A method for constructing a mobile source pollution data visualization platform

Abstract

The present invention discloses a method for constructing a mobile source pollution data visualization platform, which relates to the field of environmental monitoring technology, including: establishing a city's historical multi-source heterogeneous emission database; analyzing the pollutant emission and diffusion trends in the city's historical multi-source heterogeneous emission data, and obtaining emission trend indicators of different vehicle types in various sections of the city; analyzing the mobile source pollutant emission status, and evaluating the dynamic emission indicators of mobile sources in the urban traffic road network; identifying the execution conditions corresponding to the engineering machinery operation mode in the non-road mobile machinery data, and evaluating the dynamic emission indicators of mobile sources in the city's non-roads; using the dynamic emission indicators of mobile sources in the urban traffic road network and the dynamic emission indicators of mobile sources in the city's non-roads to correct the emission trend indicators of different vehicle types in various sections of the city, and obtain a real-time status distribution map of urban pollutant emission diffusion; the advantages of the present invention are: effectively improving pollution prevention and control capabilities and optimizing urban environmental management.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a method for constructing a mobile source pollution data visualization platform. Background Art

[0002] Mobile source pollution data visualization uses charts and maps to visually display pollutant emissions from different types of vehicles and non-road mobile sources within a specific area or time period. Using visual elements like color and size, it clearly illustrates the distribution of pollution sources, emission intensity, and temporal and spatial trends, helping decision-makers identify pollution hotspots, evaluate policy effectiveness, and develop effective environmental management measures.

[0003] Existing mobile source pollution monitoring mainly involves deploying edge sensors on urban roads to collect pollutant data and perform data fitting analysis to determine the urban pollution status. However, the main pollution sources in cities come from mobile vehicles and engineering vehicles, and the pollution status in urban areas is easily affected by external conditions. The pollution status monitoring of fixed-point edge sensors has poor accuracy and high implementation costs. Summary of the Invention

[0004] In order to solve the above technical problems, a method for constructing a mobile source pollution data visualization platform is provided. This technical solution solves the above-mentioned existing mobile source pollution monitoring, which mainly collects pollutant data by deploying edge sensors on urban roads, and performs data fitting analysis to determine the urban pollution status. However, the main pollution sources in the city come from mobile vehicles and engineering vehicles, and the pollution status in the urban area is easily affected by external conditions. The pollution status monitoring of fixed-point edge sensors has the problems of poor accuracy and high implementation cost.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for constructing a mobile source pollution data visualization platform, comprising:

[0007] Acquire historical vehicle emission test data, non-road mobile machinery data, road network data, road traffic flow data, oil product data, and meteorological data to establish a historical multi-source heterogeneous urban emission database;

[0008] Based on the city's historical multi-source heterogeneous emission database, we analyze the pollutant emission and diffusion trends in the city's historical multi-source heterogeneous emission data, obtain emission trend indicators for different vehicle types on various road sections in the city, and construct a time-series distribution map of urban pollutant emissions and diffusion;

[0009] Obtain the urban traffic road network, analyze the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluate the dynamic emission indicators of mobile sources in the urban traffic road network;

[0010] Obtain urban non-road mobile machinery data, identify the execution conditions corresponding to the operation modes of the construction machinery in the non-road mobile machinery data, and evaluate the dynamic emission indicators of urban non-road mobile sources;

[0011] Using the dynamic emission indicators of mobile sources on the urban road network and the dynamic emission indicators of mobile sources on urban non-roads, we correct the emission trend indicators of different vehicle types on various sections of the city to obtain a real-time distribution map of urban pollutant emissions.

[0012] Among them, the dynamic emission indicators of mobile sources of urban traffic road network and urban non-road mobile sources are used to revise the emission trend indicators of different vehicle types in various sections of the city. Specifically:

[0013]

[0014] in, is the emission trend correction index of the i-th vehicle type on the k-th road section in the city, is the total emission of the i-th vehicle type on the k-th road section in the city, E′ i is the dynamic emission index of the i-th vehicle type in urban non-road mobility.

