A carbon neutral zoning simulation method, system and device based on a smart city

Abstract

The application provides a carbon neutralization partition simulation method, system and device based on a smart city, relates to the technical field of carbon neutralization simulation, and mainly comprises the following steps: planning and partitioning a map of the measured city; calculating the carbon emission of each partition and performing visual processing to obtain geographic spatial data; calculating the carbon sink of each partition; collecting the output value basic data of each industry in the measured partition and marking the output value basic data in the geographic spatial data; storing the carbon emission basic data, the carbon sink basic data and the output value basic data collected by the smart city system regularly in the smart city database based on time sequence; predicting the future carbon emission, the carbon sink and the output value of the measured partition; constructing a time sequence dynamic optimization model, solving the industrial area layout scheme through a parallel genetic algorithm, and generating suggestion information. The scheme provides a quantifiable and controllable carbon management tool for urban land space overall planning, and is especially suitable for low-carbon planning and management of high-density coastal cities.

Description

Technical Field

[0001] This invention relates to the field of carbon neutrality simulation technology, and in particular to a carbon neutrality zoning simulation method, system and apparatus based on smart cities. Background Technology

[0002] Cities, as the main centers of human activity, contribute more than 75% of global carbon emissions. Against this backdrop, countries have proposed "carbon peaking" and "carbon neutrality" goals. As the core carriers for achieving these goals, cities urgently need to build scientific and accurate carbon neutrality simulation systems to optimize spatial resource allocation and promote low-carbon transformation.

[0003] Since the 1990s, academics have been gradually exploring methods for calculating urban carbon emissions. Representative achievements include:

[0004] The International Standard for Urban Greenhouse Gas Accounting (GPC) proposes an accounting framework based on the production and consumption ends, dividing urban carbon emissions into six sectors: energy activities, industrial processes, transportation, buildings, and waste management. However, it does not fully integrate spatial planning elements.

[0005] Spatial accounting methods: These methods utilize geographic information such as nighttime light data and POIs (points of interest) to achieve a spatial representation of carbon emissions through a top-down allocation model. However, these methods rely on statistical data allocation and ignore the differences in activity intensity at the plot scale, resulting in insufficient accuracy.

[0006] Land use correlation analysis: A "land use-carbon emission intensity" correlation framework is constructed, and carbon emissions during the planning period are calculated through urban and rural land use classification; however, this method is based entirely on the unit area method of land use type and does not take into account the technological differences of industrial sub-sectors, resulting in high uncertainty.

[0007] Innovative accounting framework: It proposes a land space carbon emission model based on "spatial layout - land use type - departmental division", which combines planning elements with accounting methods and solves the accounting problem of aligning central urban areas with international standards; however, the model still relies on static parameters and cannot reflect the impact of changes in energy structure on carbon emissions in real time.

[0008] Therefore, there is an urgent need to develop a "space-carbon emission-carbon sink" coupling analysis tool adapted to high-density cities, so as to provide quantifiable and controllable technical support for the city's carbon neutrality task. Summary of the Invention

[0009] The purpose of this invention is to provide a carbon neutrality zoning simulation method, system, and apparatus based on smart cities, so as to solve at least one of the above-mentioned technical problems existing in the prior art.

[0010] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a carbon neutrality zoning simulation method based on smart cities, comprising the following steps:

[0011] Step 1: Divide the map of the city under test into zones; based on standards and literature, collect basic carbon emission data, calculate the carbon emissions of each zone and visualize them to obtain geospatial data; collect basic carbon sink data and mark it in the geospatial data, calculate the carbon sink of each zone; based on carbon emissions and carbon sink, calculate the net emissions of the city under test; collect basic output data of each industry in the tested zones and mark it in the geospatial data; this provides basic data in the initial state, so that subsequent quantitative assessments of the impact of the spatial structure and scale of various zones on carbon emissions, carbon sink, and output can be performed.

[0012] In one feasible implementation, the planning zoning includes primary planning zoning and secondary planning zoning;

[0013] The primary planning zones include urban development zones, farmland protection zones, ecological control zones, ecological protection zones, and marine development zones, etc.

[0014] The secondary planning zones of the urban development area include residential areas, commercial and business areas, comprehensive service areas, cultural and tourism areas, industrial development areas, science and technology innovation development areas, logistics and warehousing areas, strategic reserve areas, green and leisure areas, transportation hub areas, and public facilities concentration areas, etc.

[0015] The secondary planning zones of the marine development zone include fishery sea areas, special sea areas, recreational sea areas, industrial, mining and communication sea areas, marine reserve areas and transportation sea areas, etc.

[0016] Among them, residential areas, commercial and business areas, comprehensive service areas, cultural and tourism areas, industrial development areas, science and technology innovation development areas, logistics and warehousing areas, green leisure areas, transportation hub areas, public facilities concentration areas, industrial, mining and communication sea areas, recreational sea areas, transportation sea areas and farmland protection areas are carbon emission land.

[0017] Ecological protection zones, ecological control zones, and farmland protection zones are designated as terrestrial carbon sink areas;

[0018] Fishing areas and special-use areas are designated as marine carbon sink areas.

[0019] In one feasible implementation, the specific method for acquiring the geospatial data includes:

[0020] Step a1: Based on the planning zoning, obtain spatial distribution data, land use scale data, etc. for each zoning;

[0021] Step a2: Construct a database of land use type codes and land area;

[0022] Step a3: Based on carbon emission standard documents, construct an industry emission factor database and build a framework for the correlation between greenhouse gas emission inventory accounting categories and land use types; based on carbon emission literature, obtain initial values ​​of carbon emission intensity.

[0023] Step a4: Through spatial overlay analysis, match land use scale data, land use type codes with corresponding carbon emission intensity, and calculate the carbon emissions of various types of land use.

[0024] Step a5: Spatially aggregate the carbon emissions of all zones within the city to generate a heat map of total carbon emissions and spatial distribution, thus obtaining geospatial data;

[0025] In this way, we can obtain relatively accurate carbon emissions, total carbon emissions, and spatial distribution heat maps for each urban district, which will be helpful for subsequent simulation analysis.

[0026] In one feasible implementation, in step a1, spatial distribution data and land use scale data of each zone can be obtained through a geographic information public service platform.

[0027] In one feasible implementation, step a2, the land use type coding includes a primary coding and a secondary coding;

[0028] The primary coding includes: CZ for urban development zones; NT for farmland protection zones; STKZ for ecological control zones; STBH for ecological protection zones; and HY for marine development zones.

[0029] The secondary codes include: CZ-jz for residential areas; CZ-ss for commercial and business areas; CZ-zh for comprehensive service areas; CZ-wh for cultural and tourism areas; CZ-gy for industrial development areas; CZ-zh for science and technology innovation development areas; CZ-wl for logistics and warehousing areas; CZ-yl for strategic reserve areas; CZ-ld for green and leisure areas; CZ-sn for transportation hub areas; CZ-gg for concentrated public facilities areas; HY-yy for fishery areas; HY-ts for special-purpose areas; HY-yq for recreational areas; HY-gk for industrial, mining, and communication areas; HY-yl for marine reserve areas; and HY-jt for transportation areas.

