrial land area and a preset industrial carbon emission factor includes: Obtain the historical traditional manufacturing proportion and historical advanced manufacturing proportion corresponding to the grid cell; Calculate the industrial emission intensity correction coefficient of the grid cell according to the historical traditional manufacturing proportion, the historical advanced manufacturing proportion, the preset city-wide historical average traditional manufacturing proportion, the preset city-wide historical average advanced manufacturing proportion, the preset traditional manufacturing emission intensity, and the preset advanced manufacturing emission intensity; Multiply the industrial land area, the industrial emission intensity correction coefficient, and the industrial carbon emission factor corresponding to the grid cell to obtain the industrial carbon emission prediction data of the grid cell.

[0008] In some embodiments, determining the traffic carbon emission prediction data corresponding to each grid cell according to the target traffic flow distribution data and the target grid map includes: Extract the traffic flow data of each traffic section under different traffic modes and different time periods from the target traffic flow distribution data; For each traffic section, each traffic mode, and each time period, calculate the total vehicle driving mileage in combination with the traffic section length and the preset average number of passengers carried by the traffic mode; Obtain the proportion data of vehicles with different fuel types under different transportation modes, and the carbon emission factor per unit mileage corresponding to the transportation mode, the fuel type, and the running speed; Multiply the total vehicle mileage, the vehicle proportion data, and the carbon emission factor per unit mileage, and accumulate for all fuel types of all transportation modes to calculate the transportation carbon emissions of each transportation section under the transportation mode and the time period; Accumulate the transportation carbon emissions of each transportation section in all time periods to obtain the total transportation carbon emissions of each transportation section; According to the spatial position relationship of the transportation section in the target grid map, allocate the total transportation carbon emissions of each transportation section to one or more grid cells corresponding to it to obtain the transportation carbon emission prediction data corresponding to each grid cell.

[0009] In some embodiments, for each grid cell, calculating the building carbon emission prediction data in the grid cell according to the building land area and the preset building carbon emission factor includes: According to the building land distribution data, determine the land areas corresponding to residential building land, commercial building land, and public service building land within the grid cell respectively; Obtain the building carbon emission factor per unit area for residential building land, commercial building land, and public service building land respectively; For each type of building land, multiply its land area within the grid cell, the preset floor area ratio, and the corresponding building carbon emission factor per unit area to obtain the building carbon emissions of this type of building in the grid cell; Sum up the building carbon emissions of all types of buildings within the grid cell to obtain the building carbon emission prediction data corresponding to the grid cell.

[0010] In some embodiments, calculating the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data, and the transportation carbon emission prediction data corresponding to each grid cell includes: Sum up the industrial carbon emission prediction data of all grid cells within the target area to obtain the total industrial carbon emission prediction data of the target area; Sum up the building carbon emission prediction data of all grid cells within the target area to obtain the total building carbon emission prediction data of the target area; Sum up the transportation carbon emission prediction data of all grid cells within the target area to obtain the total transportation carbon emission prediction data of the target area; Add the total industrial carbon emission prediction data, the total building carbon emission prediction data, and the total transportation carbon emission prediction data of the target area to obtain the total carbon emission prediction data of the target area; Sum up the carbon sink prediction data of all grid cells in the target area to obtain the total carbon sink prediction data of the target area; Subtract the total carbon sink prediction data from the total carbon emission prediction data of the target area to obtain the net carbon emission prediction data of the target area in the target prediction year.

[0011] In some embodiments, the urban system model includes a land prediction sub-module, a population and employment prediction sub-module, and a transportation prediction sub-module. Evolving and predicting the historical data of the target area through the pre-constructed urban system model to obtain the target land use distribution data and the target traffic flow distribution data of the target area, including: Through the land prediction sub-module, predict based on the historical land distribution data, historical mobile phone signaling data, historical housing price data, historical traffic data, and historical number of job positions in the historical data of the target area to obtain the target land use distribution data of the target area; Through the population and employment prediction sub-module, predict based on the target land use distribution data, the historical mobile phone signaling data, the historical housing price data, historical population quantity, historical number of job positions, historical point of interest data, historical job-housing relationship coefficient, and historical traffic network density to obtain the population spatial distribution data and the job position spatial distribution data of the target area; Through the transportation prediction sub-module, predict based on the target land use distribution data, the population spatial distribution data, the job position spatial distribution data, the historical mobile phone signaling data, the historical housing price data, and historical traffic data to obtain the target traffic flow distribution data of the target area.

[0012] In a second aspect, an embodiment of the present application provides a carbon emission prediction device based on an urban system model, including: An acquisition module that acquires a target grid map of the target area and historical data of the target area; A prediction module that evolves and predicts the historical data of the target area through a pre-constructed urban system model to obtain the target land use distribution data and the target traffic flow distribution data of the target area; A first determination module that determines the carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid cell according to the target land use distribution data and the target grid map; A second determination module, which determines traffic carbon emission prediction data corresponding to each grid unit according to the target traffic flow distribution data and the target grid map; A calculation module, which calculates the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data and the traffic carbon emission prediction data corresponding to each grid unit.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the carbon emission prediction method based on the urban system model according to any one of the embodiments in the first aspect of the present application.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the storage medium stores a program, and when the program is executed by a processor, it implements the carbon emission prediction method based on the urban system model according to any one of the embodiments in the first aspect of the present application.

[0015] The carbon emission prediction method based on the urban system model proposed by the embodiment of the present application includes: obtaining a target grid map of a target area and historical data of the target area; performing evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain target land use distribution data and target traffic flow distribution data of the target area; determining carbon sink prediction data, industrial carbon emission prediction data and building carbon emission prediction data corresponding to each grid unit according to the target land use distribution data and the target grid map; determining traffic carbon emission prediction data corresponding to each grid unit according to the target traffic flow distribution data and the target grid map; calculating the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data and the traffic carbon emission prediction data corresponding to each grid unit.

[0016] Regarding the problems existing in the existing urban carbon emission prediction technologies in the background art, the carbon emission prediction method based on the urban system model provided by the embodiments of the present application first performs evolution prediction by adopting a pre-constructed urban system model and combining historical data of the target area, deeply simulating the complex interactions and dynamic evolution processes among key factors such as internal land use and traffic flow in the city, overcoming the defect of insufficient capture of system dynamics by traditional methods, and reducing the dependence on subjectively set parameters. Secondly, after predicting the future target land use distribution data and target traffic flow distribution data, on a fine grid scale, the carbon sink, industrial carbon emissions, and building carbon emissions are determined based on land use respectively, and traffic carbon emissions are determined based on traffic flow. This classified and spatially explicit calculation method can more deeply analyze the microscopic mechanism of carbon emission generation, and implement the macroscopic urban development prediction to specific spatial units and emission / absorption categories; finally, by comprehensively calculating the various carbon emission prediction data and carbon sink prediction data of each grid cell through weighted or summary calculation, the overall carbon emission prediction result of the target area is obtained, which can better reflect the real result of the operation of the urban system compared with macroscopic statistics. The above technical synergistic effects enable this method to learn the internal development law from the complex operation history of the urban system, and based on the dynamic and spatial prediction of future land use and traffic conditions, accurately account for carbon emissions and carbon sink contributions from different sources. Therefore, the present application can improve the accuracy and reliability of carbon emission prediction.

