Urban carbon emission estimation method and device based on VCA prediction spatial form and medium

Abstract

The invention discloses an urban carbon emission estimation method and device based on a VCA prediction spatial form and a medium. The method comprises the following steps: acquiring urban three-dimensional space driving factor data, and constructing a spatio-temporal data set; constructing a deep learning network, inputting the spatio-temporal data set into the deep learning network, and extracting spatio-temporal neighborhood features of the urban three-dimensional space driving factor data; according to the extracted space-time neighborhood features, predicting urban spatial form data by adopting a coupling model of an artificial neural network and a cellular automaton; and estimating urban carbon emission according to the urban spatial form data. According to the method, an innovative planning and design support tool is provided for low-carbon city planning and design, city arrangement carbon emission is controlled through related carbon emission reduction technical indexes, meanwhile, spatial distribution and time sequence distribution of the city carbon emission are output, a designer can conveniently optimize the city spatial form in the city design stage, and the design efficiency is improved. And the scientificity and the implementability of urban planning are obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission calculation, and specifically relates to a method, device and medium for estimating urban carbon emissions based on predicting spatial form by VCA. Background Art

[0002] Carbon emission refers to the process in which greenhouse gases such as carbon dioxide generated in human activities are emitted into the atmosphere. Excessive carbon emissions will, on the one hand, lead to a continuous increase in the temperature of the earth's surface, thereby triggering various extreme climate events, and on the other hand, will affect the balance of the ecosystem, resulting in shortages of food resources and water resources; therefore, reducing carbon emissions is one of the important goals for the survival and reproduction of mankind.

[0003] However, at present, patents on the prediction and calculation of urban carbon emission reduction still mainly focus on urban land changes. The invention patent "A method and system for urban land planning based on carbon metabolism" with the patent number CN202211165386.2 conducts the prediction and calculation of carbon emissions with urban land as the research object. The invention patent "Remote sensing detection method for carbon emissions based on the research of urbanization coupling relationship" with the patent number CN202310380044.0 uses remote sensing technology to obtain spatio-temporal change data of urban and rural land for carbon emission monitoring. The invention patent "A method for optimizing urban carbon balance based on SD-FLUS model" with the patent number CN202311527528.X proposes a method for optimizing urban carbon balance based on urban land. However, relevant research on low-carbon cities shows that the development of urban land with different three-dimensional forms leads to huge differences in carbon emissions due to differences in population capacity. Therefore, the influence of different urban forms must be considered in the research of medium- and micro-scale low-carbon cities. Summary of the Invention

[0004] In view of this, the embodiments of the present invention provide a method, device and medium for estimating urban carbon emissions based on predicting spatial form by VCA.

[0005] The first aspect of the present invention provides a method for estimating urban carbon emissions based on predicting spatial form by VCA, including the following steps:

[0006] Obtain urban three-dimensional space driving factor data and construct a spatio-temporal data set;

[0007] Construct a deep learning network, input the spatio-temporal data set into the deep learning network, and extract the spatio-temporal neighborhood features of the urban three-dimensional space driving factor data;

[0008] According to the extracted spatio-temporal neighborhood features, use a coupling model of an artificial neural network and a cellular automaton to predict urban spatial form data;

[0009] According to the urban spatial form data, estimate urban carbon emissions.

[0010] Furthermore, the urban three-dimensional space driving factor data at least includes road network data, urban point of interest data, and urban digital elevation data in different historical periods of the city.

[0011] Furthermore, after the step of obtaining the urban three-dimensional space driving factor data and constructing the spatio-temporal data set, it further includes a step of filtering the spatio-temporal data set; by filtering the urban three-dimensional space driving factor data, spatial driving factors required for the cellular automaton can be obtained, including urban surface elevation, urban surface slope, distance from the city to the railway network, distance from the city to the highway network, and density of various urban points of interest.

[0012] Furthermore, the spatio-temporal neighborhood characteristics of the urban three-dimensional space driving factor data specifically include the shape space vector data of each plot in different historical periods of the city and the feature information attached to the space vector data; the feature information at least includes land use category, building height, and above-ground building development volume.

[0013] Furthermore, the constructed deep learning network is one of a convolutional neural network, a long short-term memory network, a recurrent neural network, and a Transformer model.

