Carbon emission tracking and source analysis method and device combined with geographic information system

Abstract

The invention relates to the technical field of environmental protection, and discloses a carbon emission tracking and source analysis method and device combined with a geographic information system, and the method comprises the steps: collecting carbon emission data and multi-dimensional geographic data, carrying out the carbon emission source positioning and spatial distribution analysis, and recognizing a high-carbon emission region; tracking a carbon emission path, simulating the diffusion of carbon emissions, and evaluating the contribution of each emission source and geographic features to the total carbon emission; and carrying out visual display on the carbon emission path, the diffusion simulation result and the multi-source analysis result. Through data acquisition, path tracking, diffusion simulation and multi-source analysis and contribution degree analysis, not only can the carbon emission source and the spatial distribution thereof be efficiently identified, but also the change of the carbon emission can be dynamically tracked in real time, scientific data support is provided, an effective basis is provided for making a low-carbon policy and implementing a carbon emission reduction measure, and the method is suitable for popularization and application. And accurate management of regional carbon emission can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection, and particularly to a carbon emission tracking and source analysis method and device combined with a geographic information system. Background Art

[0002] With the increasingly serious problem of global climate change, the monitoring and management of carbon emissions have become one of the key measures to address climate change. Most countries and regions have set carbon emission control targets and are continuously strengthening the monitoring and analysis of carbon emissions. Traditional carbon emission monitoring methods mainly rely on regional total statistics. Although this method can provide approximate emission data, it is difficult to accurately identify the spatial distribution and dynamic changes of emission sources, and it is also unable to effectively track the diffusion path of emissions. Therefore, how to achieve accurate carbon emission source localization, track the diffusion path of emissions, and analyze the contribution degree of different emission sources has become a difficult problem in carbon emission management.

[0003] In the existing technologies, there is less research on the spatial localization and path tracking of carbon emission sources. Most carbon emission source identification methods rely on a single data source (such as emission statistics data) or a fixed geographical model, lacking adaptability to dynamic changes. For example, conventional carbon emission source analysis methods cannot handle complex geographical information (such as traffic flow, population density, land use type, etc.), and there are also large limitations in the simulation of the diffusion path of carbon emissions. Therefore, the existing technologies often cannot accurately reflect the spatio-temporal distribution and dynamic characteristics of carbon emissions, and it is difficult to provide effective decision-making support for low-carbon policies and emission source governance.

[0004] To make up for these deficiencies, there is an urgent need for a new method that can combine carbon emission data and multi-dimensional geographical information to accurately locate carbon emission sources, track paths, simulate diffusion, and conduct multi-source analysis, so as to provide scientific support for the refined management of regional carbon emissions and the implementation of low-carbon policies. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a carbon emission tracking and source analysis method combined with a geographic information system to solve the problem of how to accurately reflect the spatio-temporal distribution and dynamic characteristics of carbon emissions.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a carbon emission tracking and source analysis method combined with a geographic information system, including: collecting carbon emission data and multi-dimensional geographical data, and performing data preprocessing; Based on the preprocessed carbon emission data and multi-dimensional geographical data, performing carbon emission source localization and spatial distribution analysis to identify high-carbon emission regions; Based on the high-carbon emission regions, track the carbon emission paths and simulate the diffusion of carbon emissions to obtain the concentration changes of carbon emissions within the regions; Through a multi-source analysis algorithm, quantitatively analyze different carbon emission sources and geographical features, and evaluate the contributions of each emission source and geographical feature to the total carbon emissions; Based on the results of the carbon emission path and diffusion simulation and the multi-source analysis results, obtain the spatial distribution and change trend of carbon emissions, and compare the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results.

[0007] As a preferred embodiment of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, the method includes: collecting carbon emission data and multi-dimensional geographical data, and performing data preprocessing including: The carbon emission data includes the carbon emissions of each emission source. The emission sources include multiple categories of emission sources, and time-dimensional change data of each emission source is obtained; The multi-dimensional geographical data includes multiple geographical features related to the locations of the emission sources; Perform preprocessing on the collected carbon emission data and multi-dimensional geographical data, including data standardization processing and spatial matching processing, associate the carbon emission data with the corresponding geographical data, and generate an associated data set including carbon emissions, emission source locations, and geographical features.

[0008] As a preferred embodiment of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, the method includes: performing carbon emission source location and spatial distribution analysis, including: Match the geographical coordinates of the carbon emission sources with the carbon emission data, perform spatial location on the carbon emission sources, mark the locations of each carbon emission source, generate a carbon emission source distribution map through map visualization, and mark the carbon emission intensities of different regions; Generate a heat map according to the carbon emissions of different regions through a hot spot analysis algorithm; Perform hot spot analysis through a spatial statistical analysis algorithm, calculate the correlation degree between the carbon emission intensity of each region and the surrounding regions to identify high-carbon emission regions.