[0017] Other features and advantages of the present application will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present application. The objectives and other advantages of the present application can be realized and obtained through the structures specifically pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic flowchart of the carbon emission prediction method based on the urban system model provided by an embodiment of the present application; Figure 2 is a schematic flowchart of the carbon emission prediction method based on the urban system model provided by another embodiment of the present application; Figure 3 is a schematic flowchart of the carbon emission prediction method based on the urban system model provided by another embodiment of the present application; Figure 4 is a schematic flowchart of the carbon emission prediction method based on the urban system model provided by another embodiment of the present application; Figure 5 is a schematic flowchart of the carbon emission prediction method based on the urban system model provided by another embodiment of the present application; Figure 6It is a schematic flowchart of a carbon emission prediction method based on an urban system model provided by another embodiment of the present application; Figure 7 It is a schematic flowchart of a carbon emission prediction method based on an urban system model provided by another embodiment of the present application; Figure 8 It is a schematic diagram of a carbon emission prediction device based on an urban system model provided by an embodiment of the present application; Figure 9 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0020] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order from the module division in the device or the order in the flowchart. Terms such as "first" and "second" in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] As the main gathering place of population and economic activities, the carbon emissions of cities have a significant impact on the total global greenhouse gas emissions. Accurately simulating and predicting urban carbon emissions is crucial for formulating effective emission reduction strategies and achieving low-carbon development goals. However, a city is an extremely complex giant system. The total carbon emissions are not a simple linear accumulation, but are determined by a variety of complex influencing factors. These factors widely cover land use patterns, the spatial distribution and density of the population, the travel behavior of residents, the industrial structure, and the overall energy consumption structure and efficiency. These elements do not exist in isolation, but interact and influence each other through complex feedback loops, jointly driving the dynamic evolution of the urban system and ultimately determining the spatio-temporal distribution characteristics of carbon emissions.

[0023] In related technologies, existing urban carbon emission prediction technologies often have difficulty fully considering the complexity and dynamic changes of the urban system, lack in-depth analysis of the micro-mechanisms of carbon emissions, and often rely on artificially set parameters during prediction, resulting in low accuracy and reliability of the prediction results.

[0024] A common technique is the carbon emission prediction technique based on regression analysis models. Such methods usually first collect or calculate the overall carbon emission data of a city over the past years, and then select a series of macroeconomic and social indicators considered to be related to carbon emissions as key regression variables, such as gross domestic product (GDP), population size, fossil energy consumption, passenger and freight turnover, energy consumption structure, industrial structure, etc. By analyzing historical data and using statistical techniques such as the STIRPAT model, LEAP model, ridge regression or Lasso regression, a mathematical regression equation between these macro variables and the total carbon emissions is established. In the prediction stage, researchers need to set or assume the values of these regression variables in future years, and then substitute these set values into the established regression model to estimate the total future carbon emissions.

[0025] Another commonly used technique is carbon emission prediction based on system dynamics models. The system dynamics method is a decision-making process that considers the mutual feedback of multiple factors. First, calculate or obtain the carbon emissions in historical years. Secondly, establish a causal loop diagram, which is an important tool to reflect the internal feedback structure of the system. By sorting out the relationships between the subsystems of the carbon emission system, construct the internal feedback relationship of the carbon emission system and draw the causal loop diagram of the carbon emission system. Generally, the subsystems related to carbon emissions include economy, population, land, energy, etc. Next, based on the causal loop diagram, construct the stock-flow diagram of the carbon emission system, that is, further construct the feedback relationships between the key models of each subsystem, including level variables, rate variables and auxiliary variables. The main variables include GDP growth rate, population growth rate, urbanization rate, industrial structure, energy consumption intensity, energy structure, land use structure, etc. After that, according to the quantitative relationships between the variables in the model, determine the equations in the carbon emission system dynamics model. Finally, set the values of each regression variable in the prediction year by oneself, substitute them into the model, and obtain the carbon emissions in the prediction year.

[0026] Although the above methods can provide certain predictive references in specific scenarios, they generally have the following problems: Regression-based models essentially seek statistical correlations in historical data, often simplifying or even ignoring the deep-seated and non-linear interactions and feedback mechanisms among various elements within the city. It is difficult for them to capture the complex impacts brought about by urban structure evolution. Moreover, most of these two methods analyze and predict at the macro level of the city or region, lacking a refined spatial analysis of carbon emissions. They cannot clearly reveal how specific land use types or specific traffic activities contribute to carbon emissions, resulting in a low spatial resolution of the prediction results. Finally, whether the regression model predicts the values of future independent variables or the system dynamics model sets exogenous parameters, significant subjectivity and uncertainty are introduced. These settings are often based on simple trend extrapolation or expert judgment, and their accuracy directly affects the reliability of the final prediction results.

[0027] Based on this, the embodiments of the present application provide a carbon emission prediction method, device, electronic device, and storage medium based on an urban system model, which can improve the accuracy and reliability of carbon emission prediction.

[0028] The carbon emission prediction method, device, electronic device, and storage medium based on an urban system model provided by the embodiments of the present application are specifically described through the following embodiments. First, the carbon emission prediction method based on an urban system model in the embodiments of the present application is described.

[0029] The present application can be used in many general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0030] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0031] Figure 1 FIG. is an alternative flowchart of the carbon emission prediction method based on the urban system model provided by the embodiments of the present application. Figure 1 The method in may include but is not limited to steps 101 to 105.

[0032] Step 101, obtain the target grid map of the target area and the historical data of the target area.

[0033] Step 102, perform evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain the target land use distribution data and the target traffic flow distribution data of the target area.

[0034] Step 103, determine the carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid unit according to the target land use distribution data and the target grid map.

[0035] Step 104, determine the traffic carbon emission prediction data corresponding to each grid unit according to the target traffic flow distribution data and the target grid map.

[0036] Step 105, calculate the carbon emission prediction data of the target area according to the carbon sink prediction data, industrial carbon emission prediction data, building carbon emission prediction data, and traffic carbon emission prediction data corresponding to each grid unit.