[0014] Furthermore, the prediction of the urban spatial form using the coupled model of the artificial neural network and the cellular automaton based on the extracted spatio-temporal neighborhood characteristics specifically includes the following steps:

[0015] Calculate the conversion probability P of each plot in the city using the artificial neural network i :

[0016] P i = A i (L self , L dt , L st );

[0017] Among them, L self represents the current state, L dt represents the vector constructed based on the spatio-temporal neighborhood characteristics, L st is the vector describing the captured neighborhood spatio-temporal characteristics, and A o is the ANN function in the sub-region r;

[0018] Calculate the land use and building development volume of each plot using the cellular automaton:

[0019]

[0020] Among them, and respectively represent the state of the land unit at position i at times t and t + 1, f represents the transition function, and P o represents the overall conversion probability, represents the state data of the surrounding cells within the m spatial distance; CON is used to define the constraint coverage of the land unit. If the land unit is available for development, the unit CON is assigned a value of 1; otherwise, it is assigned a value of 0; RND represents random perturbation;

[0021] Output urban land use, land development volume, and building height data as urban spatial form data.

[0022] Furthermore, based on the urban spatial form data, urban carbon emissions are estimated, specifically including the following steps:

[0023] Set urban carbon emission control parameters;

[0024] Based on the urban spatial form data, predict the urban life cycle carbon emissions to obtain carbon emission time series change data characterized by the urban carbon emission control parameters.

[0025] Furthermore, the urban life cycle carbon emission prediction specifically includes building carbon emission prediction, transportation carbon emission prediction, waste carbon emission prediction, water system carbon emission prediction, urban lighting carbon emission prediction, and green ecological carbon sink prediction; the urban carbon emissions at each moment are obtained by subtracting the predicted green ecological carbon sink from the sum of the predicted building carbon emissions, transportation carbon emissions, waste carbon emissions, water system carbon emissions, and urban lighting carbon emissions; integrating the calculated urban carbon emissions at each moment can obtain the carbon emission time series change data.

[0026] A second aspect of the present invention discloses an electronic device, including a processor and a memory;

[0027] The memory is used to store programs;

[0028] The processor executes the program to implement the disclosed urban carbon emission estimation method based on VCA for predicting spatial form.

[0029] A third aspect of the present invention discloses a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the disclosed urban carbon emission estimation method based on VCA for predicting spatial form.

[0030] An embodiment of the present invention also discloses a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the foregoing method.

[0031] The embodiments of the present invention have the following beneficial effects: The embodiments of the present invention propose a method, device and medium for estimating urban carbon emissions based on VCA prediction of spatial form, convert three-dimensional form into population capacity based on different land use types, and then calculate the carbon emissions throughout the life cycle based on the carbon emission calculation method of each sub-module of the city, so as to quickly calculate the carbon emissions of the future three-dimensional form of the city. The present invention expands the algorithm of the vector cellular automaton and adds a three-dimensional space prediction function to the land use change prediction model. Thus, the three-dimensional space of the future development of the city can be predicted according to the historical land use data and three-dimensional space data of the city. By observing and balancing the overall spatial distribution of carbon emissions, the scientific nature and feasibility of urban planning are significantly improved, providing strong technical support for achieving the goal of low-carbon urban development, and helping to promote the practice and theoretical development of sustainable urban planning.

[0032] The additional aspects and advantages of the present invention will be given in the following description section, some will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0034] Figure 1 is a basic implementation flowchart of a method for estimating urban carbon emissions based on VCA prediction of spatial form according to the present invention;

[0035] Figure 2 is a schematic diagram of the carbon emission prediction calculation process according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In order to make the purpose, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] At present, carbon emission prediction in the urban field mainly focuses on the macro scale, using statistical data and satellite remote sensing data as the basic data sources, and ignoring the huge differences in carbon emissions caused by different population capacities on the same land use. However, in the process of further implementation, it is necessary to manage the three-dimensional spatial form at the micro scale in the city, so as to reasonably plan the population distribution. Aiming at this gap in the research of low-carbon cities, this invention integrates advanced computer technology and proposes a method for estimating urban carbon emissions based on predicting the spatial form of VCA (Vector Cellular Automata), expanding the traditional two-dimensional vector cellular automata and land carbon calculation methods to the urban three-dimensional form to meet the needs of future urban design and research.

[0038] Specifically, as Figure 1 shown, the first embodiment of this invention provides a method for estimating urban carbon emissions based on predicting the spatial form of VCA, including the following steps:

[0039] S1. Obtain the data of driving factors of the urban three-dimensional space and construct a spatio-temporal data set.

[0040] S2. Construct a deep learning network, input the spatio-temporal data set into the deep learning network, and extract the spatio-temporal neighborhood features of the data of driving factors of the urban three-dimensional space.