[0015] Preferably, based on the city's historical multi-source heterogeneous emission database, analyzing the pollutant emission and diffusion trends in the city's historical multi-source heterogeneous emission data, and constructing a time series distribution map of urban pollutant emission diffusion specifically includes:

[0016] Based on the city's historical multi-dimensional heterogeneous emission database, data is divided according to several dimensions of urban pollutants to obtain a data array of urban historical multi-dimensional emission factors; the multi-dimensional emission factors include: vehicle dimension, environmental dimension, oil dimension, and road dimension;

[0017] Based on the vehicle emission test data in the city's historical multi-dimensional emission factor data array, several categories of emission factors for different vehicle types are determined, and a basic emission factor list for different vehicle types is determined;

[0018] Based on the meteorological data in the city's historical multi-dimensional emission factor data array and the comparison table of environmental factors affecting pollutant emissions, the comprehensive environmental correction factor is determined;

[0019] Based on the city's oil product data in the city's historical multi-dimensional emission factor data array and the oil product factor comparison table affecting pollutant emissions, the comprehensive oil product correction factor is determined;

[0020] Based on the road network data and road traffic flow data in the city's historical multi-dimensional emission factor data array, and the road grade correction factor comparison table and speed correction factor comparison table that affect pollutant emissions, the comprehensive road correction factor is determined;

[0021] Based on the basic emission factor list of different vehicle types, comprehensive environmental correction factors, comprehensive oil correction factors, and comprehensive road correction factors, we align them with time attributes, establish a time sliding window, and obtain time series data on multi-dimensional factors affecting historical pollutants in the city;

[0022] Based on the multi-dimensional time series data of historical pollutant impact factors in the city, a M0BILE neural network model was established to generate emission trend indicators for different vehicle types on various road sections in the city and construct a time series distribution map of urban pollutant emissions.

[0023] The MOBILE neural network model is specifically:

[0024]

[0025] Where, is the total emission of the i-th vehicle type on the k-th road section in the city, BEF ij is the jth basic emission factor of the i-th vehicle type, γ is the comprehensive environmental correction factor, is the comprehensive correction factor of oil products, λ k is the comprehensive correction factor of the kth road section, P i is the number of vehicles of type i in the city, VKT i is the average mileage of the i-th vehicle type, n is the total number of vehicle types, and m is the total number of road sections in the urban road network.

[0026] Preferably, obtaining the urban traffic road network, analyzing the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluating the dynamic emission indicators of the mobile sources of the urban traffic road network specifically include:

[0027] Based on urban road network data and road traffic flow data, the historical urban road traffic flow data is obtained, and the vehicle type composition information and road traffic flow information of the road section are divided and extracted to obtain the historical road vehicle type composition data and historical road section flow data;

[0028] Based on historical road vehicle composition data, a BP neural network is trained. Taking vehicle composition data, road type, and spatial characteristics from the historical road vehicle composition data as input, the BP neural network is used to fit the complex function between vehicle proportions and road section characteristics to predict future road vehicle composition data.

[0029] Based on historical urban road traffic flow data, an LSTM urban road network vehicle type flow prediction model is trained. The flow data of sections with detectors in the historical road section flow data is used to drive the spatial topological flow of sections without detectors. The upstream and downstream traffic flows and spatial feature influence coefficients are combined as input to predict future road section flow data.

[0030] Based on the predicted future road vehicle type composition data, predicted future road section traffic data, and a list of basic emission factors for different vehicle types, dynamic prediction and calculation of emissions of vehicle types in each section of the urban road network are performed to obtain dynamic emission indicators of mobile sources in the urban traffic road network;

[0031] The dynamic emission indicators of mobile sources in the urban traffic road network are specifically:

[0032]

[0033] Where, is the dynamic emission of the i-th vehicle type on the k-th road segment in the urban road network, is the traffic volume of the i-th type of vehicle on the k-th road section in the urban road network, is the travel time of the i-th vehicle type on the k-th road section in the urban road network, is the total number of vehicles of type i on the kth road section in the urban road network.