[0037] Steps 101 to 105 illustrated in the embodiments of the present application first conduct an evolution prediction by adopting a pre-constructed urban system model and combining it with the historical data of the target area, deeply simulating the complex interactions and dynamic evolution processes among key factors such as internal land use and traffic flow in the city, overcoming the defect of insufficient capture of system dynamics in traditional methods and reducing the dependence on subjectively set parameters. Secondly, after predicting the future target land use distribution data and target traffic flow distribution data, on a fine grid scale, carbon sinks, industrial carbon emissions, and building carbon emissions are determined based on land use respectively, and traffic carbon emissions are determined based on traffic flow. This categorized and spatially explicit calculation method can more deeply analyze the micro-mechanism of carbon emission generation, and implement the macroscopic urban development prediction to specific spatial units and emission / absorption categories; finally, by comprehensively calculating the various carbon emission prediction data and carbon sink prediction data of each grid unit, weighted or aggregated calculation is carried out to obtain the overall carbon emission prediction result of the target area, which can better reflect the real result of the operation of the urban system compared with macroscopic statistics. The above technical synergistic effects enable this method to learn the internal development law from the complex operation history of the urban system, and based on the dynamic and spatialized prediction of future land use and traffic conditions, accurately account for carbon emissions and carbon sink contributions from different sources. Therefore, the present application can improve the accuracy and reliability of carbon emission prediction.

[0038] In step 101 of some embodiments, the "target area" refers to a specific geographical range for which carbon emission prediction is required, such as a city or a district or county. The "target grid map" refers to an electronic map that discretizes the target area spatially into a series of regular grid cells (i.e., grids), each grid cell having a unique identifier and geographical coordinate information, and this grid map provides a unified geographical reference framework for subsequent spatialized prediction and calculation. The obtained target grid map can have a preset resolution, such as 1 km × 1 km or a finer scale. The "target area historical data" covers various time series data reflecting the development status of the area over a past period (e.g., the past 10 years or 20 years), which are the basis for driving the evolution of the urban system model and may include, but are not limited to, historical land use / cover distribution data, historical population and employment spatial distribution data, historical traffic network and flow data, historical economic indicator data (such as GDP, industrial structure), historical energy consumption data, and other auxiliary data (such as housing prices, point of interest distribution, mobile phone signaling data, etc.).

[0039] In step 102 of some embodiments, the "pre-built urban system model" refers to an urban system model built before prediction, which aims to simulate the interactions, feedback mechanisms, and dynamic evolution laws over time among various key subsystems within the city (such as land use, population, employment, transportation, etc.). This model can, based on the historical data obtained in step 101, through its internal mathematical logic and algorithms (including but not limited to various technologies such as cellular automata, discrete choice models, traffic assignment models, etc.), simulate the evolution process from the historical state to the future state. The results of the evolution prediction are two key future state data: the "target land use distribution data", which describes the expected land use type (such as industrial land, commercial land, residential land, green space, etc.) or the area proportion of various land uses in each grid cell within the target area in the target prediction year; and the "target traffic flow distribution data", which describes the key traffic characteristics such as the expected traffic flow and operating speed on each traffic section (which can be further associated with grid cells) within the target area in the target prediction year, and can also distinguish different traffic modes and different time periods. These two output data constitute the spatial basis for calculating various carbon emissions / carbon sinks in the subsequent process.

[0040] Please refer to Figure 2 , in some embodiments, the urban system model includes a land prediction sub-module, a population and employment prediction sub-module, and a traffic prediction sub-module. Step 102 may include, but is not limited to, steps 201 to 203.

[0041] Step 201, through the land prediction sub-module, based on the historical land distribution data, historical mobile phone signaling data, historical housing price data, historical traffic data, and historical number of job positions in the historical data of the target area, perform prediction to obtain the target land use distribution data of the target area.

[0042] Step 202, through the population and employment prediction sub-module, based on the target land use distribution data, historical mobile phone signaling data, historical housing price data, historical population quantity, historical number of job positions, historical point of interest data, historical commuting relationship coefficient, and historical traffic network density, perform prediction to obtain the population spatial distribution data and employment position spatial distribution data of the target area.

[0043] Step 203, through the traffic prediction sub-module, based on the target land use distribution data, population spatial distribution data, employment position spatial distribution data, historical mobile phone signaling data, historical housing price data, and historical traffic data, perform prediction to obtain the target traffic flow distribution data of the target area.

[0044] In step 201 of some embodiments, the land prediction sub-module may specifically perform the following operations: First, based on the Markov model, using the state transition probability matrix and the initial state distribution of historical land use types, predict the overall characteristics of urban land use in the target year; Next, in order to determine the conversion potential of micro spatial units, use historical mobile phone signaling data, historical housing price data, and historical traffic data to construct a variable system that includes variables such as housing prices in the previous period, location accessibility calculated from traffic data, land use mixing degree, the number of job positions in the region, and the distance from traffic stations; Then, a Logistic regression model can be used to determine the influence weights of these spatial variables on the conversion of land use types, and further calculate the conversion probability of each land use type in each grid cell; Finally, apply the Cellular Automata (CA) algorithm, based on the previously predicted overall land use characteristics and the calculated micro land use type conversion rules, simulate and determine the land use type of each grid cell (the basic spatial unit can be set as a 250-meter grid) in the target prediction year, and finally summarize to form the target land use distribution data.

[0045] In step 202 of some embodiments, the population and employment prediction sub-module may specifically perform the following operations: First, use historical mobile phone signaling data to obtain the initial population, employment distribution, and migration situation of the city in the base year; Second, for the micro behavior of the residential and employment migration selection of the existing urban population, establish and solve a discrete choice model. The input variables of this model may include, for example, the population in the previous period, the number of job positions, the POI density calculated from historical Point of Interest (POI) data, historical housing price data, historical job-housing relationship coefficients, and the location accessibility calculated by the land prediction sub-module, so as to obtain the evolution result of the relocation behavior of the existing population; Furthermore, considering the new population and employment brought by the inter-city population migration and the natural growth of the urban population and employment total, the spatial distribution can be carried out by calculating the residential and employment attraction coefficients of each spatial unit (for example, in the form of the product of the powers of the parameters of the Cobb-Douglas function, and its influencing factors may include variables such as housing prices, job-housing relationship coefficients, historical traffic network density, and commercial land area); Finally, summarize the evolution result of the existing population and the spatial distribution result of the new population and employment to obtain the population spatial distribution data and employment position spatial distribution data of the target area at a 1-kilometer grid scale, for example.