[0009] As a preferred embodiment of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, the method includes: tracking the carbon emission paths and simulating the diffusion of carbon emissions, including: Through a path analysis algorithm, track the diffusion paths of the carbon emission sources, determine the diffusion directions and paths of the carbon emissions, and calculate the shortest path from the emission source point to the target region according to the minimum cost path; Simulate the diffusion behavior of the carbon emissions through a Gaussian diffusion model and calculate the concentration changes of the carbon emissions.

[0010] As a preferred solution of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, wherein: the path analysis algorithm includes: Extract the geographical features of the carbon emission path, and use the Dijkstra algorithm or A* algorithm to calculate the minimum cost path from the carbon emission source point to the target area; According to the path costs calculated based on different geographical features, combined with the diffusion path of carbon emissions and traffic flow data, analyze the influence degree of the geographical features on carbon emission diffusion.

[0011] As a preferred solution of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, wherein: evaluating the contribution of each emission source to the total carbon emissions includes: Construct a random forest model, calculate the feature importance coefficient of each geographical feature, so as to obtain the contribution degree of different geographical features to carbon emissions; Classify different sources of carbon emission sources, identify and calibrate the emission source types, and calculate the contribution of each emission source to the total carbon emissions through machine learning algorithms.

[0012] As a preferred solution of the carbon emission tracking and source analysis method combined with a geographic information system according to the present invention, wherein: visualizing the carbon emission path, diffusion simulation results and multi-source analysis results includes: Perform visual display through GIS, generate a carbon emission distribution map, a carbon emission diffusion path map and a hotspot map, and respectively display the spatial distribution of carbon emission sources, the diffusion path and the hotspot area of carbon emissions; Among them, the carbon emission distribution map shows the carbon emission intensity and carbon emissions of each region; The diffusion path map simulates the diffusion path of carbon emissions and shows the movement trajectory of carbon emissions from the source point to the target area; The hotspot map shows the carbon emission intensive areas.

[0013] In a second aspect, the present invention provides a carbon emission tracking and source analysis device combined with a geographic information system, including: An acquisition module, configured to acquire carbon emission data and multi-dimensional geographic data, and perform data preprocessing; A positioning module, configured to perform carbon emission source positioning and spatial distribution analysis based on the preprocessed carbon emission data and multi-dimensional geographic data, and identify high-carbon emission areas; A tracking and simulation module, configured to track the carbon emission path based on the high-carbon emission area, and simulate the diffusion of carbon emissions, so as to obtain the concentration change of carbon emissions in the area; An analysis module for quantitatively analyzing different carbon emission sources and geographical features through a multi-source parsing algorithm to evaluate the contributions of each emission source and geographical feature to the total carbon emissions; An output module for obtaining the spatial distribution and change trend of carbon emissions based on the results of carbon emission path and diffusion simulation and multi-source parsing results, and comparing the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results.

[0014] In a third aspect, the present invention provides an electronic device, comprising: A memory and a processor; The memory is used for storing computer-executable instructions, and the processor is used for executing the computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the carbon emission tracking and source parsing method combined with the geographic information system are implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the carbon emission tracking and source parsing method combined with the geographic information system are implemented.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining carbon emission data and multi-dimensional geographic information, the present invention accurately locates the positions of carbon emission sources, solves the problem that traditional methods cannot accurately identify carbon emission sources. Through accurate positioning, not only can the identification accuracy of carbon emission sources be improved, but also a reliable basis for formulating low-carbon policies is provided; Dynamically track the carbon emission path. Using path analysis algorithms and diffusion simulations, the present invention can track the diffusion path of carbon emissions and analyze its impact on the surrounding areas. This technology has strong spatial accuracy and dynamic adaptability, can reflect the diffusion process of carbon emissions in real time, and provide a more accurate diffusion model; Quantitatively analyze the contribution degree of emission sources. Through multi-source analysis technology and random forest models, the contribution of different emission sources (such as transportation, industry, residential areas, etc.) to the total carbon emissions can be quantitatively analyzed, providing a scientific basis for formulating low-carbon policies. Through source analysis, policymakers can clearly understand the distribution and contribution of major emission sources, and thus formulate targeted treatment plans; Support spatio-temporal dynamic analysis. By combining time-series data, analyze the temporal dynamic changes of carbon emissions, reveal the change laws of carbon emissions during specific time periods, and provide more accurate data support for carbon emission control and prediction. Through dynamic analysis, it can respond to carbon emission changes in real time and adjust emission reduction strategies in a timely manner; Visualization and decision support. Visualize the tracking, source analysis, and diffusion simulation results of carbon emissions through a GIS platform to help decision-makers intuitively understand the spatial distribution and diffusion path of carbon emissions, and support the formulation of accurate carbon emission reduction policies and regionally differentiated environmental management measures; Optimize carbon emission management. Through carbon emission tracking and source analysis methods, it can provide more accurate data support for regional carbon emission management, help optimize carbon emission monitoring and governance measures, and promote the development of a low-carbon economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of the overall process of the carbon emission tracking and source analysis method combined with a geographic information system according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the carbon emission source and multi-dimensional geographic information data fusion process of the carbon emission tracking and source analysis method combined with a geographic information system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0020] Embodiment 1 Referring to Figure 1 - Figure 2 , for an embodiment of the present invention, a carbon emission tracking and source analysis method combined with a geographic information system is provided, including: S100, collecting carbon emission data and multi-dimensional geographic data, and performing data preprocessing; S200, based on the preprocessed carbon emission data and multi-dimensional geographic data, performing carbon emission source location and spatial distribution analysis to identify high-carbon emission regions; S300, based on the high-carbon emission regions, tracking the carbon emission paths and simulating the diffusion of carbon emission substances to obtain the concentration changes of carbon emission substances within the region; S400, through a multi-source analysis algorithm, quantitatively analyzing different carbon emission sources and geographical features to evaluate the contributions of each emission source and geographical feature to the total carbon emissions; S500, based on the carbon emission path and diffusion simulation results and the multi-source analysis results, obtaining the spatial distribution and change trend of carbon emissions, and comparing the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results.

