Building Carbon Emission Accounting Method Based on Emission Factor Method and UAV Mapping Technology

Abstract

This invention provides a building carbon emission accounting method based on emission factor method and UAV mapping technology. The invention develops a carbon emission accounting program, establishes and calls upon a carbon emission factor database, determines building type through visual recognition and machine learning, estimates building area through UAV mapping, and further calculates building material usage during the construction phase and energy consumption during construction, operation, and demolition phases. This achieves intelligent and efficient full life-cycle carbon emission accounting for existing buildings or blocks. The carbon emission factor data in this invention comes from authoritative domestic and international databases. Through data traceability, regional, temporal, and accounting boundary information is identified, and the data is statistically summarized to reduce the uncertainty caused by using default values. By utilizing UAV mapping, visual recognition, and machine learning to estimate building material usage and energy consumption throughout the building's life cycle, the invention reduces carbon emission accounting errors caused by missing statistical or monitoring data.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission accounting for existing buildings or blocks, specifically to a building carbon emission accounting method based on the emission factor method and UAV mapping technology. Background Technology

[0002] Currently available carbon emission accounting software often focuses only on the product itself, lacking specialized software specifically for building carbon emissions. Existing building carbon emission accounting software is also primarily applicable to buildings under construction. Carbon emission accounting for completed buildings or neighborhoods, especially those lacking publicly available data such as building material usage and energy consumption, urgently needs to be developed.

[0003] The complexity of carbon emission accounting for existing buildings or neighborhoods: For existing buildings, complete data on building material usage and energy consumption is often lacking, making it difficult to efficiently and conveniently calculate their carbon emissions over their entire life cycle. This is especially true for older buildings, where this data may never have been recorded in detail or may have been lost, posing a significant challenge to carbon emission accounting.

[0004] Data availability and accuracy: In many cases, the calculation of building carbon emissions relies on data from external databases, which typically contain carbon emission factors used in carbon emission accounting across various sectors. However, existing databases often suffer from problems such as overly broad coverage, poor usability, inconsistent data structures, and inconsistent data units across different data sources, significantly compromising the convenience, accuracy, and comparability of the calculation results.

[0005] Standardization and consistency issues: Globally, countries use different standards for carbon emission accounting, making it difficult to directly compare building carbon emission accounting results from different countries or regions. This diversity and lack of uniformity in standards further exacerbates the complexity of the accounting process. Summary of the Invention

[0006] The purpose of this invention is to provide a building carbon emission accounting method based on a carbon emission factor database and UAV mapping and modeling technology that can perform carbon emission accounting for existing buildings or blocks.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A building carbon emission accounting method based on the emission factor method and UAV mapping technology is used to calculate the carbon emissions of existing buildings or blocks; it includes the following steps:

[0009] Step S1: Establishment of a carbon emission factor database

[0010] Step S11: Screen carbon emission factor data related to the entire life cycle of a building from authoritative domestic and international carbon emission databases;

[0011] Step S12: Organize and summarize carbon emission factor data, standardize data units, and form a database. The database contains the following information for carbon emission factors: category, name, unit, generation stage, source type, source, applicable region, and time.

[0012] Step S2: Use UAVs for surveying, modeling, and estimating building area.

[0013] Step S21: Use drones to photograph and collect data from existing buildings or blocks;

[0014] Step S22: Perform image processing and construct a 3D model based on the above data;

[0015] Step S23: Based on the three-dimensional model, obtain a contour map to estimate the building area of ​​existing buildings or blocks;

[0016] Step S3: Machine learning determines building type

[0017] Step S31: Extract the shape parameters of the buildings in the 3D model; use a dataset of known building types for annotation, and associate each set of building shape parameters with its corresponding building type;

[0018] Step S32: Use the model to classify and learn the building types;

[0019] Step S33: Using the extracted building shape parameters as independent variables and the building type as the dependent variable, train the model using the labeled dataset;