[0046] In step 203 of some embodiments, the traffic prediction sub-module may specifically perform the following operations: First, combining the land use mixing degree and location accessibility from the land prediction sub-module, the job-housing relationship coefficient from the population and employment prediction sub-module, and variables such as historical housing price data, road network density, and the number of bus stops, predict the resident travel generation rate of each region; Next, the travel chain characteristics of different populations extracted from long-term historical mobile phone signaling data can be used to identify the scale and distribution of trips for different purposes in each spatial unit, and based on the attributes such as land use of the spatial unit, predict its traffic generation volume, attraction volume, and traffic distribution volume between spatial units (OD matrix); Then, calculate the generalized travel cost under various travel paths and traffic mode selections, and the MNL model can be used to solve the travel path and travel mode selection of residents; Finally, based on the traffic assignment principle such as the user equilibrium method, allocate the predicted traffic flow to each section of the traffic network. During this process, the calculation of the traffic distribution volume may be based on spatial units of a 1-kilometer grid, and the final flow assignment is implemented on the basic unit of the section, thereby generating target traffic flow distribution data including characteristics such as the flow and speed of each section.

[0047] Through steps 201 to 203, the embodiments of the present application use a land prediction sub-module (using models such as Markov, Logistic regression, and cellular automata), a population and employment prediction sub-module (using models such as discrete choice models and Cobb-Douglas attraction allocation), and a traffic prediction sub-module (using models such as travel generation prediction, OD estimation, MNL model, and user equilibrium allocation), and use historical land distribution data, historical mobile phone signaling data, historical housing price data, historical traffic data, historical number of employment positions, historical population quantity, historical number of employment positions, historical point of interest data, historical job-housing relationship coefficient, historical traffic line network density, and specific technical features such as the intermediate generated location accessibility, land use mixing degree, and travel chain as inputs or intermediate variables to simulate the interaction and dynamic feedback mechanism between urban land use, population and employment distribution, and traffic flow. This modeling method that combines macroscopic constraints (such as the overall land use characteristics predicted by Markov) and microscopic simulation (such as the neighborhood interaction of cellular automata) and uses different spatial resolutions (such as 250 meters, 1 kilometer, and section) at different stages can capture the microscopic mechanism of urban operation, thereby generating more accurate, reliable, and high-spatial-resolution target land use distribution data, population spatial distribution data, employment position spatial distribution data, and target traffic flow distribution data. These intermediate prediction results provide a data basis for the carbon emission and carbon sink accounting performed in the subsequent steps (steps 103 and 104), improving the accuracy and reliability of the target area's carbon emission prediction data (step 105) finally calculated in the present application, and effectively overcoming the deficiencies of the model in the background technology, such as insufficient reflection of system complexity, lack of microscopic mechanisms and spatial details, and reliance on subjective parameter settings.

[0048] In step 103 of some embodiments, for "each grid cell" in the target grid map, it is necessary to analyze the predicted land use composition in the "target land use distribution data". Based on this composition information, combined with preset carbon absorption parameters or carbon emission parameters, calculate the carbon sink contribution of the grid cell and the carbon emissions from industrial activities or buildings respectively. For example, the "carbon sink prediction data" is usually calculated by multiplying the area of ecological land such as green land, forest land, and water bodies predicted in the grid by the corresponding carbon absorption factor per unit area (i.e., "carbon sink", which refers to the ability of natural ecosystems to absorb carbon dioxide). The "industrial carbon emission prediction data" is calculated based on the predicted industrial land area in the grid and may be combined with a preset industrial emission factor per unit area. The "building carbon emission prediction data" is calculated based on the area of building land such as residential, commercial, and public service buildings predicted in the grid and may be combined with the corresponding energy consumption / carbon emission factor per unit area or per unit building area. Through this step, the macroscopic land use prediction results are decomposed and implemented to the carbon emission contributions of each microscopic grid cell.

[0049] Please refer to Figure 3 , in some embodiments, the target land use distribution data includes carbon sink land distribution data, industrial land distribution data, and building land distribution data. Step 103 may include, but is not limited to, steps 301 to 304.

[0050] Step 301, based on the carbon sink land distribution data, industrial land distribution data, and building land distribution data, determine the carbon sink land area, industrial land area, and building land area of each grid cell in the target grid map.

[0051] Step 302, for each grid cell, calculate the carbon sink prediction data in the grid cell according to the carbon sink land area and the preset carbon absorption factor.

[0052] Step 303, for each grid cell, calculate the industrial carbon emission prediction data in the grid cell according to the industrial land area and the preset industrial carbon emission factor.

[0053] Step 304, for each grid cell, calculate the building carbon emission prediction data in the grid cell according to the building land area and the preset building carbon emission factor.

[0054] In step 301 of some embodiments, the spatially distributed information of different types of land use obtained by prediction is quantified onto the basic spatial unit of the target grid map, i.e., the "grid cell". Each grid cell is analyzed, and based on the input carbon sink land use distribution data, industrial land use distribution data, and construction land use distribution data, the area values of the predicted carbon sink land, industrial land, and construction land contained within the specific grid cell are calculated respectively. This process realizes the conversion from the land use distribution map to the land area composition at the grid cell level.

[0055] In step 302 of some embodiments, the "carbon absorption factor" is a preset parameter, representing the ability or rate of carbon sink land (such as forest land, grassland, etc.) per unit area to absorb carbon dioxide within a certain period of time. By multiplying the area of the carbon sink land within the grid cell by the corresponding carbon absorption factor, the carbon sink amount expected to be generated by the grid cell in the target prediction year can be obtained, i.e., the carbon sink prediction data of the cell.

[0056] In some embodiments, step 302 may include the measurement of various specific carbon sink types such as cultivated land, grassland, forest land, wetland, garden land, and urban green space. After determining the predicted land use areas of these specific carbon sink types within each grid cell, the following formula can be applied to calculate the total carbon sink amount of the grid cell (i.e., the carbon sink prediction data of the cell):

[0057] Where, represents the predicted data of the total carbon sink amount of the grid cell (denoted as region j in the formula); represents the predicted land use area of the i-th carbon sink type (i = 1 to 6, corresponding to cultivated land, grassland, forest land, wetland, garden land, and urban green space respectively) within the grid cell, and this area is extracted from the carbon sink land use distribution data based on step 301; represents the carbon absorption factor per unit area of the i-th carbon sink land, which is a preset parameter and can be obtained from literature or other authoritative sources.

[0058] In step 303 of some embodiments, the industrial carbon emission factor is also a preset parameter, usually representing the average amount of carbon dioxide emissions generated per unit area of industrial land within a certain period, and this factor may be obtained based on historical statistical data and industry average levels. By multiplying the area of the industrial land within the grid cell by the corresponding industrial carbon emission factor, the industrial source carbon emissions expected to be generated by the grid cell in the target prediction year can be calculated, i.e., the industrial carbon emission prediction data of the grid cell.

[0059] Please refer to Figure 4 , in some embodiments, step 303 may include but is not limited to steps 401 to 403.

[0060] Step 401: Obtain the historical proportion of traditional manufacturing and the historical proportion of advanced manufacturing corresponding to the grid cell.