[0021] In a preferred embodiment, collecting carbon emission data and multi-dimensional geographic data and performing data preprocessing includes: The carbon emission data includes the carbon emissions of each emission source. The emission sources include multiple categories of emission sources, and the time-dimensional change data of each emission source is obtained; The multi-dimensional geographic data includes multiple geographical features related to the positions of the emission sources; Performing preprocessing on the collected carbon emission data and multi-dimensional geographic data, including data standardization processing and spatial matching processing, associating the carbon emission data with the corresponding geographic data, and generating an associated data set including carbon emissions, emission source locations, and geographical features.

[0022] It should be noted that data collection and preprocessing are the first step in realizing carbon emission tracking and source analysis. The present invention first collects multi-dimensional data, including carbon emission data and related geographical information data. Then, by performing standardization processing and spatial matching on the collected data, it is ensured that the data is consistent in time, unit, and space.

[0023] Specifically, the carbon emission data includes the carbon emissions from different emission sources, which can be industries, transportation, residential areas, etc. The carbon emission data of these emission sources are collected separately.

[0024] In an alternative implementation, the carbon emission data collection method for emission sources can be emission source monitoring. By installing sensor devices in industrial areas, transportation facilities, residential areas, etc., the carbon emission data of each emission source can be collected in real time.

[0025] In the second alternative implementation, the carbon emission data of emission sources is collected through remote sensing technology. Devices such as remote sensing satellites and drones are used for atmospheric monitoring to obtain large-scale carbon emission information.

[0026] In the third alternative implementation, the carbon emission data of emission sources is collected through government statistical data. By using the annual carbon emission statistical reports released by the government, the carbon emission data of certain regions or industries can be obtained.

[0027] In an alternative implementation, the multi-dimensional geographical data includes land use data, traffic flow data, population density data, etc. These geographical data can be obtained through government statistics, Geographic Information System (GIS) platforms, and third-party data providers. Among them, land use data: the land use situation of each region is obtained through remote sensing images, cadastral maps, etc., and is classified into industrial areas, residential areas, green spaces, etc.; traffic flow data: traffic flow data is collected through the urban traffic management system or road traffic sensors, especially the vehicle flow on important traffic roads; population density data: the population density information of each region is obtained through government statistical yearbooks, urban planning, etc., and is used to analyze the impact of population on carbon emissions.

[0028] In an alternative implementation, the data preprocessing includes: Data cleaning and denoising, excluding invalid data and outliers, and removing existing noise to ensure the reliability of the data; Unit standardization, converting all carbon emission data and other geographical data into a unified unit (for example, unifying carbon emissions to tons / year and traffic flow to number of vehicles / hour); Time alignment, the data collection times of different sources may be inconsistent, so time alignment is required to ensure that all data is on the same time scale; Spatial matching, using spatial interpolation methods to spatially match the carbon emission data with the geographical information data so that each carbon emission source corresponds to the geographical features of its location.

[0029] In another alternative implementation, data from different sources is standardized to ensure a unified format for subsequent analysis. The standardization steps include unit conversion, time alignment, data cleaning, etc.; a spatial matching algorithm is used to precisely match the carbon emission data with the geographical data, corresponding the geographical coordinates of each carbon emission source with its corresponding carbon emission data to form a complete carbon emission and geographical information database.