[0041] S3. According to the extracted spatio-temporal neighborhood features, use a coupled model of artificial neural network and cellular automata to predict the urban spatial form data.

[0042] S4. Estimate the urban carbon emissions according to the urban spatial form data.

[0043] S1. Obtain the data of driving factors of the urban three-dimensional space and construct a spatio-temporal data set.

[0044] The data of driving factors of the urban three-dimensional space refers to various data used for analyzing and simulating the development and change of the urban three-dimensional space, such as terrain data, building data, land use data, traffic data, etc. The data of driving factors of the urban three-dimensional space used in the embodiments of this invention include road network data, urban interest point data, and urban digital elevation data in different historical periods of the city, etc. These data are crucial for understanding the urban form, evaluating the effect of urban planning, conducting urban design, and predicting the future urban development. The data of driving factors of the urban three-dimensional space can be obtained through public data released by government departments, remote sensing images, field measurements, social surveys, etc.

[0045] Due to the large number of data types of urban three-dimensional space driving factors, in order to improve the prediction efficiency of the vector cellular automaton, it is necessary to integrate and screen the collected urban three-dimensional space driving factor data, and retain the data required by the vector cellular automaton for urban three-dimensional space driving factors. Exemplarily, urban road network data from different historical periods can be collected, and an urban traffic road network can be established based on the road network data, and the network distance between different vector plots can be calculated. The network distance is defined as the time cost required for traffic commuting between two plots. Compared with the traditional cellular automaton that uses Euclidean distance to define the distance between plots, this definition method is more conducive to explaining the complex spatial relationship between urban plots. The finally integrated and screened urban three-dimensional space driving factor data includes urban surface elevation, urban surface slope, urban distance to the railway network, urban distance to the highway network, and the density of various urban interest points. In some embodiments, data preprocessing methods such as spatial interpolation, outlier removal, and normalization can also be used to clean the urban three-dimensional space driving factor data, further improving the prediction efficiency of the vector cellular automaton.

[0046] S2. Construct a deep learning network, input the spatio-temporal data set into the deep learning network, and extract the spatio-temporal neighborhood features of the urban three-dimensional space driving factor data.

[0047] In the embodiments of the present invention, different deep learning neural networks are constructed, such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Transformer models, as encoding modules for extracting the spatio-temporal neighborhood features of spatial driving factors. Initialize the parameters of the encoding module, and use the Variational Autoencoder framework to train the weight parameters of the encoding module; input different spatial driving factors into the deep learning neural network encoding module to obtain the spatio-temporal neighborhood features of different spatial driving factors.

[0048] In the embodiments of the present invention, the spatio-temporal data set is divided into a training set and a test set in chronological order, and the prediction accuracy of the deep learning network is judged by the prediction of the deep learning network on the data at a closer time based on the data at a farther time; the predicted spatio-temporal neighborhood features specifically include the shape space vector data of each plot in different historical periods of the city and the feature information attached to the space vector data, such as land use category, building height, and above-ground building development volume.

[0049] S3. According to the extracted spatio-temporal neighborhood features, use a coupled model of an artificial neural network and a cellular automaton to predict urban spatial form data.

[0050] In the embodiment of the present invention, a coupled model of an artificial neural network and a cellular automaton is adopted to predict land changes and the development quantity of above-ground buildings, so as to calculate the building height. Specifically, the method includes the following steps:

[0051] Calculate the conversion probability P of each plot in the city by using an artificial neural network i :

[0052] P i =A i (L self ,L dt ,L st );

[0053] Among them, L self represents the current state, L dt represents the vector constructed based on spatio-temporal neighborhood features, L st is the vector describing the captured neighborhood spatio-temporal features, and A i is the ANN function in the sub-region r;

[0054] Calculate the land use and building development quantity of each plot by using a cellular automaton:

[0055]

[0056] Among them, and respectively represent the land unit states at position i at time t and t + 1, f represents the transfer function, and P i represents the overall conversion probability, represents the state data of the surrounding cells within the m spatial distance; CON is used to define the constraint coverage of the land unit. If the land unit is available for development, the value 1 is assigned to the unit CON; otherwise, the value 0 is assigned; RND represents random perturbation;

[0057] Output the urban land use, land development quantity, and building height data as urban spatial form data.

[0058] S4. Estimate the urban carbon emissions according to the urban spatial form data.