[0030] In one feasible implementation, the industry carbon emission factor database in step a3 includes a carbon emission factor matrix constructed from energy sources and corresponding carbon emission factors; the energy sources include electricity, natural gas, heating, and gasoline; the carbon emission factors are determined according to the IPCC National Greenhouse Gas Inventory Guidelines.

[0031] For example, calculating the carbon emission factor of natural gas. The specific formula can be:

[0032] ;

[0033] Among them, the lower heating value can be taken as the default value, which is 389.3 (unit: GJ / 10,000). ), which represents the energy value of fuel per unit volume;

[0034] Carbon content per unit calorific value: can be based on the elemental composition of the fuel, and is taken as 0.0153 (unit: tC / GJ), reflecting the mass of carbon element corresponding to each unit of energy;

[0035] Carbon oxidation rate: Based on actual combustion efficiency data, the value is taken as 0.99 (that is, 99% of the carbon is completely oxidized to carbon dioxide).

[0036] Conversion factor: can be determined based on the molecular weight ratio ( / C=44 / 12), with a value of 3.67.

[0037] In one feasible implementation, the association framework includes a mapping matrix between land use type, energy consumption, and carbon emission intensity.

[0038] In one feasible implementation, the formulas for calculating carbon emissions for various land uses include:

[0039] Carbon emissions from residential areas (Unit: tons of carbon dioxide equivalent):

[0040] ;

[0041] in, This indicates the amount of natural gas consumed, expressed in gigajoules (GJ). This indicates the lower heating value of natural gas, expressed in gigajoules per 10,000 standard cubic meters (GJ / 10,000 cubic meters). ); This indicates the carbon content per unit of calorific value, expressed in tons of carbon per gigajoul (tC / GJ). Indicates the carbon oxidation rate; express Conversion factor; This indicates the number of motor vehicles owned by an individual. Indicates the average annual mileage; This indicates fuel consumption per 100 kilometers; Indicates the gasoline volume conversion factor; This indicates the total electricity consumption, expressed in ten thousand kilowatt-hours (kWh). ); The carbon emission factor for electricity is expressed in tons of carbon dioxide equivalent per 10,000 kilowatt-hours.

[0042] Carbon emissions from industrial development zones :

[0043] ;

[0044] in, Indicates the amount of heat supplied; Indicates the thermal carbon emission factor; Indicates the total amount of gasoline used; Indicates the carbon emission factor of gasoline;

[0045] Carbon emissions from business districts :

[0046] ;

[0047] Carbon emissions from integrated service areas :

[0048] ;

[0049] Carbon emissions of the science and technology innovation development zone :

[0050] ;

[0051] Carbon emissions from public facilities concentration areas :

[0052] ;

[0053] Carbon emissions from marine areas used for industrial, mining, and communications purposes :

[0054] ;

[0055] Carbon emissions of cultural tourism areas :

[0056] ;

[0057] in, Indicates the number of tourists; Indicates per capita carbon footprint;

[0058] Carbon emissions from transportation hubs :

[0059] ;

[0060] in, Indicates passenger flow;

[0061] Carbon emissions from logistics and warehousing areas :

[0062] ;

[0063] in, This indicates the freight turnover on highways, expressed in ton-kilometers (t·km). Expressed as carbon intensity of highways, the unit is kilograms of CO2 equivalent per ton-kilometer (tKL). ); Indicates the volume of goods transported by waterway; Indicates the carbon intensity of the waterway;

[0064] Carbon emissions from green recreational areas :

[0065] ;

[0066] in, Indicates the first The area of ​​plant-like carbon fixation factors; Indicates the carbon sequestration ratio of the carbon fixation factor;

[0067] Carbon emissions from sea areas used for transportation :

[0068] ;

[0069] in, This indicates throughput, expressed in tons. This indicates the intensity of cargo turnover per unit, expressed in kilograms of carbon dioxide equivalent per ton-kilometer.

[0070] Carbon emissions from recreational marine areas :

[0071]

[0072] Carbon emissions from farmland protection areas :

[0073] ;

[0074] in, Indicates the total amount of fertilizer applied; Indicates the carbon emission factor of fertilizer; Indicates the first The area of ​​carbon sequestration factors similar to those found in crops.

[0075] In one feasible implementation, the spatial overlay analysis in step a4 includes associating land use codes with a carbon emission factor matrix using the Spatial Join tool in ArcGIS Pro, thereby facilitating the calculation of carbon emissions for individual zones.

[0076] In one feasible implementation, the spatial aggregation refers to calculating the total carbon emissions by summarizing them level by level according to land use type codes.

[0077] In one feasible implementation, the specific method for generating the spatial distribution heatmap includes:

[0078] Step a51: Employ the Weighted Kernel Density Estimation (WKDE) method, incorporating carbon emissions as a weighting factor into the spatial density analysis. The specific formula includes:

[0079] ;

[0080] in, Indicates spatial location Carbon emission density value at the location; Indicates the number of carbon emission points; Indicates the first The weighting factor for each carbon emission point is expressed in tons of CO2 equivalent per square kilometer. Represents the kernel function; This represents the bandwidth, i.e., the search radius, for example, set to 500 meters;

[0081] Step a52: Collect carbon emission point data and preprocess it, with the format uniformly set to GeoJSON; the carbon emission point data includes latitude and longitude and carbon emission amount;

[0082] Step a53: Generate grid density from carbon emission point data using a weighted kernel density estimation method;

[0083] Step a54: Based on the grid density, use geographic information tools to perform visualization output to obtain geospatial data.

[0084] In one feasible implementation, the visualization output includes:

[0085] When the carbon emission density is less than 5 tons / km², cool colors should be used;

[0086] When the carbon emission density is greater than 20 tons / km², a red-black gradient color scheme is used.

[0087] Overlay contour lines;

[0088] Mark the carbon emission intensity threshold warning line;

[0089] This makes it easier to visually represent the stepwise distribution of carbon emission density.

[0090] In one feasible implementation, carbon sink land is manually labeled in geospatial data using geographic information tools: green fill indicates terrestrial carbon sink land; light blue fill indicates marine carbon sink land.

[0091] In one feasible implementation, the specific calculation method for the carbon sink includes terrestrial carbon sink calculation and marine carbon sink calculation;

[0092] The land carbon sink The specific formulas for the calculation include:

[0093] ;

[0094] in, Indicates the first The land area for carbon sink elements is measured in hectares (ha). Carbon sink elements mainly include mountains (forests), water (inland lakes and rivers), fields and grasslands. The land area for each element can be determined based on planning zones and satellite remote sensing observations. Indicates the first The carbon sequestration rate of carbon sink elements is expressed in tons of carbon per hectare per year (tC / ha•yr), and can be initially determined according to the "Guidelines for Carbon Sequestration Accounting in Terrestrial Ecosystems" or the "Table of Carbon Sequestration Rates in Farmland Soils". The coefficient representing the conversion of carbon dioxide into carbon;

[0095] The marine carbon sink specifically includes mangrove carbon sink, shellfish carbon sink, and sediment carbon sink, etc.