[0030] It should be noted that carbon emission data collection usually has a time dimension. Therefore, it is necessary to synchronize the data in time to ensure the consistency of the data on the time axis. If the collected data has missing values, interpolation or smoothing algorithms need to be used to fill the data gaps. The key to data preprocessing is to ensure the consistency and accuracy of the data and avoid the impact of data noise or inconsistency on the analysis results. For example, traffic flow data may have periodic fluctuations, and carbon emission data may have errors between different sources. Therefore, it is necessary to denoise, smooth, and weight the data to ensure the reliability of the analysis results. Through these data preprocessing steps, it can be ensured that the collected data can effectively support subsequent carbon emission tracking and source analysis.

[0031] In a preferred implementation, the carbon emission source location and spatial distribution analysis includes: Match the geographical coordinates of the carbon emission sources with the carbon emission data, spatially locate the carbon emission sources, mark the locations of each carbon emission source, generate a carbon emission source distribution map through map visualization, and mark the carbon emission intensity of different regions; Generate a heat map through a hotspot analysis algorithm based on the carbon emissions of different regions; Conduct hotspot analysis through a spatial statistical analysis algorithm, calculate the correlation between the carbon emission intensity of each region and the surrounding regions to identify high-carbon emission regions.

[0032] It should be noted that after the data preprocessing is completed, this embodiment uses GIS technology for carbon emission source location and spatial distribution analysis. This process mainly includes the spatial location of carbon emission sources, heat map generation, and spatial statistical analysis to help decision-makers quickly identify regions with high carbon emission density.

[0033] In an alternative implementation, the geographical coordinates of the carbon emission sources are combined with the carbon emission data through GIS mapping to precisely locate the position of each emission source on the map and mark it with different colors or symbols according to the level of its emission intensity.

[0034] Specifically, the spatial coordinates of each carbon emission source are matched with its carbon emissions. Through the GIS platform, a spatial distribution map of carbon emission sources is generated. Areas with higher carbon emission intensity are marked in dark red, while areas with lower carbon emissions are marked in light green. In this embodiment, the GIS platform visualizes the geographical coordinates of carbon emission sources, marks the location of each carbon emission source on the map, and uses different colors to mark according to the level of emission intensity, so as to intuitively display the spatial distribution of carbon emissions. The GIS mapping formula is as follows: , wherein, represents the carbon emission data at location . This formula can generate a spatial distribution map showing carbon emission intensity, and the darker the color, the higher the emission intensity.

[0035] In an alternative embodiment, through spatial statistical analysis methods, hotspots of carbon emissions are further identified, that is, areas where carbon emissions are relatively concentrated. Among them, the spatial statistical analysis method can be hotspot analysis (such as Getis-Ord Gi* statistic). The formula for the Getis-Ord Gi* statistic is: , wherein, is the spatial weight between region and region , is the carbon emission of region , is the average value of carbon emissions, is the standard deviation.

[0036] It should be noted that the Getis-Ord Gi* statistic helps analyze the spatial relationship between each region and its surrounding regions, reveals which regions are hotspots of carbon emissions, is applicable to large-scale spatial data analysis, and can accurately identify hotspots with high carbon emission intensity. The hotspot analysis method can identify regions with high carbon emission intensity and analyze the reasons, which is of great significance for determining the main concentrated areas of emission sources and helps decision-makers to carry out targeted governance of these high-emission regions.

[0037] In another alternative embodiment, the spatial statistical analysis method can be spatial autocorrelation analysis, which can identify hotspots (high-value aggregation areas) and cold spots (low-value aggregation areas) of carbon emissions, define indicators, judge whether the spatial data has aggregation by comparing whether the attribute values of adjacent regions are similar, and construct a spatial weight matrix to determine the proximity relationship between observation points within the region, and complete the identification of carbon emission regions.

[0038] It should be noted that through spatial analysis methods, the areas with the most concentrated emissions can be identified and a carbon emission hot spot map can be formed. This map will provide valuable reference data for subsequent carbon emission path tracking and source analysis, and provide data support for formulating more refined regional carbon emission reduction policies.

[0039] Precisely locate and conduct spatial analysis on carbon emission sources, visualize the spatial positions of carbon emission sources, generate a carbon emission source distribution map, and mark each carbon emission source on the map according to its geographical coordinates. Different regions in the map represent regions with different carbon emission intensities. The higher the intensity, the darker the color. Through spatial statistical analysis algorithms, further identify the hot spot areas of carbon emissions, that is, the areas where carbon emissions are relatively concentrated. The hot spot analysis method can identify areas with high carbon emission intensity and analyze the reasons, which is of great significance for determining the main concentrated areas of emission sources and helps decision-makers to carry out targeted governance on these high-emission areas. Through spatial analysis methods, the areas with the most concentrated emissions can be identified and a carbon emission hot spot map can be formed. This map will provide valuable reference data for subsequent carbon emission path tracking and source analysis, and provide data support for formulating more refined regional carbon emission reduction policies.