[0020] Step S34: Input the newly collected building shape parameters into the trained model and output the predicted building type;

[0021] Step S35: The predicted building type is compared with the actual building type to verify the judgment result of the model, and adjustments and improvements are made accordingly;

[0022] Step S4: Estimation of carbon emission activity levels throughout the building's life cycle

[0023] Step S41: Estimate the amount of building materials used during the building construction phase based on the building area and building type;

[0024] Step S42: Estimate the energy consumption during the building construction phase based on the building area and building type, including electricity consumption and fossil fuel consumption;

[0025] Step S43: Estimate the energy consumption during the building operation phase based on the building area and building type, including electricity consumption and fossil fuel consumption;

[0026] Step S44: Estimate the energy consumption during the building demolition phase based on the building area and building type, including electricity consumption and fossil fuel consumption;

[0027] The amount of building materials used during the building construction phase and the energy consumption during the building construction, operation, and demolition phases constitute the activity level data of carbon emissions throughout the building's life cycle.

[0028] Step S5: Data Import and Carbon Emission Calculation

[0029] Develop an accounting program to calculate carbon emissions using the following formula:

[0030] Carbon emissions = ∑(activity level × carbon emission factor);

[0031] In the formula, the carbon emission factors are provided through the database, including carbon emission factors for major energy sources, electricity, building materials, and building material transportation.

[0032] The activity level data is estimated using the building area and building type, and includes the amount of building materials used during the building construction phase and the energy consumption during the building construction, operation, and demolition phases.

[0033] Preferably, in step S11, the carbon emission factor database selects high-quality data from authoritative domestic and international carbon emission factor databases such as the CPCD China Product Life Cycle Greenhouse Gas Emission Coefficients Set, the IPCC Carbon Emission Factor Database, and the "Building Carbon Emission Calculation Standard" GB / T 51366-2019.

[0034] Preferably, in step S12, the carbon emission factor data is processed in accordance with the unified data unit of the "Building Carbon Emission Calculation Standard" GB / T51366-2019. Through data traceability, elements such as region, time and accounting boundary are identified. The carbon emission factor database contains the following information about carbon emission factors: category, name, unit, generation stage, source type, source, applicable region and time.

[0035] Preferably, in step S23, the elevation data of the buildings are extracted based on the three-dimensional model to generate a digital elevation model, and a contour map of the buildings is drawn.

[0036] The building's footprint is calculated by projecting the bottom surface of the three-dimensional model onto a two-dimensional plane; based on the three-dimensional model, the total surface area of ​​the building, including walls, roof, and other components, is calculated.

[0037] Preferably, in step S31, the shape parameters of the building are extracted from the three-dimensional model, including height, width, length, surface area, volume and contour line distribution, and the corresponding building type is associated with the building shape parameters.

[0038] Preferably, in step S32, the model includes a vector machine, a decision tree, a random forest, or a neural network.

[0039] Preferably, in step S35, the performance of the model is evaluated using a cross-validation method, and the model parameters are adjusted or the feature extraction method is improved based on the results to ensure the accuracy and robustness of the model.

[0040] Preferably, the activity level data in step S4 covers carbon emission activity level data throughout the entire life cycle of a building, including the amount of building materials used during the building construction phase and the energy consumption during the building construction, operation, and demolition phases.

[0041] Preferably, the accounting program in step S5 is developed based on the SQL-Server Management Studio database and the C# language.

[0042] Preferably, in step S5, the amount of building materials used in the building construction phase and the energy consumption in the building construction, operation and demolition phases are summarized; and the activity level data of carbon emissions throughout the building's life cycle are imported into the accounting program for carbon emission accounting, and finally a detailed carbon emission accounting report is generated.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] (1) This product fills the gap in the market for convenient and efficient building carbon emission accounting tools that are not available to the general public. It is intelligent, fast and large-scale, and can perform carbon emission accounting for existing buildings or blocks.

[0045] (2) The database source used in this invention is more authoritative, the data structure is more unified, the quality is high, and the credibility is high.