[0096] The carbon sequestration of mangroves The specific calculation formulas include:

[0097] ;

[0098] in, Biomass is expressed in tons. This indicates the carbon content of biomass, expressed in tons of carbon per ton (tC / t).

[0099] The carbon sequestration of shellfish The specific calculation formulas include:

[0100] ;

[0101] in, This indicates stocking density, expressed as individuals per hectare. This represents the average shell weight of a single mollusk, expressed in grams per mollusk. Indicates the carbon content coefficient of seashells;

[0102] The carbon sink in the sediment The specific calculation formulas include:

[0103] ;

[0104] in, This indicates the area of ​​the ocean, expressed in square meters. Indicates the first Organic carbon content of sedimentary layers, expressed as a percentage; This represents the percentage of ocean area covered by sediment.

[0105] In one feasible implementation, the net emissions are specifically calculated as follows: the carbon emissions of the statistical subject minus the carbon sink of the statistical subject; the statistical subject can be the city being measured or several districts of the city being measured, without limitation.

[0106] Step 2: Store the basic carbon emission data, carbon sink data, and output data collected periodically by the smart city system in the smart city database based on time series data. Based on a trained LSTM (Long Short-Term Memory) model, predict the future carbon emissions, carbon sinks, and output of the tested area, thereby effectively capturing long-term dependencies in the time series. Construct a time series dynamic optimization model, and based on the future carbon emissions, carbon sinks, and output of the tested area, dynamically adjust the fitness evaluation function through a parallel genetic algorithm to iteratively solve for the optimal industrial area layout scheme for the tested area in the future.

[0107] In one feasible implementation, the smart city system includes a carbon emission sensing system, a carbon sink sensing system, and an output value sensing system.

[0108] The carbon emission sensing system includes chimney sensors, monitoring cameras, energy consumption IoT networks, etc.

[0109] The chimney sensor is used to collect the carbon emissions from the chimney.

[0110] The monitoring camera is used to collect passenger flow data;

[0111] The energy consumption IoT network (including smart meters, smart water meters, smart natural gas meters, smart heating stations, smart gas stations, etc.) is used to collect data on electricity consumption, gas consumption, heat supply, and oil consumption.

[0112] The carbon sink sensing system includes remote sensing satellites, soil sensors, smart buoys, and marine sonar, etc.

[0113] The remote sensing satellite is used to collect data on the area of ​​terrestrial vegetation and carbon dioxide absorption efficiency.

[0114] The smart buoy is used to collect data on the carbon dioxide absorption efficiency of mangroves.

[0115] The marine sonar is used to collect carbon sequestration data from shellfish and seabed sediments.

[0116] The output value sensing system is connected to the enterprise's ERP system and other systems to collect enterprise output value data.

[0117] In one feasible implementation, the time-series dynamic optimization model includes a sliding time window based on the planning period, dynamic variables, an objective function, and dynamic constraints.

[0118] In one feasible implementation, the parallelized genetic algorithm includes:

[0119] Step b1: Use the objective function of the time-series dynamic optimization model as the fitness evaluation function; configure the DEAP (Distributed Evolutionary Algorithms in Python) toolbox to support parallel processing;

[0120] Step b2: Perform multi-process distributed computing using the scoop (Simple Concurrent Object-Oriented Programming) framework;

[0121] Step b3: Based on the sliding time window, periodically obtain the latest data from the smart city database, update the fitness evaluation function, iteratively execute the genetic algorithm, and extract the optimal solution.

[0122] In one feasible implementation, the industrial area layout scheme includes the land area, output value, and net carbon emission value of each industry in the zone, so as to obtain the zone benefits with the highest output value and the lowest net carbon emission value in the shortest time.

[0123] Step 3: Based on the industrial area layout plan, generate suggested information through preset strategies and send it to the server of the competent department of the tested area through smart contracts to ensure data security and prevent tampering; based on the smart city database, compare the predicted data (carbon emissions, carbon sinks and output value) with the actual data at regular intervals and update the parameters of the LSTM model; in this way, the industrial area layout plan can be effectively implemented and the LSTM model can be calibrated through closed-loop feedback.

[0124] In one feasible implementation, the preset strategy includes a land use adjustment strategy: first, sort the industries in the partition according to their net carbon emissions, select the high-carbon industries with the largest net carbon emissions, and generate suggestions for reducing the land area; then, sort the remaining industries according to their output value, select the high-yield industries with the largest output value, and generate suggestions for expanding the land area.

[0125] In one feasible implementation, the preset strategy further includes a spatial layout assessment strategy, an industrial structure assessment strategy, and a carbon sink capacity assessment strategy.

[0126] The spatial layout assessment strategy includes generating a carbon emission density raster based on geospatial data bound to land use codes using spatial interpolation (IDW / Kriging) method, visually displaying carbon emission intensity based on preset color grading thresholds, and mapping it to preset spatial layout optimization suggestion clauses.

[0127] The specific provisions regarding the spatial layout optimization recommendations include:

[0128] Recommendation for industrial land reorganization: Relocate high-carbon industries from ecologically sensitive areas to concentrated industrial parks, and provide supporting green electricity supply facilities;

[0129] Recommendations for revitalizing existing land use: Utilize urban villages, old residential areas, and idle or inefficiently used commercial and office spaces to develop large-scale rental housing;

[0130] Work-life balance planning recommendations: Reduce carbon emissions from commuting;

[0131] The industry assessment strategy includes analyzing the impact of economic activities on resource consumption and pollution emissions based on the existing Environmental Input-Output Model (EIO), and mapping it to pre-defined industrial structure upgrading recommendations.

[0132] The specific provisions of the proposed industrial structure upgrading include:

[0133] Recommendations for green industry alternatives: Promote hydrogen energy industrial parks to replace traditional petrochemical projects;

[0134] Recommendations for the circular economy pilot program: Build a cluster of zero-carbon buildings, mandate the use of recycled building materials, and promote recycled construction;

[0135] The carbon sink capacity assessment strategy includes dividing carbon sink land into high, medium and low carbon sink zones based on preset thresholds; quantitatively calculating the demand for carbon sink land based on the net carbon value of each zone; and mapping it to preset carbon sink function enhancement recommendation clauses.

[0136] The proposed clauses for enhancing carbon sequestration functions specifically include:

[0137] The Ocean Blue Carbon Project recommends expanding the scale of mangrove restoration.

[0138] Suggestions for improving urban green space quality: Improve the carbon sequestration efficiency of green spaces through vertical greening and replacement with drought-resistant plants;

[0139] Recommendation for ecological network restoration: Connect fragmented carbon sink nodes through ecological corridors to improve carbon sink connectivity.

[0140] Secondly, based on the same inventive concept, this application also provides a carbon neutrality zoning simulation system based on smart cities, including a data receiving module, a data processing module and a result generation module;

[0141] The data receiving module is used to receive maps of the planned zones of the tested city, basic carbon emission data, basic carbon sink data, and basic output data.