[0040] In a preferred embodiment, tracking the carbon emission path and simulating the diffusion of carbon emission substances includes: Through the path analysis algorithm, track the diffusion path of the carbon emission source, determine the diffusion direction and path of the carbon emission substances, and calculate the shortest path from the emission source point to the target area according to the minimum cost path. Simulate the diffusion behavior of carbon emission substances through the Gaussian diffusion model and calculate the concentration change of carbon emission substances.

[0041] It should be noted that this embodiment combines the spatial information of carbon emission sources with data such as traffic flow and terrain, and tracks the diffusion path of carbon emission substances through the path analysis method. The path analysis algorithm simulates the diffusion process of carbon emission substances from the source point to the target area by calculating the minimum cost path. The calculation of the diffusion path not only considers the geographical distance in the space, but also needs to consider factors such as road network, traffic flow, and meteorological conditions. Tracking the carbon emission path and simulating the diffusion of carbon emission substances can provide a prediction basis for the management and control of carbon emissions.

[0042] In a preferred embodiment, the path analysis algorithm includes: Extract the geographical features of the carbon emission path, and use the Dijkstra algorithm or A* algorithm to calculate the minimum cost path from the carbon emission source point to the target area. According to the path costs calculated based on different geographical features, combined with the diffusion path of carbon emission substances and traffic flow data, analyze the influence degree of geographical features on carbon emission diffusion.

[0043] In an optional embodiment, the GIS path analysis algorithm may be an A* algorithm, which uses heuristic search to improve efficiency to calculate the diffusion path of carbon emissions, which is expressed as: , in, Indicates that from the source To the destination The minimum cost path, For the path The cost of a node.

[0044] In another optional implementation, the GIS path analysis algorithm can be a Dijkstra algorithm, which calculates the shortest path from the starting point to the target point. It gradually finds the global optimal solution by continuously expanding the currently known shortest path nodes and updating the distance values of adjacent nodes. It is applicable to the case where all edge weights are the same. The algorithm can calculate the shortest path of carbon emissions from the source point to the target area by minimizing the path cost. In the path analysis, not only the geographical distance is considered, but also factors such as traffic flow and road capacity.

[0045] In an optional embodiment, based on path tracing, for the diffusion of carbon emissions, this embodiment uses a Gaussian diffusion model to simulate the diffusion behavior of carbon emissions in the air. The model assumes that the concentration distribution of carbon emissions in space obeys a Gaussian distribution and simulates its diffusion process in the atmosphere. The diffusion model can predict the concentration distribution of carbon emissions in a specific area and provide a scientific basis for evaluating the impact of emissions on the surrounding environment. The Gaussian diffusion model assumes that the concentration distribution of carbon emissions presents a normal distribution and calculates the concentration change of carbon emissions through the diffusion coefficient.

[0046] , in, For location The carbon concentration, is the emission source intensity, is the emission source location, and is the diffusion coefficient.

[0047] It should be noted that the Gaussian diffusion model can effectively simulate the spatial diffusion of carbon emissions, provide a more accurate assessment of the impact of carbon emissions, and obtain a concentration distribution map of carbon emissions, thereby revealing the scope and intensity of its impact on the surrounding areas. The simulation results provide policymakers with specific diffusion path data, which helps to evaluate the environmental impact of carbon emissions.

[0048] In a preferred embodiment, evaluating the contribution of each emission source to the total carbon emissions includes: Build a random forest model, calculate the feature importance coefficients of each geographical feature to obtain the contribution degrees of different geographical features to carbon emissions; Classify different sources of carbon emission sources, identify and calibrate the emission source types, and calculate the contribution of each emission source to the total carbon emissions through machine learning algorithms.

[0049] It should be noted that after the carbon emission path tracking and diffusion simulation are completed, in this embodiment, through the multi-source analysis method, quantitative analysis is carried out on different carbon emission sources (such as industry, transportation, residential areas, etc.), and the contribution of each emission source to the total carbon emissions is evaluated. This process provides data support for formulating differentiated carbon emission reduction measures.

[0050] Specifically, source analysis combines carbon emission data with multiple geographical factors, and through mathematical modeling and machine learning methods, identifies the contribution of each emission source to the total emissions. Through this method, the carbon emissions of different emission sources can be effectively quantified, and their relative impact on total carbon emissions can be analyzed.