[0059] The overall process of step S4 is as Figure 2 shown, and specifically includes the following steps:

[0060] S4-1. Set the urban carbon emission control parameters.

[0061] In order to reflect the differences in the emission reduction effects of different urban planning and construction paths, it is necessary to set different urban carbon emission reduction scenario parameters, and calculate the carbon emissions of the same region by using the subsequent urban full-life cycle carbon emission accounting method. The urban carbon emission reduction scenario parameters include the following parameters:

[0062] 1) Renewable energy substitution rate: It refers to the proportion of renewable energy in the total energy consumption in the urban carbon accounting area during the process of substituting traditional energy.

[0063] 2) Photovoltaic coverage rate of building roofs: It is the proportion of the area of the building roof installed with a photovoltaic power generation system in the total roof area suitable for installing photovoltaics.

[0064] 3) Photovoltaic coverage rate of building facades: It is the proportion of the area of the building facade installed with a photovoltaic power generation system in the total facade area suitable for installing photovoltaics.

[0065] 4) Building electrification ratio: It is the proportion of electricity used in buildings in the total energy consumption, including heating, cooling, and lighting.

[0066] 5) Proportion of ultra-low energy consumption buildings: It is the proportion of ultra-low energy consumption building area in the total building area. Among them, ultra-low energy consumption buildings are defined as: taking one year as the calculation period and the end-use energy form as the measurement index, the energy consumption of newly built buildings is 50% more energy-efficient than that of buildings constructed in accordance with energy-saving standards.

[0067] 6) Proportion of new energy vehicles (social vehicles): It refers to the proportion of vehicles driven by new energy such as electricity and hydrogen in all social vehicles.

[0068] 7) Proportion of new energy vehicles (buses): It refers to the proportion of vehicles driven by new energy such as electricity and hydrogen in buses.

[0069] 8) Recycling and utilization rate of domestic waste: It is the proportion of recyclable domestic waste in the total domestic waste;

[0070] 9) Recycling and utilization rate of reclaimed water: It is the proportion of sewage that is reused after treatment;

[0071] 10) Proportion of new energy street lamps: It is the proportion of new energy street lamps in the total street lamps;

[0072] 11) Proportion of composite greening planting: It is the proportion of the greening planting area of trees, shrubs, and grass in the total greening area.

[0073] S4-2. Based on the urban spatial form data, conduct carbon emission prediction for the entire life cycle of the city to obtain the carbon emission time series change data characterized by urban carbon emission control parameters.

[0074] In step S4-2, the carbon emissions prediction for the entire urban life cycle specifically includes the prediction of building carbon emissions, transportation carbon emissions, waste carbon emissions, water system carbon emissions, urban lighting carbon emissions, and green ecological carbon sequestration; the urban carbon emissions at each moment are obtained by subtracting the predicted green ecological carbon sequestration from the sum of the predicted building carbon emissions, transportation carbon emissions, waste carbon emissions, water system carbon emissions, and urban lighting carbon emissions; integrating the calculated urban carbon emissions at each moment can obtain the time-series change data of carbon emissions.

[0075] The following presents an exemplary prediction process for the prediction of building carbon emissions, transportation carbon emissions, waste carbon emissions, water system carbon emissions, urban lighting carbon emissions, and green ecological carbon sequestration respectively:

[0076] 1. Building carbon emissions:

[0077] Building carbon emissions can be divided into four stages according to the entire building life cycle:

[0078] 1.1 Building material production stage:

[0079]

[0080] In the formula:

[0081] CE build,pro —— Carbon emissions in the building material production stage, kgCO2.

[0082] AR i —— Total area of the i-th building envelope system or structural system of the building, m 2 (Can be obtained by geometric calculation based on land development volume and building height).

[0083] MW i,j —— Weight of the j-th building material per unit area of the i-th building envelope system or structural system of the building, kg / m 2 .

[0084] EF pr,j —— Emission factor for producing the j-th material, kgCO2 / kg.

[0085] TD raw,k —— Transportation distance of the k-th raw material required for producing the j-th material to the production site, km.

[0086] MW raw,i —— Weight of the k-th raw material required for producing the j-th material, kg.

[0087] EF t,j—— Emission factor per unit weight per kilometer of the kth raw material required for producing the jth material, kgCO2 / (kg·km).

[0088] 1.2 Construction stage:

[0089]

[0090] Where:

[0091] CE build,con —— Carbon emissions during the construction stage of the building, kgCO2.

[0092] EC con,i —— Energy consumption of the ith construction equipment, kg or kWh.