[0034] Preferably, obtaining urban non-road mobile machinery data, identifying the execution conditions corresponding to the engineering machinery operation modes in the non-road mobile machinery data, and evaluating the dynamic emission indicators of urban non-road mobile sources specifically include:

[0035] Based on the non-road mobile machinery data, according to the operation modes of engineering machinery of different non-road mobile vehicle types, an original data set of the operation modes of engineering machinery of non-road mobile vehicle types is established;

[0036] Determine the operating parameters corresponding to the operation mode of the construction machinery of the non-road mobile vehicle type;

[0037] Based on the original data set of engineering machinery operation modes of non-road mobile vehicle types, a C-SVC vector machine is trained, with the engineering machinery operation modes corresponding to the original data of the engineering machinery operation modes as input and the operating condition parameters of the engineering machinery operation modes of non-road mobile vehicle types as output;

[0038] Converting the operating condition parameters of the non-road mobile vehicle type engineering machinery operation mode by using a linear mapping to obtain an operating condition parameter vector of the non-road mobile vehicle type engineering machinery operation mode;

[0039] Calculate the linear regression coefficient between the operating condition parameter vector of the non-road mobile vehicle type construction machinery operation mode and the pollutant emissions as the pollutant emission impact coefficient of the non-road mobile vehicle type construction machinery operation mode;

[0040] Based on the pollutant emission impact coefficient of the engineering machinery operation mode of non-road mobile vehicle types and real-time urban non-road mobile machinery data, the dynamic emission indicators of urban non-road mobile vehicle types are calculated, and the dynamic emission indicators of urban non-road mobile sources are determined;

[0041] The dynamic emission index for urban non-road mobile vehicles is calculated as follows:

[0042]

[0043] Where, E′ i is the dynamic emission index of the i-th vehicle type in the city’s non-road mobility, E i is the emission index of the i-th vehicle type in urban non-road mobility, δ iv is the pollutant emission impact coefficient of the vth construction machinery operation mode of the i-th non-road mobile vehicle type, X iv The operating condition parameters of the vth construction machinery operation mode of the i-th non-road mobile vehicle type.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] This paper proposes a mobile source pollution data visualization platform. By constructing a historical multi-source heterogeneous urban emissions database and integrating multiple data sources, including traffic, non-road machinery, road networks, and meteorology, this platform analyzes urban mobile source pollutant emissions and diffusion trends. By monitoring traffic flow and non-road machinery emissions in real time, it dynamically assesses mobile source pollutant emission indicators and modifies pollutant diffusion maps, ultimately achieving accurate time-series predictions of urban pollutant emissions and diffusion. This method can provide real-time, dynamic, and accurate decision-making support for urban pollution control, effectively improving pollution prevention and control capabilities and optimizing urban environmental management. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of the method for building a mobile source pollution data visualization platform;

[0047] Figure 2 A flow chart of the method for analyzing emission trend indicators of different vehicle types on various road sections in the city;

[0048] Figure 3 Flowchart of the method for evaluating dynamic emission indicators of mobile sources in urban traffic road networks;

[0049] Figure 4 Flowchart of the method for evaluating dynamic emission indicators of urban non-road mobile sources. DETAILED DESCRIPTION

[0050] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0051] Reference Figure 1 As shown, a method for constructing a mobile source pollution data visualization platform includes:

[0052] Acquire historical vehicle emission test data, non-road mobile machinery data, road network data, road traffic flow data, oil product data, and meteorological data to establish a historical multi-source heterogeneous urban emission database;

[0053] Based on the city's historical multi-source heterogeneous emission database, we analyze the pollutant emission and diffusion trends in the city's historical multi-source heterogeneous emission data, obtain emission trend indicators for different vehicle types on various road sections in the city, and construct a time-series distribution map of urban pollutant emissions and diffusion;

[0054] Obtain the urban traffic road network, analyze the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluate the dynamic emission indicators of mobile sources in the urban traffic road network;

[0055] Obtain urban non-road mobile machinery data, identify the execution conditions corresponding to the operation modes of the construction machinery in the non-road mobile machinery data, and evaluate the dynamic emission indicators of urban non-road mobile sources;

[0056] Using the dynamic emission indicators of mobile sources on the urban road network and the dynamic emission indicators of mobile sources on urban non-roads, we correct the emission trend indicators of different vehicle types on various sections of the city to obtain a real-time distribution map of urban pollutant emissions.

[0057] Among them, the dynamic emission indicators of mobile sources of urban traffic road network and urban non-road mobile sources are used to revise the emission trend indicators of different vehicle types in various sections of the city. Specifically:

[0058]

[0059] in, is the emission trend correction index of the i-th vehicle type on the k-th road section in the city, is the total emission of the i-th vehicle type on the k-th road section in the city, E′ i is the dynamic emission index of the i-th vehicle type in urban non-road mobility.