[0142] The data processing module includes a geospatial data unit, a data prediction unit, a dynamic optimization unit, and a suggestion information unit;

[0143] The geospatial data unit calculates the carbon emissions of each region based on maps and basic carbon emission data, and performs visualization processing to obtain geospatial data; it also marks the basic carbon sink data in the geospatial data and calculates the carbon sink amount of each region; it calculates the net emissions of the measured city based on carbon emissions and carbon sink amount; and it marks the basic output value data of each industry in the geospatial data.

[0144] The data prediction unit, based on a trained LSTM (Long Short-Term Memory) model, predicts the future carbon emissions, carbon sinks, and output value of the tested partition; it also compares the predicted data with the actual data at regular intervals and updates the parameters of the LSTM model.

[0145] The dynamic optimization unit constructs a time-series dynamic optimization model. Based on the future carbon emissions, carbon sinks, and output value of the tested area, it dynamically adjusts the fitness evaluation function through a parallel genetic algorithm and iteratively solves the optimal industrial area layout scheme for the tested area in the future.

[0146] The suggestion information unit generates suggestion information based on the industrial area layout plan and through a preset strategy;

[0147] The result generation module is used to send out the industrial area layout plan and the suggested information.

[0148] In one feasible implementation, the data receiving module is connected to the smart city system of the city being tested, and is used to access the smart city database.

[0149] Thirdly, based on the same inventive concept, this application also provides a carbon neutrality zoning simulation device based on smart cities, including a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute the carbon neutrality zoning simulation method based on smart cities as described above. The bus connects the various functional components for transmitting information.

[0150] By adopting the above technical solution, the present invention has the following beneficial effects:

[0151] This invention provides a carbon neutrality zoning simulation method, system, and device based on smart cities, offering a quantifiable and controllable carbon management tool for urban land space master planning, helping to achieve carbon peaking and carbon neutrality goals, and is particularly suitable for low-carbon planning and governance in high-density coastal cities; it facilitates intuitive decision support through visualization; it takes into account the differences in activity intensity at the plot scale, improving planning accuracy; it facilitates the subdivision of industries, reducing the uncertainty of planning schemes; and based on a time-series dynamic optimization model, it can reflect the impact of energy structure changes on carbon emissions in real time, obtaining the optimal industrial area layout scheme for the future. Attached Figure Description

[0152] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0153] Figure 1 A flowchart of a carbon neutrality zoning simulation method based on smart cities provided in this embodiment of the invention;

[0154] Figure 2 A flowchart illustrating the specific method for acquiring geospatial data provided in this embodiment of the invention;

[0155] Figure 3 A flowchart of a parallelized genetic algorithm provided in an embodiment of the present invention;

[0156] Figure 4 A flowchart illustrating the specific method for generating reduction suggestion information provided in this embodiment of the invention;

[0157] Figure 5 A flowchart illustrating the specific method for generating magnification suggestion information provided in embodiments of the present invention;

[0158] Figure 6 This is a diagram of a carbon neutrality zoning simulation system based on smart cities, provided as an embodiment of the present invention. Detailed Implementation

[0159] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0160] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0161] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0162] The present invention will be further explained below with reference to specific embodiments.

[0163] It should also be noted that the specific embodiments or implementation methods described below are a series of optimized settings listed by the present invention to further explain the specific content of the invention, and these settings can be combined or used in conjunction with each other.

[0164] Example 1:

[0165] like Figure 1 As shown in the figure, this embodiment provides a carbon neutrality zoning simulation method based on smart cities, which includes the following steps:

[0166] Step 1: Divide the map of the city under test into zones; based on standards and literature, collect basic carbon emission data (such as greenhouse gas emissions, carbon emission intensity, etc.), calculate the carbon emissions of each zone and visualize them to obtain geospatial data (such as heat maps); collect basic carbon sink data and mark it in the geospatial data, calculate the carbon sink of each zone; based on carbon emissions and carbon sink, calculate the net emissions of the city under test; collect basic output data of each industry in the tested zone and mark it in the geospatial data; this can obtain basic data in the initial state, so as to quantitatively evaluate the impact of the spatial structure and scale of various zones on carbon emissions, carbon sink and output in subsequent steps.

[0167] Furthermore, the planning zones include primary planning zones and secondary planning zones;

[0168] The primary planning zones include urban development zones, farmland protection zones, ecological control zones, ecological protection zones, and marine development zones, etc.

[0169] The secondary planning zones of the urban development area include residential areas, commercial and business areas, comprehensive service areas, cultural and tourism areas, industrial development areas, science and technology innovation development areas, logistics and warehousing areas, strategic reserve areas, green and leisure areas, transportation hub areas, and public facilities concentration areas, etc.

[0170] The secondary planning zones of the marine development zone include fishery sea areas, special sea areas, recreational sea areas, industrial, mining and communication sea areas, marine reserve areas and transportation sea areas, etc.

[0171] Among them, residential areas, commercial and business areas, comprehensive service areas, cultural and tourism areas, industrial development areas, science and technology innovation development areas, logistics and warehousing areas, green leisure areas, transportation hub areas, public facilities concentration areas, industrial, mining and communication sea areas, recreational sea areas, transportation sea areas and farmland protection areas are carbon emission land.

[0172] Ecological protection zones (such as forests and wetlands), ecological control zones (such as grasslands and ecological corridors), and farmland protection zones are designated as terrestrial carbon sink land.

[0173] Fishing areas and special-use areas (such as mangroves) are designated as marine carbon sink areas.

[0174] Furthermore, such as Figure 2 As shown, the specific methods for acquiring the geospatial data include:

[0175] Step a1: Based on the planning zoning, obtain spatial distribution data, land use scale data, etc. for each zoning;

[0176] Step a2: Construct a database of land use type codes and land area;

[0177] Step a3: Based on carbon emission standard documents, construct an industry emission factor database and build a framework for the correlation between greenhouse gas emission inventory accounting categories and land use types; based on carbon emission literature (such as the IEA Global Energy Transition Report, etc.), obtain the initial value of carbon emission intensity;

[0178] Step a4: Through spatial overlay analysis, match land use scale data, land use type codes with corresponding carbon emission intensity, and calculate the carbon emissions of various types of land use.

[0179] Step a5: Spatially aggregate the carbon emissions of all zones within the city to generate a heat map of total carbon emissions and spatial distribution, thus obtaining geospatial data;

[0180] In this way, we can obtain relatively accurate carbon emissions, total carbon emissions, and spatial distribution heat maps for each urban district, which will be helpful for subsequent simulation analysis.

[0181] Furthermore, in step a1, spatial distribution data and land use scale data of each zone can be obtained through the geographic information public service platform.

[0182] Furthermore, in step a2, the land use type coding includes a primary coding and a secondary coding;

[0183] The primary coding includes: CZ for urban development zones; NT for farmland protection zones; STKZ for ecological control zones; STBH for ecological protection zones; and HY for marine development zones.