[0051] In an alternative embodiment, the source analysis algorithm can be a random forest algorithm. Random forest is an ensemble learning algorithm based on decision trees. Through the voting mechanism of multiple decision trees, it can effectively capture the non-linear relationships in the data, evaluate the contribution of different features to carbon emissions, and can effectively handle the complexity of multi-dimensional data. In this embodiment, the random forest model is used to analyze the impact of different geographical features (such as traffic flow, land use, population density, etc.) on carbon emissions, calculate the contribution degree of each geographical feature. The training process of the random forest model includes feature selection, training set construction, and prediction model generation, thus providing a powerful tool for source analysis. Through the training process of the random forest algorithm, the impact degree of each input feature on the output carbon emissions can be evaluated, and the contribution degree of each geographical feature is measured by the feature importance score of the random forest. The formula for calculating the feature importance of the random forest is as follows: , where, is the increase in the mean squared error after removing the feature , is the number of decision trees. Through this formula, the impact of each geographical feature on carbon emissions can be quantified, and then the main influencing factors can be identified.

[0052] In another alternative embodiment, the source analysis algorithm can also be a regression analysis algorithm, calculate the contribution degree of each emission source to the total carbon emissions, establish a mathematical model between carbon emissions and different emission sources through the regression analysis method, and calculate the relative contribution of each emission source to the total carbon emissions. In this embodiment, the following formula is used to calculate the contribution degree of the emission source: , Among them, is the carbon emission of a specific emission source (such as transportation, industry, etc.), is the total carbon emission; this formula can help identify and quantify the contribution of each emission source to carbon emissions, providing data support for formulating emission reduction policies.

[0053] It should be noted that through the source apportionment algorithm, it is possible to clearly identify the contribution of each emission source (such as industrial areas, traffic arteries, residential areas, etc.) to carbon emissions, providing accurate decision-making basis for carbon emission management.

[0054] In a preferred embodiment, the visualization display of the carbon emission path and diffusion simulation results and multi-source analysis results includes: Visualization display through GIS to generate a carbon emission distribution map, a carbon emission diffusion path map, and a hotspot map, respectively showing the spatial distribution of carbon emission sources, the diffusion path, and the hotspot areas of carbon emissions; Among them, the carbon emission distribution map shows the intensity and carbon emissions of each region, and uses the depth of color to represent the carbon emissions; The diffusion path map simulates the diffusion path of carbon emission substances and shows the movement trajectory of carbon emission substances from the source point to the target area; The hotspot map shows the carbon emission intensive areas (carbon emission hotspot map generated based on the Getis-Ord Gi* statistic).

[0055] It should be noted that the visualization of the results of carbon emission tracking, diffusion simulation, and source analysis through the GIS platform can be presented in the form of graphs and maps. By generating carbon emission distribution maps, diffusion path maps, hotspot maps, etc., these diagrams provide intuitive data support for decision-makers, helping to quickly identify high-intensity areas, paths, and influence ranges of carbon emissions, so that decision-makers can intuitively understand the spatial distribution and change trends of carbon emissions, and then optimize carbon emission reduction policies. At the same time, the accuracy of the model is ensured through the verification step, and the reliability of the results is improved.

[0056] Furthermore, in order to ensure the accuracy and reliability of the model, this embodiment uses real observation data to verify the carbon emission tracking and source analysis results. By calculating the error between the predicted value and the actual observed value, the accuracy of the model is evaluated. By comparing the data of the carbon emission monitoring sites with the prediction results of the model of the present invention, the accuracy of the carbon emission source location and path tracking is verified. The mean square error (MSE) index is used to quantify the gap between the model prediction results and the actual observed data, and the formula is as follows: , Among them, is the real carbon emission data, is the carbon emission data predicted by the model, Let \(n\) be the number of data samples. By calculating the MSE, the error of the model prediction results can be evaluated, providing a basis for further optimizing the model.

[0057] Finally, perform spatio-temporal dynamic analysis and real-time feedback. Combine time-series data to dynamically track carbon emissions, and adjust the tracking and source analysis results of carbon emission sources according to real-time data feedback. Spatio-temporal dynamic analysis makes the tracking and governance of carbon emissions more flexible and refined.

[0058] In an alternative implementation, carbon emissions and their distribution change over time. Therefore, it is necessary to use time-series data to perform dynamic analysis on the changes in carbon emissions. By analyzing the carbon emission data for each time period, the trends and patterns of carbon emission changes can be identified.

[0059] Time-series data collection: Regularly collect carbon emission data from each emission source to ensure the integrity of the data within each time period; Dynamic update: According to the carbon emission data for each time period, adjust the carbon emission path and diffusion simulation in real time to ensure the timeliness and accuracy of the simulation results; Carbon emission change patterns: By analyzing spatio-temporal dynamic data, reveal the change patterns of carbon emissions to help the government and enterprises make timely emission reduction decisions.

[0060] In an alternative implementation, this embodiment introduces a real-time feedback mechanism, which continuously adjusts the results of carbon emission source positioning, path tracking, and source analysis according to new carbon emission data. This mechanism enables the monitoring and governance of carbon emissions to quickly respond to environmental changes and policy requirements.