[0046] (3) The present invention can identify different types of buildings and can also make data corrections according to different regions, etc.

[0047] This invention achieves intelligent and efficient full life-cycle carbon emission accounting for existing buildings or blocks by using UAV mapping and modeling, visual recognition, machine learning, establishing and accessing a carbon emission factor database, and developing an application. For existing buildings with material lists, carbon emission accounting can be performed directly through the accounting program; while for existing buildings or blocks lacking publicly available data such as building material usage and energy consumption data, this project can be fully applied for carbon emission accounting.

[0048] This invention utilizes drone technology for building area estimation, providing an efficient and accurate method that avoids the workload of traditional manual measurement. The calculation program effectively integrates a carbon emission factor database and, based on building type and area, estimates the amount of building materials used during the construction phase and the energy consumption during the construction, operation, and demolition phases. The database in this patent originates from authoritative domestic and international open-source databases and has undergone unit conversion, classification, and unified data structure according to the "Building Carbon Emission Calculation Standard" (GB / T 51366). Through data traceability, it identifies regional, temporal, and accounting boundary information and performs statistical summarization of the data, reducing the uncertainty caused by default values ​​and improving data reliability. By using drone mapping, visual recognition, and machine learning to estimate the activity levels of building materials usage and energy consumption throughout the building's entire life cycle, it reduces carbon emission calculation errors caused by missing statistical or monitoring data. Attached Figure Description

[0049] Figure 1 A system flowchart illustrating a building carbon emission accounting method based on the emission factor method and UAV mapping technology is provided for embodiments of the present invention.

[0050] Figure 2 A schematic diagram of the workflow of the accounting procedure in a building carbon emission accounting method based on emission factor method and UAV mapping technology, provided for embodiments of the present invention;

[0051] Figure 3 for Figure 1 A flowchart illustrating the process of calculating building area in China;

[0052] Figure 4 for Figure 1 A flowchart illustrating the process of predicting building types. Detailed Implementation

[0053] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0054] like Figures 1 to 4 The diagram illustrates a building carbon emission accounting method based on the emission factor method and UAV mapping technology, disclosed in this invention. This method is used to calculate carbon emissions from existing buildings or neighborhoods and includes the following steps:

[0055] Step S1: Establishment of a carbon emission factor database

[0056] Step S11: Screen carbon emission factor data related to the entire life cycle of buildings from authoritative domestic and international carbon emission databases; the carbon emission factor database screens high-quality data from authoritative domestic and international carbon emission factor databases such as CPCC China Product Life Cycle Greenhouse Gas Emission Coefficients Set, IPCC Carbon Emission Factor Database, and the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019).

[0057] Step S12: Organize and summarize carbon emission factor data, unify data units, and form a database; carbon emission factor data are unified in data units according to the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019).

[0058] In this embodiment, by tracing data sources and identifying elements such as region, time, and accounting boundaries, the established carbon emission factor database contains the following information about carbon emission factors: category, name, unit, generation stage, source type, source, applicable region, and time.

[0059] Step S2: Use UAVs for surveying, modeling, and estimating building area.

[0060] Step S21: Use a drone to photograph and collect data on existing buildings or blocks; the drone adopts a multi-beam equal-interval photography method to take two-dimensional photos of buildings at equal intervals; the shooting angle and interval are determined by preset parameters to ensure that a high overlap rate image covering the entire building is obtained; acquire the two-dimensional photo information of the target building, including images from different perspectives and heights, to ensure full coverage of the building's external structure.

[0061] In this embodiment, a DJI drone is used to take photos of a designated building or area from various angles through equal-interval cruising. These photos are then imported into DJI Terra software, which can construct a 3D model of the building or area based on this set of photos. By selecting points on the model, some key parameters such as length, width, and height can be obtained for machine learning.