[0184] The secondary codes include: CZ-jz for residential areas; CZ-ss for commercial and business areas; CZ-zh for comprehensive service areas; CZ-wh for cultural and tourism areas; CZ-gy for industrial development areas; CZ-zh for science and technology innovation development areas; CZ-wl for logistics and warehousing areas; CZ-yl for strategic reserve areas; CZ-ld for green and leisure areas; CZ-sn for transportation hub areas; CZ-gg for concentrated public facilities areas; HY-yy for fishery areas; HY-ts for special-purpose areas; HY-yq for recreational areas; HY-gk for industrial, mining, and communication areas; HY-yl for marine reserve areas; and HY-jt for transportation areas.

[0185] Furthermore, the industry carbon emission factor database in step a3 includes a carbon emission factor matrix constructed from energy sources and corresponding carbon emission factors; the energy sources include electricity, natural gas, heating, and gasoline; the carbon emission factors are determined according to the IPCC National Greenhouse Gas Inventory Guidelines.

[0186] For example, calculating the carbon emission factor of natural gas. The specific formula can be:

[0187] ;

[0188] Among them, the lower heating value can be taken as the default value, which is 389.3 (unit: GJ / 10,000). ), which represents the energy value of fuel per unit volume;

[0189] Carbon content per unit calorific value: can be based on the elemental composition of the fuel, and is taken as 0.0153 (unit: tC / GJ), reflecting the mass of carbon element corresponding to each unit of energy;

[0190] Carbon oxidation rate: Based on actual combustion efficiency data, the value is taken as 0.99 (that is, 99% of the carbon is completely oxidized to carbon dioxide).

[0191] Conversion factor: can be determined based on the molecular weight ratio ( =44 / 12), with a value of 3.67.

[0192] Furthermore, the correlation framework includes a mapping matrix between land use type, energy consumption, and carbon emission intensity.

[0193] Furthermore, the formulas for calculating carbon emissions for various land uses include:

[0194] Carbon emissions from residential areas (Unit: tons of carbon dioxide equivalent):

[0195] ;

[0196] in, This indicates the amount of natural gas consumed, expressed in gigajoules (GJ). This indicates the lower heating value of natural gas, expressed in gigajoules per 10,000 standard cubic meters (GJ / 10,000 cubic meters). ); This indicates the carbon content per unit of calorific value, expressed in tons of carbon per gigajoul (tC / GJ). Indicates the carbon oxidation rate; express Conversion factor; This indicates the number of motor vehicles owned by an individual. Indicates the average annual mileage; This indicates fuel consumption per 100 kilometers; Indicates the gasoline volume conversion factor; This indicates the total electricity consumption, expressed in ten thousand kilowatt-hours (kWh). ); The carbon emission factor for electricity is expressed in tons of carbon dioxide equivalent per 10,000 kilowatt-hours.

[0197] Carbon emissions from industrial development zones :

[0198] ;

[0199] in, Indicates the amount of heat supplied; Indicates the thermal carbon emission factor; Indicates the total amount of gasoline used; Indicates the carbon emission factor of gasoline;

[0200] Carbon emissions from business districts :

[0201] ;

[0202] Carbon emissions from integrated service areas :

[0203] ;

[0204] Carbon emissions of the science and technology innovation development zone :

[0205] ;

[0206] Carbon emissions from public facilities concentration areas :

[0207] ;

[0208] Carbon emissions from marine areas used for industrial, mining, and communications purposes :

[0209] ;

[0210] Carbon emissions of cultural tourism areas :

[0211] ;

[0212] in, Indicates the number of tourists; Indicates per capita carbon footprint;

[0213] Carbon emissions from transportation hubs :

[0214] ;

[0215] in, Indicates passenger flow;

[0216] Carbon emissions from logistics and warehousing areas :

[0217] ;

[0218] in, This indicates the freight turnover on highways, expressed in ton-kilometers (t·km). Expressed as carbon intensity of highways, the unit is kilograms of CO2 equivalent per ton-kilometer (tKL). ); Indicates the volume of goods transported by waterway; Indicates the carbon intensity of the waterway;

[0219] Carbon emissions from green recreational areas :

[0220] ;

[0221] in, Indicates the first The area of ​​plant-like carbon fixation factors; Indicates the carbon sequestration ratio of the carbon fixation factor;

[0222] Carbon emissions from sea areas used for transportation :

[0223] ;

[0224] in, This indicates throughput, expressed in tons. This indicates the intensity of cargo turnover per unit, expressed in kilograms of carbon dioxide equivalent per ton-kilometer.

[0225] Carbon emissions from recreational marine areas :

[0226]

[0227] Carbon emissions from farmland protection areas :

[0228] ;

[0229] in, Indicates the total amount of fertilizer applied; Indicates the carbon emission factor of fertilizer; Indicates the first The area of ​​carbon sequestration factors similar to those found in crops.

[0230] Furthermore, the spatial overlay analysis in step a4 includes associating land use codes with the carbon emission factor matrix using the Spatial Join tool in ArcGIS Pro, thereby facilitating the calculation of carbon emissions for individual zones.

[0231] Furthermore, the spatial aggregation refers to calculating the total carbon emissions by summarizing them level by level according to the land use type code.

[0232] Furthermore, the specific method for generating the spatial distribution heatmap includes:

[0233] Step a51: Employ the Weighted Kernel Density Estimation (WKDE) method, incorporating carbon emissions as a weighting factor into the spatial density analysis. The specific formula includes:

[0234] ;

[0235] in, Indicates spatial location Carbon emission density value at the location; Indicates the number of carbon emission points; Indicates the first The weighting factor for each carbon emission point is expressed in tons of CO2 equivalent per square kilometer. Represents the kernel function; This represents the bandwidth, i.e., the search radius, for example, set to 500 meters;

[0236] Step a52: Collect carbon emission point data and preprocess it, with the format uniformly set to GeoJSON; the carbon emission point data includes latitude and longitude and carbon emission amount;

[0237] Step a53: Generate grid density from carbon emission point data using a weighted kernel density estimation method;

[0238] Step a54: Based on the grid density, visualize the data using a geographic information tool (such as PyQGIS) to obtain geospatial data.

[0239] Furthermore, the visualization output includes:

[0240] When the carbon emission density is less than 5 tons / km², cool colors (such as blue) are used.

[0241] When the carbon emission density is greater than 20 tons / km², a red-black gradient color scheme is used.

[0242] Overlay contour lines;

[0243] Mark the carbon emission intensity threshold (e.g., 10 tons / km²) as a warning line;

[0244] This makes it easier to visually represent the stepwise distribution of carbon emission density.

[0245] Furthermore, in geospatial data, carbon sink land is manually labeled using geographic information tools (such as ArcGIS): green fill indicates terrestrial carbon sink land; light blue fill indicates marine carbon sink land.