[0061] Real-time data collection: Through carbon emission sensors installed in different regions, collect the latest carbon emission data in real time; Dynamic adjustment of the model: Dynamically adjust the path tracking and source analysis models according to real-time data to ensure that the models are consistent with the current carbon emission situation; Feedback regulation: Through real-time data feedback, timely adjust the governance measures for carbon emissions to ensure real-time control of the total carbon emissions.

[0062] It should be noted that the present invention is applicable to multiple fields, including but not limited to environmental monitoring, carbon emission reduction policy formulation, air quality control, urban planning, etc. Through the method of the present invention, accurate tracking, dynamic analysis and source analysis of carbon emissions can be achieved, so as to provide accurate data support for environmental governance and low-carbon policies. For example, urban carbon emission management: By analyzing the carbon emission sources in each region of the city, it helps the government formulate differentiated carbon emission reduction policies, especially taking more stringent governance measures for high-emission regions; Carbon emission monitoring and auditing: Provide detailed carbon emission data for the carbon emission audit of enterprises or regions to ensure that the monitoring and control of carbon emissions meet national or international standards; Air quality prediction and early warning: Combine real-time carbon emission data with meteorological data to provide support for air quality prediction and early warning, and help relevant departments issue air quality alerts in a timely manner. Through the method of the present invention, refined carbon emission source analysis and path tracking can be achieved, improving the scientificity and accuracy of carbon emission governance. High spatial accuracy: Using GIS technology, accurate positioning and spatial distribution analysis of carbon emission sources can be achieved to ensure accurate spatial identification of carbon emission sources; Spatiotemporal dynamic analysis: Combining time series data, the changing trend of carbon emissions can be tracked in real time to ensure that carbon emission control strategies can quickly respond to changes; Multi-source analysis and contribution analysis: Through multi-source data analysis, the contribution of different emission sources to the total carbon emissions can be quantitatively analyzed to help formulate targeted emission reduction measures.

[0063] Through precise data collection, advanced path tracking and diffusion simulation, as well as multi-source analysis and contribution degree analysis, the present invention can not only efficiently identify carbon emission sources and their spatial distribution, but also dynamically track the changes of carbon emissions in real time, provide scientific data support, provide an effective basis for the formulation of low-carbon policies and the implementation of carbon emission reduction measures, and can achieve precise management of regional carbon emissions, providing strong technical support for environmental protection and sustainable development.

[0064] A schematic solution of a carbon emission tracking and source analysis method combined with a geographic information system in the previous embodiment. It should be noted that the technical solution of the carbon emission tracking and source analysis device combined with the geographic information system belongs to the same concept as the technical solution of the carbon emission tracking and source analysis method combined with the geographic information system described above. For the details not described in detail in the technical solution of the carbon emission tracking and source analysis device combined with the geographic information system in this embodiment, reference can be made to the description of the technical solution of the carbon emission tracking and source analysis method combined with the geographic information system described above.

[0065] Embodiment 2 This embodiment provides a carbon emission tracking and source analysis device combined with a geographic information system, including: A collection module for collecting carbon emission data and multi-dimensional geographic data and performing data preprocessing; A positioning module, configured to perform carbon emission source positioning and spatial distribution analysis based on the preprocessed carbon emission data and multi-dimensional geographical data, and identify high-carbon emission regions; A tracking and simulation module, configured to track the carbon emission path and simulate the diffusion of carbon emissions based on the high-carbon emission regions, and obtain the concentration change of carbon emissions within the region; An analysis module, configured to perform quantitative analysis on different carbon emission sources and geographical features through a multi-source parsing algorithm, and evaluate the contribution of each emission source and geographical feature to the total carbon emissions; An output module, configured to obtain the spatial distribution and change trend of carbon emissions based on the carbon emission path and diffusion simulation results and the multi-source parsing results, and compare the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results.

[0066] Embodiment 3 This embodiment provides an electronic device, which is applicable to the situation of carbon emission tracking and source parsing in combination with a geographic information system, including: A memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for carbon emission tracking and source parsing in combination with a geographic information system as proposed in the above embodiment.

[0067] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by the processor, it implements the method for carbon emission tracking and source parsing in combination with a geographic information system as proposed in the above embodiment.