[0093] EF E,i —— Emission factor of the equipment energy consumption type, kgCO2 / kg or kgCO2 / kWh.

[0094] AR i —— Total area of the ith building envelope system or structural system, m 2 (Can be obtained by geometric calculation based on the land development volume and building height).

[0095] MW i,j —— Weight of the jth construction material per unit area of the ith building envelope system or structural system, kg / m 2 .

[0096] TD mat,j —— Transportation distance of the jth construction material to the production site, km.

[0097] EF T,j —— Emission factor per unit weight per kilometer of the ith construction material, kgCO2 / (kg·km).

[0098] 1.3 Building operation stage:

[0099] CE built,op,year =Energy×R elec ×EC×EF grid +Energy×(1 - R elec )×EF coal ;

[0100]

[0101] Where:

[0102] CE build,op,year —— Annual carbon emissions during the operation stage of urban buildings, kgCO2 / a.

[0103] Relec —— Proportion of building electrification, %.

[0104] EF grid —— Annual carbon emission factor of State Grid, kgCO2 / kWh.

[0105] EC - Coefficient of converting electricity into standard coal, 0.1229 Kgce / kWh.

[0106] EF coal —— Carbon emission factor of primary energy calculated by standard coal, kgCO2 / Kgce.

[0107] Energy - Annual energy consumption benchmark of actual buildings, Kgce / a.

[0108] R re —— Renewable energy substitution rate, %.

[0109] BA i —— Total floor area of the i-th type of urban land use, m 2 .

[0110] E i —— Annual energy consumption benchmark value per unit area of the i-th type of urban land use, Kgce / (m 2 ·a).

[0111] RA i —— Total roof area of the i-th type of urban land use, m 2 .

[0112] PV roof —— Roof photovoltaic conversion efficiency per unit area, Kgce / m 2 .

[0113] R roof —— Building roof photovoltaic coverage rate, %.

[0114] FA i —— Total facade area of the i-th type of urban land use, m 2 .

[0115] PV fac —— Facade photovoltaic conversion efficiency per unit area, Kgce / m 2 .

[0116] R fac —— Building facade photovoltaic coverage rate, %.

[0117] R low —— Proportion of ultra-low energy consumption buildings, %.

[0118] 1.4 Building demolition stage:

[0119]

[0120] In the formula:

[0121] CE build,dem —— Carbon emissions during the demolition stage of transportation facilities, kgCO2.

[0122] EC dem,i —— Energy consumption of demolition equipment, kg or kWh.

[0123] EF E,i —— Emission factor of the energy used by demolition equipment, kgCO2 / kg or kgCO2 / kWh.

[0124] AR i —— Total area of the i-th building envelope system or structural system, m 2 (Can be obtained by geometric calculation based on land development volume and building height).

[0125] MW i,j —— Weight of the j-th building material per unit area of the i-th building envelope system or structural system, kg / m 2 .

[0126] TD dem,j —— Transportation distance of the j-th waste from the demolition site to the disposal or recycling site, km.

[0127] EF T,j —— Emission factor for transporting the j-th waste, kgCO2 / (kg·km).

[0128] 2. Carbon emissions from transportation:

[0129] Carbon emissions from transportation can be divided into four stages according to the whole life cycle of transportation infrastructure:

[0130] 2.1 Production stage of transportation facility building materials:

[0131]

[0132] In the formula,

[0133] CE trans,pro —— Carbon emissions during the production stage of transportation facility building materials, kgCO2.

[0134] AR i —— Total area of the i-th road grade in the city, m 2 .

[0135] MW i,j —— Weight of the j-th building material per unit area of the i-th road grade in the city, kg / m 2 .

[0136] EF pr,j —— Emission factor for producing the j-th material, kgCO2 / kg.

[0137] TD raw,k —— Transportation distance of the k-th raw material required for producing the j-th material to the production site, km.

[0138] MW raw,i —— Weight of the k-th raw material required for producing the j-th material, kg.

[0139] EF t,j —— Transportation emission coefficient per unit weight per kilometer of the k-th raw material required for producing the j-th material, kgCO2 / (kg·km).

[0140] 2.2 Construction stage of transportation facilities:

[0141]

[0142] Wherein,

[0143] CE trans,con —— Carbon emissions during the construction stage of transportation facilities, kgCO2.

[0144] EC con,i —— Energy consumption of the i-th construction equipment, kg or kWh.

[0145] EF E,i —— Emission factor for the type of equipment energy consumption, kgCO2 / kg or kgCO2 / kWh.