[0061] Step 402: Calculate the industrial emission intensity correction coefficient of the grid cell based on the historical proportion of traditional manufacturing, the historical proportion of advanced manufacturing, the preset city-wide historical average proportion of traditional manufacturing, the preset city-wide historical average proportion of advanced manufacturing, the preset emission intensity of traditional manufacturing, and the preset emission intensity of advanced manufacturing.

[0062] Step 403: Multiply the industrial land area, the industrial emission intensity correction coefficient, and the industrial carbon emission factor corresponding to the grid cell to obtain the predicted industrial carbon emission data of the grid cell.

[0063] In step 401 of some embodiments, the "historical proportion of traditional manufacturing" and the "historical proportion of advanced manufacturing" are key indicators for measuring the proportion of two types of industrial activities with different environmental impact intensities in the region. For example, the average proportion of traditional manufacturing in region j in the past three years or the average proportion of advanced manufacturing in region j in the past three years. These data can be obtained through channels such as analyzing historical economic census data, enterprise registration information, or industrial statistical reports of specific regions, and associated with each grid cell of the target grid map.

[0064] In step 402 of some embodiments, according to the historical proportion of traditional manufacturing obtained in step 401 , the historical proportion of advanced manufacturing , the preset city-wide historical average proportion of traditional manufacturing , the preset city-wide historical average proportion of advanced manufacturing , the preset emission intensity of traditional manufacturing (the emission intensity per unit output value or per unit area that can be obtained from the literature), and the preset emission intensity of advanced manufacturing (corresponding to , which can also be obtained from the literature), calculate the industrial emission intensity correction coefficient of the grid cell. The core of this step is to quantify the difference in the industrial structure of this grid cell relative to the city-wide average level and adjust its emission intensity accordingly. The "industrial emission intensity correction coefficient , that is, the emission intensity correction coefficient of region j in the target prediction year, can be calculated by the following formula:

[0065] This coefficient reflects the ratio of the average emission intensity of this grid cell (region j) relative to the city-wide average level due to its specific composition of traditional and advanced manufacturing.

[0066] In step 403 of some embodiments, the method multiplies the industrial land area corresponding to the grid cell , the industrial emission intensity correction factor calculated in step 402 , and the preset industrial carbon emission factor to obtain the industrial carbon emission prediction data for the grid cell (region j) .

[0067] Through steps 401 to 403, when calculating the industrial carbon emission prediction data in the embodiments of the present application, the consideration of the change in the industrial structure is introduced. First, through step 401, the specific historical proportion of traditional manufacturing and the historical proportion of advanced manufacturing in each grid cell are obtained. Then, in step 402, combined with the preset city-wide average proportion and the emission intensity of each type of manufacturing, an industrial emission intensity correction factor that can reflect the particularity of the industrial structure of the grid cell is calculated. Finally, in step 403, this correction factor is used to adjust the preliminary estimation based on the industrial land area and the preset industrial carbon emission factor. This approach makes the calculation of industrial carbon emissions no longer rely on a single, averaged emission factor, but can be differentially adjusted according to the actual industrial composition of each region (especially the ratio of high-emission traditional manufacturing to relatively low-emission advanced manufacturing). Therefore, by introducing an industrial emission calculation method based on industrial structure correction, the embodiments of the present application can improve the accuracy of industrial carbon emission prediction data and the ability to reflect the actual situation, thereby enhancing the accuracy and reliability of the overall carbon emission prediction.

[0068] In step 304 of some embodiments, the "building carbon emission factor" is also a preset parameter, representing the average carbon emissions generated per unit area of building land (or based on more refined information such as building area, type, energy consumption standard, etc.) within a certain period. By multiplying the building land area within the grid cell by the corresponding building carbon emission factor, the building source carbon emissions expected to be generated by the grid cell in the target prediction year can be calculated, that is, the building carbon emission prediction data for the cell.

[0069] Please refer to Figure 5 , in some embodiments, step 304 may include, but is not limited to, steps 501 to 504.

[0070] Step 501, according to the building land distribution data, determine the corresponding land areas of residential building land, commercial building land, and public service building land within the grid cell.

[0071] Step 502, respectively obtain the unit area building carbon emission factors for residential building land, commercial building land, and public service building land.

[0072] Step 503: For each type of building land, multiply the land area within the grid cell, the preset floor area ratio, and the corresponding carbon emission factor per unit area of the building to obtain the building carbon emissions of this type of building in the grid cell.

[0073] Step 504: Sum up the building carbon emissions of all types of buildings within the grid cell to obtain the predicted building carbon emission data corresponding to the grid cell.

[0074] In step 501 of some embodiments, based on more detailed building land distribution data, the total building land area determined in step 301 is further refined and decomposed into the areas occupied by different functional types of building land within this grid cell, which may specifically include residential, commercial, and public services. That is, for a specific grid cell (area j), determine the land area of each type of building land c (c = residential, commercial, public service). .

[0075] In step 502 of some embodiments, prepare corresponding emission parameters for different types of building activities. The "carbon emission factor per unit area of the building" refers to the average carbon emissions generated per unit building area during the operation (such as heating, ventilation, air conditioning, lighting, equipment use, etc.) of a building of a specific type c, which can be determined according to authoritative standards (such as the "Civil Building Energy Consumption Standard") or research based on the energy structure and building energy efficiency level of a specific region. Different types of buildings will correspond to different values.

[0076] In step 503 of some embodiments, for each type of building land c, multiply the land area within the said grid cell , the preset floor area ratio and the corresponding carbon emission factor per unit area of the building obtained in step 502 to obtain the building carbon emissions of this type of building in the said grid cell. The "floor area ratio" refers to the ratio of the total building area on a plot to the area of the plot, which is a preset parameter and can be set according to the planning data or the statistical average value of this area. By multiplying the land area by the floor area ratio , the total building area of this type of building can be estimated. Then, multiply the estimated total building area by the carbon emission factor per unit area of this type of building to obtain the total carbon emissions of building type c in grid cell j; In step 504 of some embodiments, summarize the carbon emission contributions of all major types of buildings within the grid cell to obtain the total predicted building carbon emission value of this unit. The formula is as follows

[0077] Among them, are the predicted building carbon emission data for this grid cell (area j).

[0078] Through steps 501 to 504, when calculating the predicted building carbon emission data in the embodiments of the present application, in step 501, the building land area within the grid cell is decomposed into three types: residential building land, commercial building land, and public service building land. Then, in step 502, specific carbon emission factors per unit area are obtained for each type. Next, in step 503, not only the area of each type of land is considered, but also a preset floor area ratio is introduced to estimate the actual building volume (total building area), and the emissions of each type of building are calculated in combination with the type-specific emission factors. Finally, through step 504, the emissions of each type are summed up. Compared with estimating only using a single average building carbon emission factor and land area, it can more accurately reflect the actual carbon emission contributions of different functional buildings (such as residences, shopping malls, office buildings, etc., whose energy consumption intensities are usually different), as well as the impact of different development intensities under the same land area, improving the accuracy and reliability of the predicted building carbon emission data and making it closer to the actual building operation emission situation.