[0060] This solution builds a historical multi-source, heterogeneous urban emissions database and integrates multiple data sources, including traffic, non-road machinery, road networks, and meteorology, to analyze urban mobile source pollutant emissions and diffusion trends. By monitoring traffic flow and non-road machinery emissions in real time, it dynamically assesses mobile source pollutant emission indicators and refines pollutant diffusion maps, ultimately achieving accurate time-series predictions of urban pollutant emissions and diffusion. This approach can provide real-time, dynamic, and accurate decision-making support for urban pollution control, effectively improving pollution prevention and control capabilities and optimizing urban environmental management.

[0061] Reference Figure 2 As shown in the figure, based on the urban historical multi-source heterogeneous emission database, the pollutant emission and diffusion trends in the urban historical multi-source heterogeneous emission data are analyzed, and the time series distribution map of urban pollutant emission diffusion is constructed. Specifically, the following are included:

[0062] Based on the city's historical multi-dimensional heterogeneous emission database, data is divided according to several dimensions of urban pollutants to obtain a data array of urban historical multi-dimensional emission factors; the multi-dimensional emission factors include: vehicle dimension, environmental dimension, oil dimension, and road dimension;

[0063] Based on the vehicle emission test data in the city's historical multi-dimensional emission factor data array, several categories of emission factors for different vehicle types are determined, and a basic emission factor list for different vehicle types is determined;

[0064] Based on the meteorological data in the city's historical multi-dimensional emission factor data array and the comparison table of environmental factors affecting pollutant emissions, the comprehensive environmental correction factor is determined;

[0065] Based on the city's oil product data in the city's historical multi-dimensional emission factor data array and the oil product factor comparison table affecting pollutant emissions, the comprehensive oil product correction factor is determined;

[0066] Based on the road network data and road traffic flow data in the city's historical multi-dimensional emission factor data array, and the road grade correction factor comparison table and speed correction factor comparison table that affect pollutant emissions, the comprehensive road correction factor is determined;

[0067] Based on the basic emission factor list of different vehicle types, comprehensive environmental correction factors, comprehensive oil correction factors, and comprehensive road correction factors, we align them with time attributes, establish a time sliding window, and obtain time series data on multi-dimensional factors affecting historical pollutants in the city;

[0068] Based on the multi-dimensional time series data of historical pollutant impact factors in the city, a M0BILE neural network model was established to generate emission trend indicators for different vehicle types on various road sections in the city and construct a time series distribution map of urban pollutant emissions.

[0069] The MOBILE neural network model is specifically:

[0070]

[0071] Where, is the total emission of the i-th vehicle type on the k-th road section in the city, BEF ij is the jth basic emission factor of the i-th vehicle type, γ is the comprehensive environmental correction factor, is the comprehensive correction factor of oil products, λ k is the comprehensive correction factor of the kth road section, P i is the number of vehicles of type i in the city, VKT i is the average mileage of the i-th vehicle type, n is the total number of vehicle types, and m is the total number of road sections in the urban road network.

[0072] Based on data from the city's historical multi-source heterogeneous emissions database, this solution systematically analyzes urban pollutant emissions and diffusion trends, covering multiple emission factors, including vehicles, the environment, oil products, and roads. During data processing, on-board emission test data, meteorological data, oil product information, and traffic flow data are combined to calculate basic emission factors and comprehensive correction factors for each dimension. Using time sliding window technology, these factors are aligned with time attributes to form multi-dimensional time series data of pollutant influencing factors. Finally, based on this time series data, a MOBILE neural network model is established, which can predict pollutant emission trends for various sections of the city and construct a time series distribution map of pollutant diffusion. This method not only provides an accurate tool for real-time prediction of pollutant diffusion trends, but also helps city managers optimize pollution control measures, improve the efficiency of air quality management, and reduce the negative impact of pollution on the urban environment.

[0073] Reference Figure 3 As shown, obtaining the urban traffic road network, analyzing the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluating the dynamic emission indicators of mobile sources in the urban traffic road network specifically include:

[0074] Based on urban road network data and road traffic flow data, the historical urban road traffic flow data is obtained, and the vehicle type composition information and road traffic flow information of the road section are divided and extracted to obtain the historical road vehicle type composition data and historical road section flow data;

[0075] Based on historical road vehicle composition data, a BP neural network is trained. Taking vehicle composition data, road type, and spatial characteristics from the historical road vehicle composition data as input, the BP neural network is used to fit the complex function between vehicle proportions and road section characteristics to predict future road vehicle composition data.