[0146] AR i —— Total area of the i-th road grade in the city, m 2 .

[0147] MW i,j —— The i-th road grade in the city, weight of the j-th construction material per unit area, kg / m 2 .

[0148] TD mat,j —— Transportation distance of the j-th construction material to the production site, km.

[0149] EF T,j —— Transportation emission coefficient per unit weight per kilometer of the i-th construction material, kgCO2 / (kg·km).

[0150] 2.3 Operation stage of transportation facilities:

[0151] CE trans,op,year =Car × R car × E car × EFelec + Car × (1 - R car ) × O car × EF oil + Bus × R bus × E bus × EF elec + Bus × (1 - R bus ) × O bus × EF oil ;

[0152]

[0153] In the formula,

[0154] CE trans,op,year —— Annual carbon emissions during the urban traffic operation stage, kgCO2 / a.

[0155] Car —— Number of social vehicles, vehicles.

[0156] R car —— Proportion of new energy vehicles (social vehicles), %.

[0157] O car —— Fuel consumption intensity of fuel vehicles of social vehicles, L / 100km.

[0158] E car —— Power consumption intensity of new energy vehicles of social vehicles, kWh / 100km.

[0159] Bus —— Number of buses, vehicles.

[0160] R bus —— Proportion of new energy vehicles (buses), %.

[0161] O bus —— Fuel consumption intensity of fuel vehicles of buses, L / 100km.

[0162] E bus —— Power consumption intensity of new energy vehicles of buses, kWh / 100km.

[0163] EF oil —— Fuel carbon emission intensity, kgCO2 / L.

[0164] EF elec —— Carbon emission intensity of electric energy of new energy vehicles, kgCO2 / kWh.

[0165] HouseArea i —— Total building area of urban residential land, m 2 (Obtained from the previous model simulation).

[0166] Population i —— Floor area per capita of residential land, m 2 / person.

[0167] Car avg —— Number of social vehicles per capita in the city, vehicle.

[0168] 2.4 Traffic facility demolition stage:

[0169]

[0170] Wherein,

[0171] CE trans,dem —— Carbon emissions in the traffic facility demolition stage, kgCO2.

[0172] EC dem,i —— Energy consumption of demolition equipment, kg or kWh.

[0173] EF E,i —— Emission factor of the energy used by the demolition equipment, kgCO2 / kg or kgCO2 / kWh.

[0174] AR i —— Total area of the i-th road grade in the city, m 2 .

[0175] MW i,j —— Weight of the j-th building material per unit area of the i-th road grade in the city, kg / m 2 .

[0176] TD dem,j —— Transportation distance of the j-th waste from the demolition site to the disposal or recycling site, km.

[0177] EF T,j —— Emission factor for transporting the j-th waste, kgCO2 / (kg·km).

[0178] 3. Carbon emissions from domestic waste:

[0179] Carbon emissions from domestic waste can be calculated according to the following formula:

[0180] CE waste,year =W year ×R bury ×EF bury +W year ×R fire ×EF fire +W year ×R other ×EF other ;

[0181]

[0182] In the formula,

[0183] CE waste,year —— Annual carbon emissions from urban domestic waste, kgCO2 / a.

[0184] BuildingArea i —— Total floor area of the i-th type of urban land use, m 2 (Obtained from the previous model simulation).

[0185] Population i —— Floor area per capita of the i-th type of urban land use, m 2 / person.

[0186] W avg —— Annual per capita garbage production, kg / (person·a).

[0187] R—— Recycling rate of domestic waste, %.

[0188] R bury —— Proportion of sanitary landfill treatment method, %.

[0189] R fire —— Proportion of incineration treatment method, %.

[0190] R other —— Proportion of other treatment methods, %.

[0191] EF bury —— Carbon emission intensity of sanitary landfill treatment method, kgCO2 / kg.

[0192] EF fire —— Carbon emission intensity of incineration treatment method, kgCO2 / kg.

[0193] EF other —— Carbon emission intensity of other treatment methods, kgCO2 / kg.

[0194] 4. Carbon emissions from the water system:

[0195] Carbon emissions from the water system are mainly divided into two parts: the water supply system and the sewage treatment system. Among them, the water supply system can be further divided into two parts: the external water transfer system and the reclaimed water system:

[0196] Carbon emissions from the water system can be calculated according to the following formula:

[0197] CE water,year =(E supply +E sewage )·EF Grid,year ;

[0198] E supply = W × R × (E og,avg + E oc,avg + E od,avg ) + W × (1 - R) × (E rg,avg + E rc,avg + E rd,avg );E sewage = W × E s,avg ;

[0199]

[0200] Wherein,

[0201] CE water,year ——Annual carbon emissions of the urban water system, kgCO2 / a.