[0062] Step S22: Based on the above data, perform image processing and construct a three-dimensional model; use image processing software to process the images collected by the UAV, eliminate distortion and color difference, and stitch them together; use computer vision algorithms to extract feature points from the two-dimensional images, generate point cloud data, and construct the three-dimensional model.

[0063] In this embodiment, we use DJI Terra software, which is compatible with DJI drones, to process the acquired graphics. After preprocessing, the 3D model and contour map generated by DJI Terra can be used for further data processing.

[0064] Step S23: Based on the 3D model, obtain a contour map to estimate the building area of ​​existing buildings or blocks; we extract the elevation data of buildings from the 3D model generated by DJI Terra, generate a digital elevation model, and draw the contour map of the buildings; by projecting the bottom surface of the 3D model onto a 2D plane, calculate the building's footprint; based on the 3D model, calculate the total surface area of ​​the building, including walls, roof, etc.

[0065] Step S3: Machine learning determines building type

[0066] Step S31: Extract the shape parameters of the building in the 3D model; use a dataset of known building types for annotation, and associate each set of building shape parameters with its corresponding building type; in this embodiment, the shape parameters of the building are extracted from the 3D model, including height, width, length, surface area, volume and contour distribution, and the selection principle is based on associating the building shape parameters with its corresponding building type.

[0067] Step S32: Use the model to classify the building type; convert the raw data into features suitable for use by the machine learning model.

[0068] (1) Feature engineering: This involves transforming raw data into features suitable for use by machine learning models. The length, width, height, volume, and proportions of a building are considered as features and used to describe the shape and structure of the building.

[0069] (2) Similarity measurement: By comparing the feature differences between buildings, we can quantify the degree of similarity between them.

[0070] (3) Optimization Algorithm: A simple yet effective optimization algorithm, namely the negative exponential function, was used to calculate the similarity score. By converting feature differences into a score and mapping the score range through the negative exponential function, we were able to better capture the differences between buildings.

[0071] (4) Structured data processing: Building type information is organized by using structures and multiple building types are managed by arrays.

[0072] Step S33: Using the extracted building shape parameters as independent variables and the building type as the dependent variable, train the model using the labeled dataset; the model includes vector machine, decision tree, random forest, and neural network.

[0073] Step S34: Input the newly collected building shape parameters into the trained model, calculate the similarity score to determine the most suitable building type, and output the predicted building type.

[0074] Step S35: The predicted building type is compared with the actual building type to verify the judgment result of the model, and adjustments and improvements are made; the performance of the model is evaluated by cross-validation, and the model parameters are adjusted or the feature extraction method is improved according to the results to ensure the accuracy and robustness of the model.

[0075] Step S4: Estimation of carbon emission activity levels throughout the building's life cycle

[0076] Step S41: Estimate the amount of building materials used during the building construction stage based on the building area and building type; the estimated building materials include metal building materials such as steel and aluminum alloy, non-metal building materials such as cement, glass, and wood, and other building materials such as composite panels.

[0077] Step S42: Estimate the energy consumption during the building construction phase based on the building area and building type, including electricity consumption and fossil fuel consumption; the method for estimating energy consumption in this embodiment refers to the provisions of Section 3.1 of the "Guidelines for Calculating Building Carbon Emissions (Trial)" issued by the Guangdong Provincial Department of Housing and Urban-Rural Development.

[0078] Step S43: Estimate the energy consumption during the building's operation phase based on the building area and building type, including electricity consumption and fossil fuel consumption; in this embodiment, the method for estimating energy consumption refers to the electricity intensity of public buildings in the "2021 Shanghai Municipal Government Office Buildings and Large Public Buildings Energy Consumption Monitoring and Analysis Report".

[0079] Step S44: Estimate the energy consumption in the demolition phase of the embodiment based on the building area and building type, including electricity consumption and fossil fuel consumption; the method for estimating energy consumption in this embodiment refers to the provisions of Section 3.1 of the "Guidelines for Calculating Building Carbon Emissions (Trial)" issued by the Guangdong Provincial Department of Housing and Urban-Rural Development.