[0246] Furthermore, the specific calculation methods for the carbon sink include the calculation of terrestrial carbon sink and the calculation of marine carbon sink;

[0247] The land carbon sink The specific formulas for the calculation include:

[0248] ;

[0249] in, Indicates the first The land area for carbon sink elements is measured in hectares (ha). Carbon sink elements mainly include mountains (forests), water (inland lakes and rivers), fields and grasslands. The land area for each element can be determined based on planning zones and satellite remote sensing observations. Indicates the first The carbon sequestration rate of carbon sink elements is expressed in tons of carbon per hectare per year (tC / ha•yr), and can be initially determined according to the "Guidelines for Carbon Sequestration Accounting in Terrestrial Ecosystems" or the "Table of Carbon Sequestration Rates in Farmland Soils". The coefficient representing the conversion of carbon dioxide into carbon;

[0250] The marine carbon sink specifically includes mangrove carbon sink, shellfish carbon sink, and sediment carbon sink, etc.

[0251] The carbon sequestration of mangroves The specific calculation formulas include:

[0252] ;

[0253] in, Biomass is expressed in tons. This indicates the carbon content of biomass, expressed in tons of carbon per ton (tC / t).

[0254] The carbon sequestration of shellfish The specific calculation formulas include:

[0255] ;

[0256] in, This indicates stocking density, expressed as individuals per hectare. This represents the average shell weight of a single mollusk, expressed in grams per mollusk. Indicates the carbon content coefficient of seashells;

[0257] The carbon sink in the sediment The specific calculation formulas include:

[0258] ;

[0259] in, This indicates the area of ​​the ocean, expressed in square meters. Indicates the first Organic carbon content of sedimentary layers, expressed as a percentage; This represents the percentage of ocean area covered by sediment.

[0260] Furthermore, the specific calculation method for the net emissions is as follows: the carbon emissions of the statistical subject minus the carbon sink of the statistical subject; the statistical subject can be the city being measured, or several districts of the city being measured, without limitation.

[0261] Step 2: Store the basic carbon emission data, carbon sink data, and output data collected periodically by the smart city system in the smart city database based on time series. Based on a trained conventional LSTM (Long Short-Term Memory) model, predict the future carbon emissions, carbon sinks, and output of the tested area, thereby effectively capturing long-term dependencies in the time series. Construct a time series dynamic optimization model, and based on the future carbon emissions, carbon sinks, and output of the tested area, dynamically adjust the fitness evaluation function through a parallelized conventional genetic algorithm to iteratively solve for the optimal industrial area layout scheme for the tested area in the future.

[0262] Furthermore, the smart city system includes a carbon emission sensing system, a carbon sink sensing system, and an output value sensing system;

[0263] The carbon emission sensing system includes chimney sensors, monitoring cameras, energy consumption IoT networks, etc.

[0264] The chimney sensor is used to collect the carbon emissions from the chimney.

[0265] The monitoring camera is used to collect passenger flow data;

[0266] The energy consumption IoT network (including smart meters, smart water meters, smart natural gas meters, smart heating stations, smart gas stations, etc.) is used to collect data on electricity consumption, gas consumption, heat supply, and oil consumption.

[0267] The carbon sink sensing system includes remote sensing satellites, soil sensors, smart buoys, and marine sonar, etc.

[0268] The remote sensing satellite is used to collect data on the area of ​​terrestrial vegetation and carbon dioxide absorption efficiency.

[0269] The smart buoy is used to collect data on the carbon dioxide absorption efficiency of mangroves.

[0270] The marine sonar is used to collect carbon sequestration data from shellfish and seabed sediments.

[0271] The output value sensing system is connected to the enterprise's ERP system and other systems to collect enterprise output value data.

[0272] Furthermore, the time-series dynamic optimization model includes a sliding time window based on the planning period; for example, the model is optimized once per quarter, with each planning (phase) covering the next three years;

[0273] It also includes dynamic variables, specifically:

[0274] No. The first time period The first partition Land area for each industry ;

[0275] No. The first time period The first partition Area of ​​each carbon sink element ;

[0276] It also includes the objective function, specifically including:

[0277] ;

[0278] in, This represents the total planning duration, and this value needs to be minimized in order to achieve the goal of emission reduction and efficiency improvement as soon as possible; This indicates the duration of each planning phase; Indicates the planning stage; This represents the discount rate, which is set according to the fiscal policy of the city being measured. and This indicates a dynamic weight that can be adjusted according to the policy priorities of the city being measured. The cumulative output value is represented by the following formula:

[0279] ;

[0280] in, Indicates the first The first partition The industry in The output value per unit area in a given period can increase over time due to factors such as technological advancements.

[0281] The net emission penalty during the planning phase is represented by the following formula:

[0282] ;

[0283] in, Indicates the first The first partition The carbon emission intensity of an industry can decrease over time due to factors such as technological progress; Indicates the first The first partition The carbon sequestration capacity of each carbon sink element increases over time due to factors such as plant growth, as shown in the specific formula:

[0284] ;

[0285] in, It represents the carbon sequestration maturity rate, used to simulate the growth of vegetation's carbon sequestration capacity from planting to forestation; Represents the natural constant;

[0286] It also includes dynamic constraints, specifically including:

[0287] The total land area constraint is expressed as follows:

[0288] ;

[0289] in, Indicates the first The total area of ​​each zone;

[0290] The industrial continuity constraint is specifically expressed as follows:

[0291] ;

[0292] in, This represents the threshold for changes in land area, used to restrict a sharp decrease in industrial area.

[0293] The carbon neutrality path constraint is specifically expressed as follows:

[0294] ;

[0295] in, Indicates the first time period of each time period Net emissions at each point in time; This represents the slope of the linearly decreasing target line.

[0296] Furthermore, such as Figure 3 As shown, the parallelized genetic algorithm includes:

[0297] Step b1: Use the objective function of the time-series dynamic optimization model as the fitness evaluation function; configure the DEAP (Distributed Evolutionary Algorithms in Python) toolbox to support parallel processing;

[0298] Step b2: Perform multi-process (e.g., 4-process) distributed computing using the conventional scoop (Simple Concurrent Object-Oriented Programming) framework;

[0299] Step b3: Based on the sliding time window, periodically obtain the latest data from the smart city database, update the fitness evaluation function, iteratively execute the genetic algorithm, and extract the optimal solution.

[0300] Furthermore, the industrial area layout plan includes the land area, output value, and net carbon emission value of each industry in the zone, so as to obtain the zone benefits with the highest output value and the lowest net carbon emission value in the shortest time.

[0301] Step 3: Based on the industrial area layout plan, generate suggested information through preset strategies and send it to the server of the competent department of the tested area through smart contracts (such as blockchain) to ensure data security and prevent tampering; based on the smart city database, compare the predicted data (carbon emissions, carbon sinks and output value) with the actual data at regular intervals and update the parameters of the LSTM model; in this way, the industrial area layout plan can be effectively implemented and the LSTM model can be calibrated through closed-loop feedback.

[0302] Furthermore, the preset strategy includes a land use adjustment strategy: first, sort the industries in the partition according to their net carbon emissions, then select the high-carbon industries with the largest net carbon emissions, and generate suggestions for reducing the land area; then, sort the remaining industries according to their output value, then select the high-yield industries with the largest output value, and generate suggestions for expanding the land area.