[0202] E supply ——Annual carbon emissions during the water treatment and transportation process in the urban area, kWh / a.

[0203] R——Recycled water utilization rate, %.

[0204] E og,avg ——Power consumption for the intake of externally transferred water, kWh / (a·m 3 ).

[0205] E oc,avg ——Power consumption for the purification of externally transferred water, kWh / (a·m 3 ).

[0206] E od,avg ——Power consumption for the distribution of externally transferred water, kWh / (a·m 3 ).

[0207] E rg,avg ——Power consumption for the intake of recycled water, kWh / (a·m 3 ).

[0208] E rc,avg ——Power consumption for the purification of recycled water, kWh / (a·m 3 ).

[0209] E rd,avg ——Power consumption for the distribution of recycled water, kWh / (a·m 3 ).

[0210] E sewage ——Annual energy consumption during the filtration and purification process of urban water use, kWh / a.

[0211] E s,avg ——Average energy consumption level of sewage treatment plants, kWh / m 3 .

[0212] W —— Total annual urban water consumption, m 3 / a.

[0213] BuildingArea i —— Total floor area of the i-th type of urban land use, m 2 (Obtained from the previous model simulation).

[0214] Population i —— Floor area per capita of the i-th type of urban land use, m 2 / person.

[0215] Water —— Annual water consumption per capita of the i-th type of urban land use, m 3 / (a·person).

[0216] EF Grid,year —— Annual carbon emission factor of the State Grid, kgCO2 / kWh.

[0217] 5. Carbon emissions from urban lighting:

[0218] Carbon emissions from urban lighting are mainly divided into four parts: road lighting, urban square lighting, green landscape lighting, and other lighting (mainly night view lighting of main buildings, urban event lighting, etc.):

[0219] Carbon emissions from urban lighting can be calculated according to the following formula:

[0220]

[0221] In the formula,

[0222] CE Light,year —— Annual carbon emissions of urban municipal lamps, kgCO2 / a.

[0223] AR i —— Total area of the i-th road grade in the city, m 2 .

[0224] ER i —— Lighting power density of the i-th road grade in the city, kW / m 2 .

[0225] TR i —— Lighting time of the i-th road grade in the city, h / a.

[0226] AS i —— Area of the i-th square in the city, m 2 .

[0227] ES i —— Lighting power density of the i-th square in the city, kW / m 2。

[0228] TS i —— Lighting time of the i-th square in the city, h / a.

[0229] AG —— Total area of urban green space, m 2 (Obtained by simulation of the previous model).

[0230] EG —— Lighting power density of urban green space, kW / m 2 。

[0231] TG —— Lighting time of urban green space, h / a.

[0232] LB —— Annual average lighting power consumption of main buildings, kWh / a.

[0233] EF Grid,year —— Annual carbon emission factor of the national power grid, kgCO2 / kWh.

[0234] R —— Proportion of new energy street lights;

[0235] 6. Green ecological carbon sink:

[0236] The green ecological carbon sink is calculated according to the following formula:

[0237]

[0238] In the formula,

[0239] CE Green —— Annual urban green ecological carbon sink volume, kgCO2 / a.

[0240] AG i —— Planting area of the i-th green space type or the i-th plant in greening, m 2 (The proportion of trees, shrubs and grasses is controlled by the composite greening planting proportion).

[0241] EF i —— Carbon sink volume per unit planting area of the i-th green space type or the i-th plant in greening, kgCO2 / (m 2 ·a).

[0242] The embodiments of the present invention comprehensively cover all aspects of urban carbon emissions, and propose a bottom-up urban carbon emission estimation method based on each sub-module of the city, so as to realize rapid estimation of urban carbon emissions in the early stage of urban planning and design. At the same time, the calculation method of the present invention incorporates control indicators of urban-related carbon emission reduction technologies, so as to consider the application of carbon emission reduction technologies in the early stage of design, assist designers and urban managers in making planning and design decisions, and achieve urban goals.