[0080] The amount of building materials used during the building construction phase and the energy consumption during the building construction, operation, and demolition phases constitute the activity level data of carbon emissions throughout the building's life cycle.

[0081] Step S5: Data Import and Carbon Emission Calculation

[0082] The accounting program was developed using the SQL-ServerManagement Studio database and the C# language.

[0083] Summarize the 3D model, the building area, the contour map, and the building type determination results; and ensure that all data is imported into the calculation program in a consistent format, including shape parameters, area, and type.

[0084] Carbon emissions can be calculated using the following formula:

[0085] Carbon emissions = ∑(activity level × carbon emission factor);

[0086] In the formula, the carbon emission factors are provided through the database, including carbon emission factors for major energy sources, electricity, building materials, and building material transportation.

[0087] The activity level data is estimated using the building area and building type, and includes the amount of building materials used during the building construction phase and the energy consumption during the building construction, operation, and demolition phases.

[0088] The calculation procedure of this invention mainly refers to the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019), converting carbon emission factors from some authoritative domestic and international databases into units specified in the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019) before storing them in the database. The data structure combines the structures of multiple databases, simplifying it as much as possible while ensuring the integrity of important information. The data structure includes: category, name, unit, generation stage, source type, source, applicable region, and time.

[0089] Finally, the accounting process generates a detailed carbon emission accounting report.

[0090] The database in this embodiment is based on the data in the "Standard for Calculating Carbon Emissions from Buildings" (GB / T51366-2019). Following the same classification method, carbon emission factor data that meets the accounting requirements is selected from authoritative domestic and international open-source databases such as the IPCC carbon emission factor database and the CPCD China Product Life Cycle Greenhouse Gas Emission Coefficients Set. The data in the database in this embodiment has undergone unit conversion, classification, and unified data structure in accordance with the "Standard".

[0091] The data in the database is mostly extracted from authoritative statistical yearbooks, with some from academic papers or research reports, ensuring a high degree of reliability. However, different databases use different units for carbon emission factors and have inconsistent data structures; therefore, they need to be organized and categorized. In this embodiment, the main target of carbon emissions is Chinese buildings; therefore, the selected data primarily belongs to Chinese or global data.

[0092] In this embodiment, a database classification method was developed based on the classification criteria for carbon emission factors in the IPCC and the "Building Carbon Emission Calculation Standard" (GB / T51366-2019). This method can meet the needs of building carbon emission accounting, and there is a logical connection between carbon emission factors of the same type, which is scientific.

[0093] To improve the reliability of the data and make it more applicable to monitoring actual carbon emission levels in China, we analyzed and summarized all the data based on the data in the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019). For data with a large volume, we mainly focused on its extreme points and quartiles. We found that the data in the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019) often fell in the middle of the data range. This indicates that the data in the "Building Carbon Emission Calculation Standard" (GB / T 51366-2019) is representative and, to some extent, verifies the scientific reliability of the data we selected.

[0094] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and 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 this invention.