[0079] Through the implementation of steps 301 to 304, the embodiments of the present application achieve a process of converting predicted, spatialized land use information into specific carbon accounting components. First, through step 301, the carbon sink land distribution data, industrial land distribution data, and building land distribution data information contained in the target land use distribution data are accurately parsed and quantified into each grid cell of the target grid map to obtain the specific areas of each type of land. Subsequently, steps 302, 303, and 304 respectively use these area data and the corresponding preset factors (carbon absorption factor, industrial carbon emission factor, building carbon emission factor) to independently calculate the carbon sink predicted data, industrial carbon emission predicted data, and building carbon emission predicted data at the level of each grid cell. This per-grid, type-by-type calculation method gives the predicted results of carbon sink, industrial carbon emission, and building carbon emission clear spatial attributes and source distinctions, achieving refined accounting, facilitating the accurate aggregation in the subsequent step (step 105) to obtain the overall carbon emission situation with spatial differentiation within the target area and effectively improving the fineness of carbon emission prediction in the spatial dimension and its correlation with actual land use.

[0080] In step 104 of some embodiments, using information such as traffic flow, operating speed, and traffic mode composition of each road section (or between regions) predicted in the "target traffic flow distribution data", first calculate the vehicle travel mileage of each road section or traffic zone. Then, combining the proportion data of vehicles of different traffic modes (such as cars, buses, trucks, etc.) and different fuel types (such as gasoline, diesel, electricity, etc.), as well as the unit mileage carbon emission factors related to speed, vehicle type, and fuel type, calculate the total traffic carbon emissions of each road section or traffic zone. Since traffic emissions occur on roads (linear) or regions (areal), and the final result needs to be unified onto a grid map, a spatial allocation process is also required to allocate the calculated traffic carbon emissions to each of the "grid cells" that it passes through or is adjacent to according to certain rules, and finally obtain the "traffic carbon emission prediction data" borne by each grid cell.

[0081] Please refer to Figure 6 , in some embodiments, step 104 may include, but is not limited to, steps 601 to 606.

[0082] Step 601, extract the traffic flow data of each traffic road section under different traffic modes and different time periods from the target traffic flow distribution data.

[0083] Step 602, for each traffic road section, each traffic mode, and each time period, combine the length of the traffic road section and the preset average number of passengers carried by the traffic mode to calculate the total vehicle travel mileage.

[0084] Step 603, obtain the proportion data of vehicles of different fuel types under different traffic modes preset, and the unit mileage carbon emission factors corresponding to traffic mode, fuel type, and operating speed.

[0085] Step 604, multiply the total vehicle travel mileage, the vehicle proportion data, and the unit mileage carbon emission factor, and accumulate for all fuel types of all traffic modes to calculate the traffic carbon emissions of each traffic road section under the traffic mode and time period.

[0086] Step 605, accumulate the traffic carbon emissions of each traffic road section under all time periods to obtain the total traffic carbon emissions of each traffic road section.

[0087] Step 606, according to the spatial position relationship of the traffic road section in the target grid map, allocate the total traffic carbon emissions of each traffic road section to one or more corresponding grid cells to obtain the traffic carbon emission prediction data corresponding to each grid cell.

[0088] In step 601 of some embodiments, the method extracts the traffic flow data of each traffic section l under different traffic modes k (such as cars, buses, motorcycles) and different time periods t (such as off-peak hours, morning rush hours, evening rush hours) from the target traffic flow distribution data output by step 102. .

[0089] In step 602 of some embodiments, for each traffic section l, each traffic mode k, and each time period t, in combination with the length of the traffic section and the preset average number of passengers carried by the traffic mode, , calculate the total vehicle mileage, denoted as . The purpose of this step is to quantify the total amount of vehicle driving activities under specific conditions. The specific formula is:

[0090] In step 603 of some embodiments, obtain the vehicle proportion data of different fuel types (such as gasoline, diesel, electricity, etc., denoted as e) under different traffic modes (k) preset , that is, the proportion of the energy type e used within the traffic mode k in the city, and the carbon emission factor per unit mileage corresponding to the traffic mode (k), fuel type (e), and operating speed (v, this speed information can be obtained from the target traffic flow distribution data) (which can be obtained from the literature). This step is to prepare the parameters required for calculating emissions. The key lies in obtaining refined emission factors that distinguish fuel types and consider the impact of speed.

[0091] In step 604 of some embodiments, multiply the total vehicle mileage calculated in step 602, the corresponding vehicle proportion data obtained in step 603, and the carbon emission factor per unit mileage , and accumulate for all fuel types (e) of all traffic modes (k) to calculate the traffic carbon emissions of each traffic section (l) under a specific time period (t) . The formula can be expressed as:

[0092] In step 605 of some embodiments, accumulate the traffic carbon emissions of each traffic section l under all time periods t to obtain the total traffic carbon emissions of each traffic section l .

[0093] In step 606 of some embodiments, according to the spatial position relationship of the traffic section l in the target grid map (for example, determining whether the section passes through a certain grid, or calculating the length ratio of the section within the grid), the total traffic carbon emissions of each traffic section l Allocate it to one or more corresponding grid cells according to a certain allocation rule (such as allocation by length ratio), and finally obtain the traffic carbon emission prediction data corresponding to each grid cell.

[0094] Alternatively, in some embodiments, step 606 may, according to the spatial correspondence between traffic section l and grid cell j in the target grid map, aggregate the total traffic carbon emissions of each previously calculated traffic section to obtain the traffic carbon emission prediction data corresponding to each grid cell j , and the formula can be expressed as:

[0095] Through steps 601 to 606, the embodiment of the present application first extracts traffic flow data by section, mode, and time period based on the target traffic flow distribution data (step 601), then calculates the total vehicle driving mileage (step 602). Next, introduce the vehicle proportion data distinguishing fuel types and the carbon emission factor per unit mileage considering the influence of operating speed (step 603), accurately calculate the emissions under different conditions (step 604), and summarize to obtain the total emissions of each section (step 605). Finally, through spatial allocation, the section emissions are implemented to each grid cell (step 606). It not only considers the differences in multiple traffic modes, time period changes, and vehicle compositions, but also particularly introduces the influence of speed on the emission factor, and can more accurately reflect the actual road operation conditions (such as speed reduction and increased emissions caused by congestion). The calculated emissions are finally allocated to the grid cells, making the prediction results of traffic carbon emissions have a high spatial resolution, and improving the accuracy, reliability, and spatial fineness of traffic carbon emission prediction data.