[0243] Generally speaking, the method proposed by the present invention provides an innovative planning and design support tool for low-carbon urban planning and design. It can quickly estimate the urban carbon emissions only with the design plan and data in the early stage of urban design, control the total urban carbon emissions through relevant carbon emission reduction technical indicators, and output the spatial and temporal distributions of urban carbon emissions, facilitating designers to optimize the urban spatial form in the urban design stage, observe and balance the overall spatial distribution of carbon emissions, significantly improving the scientificity and implementability of urban planning, providing strong technical support for achieving the goal of low-carbon urban development, and contributing to promoting the practice and theoretical development of sustainable urban planning.

[0244] The embodiment of the present invention also discloses a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute Figure 1 the method shown.

[0245] In some alternative embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are foreseeable, where the order of various operations is changed and the sub-operations described as part of a larger operation are executed independently.

[0246] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features described may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It can also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More precisely, considering the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skills of an engineer. Therefore, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It can also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0247] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0248] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0249] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROMs). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0250] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0251] In the description of this specification, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0252] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0253] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for estimating urban carbon emissions based on VCA prediction of spatial morphology, characterized in that: The following steps are involved: Obtain data on driving factors of urban three-dimensional space and construct a spatiotemporal dataset; Constructing a deep learning network, inputting the spatiotemporal data set into the deep learning network, and extracting the spatiotemporal neighborhood features of the urban three-dimensional spatial driving factor data; According to the extracted spatiotemporal neighborhood features, the coupling model of artificial neural network and cellular automation is used to predict urban spatial morphological data; Urban carbon emissions are estimated based on urban spatial morphology data.

2. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: The urban three-dimensional spatial driving factor data at least includes road network data of the city in different historical periods, urban point of interest data and urban digital elevation data.

3. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: After the steps of obtaining the urban three-dimensional spatial driving factor data and constructing the spatiotemporal data set, the method further includes the step of performing data screening on the spatiotemporal data set. By performing data screening on the urban three-dimensional spatial driving factor data, the spatial driving factors required for the cellular automaton, including urban surface elevation, urban surface slope, distance from the city to the railway network, distance from the city to the highway network, and density of various urban points of interest, can be obtained.

4. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: The spatiotemporal neighborhood characteristics of the three-dimensional spatial driving factor data of the city specifically include shape spatial vector data of each plot in different historical periods of the city and characteristic information attached to the spatial vector data; The characteristic information includes at least land use category, building height and ground building development volume.

5. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: The constructed deep learning network is one of the convolutional neural network, long short-term memory network, recurrent neural network and Transformer model.

6. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: The method of predicting the urban spatial form by using the coupling model of artificial neural network and cellular automation according to the extracted spatiotemporal neighborhood features specifically includes the following steps: Artificial neural network is used to calculate the conversion probability P of each plot in the city. i : P i =A i (L self ,L dt ,L st ); Among them, L self Indicates the current state, L dt represents the vector constructed based on the spatiotemporal neighborhood features, L st is a vector describing the captured spatiotemporal characteristics of the neighborhood, A i is the ANN function in subregion r; The cellular automaton is used to calculate the land use and building development of each plot: in, and represents the land unit state at position i at time t and t+1, f represents the transfer function, P i represents the overall conversion probability, Represents the state data of the surrounding cells within the m spatial distance; CON is used to define the constraint coverage of the land unit. If the land unit can be used for development, the CON value of the unit is assigned 1; otherwise, it is assigned a value of 0; RND represents random disturbance; The urban land use, land development volume and building height data are output as urban spatial morphology data.

7. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 1 is characterized in that: The urban carbon emission estimation is performed based on the urban spatial morphology data, specifically including the following steps: Set city carbon emission control parameters; Based on the urban spatial morphology data, a city's carbon emissions over its entire life cycle are predicted to obtain carbon emissions time series change data represented by urban carbon emission control parameters.

8. The urban carbon emission estimation method based on VCA prediction of spatial morphology according to claim 7 is characterized in that: The city's full life cycle carbon emission forecast specifically includes building carbon emission forecast, transportation carbon emission forecast, waste carbon emission forecast, water system carbon emission forecast, urban lighting carbon emission forecast and green ecological carbon sink forecast; The city's carbon emissions at each moment are obtained by subtracting the sum of the predicted building carbon emissions, traffic carbon emissions, waste carbon emissions, water system carbon emissions and urban lighting carbon emissions from the predicted green ecological carbon sequestration; by integrating the calculated city carbon emissions at each moment, the carbon emissions time series change data can be obtained.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement a method for estimating urban carbon emissions based on VCA prediction of spatial morphology as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement a method for estimating urban carbon emissions based on VCA prediction of spatial morphology as described in any one of claims 1 to 8.

Images