[0095] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0096] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A building carbon emission accounting method based on emission factor method and unmanned aerial vehicle mapping technology, used for carbon emission accounting of built buildings or blocks; characterized in that, Comprising the following steps: Step S1: Establishment of carbon emission factor database Step S11: Screening of carbon emission factor data related to building life cycle from carbon emission database; Step S12: Arrangement and induction of carbon emission factor data, unification of data units, formation of database; the database contains the following information of carbon emission factors: category, name, unit, production link, source type, source, applicable region and time; Step S2: Estimation of building area by unmanned aerial vehicle mapping and modeling Step S21: Taking pictures and data collection of built buildings or blocks by unmanned aerial vehicle; Step S22: Image processing and construction of three-dimensional model based on the above data; Step S23: Estimation of building area of built buildings or blocks based on contour distribution map obtained from the three-dimensional model; Based on the elevation data of buildings extracted from the three-dimensional model, a digital elevation model is generated, and a contour distribution map of the building is drawn; By projecting the bottom surface of the three-dimensional model on a two-dimensional plane, the floor area of the building is calculated; based on the three-dimensional model, the total surface area of the building is calculated, including the wall and roof parts; Step S3: Machine learning to determine building type Step S31: Extracting the shape parameters of the building in the three-dimensional model; using a dataset of known building types for labeling, associating each set of building shape parameters with its corresponding building type; The shape parameters of the building in the three-dimensional model are extracted, including height, width, length, surface area, volume and contour distribution, based on the building shape parameters to associate their corresponding building types; Step S32: Classification learning of the building type using the model; Step S33: Using the extracted building shape parameters as independent variables and the building type as dependent variables, the model is trained using the labeled dataset; Step S34: Input the newly collected building shape parameters into the trained model, and output the predicted building type; Step S35: Comparing the predicted building type with the actual building type to verify the judgment result of the model and make adjustments and improvements; The performance of the model is evaluated by cross-validation method, and the model parameters or feature extraction method are adjusted according to the results to ensure the accuracy and robustness of the model; Step S4: Estimation of building life cycle carbon emission activity level data Step S41: Estimating the amount of building materials used in the building construction stage based on the building area and building type; Step S42: Estimating the amount of energy consumed in the building construction stage based on the building area and building type, including electricity consumption and fossil energy consumption; Step S43: Estimating the amount of energy consumed in the building operation stage based on the building area and building type, including electricity consumption and fossil energy consumption; Step S44: Estimating the amount of energy consumed in the building demolition stage based on the building area and building type, including electricity consumption and fossil energy consumption; The amount of building materials used in the building construction stage and the amount of energy consumed in the building construction, operation and demolition stages constitute the activity level data of building life cycle carbon emission; The activity level data covers the activity level data of building life cycle carbon emissions, including the building material usage in the building construction stage and the energy consumption in the building construction, operation and demolition stages; Step S5: data import and carbon emission accounting Develop an accounting program to calculate carbon emissions using the following formula: Carbon emissions = ∑(activity level x carbon emission factor); In the formula, the carbon emission factor is provided by the database, including the carbon emission factor of main energy, the carbon emission factor of electricity, the carbon emission factor of building materials and the carbon emission factor of building materials transportation; The activity level data is estimated by the building area and building type, including the building material usage in the building construction stage and the energy consumption in the building construction, operation and demolition stages.

2. The building carbon emission accounting method based on the emission factor method and the UAV surveying technology according to claim 1, characterized in that, In step S11, the carbon emission factor database selects high-quality data from CPCD China Product Life Cycle Greenhouse Gas Emission Coefficient Set, IPCC Carbon Emission Factor Library and "Building Carbon Emission Calculation Standard" GB / T 51366-2019 Carbon Emission Factor Database.

3. The building carbon emission accounting method based on the emission factor method and the UAV surveying technology according to claim 1, characterized in that, In step S12, the carbon emission factor data is in accordance with the unified data unit of "Building Carbon Emission Calculation Standard" GB / T 51366-2019, and through data tracing, the regional, time and accounting boundary elements are identified. The carbon emission factor database contains the following information of carbon emission factor: category, name, unit, production link, source type, source, applicable area and time.

4. The building carbon emission accounting method based on the emission factor method and the UAV surveying technology according to claim 1, characterized in that, In step S32, the model includes vector machine, decision tree, random forest and neural network.

5. The building carbon emission accounting method based on emission factor method and UAV surveying technology according to claim 1, characterized in that, In step S5, the accounting program is developed based on SQL-Server Management Studio database and C# language.

6. The building carbon emission accounting method based on emission factor method and UAV surveying technology according to claim 1, characterized in that, In step S5, the building material usage in the building construction stage and the energy consumption in the building construction, operation and demolition stages are summarized; And constitute the activity level data of building life cycle carbon emissions, import into the accounting program for carbon emission accounting, and finally generate detailed carbon emission accounting report.

Images