[0303] Furthermore, such as Figure 4 As shown, the specific method for generating the narrowed suggestion information includes:

[0304] Step c1: Calculate the reduced total area The specific formula is as follows:

[0305] ;

[0306] in, Indicates the first The current land area used by a high-carbon industry; Indicates the preset total reduction ratio;

[0307] Step c2: Sort high-carbon industries in descending order of carbon emission intensity per unit area;

[0308] Step c3: Starting with the highest-ranked high-carbon industries, reduce their area as needed until the requirements are met. The specific formulas include:

[0309] ;

[0310] in, Indicates the first The reduction in the area of ​​a high-carbon industry; express The remaining area is calculated using the following formula:

[0311] .

[0312] Furthermore, such as Figure 5 As shown, the specific method for generating the expanded suggestion information includes:

[0313] Step d1: Reduce the total area of ​​high-carbon industries. This represents an expansion of the total area for high-yield industries.

[0314] Step d2: Arrange high-yield industries in descending order of output value per unit area;

[0315] Step d3: Starting with the highest-ranked high-yield industry, allocate resources. Until exhausted, the specific formula includes:

[0316] ;

[0317] in, Indicates the first The expansion of the area of ​​a high-yield industry; express The remaining area is calculated using the following formula:

[0318] .

[0319] In this way, while keeping the zoning land area unchanged, we can obtain more accurate land area adjustment suggestions by greedily shrinking and greedily expanding, which is conducive to the goal of low-carbon and high-growth urban development.

[0320] Example 2:

[0321] like Figure 6 As shown, this embodiment provides a carbon neutrality zoning simulation system based on smart cities, including a data receiving module, a data processing module, and a result generation module;

[0322] The data receiving module is used to receive maps of the planned zones of the tested city, basic carbon emission data, basic carbon sink data, and basic output data.

[0323] The data processing module includes a geospatial data unit, a data prediction unit, a dynamic optimization unit, and a suggestion information unit;

[0324] The geospatial data unit calculates the carbon emissions of each region based on maps and basic carbon emission data, and performs visualization processing to obtain geospatial data; it also marks the basic carbon sink data in the geospatial data and calculates the carbon sink amount of each region; it calculates the net emissions of the measured city based on carbon emissions and carbon sink amount; and it marks the basic output value data of each industry in the geospatial data.

[0325] The data prediction unit, based on a trained LSTM (Long Short-Term Memory) model, predicts the future carbon emissions, carbon sinks, and output value of the tested partition; it also compares the predicted data with the actual data at regular intervals and updates the parameters of the LSTM model.

[0326] The dynamic optimization unit constructs a time-series dynamic optimization model. Based on the future carbon emissions, carbon sinks, and output value of the tested area, it dynamically adjusts the fitness evaluation function through a parallel genetic algorithm and iteratively solves the optimal industrial area layout scheme for the tested area in the future.

[0327] The suggestion information unit generates suggestion information based on the industrial area layout plan and through a preset strategy;

[0328] The result generation module is used to send out the industrial area layout plan and the suggested information.

[0329] Furthermore, the data receiving module is connected to the smart city system of the city being tested, and is used to access the smart city database.

[0330] Example 3:

[0331] This embodiment provides a carbon neutrality zoning simulation device based on smart cities, including a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute the carbon neutrality zoning simulation method based on smart cities as described above. The bus connects the various functional components for information transmission.

[0332] In another implementation, this solution can be achieved through an integrated device, which may include corresponding modules that perform one or more steps in the various embodiments described above. A module may be one or more hardware modules specifically configured to perform the corresponding step, or implemented by a processor configured to perform the corresponding step, or stored in a computer-readable medium for implementation by a processor, or implemented through some combination thereof.

[0333] The processor executes the various methods and processes described above. For example, the method implementations in this scheme can be implemented as software programs tangibly contained in a machine-readable medium, such as memory. In some implementations, part or all of the software program can be loaded and / or installed via memory and / or a communication interface. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above can be performed. Alternatively, in other implementations, the processor can be configured to execute one of the methods described above by any other suitable means (e.g., by means of firmware).

[0334] This device can be implemented using a bus architecture. A bus architecture can include any number of interconnect buses and bridges, depending on the specific application of the hardware and overall design constraints. The bus connects various circuits, including one or more processors, memory, and / or hardware modules. The bus can also connect various other circuits such as peripherals, voltage regulators, power management circuitry, external antennas, etc.

[0335] Buses can be Industry Standard Architecture (ISA) buses, Peripheral Component Interconnect (PCI) buses, or Extended Industry Standard Component (EISA) buses, etc. Buses can be divided into address buses, data buses, control buses, etc.

[0336] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A carbon neutrality zoning simulation method based on smart cities, characterized in that, include: Step 1: Divide the map of the city being tested into different zones; Based on standards and literature, we collected basic carbon emission data, calculated the carbon emissions of each zone and visualized them to obtain geospatial data; we collected basic carbon sink data and marked it in the geospatial data, and calculated the carbon sink of each zone; based on carbon emissions and carbon sink, we calculated the net emissions of the tested city; and we collected basic output data of each industry in the tested zone and marked it in the geospatial data. Step 2: The carbon emission, carbon sink, and output data collected periodically by the smart city system are stored in the smart city database based on time series data. Then, based on a trained LSTM model, the future carbon emissions, carbon sinks, and output of the tested area are predicted. A time-series dynamic optimization model is constructed. Based on the future carbon emissions, carbon sinks, and output of the tested area, a parallel genetic algorithm is used to dynamically adjust the fitness evaluation function and iteratively solve for the optimal industrial area layout scheme for the tested area. The industrial area layout scheme includes the land area, output, and net carbon emissions of each industry in the area. Step 3: Based on the optimal industrial area layout plan for the tested area in the future, generate suggested information through preset strategies and send it to the competent authority's server of the tested area through smart contracts. Based on the smart city database, the predicted data is compared with the actual data at regular intervals to update the parameters of the LSTM model.

2. The method according to claim 1, characterized in that, The planning zones include primary planning zones and secondary planning zones; The primary planning zones include urban development zones, farmland protection zones, ecological control zones, ecological protection zones, and marine development zones. The secondary planning zones of the urban development area include residential areas, commercial and business areas, comprehensive service areas, cultural and tourism areas, industrial development areas, science and technology innovation development areas, logistics and warehousing areas, strategic reserve areas, green and leisure areas, transportation hub areas, and public facilities concentration areas. The secondary planning zones of the marine development zone include fishery sea areas, special sea areas, recreational sea areas, industrial, mining and communication sea areas, marine reserve areas, and transportation sea areas.