[0096] In step 105 of some embodiments, all grid cells in the target area can be traversed, and the various carbon emission prediction data (industry, building, traffic) of each grid cell are added up to obtain the total emissions divided by source in the target area, and then the total carbon emission prediction data of the area is obtained. At the same time, the carbon sink prediction data of all grid cells can also be added up to obtain the total carbon sink amount prediction data of the target area. Finally, by subtracting the total carbon sink amount prediction data from the total carbon emission prediction data of the area, the net carbon emission prediction data of the target area in the target prediction year can be calculated. This final "carbon emission prediction data of the target area" (usually referring to the net emissions) is the main prediction output aimed to be provided by this method, which comprehensively reflects the comprehensive impact of land use, industry, building, and traffic activities on the overall carbon balance of the region under the evolution of the urban system.

[0097] Please refer to Figure 7, in some embodiments, step 105 may include, but is not limited to, steps 701 to 706.

[0098] Step 701, sum up the industrial carbon emission prediction data of all grid cells in the target area to obtain the total industrial carbon emission prediction data of the target area.

[0099] Step 702, sum up the building carbon emission prediction data of all grid cells in the target area to obtain the total building carbon emission prediction data of the target area.

[0100] Step 703, sum up the transportation carbon emission prediction data of all grid cells in the target area to obtain the total transportation carbon emission prediction data of the target area.

[0101] Step 704, add the total industrial carbon emission prediction data, the total building carbon emission prediction data, and the total transportation carbon emission prediction data of the target area to obtain the total carbon emission prediction data of the target area.

[0102] Step 705, sum up the carbon sink prediction data of all grid cells in the target area to obtain the total carbon sink prediction data of the target area.

[0103] Step 706, subtract the total carbon sink prediction data from the total carbon emission prediction data of the target area to obtain the net carbon emission prediction data of the target area in the target prediction year.

[0104] In steps 701 to 706 of some embodiments, it is first necessary to traverse all grid cells in the target area, and sum up the industrial carbon emission prediction data corresponding to each grid cell to obtain the total industrial carbon emission prediction data of the target area . Similarly, sum up the building carbon emission prediction data of all grid cells to obtain the total building carbon emission prediction data of the target area ; and sum up the transportation carbon emission prediction data of all grid cells to obtain the total transportation carbon emission prediction data of the target area . Then, add the total emissions of these three to calculate the total carbon emission prediction data of the target area , that is:

[0105] At the same time, it is also necessary to sum up the carbon sink prediction data of all grid cells in the target area to obtain the total carbon sink prediction data of the target area . Finally, by subtracting the total carbon sink prediction data from the total carbon emission prediction data of the target area Subtract its total carbon sink prediction data to calculate the final net carbon emission prediction data of the target area in the target prediction year The formula is:

[0106] The above steps complete the aggregation process from the carbon budget accounting of micro-grid units to the prediction of the overall carbon emission status of the macro target area.

[0107] The carbon emission prediction method based on the urban system model provided by the embodiments of the present application first performs evolution prediction by adopting a pre-constructed urban system model and combining historical data of the target area, deeply simulating the complex interactions and dynamic evolution processes among key factors such as internal land use and traffic flow in the city, overcoming the defect of insufficient capture of system dynamics by traditional methods, and reducing the dependence on subjectively set parameters. Secondly, after predicting the future target land use distribution data and target traffic flow distribution data, at a fine grid scale, the carbon sink, industrial carbon emissions, and building carbon emissions are determined based on land use respectively, and traffic carbon emissions are determined based on traffic flow. This classified and spatially explicit calculation method can more deeply analyze the micro-mechanism of carbon emission generation, and implement the macro urban development prediction to specific spatial units and emission / absorption categories; finally, by comprehensively calculating the various carbon emission prediction data and carbon sink prediction data of each grid unit, weighted or aggregated calculation is performed to obtain the overall carbon emission prediction result of the target area, which can better reflect the real result of the operation of the urban system compared with macro statistics. The above technical synergistic effects enable this method to learn the internal development law from the complex operation history of the urban system, and based on the dynamic and spatial prediction of future land use and traffic conditions, accurately account for carbon emissions and carbon sink contributions from different sources. Therefore, the present application can improve the accuracy and reliability of carbon emission prediction.

[0108] Please refer to Figure 8 , the embodiments of the present application also provide a carbon emission prediction device based on the urban system model, which can implement the above carbon emission prediction method based on the urban system model, including: An acquisition module that acquires the target grid map of the target area and the historical data of the target area; A prediction module that performs evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain the target land use distribution data and target traffic flow distribution data of the target area; A first determination module that determines the carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid unit according to the target land use distribution data and the target grid map; A second determination module, which determines traffic carbon emission prediction data corresponding to each grid cell according to the target traffic flow distribution data and the target grid map; A calculation module, which calculates the carbon emission prediction data of the target area according to the carbon sink prediction data, industrial carbon emission prediction data, building carbon emission prediction data, and traffic carbon emission prediction data corresponding to each grid cell.

[0109] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the carbon emission prediction method based on the urban system model according to any one of the embodiments in the first aspect of the present application.

[0110] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The storage medium stores a program, and when the program is executed by a processor, it implements the carbon emission prediction method based on the urban system model according to any one of the embodiments in the first aspect of the present application.

[0111] Please refer to Figure 9 , Figure 9 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes: A processor 901, which can be implemented in a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application; A memory 902, which can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902, and the processor 901 is used to call and execute the carbon emission prediction method based on the urban system model of the embodiments of the present application; An input / output interface 903, which is used to implement information input and output; A communication interface 904, which is used to implement communication interaction between this device and other devices. Communication can be achieved through a wired method (such as USB, network cable, etc.) or through a wireless method (such as mobile network, WIFI, Bluetooth, etc.); The bus 905 transmits information among various components of the device, such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904. Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 achieve communication connections with each other inside the device through the bus 905.

[0112] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned carbon emission prediction method based on the urban system model is implemented.

[0113] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory can optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0114] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0115] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0118] In the description of this application and the above-mentioned drawings, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the application described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0119] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (individual) of the following" or its similar expression refers to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0120] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0121] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0123] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The aforementioned storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0124] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings. However, this does not limit the scope of the rights of the embodiments of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall fall within the scope of the rights of the embodiments of the present application.

Claims

1. A carbon emission prediction method based on an urban system model, characterized in that, The method includes: Obtaining a target grid map of a target area and historical data of the target area; Performing an evolution prediction on the historical data of the target area through a pre-constructed urban system model to obtain target land use distribution data and target traffic flow distribution data of the target area; Determining carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid cell according to the target land use distribution data and the target grid map; Determining traffic carbon emission prediction data corresponding to each grid cell according to the target traffic flow distribution data and the target grid map; Calculating carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data, and the traffic carbon emission prediction data corresponding to each grid cell.