[0068] The storage medium proposed in this embodiment and the method for carbon emission tracking and source parsing in combination with a geographic information system proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk, or an optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present invention.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A carbon emission tracking and source analysis method combined with a geographic information system, characterized in that Including: Collect carbon emission data and multi-dimensional geographical data, and perform data preprocessing; Based on the preprocessed carbon emission data and multi-dimensional geographical data, conduct carbon emission source location and spatial distribution analysis to identify high-carbon emission regions; Based on the high-carbon emission regions, track the carbon emission paths and simulate the diffusion of carbon emissions to obtain the concentration changes of carbon emissions within the region; Through multi-source analysis algorithms, quantitatively analyze different carbon emission sources and geographical characteristics, and evaluate the contributions of each emission source and geographical characteristic to the total carbon emissions; Based on the carbon emission path and diffusion simulation results and multi-source analysis results, obtain the spatial distribution and change trend of carbon emissions, and compare the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results; Tracking the carbon emission paths and simulating the diffusion of carbon emissions includes: Through path analysis algorithms, track the diffusion paths of carbon emission sources, determine the diffusion directions and paths of carbon emissions, and calculate the shortest path from the emission source point to the target area according to the minimum-cost path; Simulate the diffusion behavior of carbon emissions through the Gaussian diffusion model and calculate the concentration changes of carbon emissions; The path analysis algorithms include: Extract the geographical characteristics of the carbon emission paths, and use the Dijkstra algorithm or A* algorithm to calculate the minimum-cost path from the carbon emission source point to the target area; Based on the path costs calculated according to different geographical characteristics, combined with the diffusion paths of carbon emissions and traffic flow data, analyze the influence degree of the geographical characteristics on carbon emission diffusion.

2. The carbon emission tracking and source analysis method combined with a geographic information system according to claim 1, characterized in that, Collect carbon emission data and multi-dimensional geographical data, and perform data preprocessing including: The carbon emission data includes the carbon emissions of each emission source. The emission sources include multiple categories of emission sources, and obtain the time-dimensional change data of each emission source; The multi-dimensional geographical data includes multiple geographical characteristics related to the locations of emission sources; Perform preprocessing on the collected carbon emission data and multi-dimensional geographical data, including data standardization processing and spatial matching processing, associate the carbon emission data with the corresponding geographical data, and generate an associated dataset containing carbon emissions, emission source locations, and geographical characteristics.

3. The method for carbon emission tracking and source analysis combined with a geographic information system according to claim 2, characterized in that, Conduct carbon emission source location and spatial distribution analysis including: Match the geographical coordinates of carbon emission sources with the carbon emission data, perform spatial positioning of carbon emission sources, mark the locations of each carbon emission source, generate a carbon emission source distribution map through map visualization, and mark the carbon emission intensities of different regions; Generate a heat map according to the carbon emissions of different regions through hotspot analysis algorithms; Conduct hotspot analysis through spatial statistical analysis algorithms, calculate the correlation degree between the carbon emission intensity of each region and the surrounding regions to identify high-carbon emission regions.

4. The carbon emission tracking and source analysis method combined with a geographic information system according to claim 1, characterized in that, Evaluating the contributions of each emission source to the total carbon emissions includes: Construct a random forest model, calculate the feature importance coefficients of each geographical characteristic to obtain the contribution degrees of different geographical characteristics to carbon emissions; Classify the different sources of carbon emission sources, identify and calibrate the emission source types, and calculate the contributions of each emission source to the total carbon emissions through machine learning algorithms.

5. The carbon emission tracking and source analysis method combined with a geographic information system according to claim 4, wherein, Visualize the carbon emission path and diffusion simulation results and multi-source analysis results including: Visualize through GIS to generate carbon emission distribution maps, carbon emission diffusion path maps, and hotspot maps, which respectively display the spatial distribution, diffusion paths, and hotspot areas of carbon emission sources; Among them, the carbon emission distribution map shows the intensity and carbon emission amount of each region; The diffusion path map simulates the diffusion path of carbon emissions and shows the movement trajectory of carbon emissions from the source point to the target area; The hotspot map shows the areas with intensive carbon emissions.

6. A carbon emission tracking and source analysis device combined with a geographic information system, which applies a carbon emission tracking and source analysis method combined with a geographic information system as described in any one of claims 1-5, characterized in that, It includes: A collection module for collecting carbon emission data and multi-dimensional geographical data and performing data preprocessing; A positioning module for performing carbon emission source positioning and spatial distribution analysis based on the preprocessed carbon emission data and multi-dimensional geographical data to identify high-carbon emission areas; A tracking and simulation module for tracking the carbon emission path and simulating the diffusion of carbon emissions based on the high-carbon emission areas to obtain the concentration change of carbon emissions within the region; An analysis module for quantitatively analyzing different carbon emission sources and geographical features through a multi-source parsing algorithm to evaluate the contribution of each emission source and geographical feature to the total carbon emission; An output module for obtaining the spatial distribution and change trend of carbon emissions based on the carbon emission path and diffusion simulation results and multi-source parsing results, and comparing the prediction results with the actual carbon emission data to evaluate the accuracy of the prediction results.

7. An electronic device, characterized in that, It includes: A memory and a processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for carbon emission tracking and source parsing combined with a geographic information system according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that, It stores computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for carbon emission tracking and source parsing combined with a geographic information system according to any one of claims 1 to 5 are implemented.

Images