3. The method according to claim 1, characterized in that, The specific methods for acquiring the geospatial data include: Step a1: Based on the planning zoning, obtain the spatial distribution data and land use scale data of each zoning; Step a2: Construct a database of land use type codes and land area; Step a3: Based on carbon emission standard documents, construct an industry emission factor database and build a framework for the correlation between greenhouse gas emission inventory accounting categories and land use types; based on carbon emission literature, obtain initial values ​​of carbon emission intensity. Step a4: Through spatial overlay analysis, match land use scale data, land use type codes with corresponding carbon emission intensity, and calculate the carbon emissions of various types of land use. Step a5: Spatially aggregate the carbon emissions of all zones within the city to generate a heat map of total carbon emissions and spatial distribution, thus obtaining geospatial data.

4. The method according to claim 3, characterized in that, In step a2, the land use type coding includes primary coding and secondary coding; The primary coding includes: CZ for urban development zones; NT for farmland protection zones; STKZ for ecological control zones; STBH for ecological protection zones; and HY for marine development zones. The secondary codes include: CZ-jz for residential areas; CZ-ss for commercial and business areas; CZ-zh for comprehensive service areas; CZ-wh for cultural and tourism areas; CZ-gy for industrial development areas; CZ-kc for science and technology innovation development areas; CZ-wl for logistics and warehousing areas; CZ-yl for strategic reserve areas; CZ-ld for green and leisure areas; CZ-sn for transportation hub areas; CZ-gg for concentrated public facilities areas; HY-yy for fishery areas; HY-ts for special-purpose areas; HY-yq for recreational areas; HY-gk for industrial, mining, and communication areas; HY-yl for marine reserve areas; and HY-jt for transportation areas.

5. The method according to claim 4, characterized in that, The formulas for calculating carbon emissions for various land uses include: Carbon emissions from residential areas : ； in, Indicates the amount of natural gas used; This indicates the lower heating value of natural gas; This indicates the carbon content per unit of calorific value. Indicates the carbon oxidation rate; express Conversion factor; This indicates the number of motor vehicles owned by an individual. Indicates the average annual mileage; Indicates fuel consumption per 100 kilometers; Indicates the gasoline volume conversion factor; Indicates total electricity consumption; Indicates the carbon emission factor of electricity; Carbon emissions from industrial development zones : ； in, Indicates the amount of heat supplied; Indicates the thermal carbon emission factor; This indicates the total amount of gasoline used; Indicates the carbon emission factor of gasoline; Carbon emissions from business districts : ； Carbon emissions from integrated service areas : ； Carbon emissions of the science and technology innovation development zone : ； Carbon emissions from public facilities concentration areas : ； Carbon emissions from marine areas used for industrial, mining, and communications purposes : ； Carbon emissions of cultural tourism areas : ； in, Indicates the number of tourists; Indicates per capita carbon footprint; Carbon emissions from transportation hubs : ； in, Indicates passenger flow; Carbon emissions from logistics and warehousing areas : ； in, Indicates highway freight turnover; Indicates the carbon intensity of the highway; Indicates the volume of goods transported by waterway; Indicates the carbon intensity of the waterway; Carbon emissions from green recreational areas : ； in, Indicates the first The area of ​​plant-like carbon fixation factors; Indicates the carbon sequestration ratio of the carbon fixation factor; Carbon emissions from sea areas used for transportation : ； in, Indicates throughput; Indicates the intensity of unit cargo turnover; Carbon emissions from recreational marine areas : ； Carbon emissions from farmland protection areas : ； in, Indicates the total amount of fertilizer applied; Indicates the carbon emission factor of fertilizer; Indicates the first The area of ​​carbon sequestration factors similar to those found in crops.

6. The method according to claim 3, characterized in that, The specific method for generating the spatial distribution heatmap includes: Step a51: Employ the weighted kernel density estimation method, incorporating carbon emissions as a weighting factor into the spatial density analysis. Specific formulas include: ； in, Indicates spatial location Carbon emission density value at the location; Indicates the number of carbon emission points; Indicates the first Weighting factors for each carbon emission point; Represents the kernel function; Indicates bandwidth; Step a52: Collect carbon emission point data and preprocess it, with the format uniformly set to GeoJSON; the carbon emission point data includes latitude and longitude and carbon emission amount; Step a53: Generate grid density from carbon emission point data using a weighted kernel density estimation method; Step a54: Based on the grid density, use geographic information tools to generate a visualization output to obtain a spatial distribution heat map.

7. The method according to claim 6, characterized in that, The visualization output includes: When the carbon emission density is less than 5 tons / km², cool colors should be used; When the carbon emission density is greater than 20 tons / km², a red-black gradient color scheme is used. Overlay contour lines; Mark the carbon emission intensity threshold warning line.

8. The method according to claim 6, characterized in that, The specific calculation methods for carbon sink include land carbon sink calculation and marine carbon sink calculation; The land carbon sink The specific formulas for the calculation include: ； in, Indicates the first The land area for carbon sink elements, which include mountains, water, fields and grasslands; Indicates the first Carbon sequestration rate of carbon sink elements; The coefficient representing the conversion of carbon dioxide into carbon; The marine carbon sink specifically includes mangrove carbon sink, shellfish carbon sink, and sediment carbon sink; The carbon sequestration of mangroves The specific calculation formulas include: ； in, Indicates biomass; Indicates the carbon content of biomass; The carbon sequestration of shellfish The specific calculation formulas include: ； in, Indicates stocking density; This represents the average shell weight of a single mollusk; Indicates the carbon content coefficient of seashells; The carbon sink in the sediment The specific calculation formulas include: ； in, Indicates the area of ​​the ocean; Indicates the first Organic carbon content of sediment layers; This represents the percentage of ocean area covered by sediment.

9. A carbon neutrality zoning simulation system for smart cities using any one of the simulation methods described in claims 1-8, characterized in that, It includes a data receiving module, a data processing module, and a result generation module; The data receiving module is used to receive maps of the planned zones of the tested city, basic carbon emission data, basic carbon sink data, and basic output data. The data processing module includes a geospatial data unit, a data prediction unit, a dynamic optimization unit, and a suggestion information unit; The geospatial data unit, based on maps and basic carbon emission data, calculates the carbon emissions of each zone and performs visualization processing to obtain geospatial data. Carbon sink baseline data are annotated in geospatial data and carbon sink volume for each region is calculated; net emissions for the measured city are calculated based on carbon emissions and carbon sink volume; and output value baseline data for each industry are annotated in geospatial data. The data prediction unit, based on a trained LSTM model, predicts the future carbon emissions, carbon sinks, and output value of the tested area; it also compares the predicted data with the actual data at regular intervals and updates the parameters of the LSTM model. The dynamic optimization unit constructs a time-series dynamic optimization model. Based on the future carbon emissions, carbon sinks, and output value of the tested area, it dynamically adjusts the fitness evaluation function through a parallel genetic algorithm and iteratively solves the optimal industrial area layout scheme for the tested area in the future. The suggestion information unit generates suggestion information based on the industrial area layout plan and through a preset strategy; The result generation module is used to send out the industrial area layout plan and the suggested information.

10. A carbon neutrality zoning simulation device based on smart cities, characterized in that, It includes a processor, a memory, and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory to execute the method as described in any one of claims 1-8. The bus connects the functional components for transmitting information.

Images