2. The carbon emission prediction method based on the urban system model according to claim 1, wherein The target land use distribution data includes carbon sink land use distribution data, industrial land use distribution data, and building land use distribution data. The determining of the carbon sink prediction data, the industrial carbon emission prediction data, and the building carbon emission prediction data corresponding to each grid cell according to the target land use distribution data and the target grid map includes: Determining the carbon sink land area, industrial land area, and building land area of each grid cell in the target grid map according to the carbon sink land use distribution data, the industrial land use distribution data, and the building land use distribution data; For each grid cell, calculating the carbon sink prediction data in the grid cell according to the carbon sink land area and a preset carbon absorption factor; For each grid cell, calculating the industrial carbon emission prediction data in the grid cell according to the industrial land area and a preset industrial carbon emission factor; For each grid cell, calculating the building carbon emission prediction data in the grid cell according to the building land area and a preset building carbon emission factor.

3. The carbon emission prediction method based on the urban system model according to claim 2, wherein The calculating of the industrial carbon emission prediction data in the grid cell for each grid cell according to the industrial land area and a preset industrial carbon emission factor includes: Obtaining the historical proportion of traditional manufacturing and the historical proportion of advanced manufacturing corresponding to the grid cell; Calculating an industrial emission intensity correction coefficient of the grid cell according to the historical proportion of traditional manufacturing, the historical proportion of advanced manufacturing, a preset city-wide historical average proportion of traditional manufacturing, a preset city-wide historical average proportion of advanced manufacturing, a preset emission intensity of traditional manufacturing, and a preset emission intensity of advanced manufacturing; Multiplying the industrial land area, the industrial emission intensity correction coefficient, and the industrial carbon emission factor corresponding to the grid cell to obtain the industrial carbon emission prediction data of the grid cell.

4. The carbon emission prediction method based on the urban system model according to claim 1, wherein The determining of the traffic carbon emission prediction data corresponding to each grid cell according to the target traffic flow distribution data and the target grid map includes: Extracting traffic flow data of each traffic section under different traffic modes and different time periods from the target traffic flow distribution data; For each of the traffic sections, each of the transportation modes, and each of the time periods, calculate the total vehicle mileage by combining the length of the traffic section and the average number of passengers carried per unit of the preset transportation mode. Obtain the data on the proportion of vehicles of different fuel types under different transportation modes preset, and the carbon emission factor per unit mileage corresponding to the transportation mode, the fuel type, and the operating speed. Multiply the total vehicle mileage, the vehicle proportion data, and the carbon emission factor per unit mileage, and sum up for all fuel types of all transportation modes to calculate the traffic carbon emissions of each traffic section under the transportation mode and the time period. Sum up the traffic carbon emissions of each traffic section over all time periods to obtain the total traffic carbon emissions of each traffic section. According to the spatial position relationship of each traffic section in the target grid map, allocate the total traffic carbon emissions of each traffic section to one or more grid cells corresponding to it to obtain the traffic carbon emission prediction data corresponding to each grid cell.

5. The carbon emission prediction method based on the urban system model according to claim 2, characterized in that For each grid cell, calculate the building carbon emission prediction data of the grid cell according to the building land area and the preset building carbon emission factor, including: According to the building land distribution data, determine the corresponding land areas of residential building land, commercial building land, and public service building land within the grid cell. Obtain the building carbon emission factors per unit area for residential building land, commercial building land, and public service building land respectively. For each type of building land, multiply its land area within the grid cell, the preset floor area ratio, and the corresponding building carbon emission factor per unit area to obtain the building carbon emissions of this type of building in the grid cell. Sum up the building carbon emissions of all types of buildings within the grid cell to obtain the building carbon emission prediction data corresponding to the grid cell.

6. The carbon emission prediction method based on the urban system model according to claim 1, wherein Calculate the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data, and the traffic carbon emission prediction data corresponding to each grid cell, including: Sum up the industrial carbon emission prediction data of all grid cells within the target area to obtain the total industrial carbon emission prediction data of the target area. Sum up the building carbon emission prediction data of all grid cells within the target area to obtain the total building carbon emission prediction data of the target area. Sum up the traffic carbon emission prediction data of all grid cells within the target area to obtain the total traffic carbon emission prediction data of the target area. Add the total industrial carbon emission prediction data, the total building carbon emission prediction data, and the total traffic carbon emission prediction data of the target area to obtain the total carbon emission prediction data of the target area. Sum up the carbon sink prediction data of all grid cells within the target area to obtain the total carbon sink prediction data of the target area. Subtract the total carbon sink prediction data from the total carbon emission prediction data of the target area to obtain the net carbon emission prediction data of the target area in the target prediction year.

7. The carbon emission prediction method based on the urban system model according to claim 1, wherein The urban system model includes a land prediction sub-module, a population and employment prediction sub-module, and a traffic prediction sub-module. The evolution prediction of the historical data of the target area is performed through the pre-constructed urban system model to obtain the target land use distribution data and the target traffic flow distribution data of the target area, including: Through the land prediction sub-module, based on the historical land distribution data, historical mobile phone signaling data, historical housing price data, historical traffic data, and historical number of job positions in the historical data of the target area, a prediction is made to obtain the target land use distribution data of the target area; Through the population and employment prediction sub-module, based on the target land use distribution data, the historical mobile phone signaling data, the historical housing price data, the historical population quantity, the historical number of job positions, the historical point of interest data, the historical job-housing relationship coefficient, and the historical traffic network density, a prediction is made to obtain the population spatial distribution data and the job position spatial distribution data of the target area; Through the traffic prediction sub-module, based on the target land use distribution data, the population spatial distribution data, the job position spatial distribution data, the historical mobile phone signaling data, the historical housing price data, and historical traffic data, a prediction is made to obtain the target traffic flow distribution data of the target area.

8. An apparatus for carbon emission prediction based on an urban system model, characterized in that, Including: An acquisition module that acquires the target grid map of the target area and the historical data of the target area; A prediction module that performs evolution prediction on the historical data of the target area through the pre-constructed urban system model to obtain the target land use distribution data and the target traffic flow distribution data of the target area; A first determination module that determines the carbon sink prediction data, industrial carbon emission prediction data, and building carbon emission prediction data corresponding to each grid cell according to the target land use distribution data and the target grid map; A second determination module that determines the traffic carbon emission prediction data corresponding to each grid cell according to the target traffic flow distribution data and the target grid map; A calculation module that calculates the carbon emission prediction data of the target area according to the carbon sink prediction data, the industrial carbon emission prediction data, the building carbon emission prediction data, and the traffic carbon emission prediction data corresponding to each grid cell.

9. An electronic device, characterized in that, Including: A memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the carbon emission prediction method based on the urban system model according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and when the program is executed by the processor, it implements the carbon emission prediction method based on the urban system model according to any one of claims 1 to 7.

Images