[0076] Based on historical urban road traffic flow data, an LSTM urban road network vehicle type flow prediction model is trained. The flow data of sections with detectors in the historical road section flow data is used to drive the spatial topological flow of sections without detectors. The upstream and downstream traffic flows and spatial feature influence coefficients are combined as input to predict future road section flow data.

[0077] Based on the predicted future road vehicle type composition data, predicted future road section traffic data, and a list of basic emission factors for different vehicle types, dynamic prediction and calculation of emissions of vehicle types in each section of the urban road network are performed to obtain dynamic emission indicators of mobile sources in the urban traffic road network;

[0078] The dynamic emission indicators of mobile sources in the urban traffic road network are specifically:

[0079]

[0080] Where, is the dynamic emission of the i-th vehicle type on the k-th road segment in the urban road network, is the traffic volume of the i-th type of vehicle on the k-th road section in the urban road network, is the travel time of the i-th vehicle type on the k-th road section in the urban road network, is the total number of vehicles of type i on the kth road section in the urban road network.

[0081] This solution integrates urban road network data and road traffic flow data, leveraging historical traffic flow and vehicle type composition information. It employs a BP neural network and an LSTM model to predict vehicle type composition and traffic flow, respectively. In its implementation, the BP neural network fits the complex relationship between vehicle type composition and road segment characteristics, and combines this with an LSTM model to predict future traffic flow, thereby dynamically forecasting future road segment traffic flow. By combining emission factors for different vehicle types, mobile source pollutant emissions for each road segment are ultimately calculated. This method not only accurately predicts future traffic flow and vehicle type composition but also effectively assesses the dynamic emissions of mobile sources within the road network, providing data support for environmental protection and reducing pollutant emissions.

[0082] Reference Figure 4 As shown, obtaining urban non-road mobile machinery data, identifying the execution conditions corresponding to the engineering machinery operation modes in the non-road mobile machinery data, and evaluating the dynamic emission indicators of urban non-road mobile sources specifically include:

[0083] Based on the non-road mobile machinery data, according to the operation modes of engineering machinery of different non-road mobile vehicle types, an original data set of the operation modes of engineering machinery of non-road mobile vehicle types is established;

[0084] Determine the operating parameters corresponding to the operation mode of the construction machinery of the non-road mobile vehicle type;

[0085] Based on the original data set of engineering machinery operation modes of non-road mobile vehicle types, a C-SVC vector machine is trained, with the engineering machinery operation modes corresponding to the original data of the engineering machinery operation modes as input and the operating condition parameters of the engineering machinery operation modes of non-road mobile vehicle types as output;

[0086] Converting the operating condition parameters of the non-road mobile vehicle type engineering machinery operation mode by using a linear mapping to obtain an operating condition parameter vector of the non-road mobile vehicle type engineering machinery operation mode;

[0087] Calculate the linear regression coefficient between the operating condition parameter vector of the non-road mobile vehicle type construction machinery operation mode and the pollutant emissions as the pollutant emission impact coefficient of the non-road mobile vehicle type construction machinery operation mode;

[0088] Based on the pollutant emission impact coefficient of the engineering machinery operation mode of non-road mobile vehicle types and real-time urban non-road mobile machinery data, the dynamic emission indicators of urban non-road mobile vehicle types are calculated, and the dynamic emission indicators of urban non-road mobile sources are determined;

[0089] The dynamic emission index for urban non-road mobile vehicles is calculated as follows:

[0090]

[0091] Where, E′ i is the dynamic emission index of the i-th vehicle type in the city’s non-road mobility, E i is the emission index of the i-th vehicle type in urban non-road mobility, δ iv is the pollutant emission impact coefficient of the vth construction machinery operation mode of the i-th non-road mobile vehicle type, X iv The operating condition parameters of the vth construction machinery operation mode of the i-th non-road mobile vehicle type.

[0092] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for constructing a mobile source pollution data visualization platform, characterized in that: include: Acquire historical vehicle emission test data, non-road mobile machinery data, road network data, road traffic flow data, oil product data, and meteorological data to establish a historical multi-source heterogeneous urban emission database; Based on the city's historical multi-source heterogeneous emission database, we analyze the pollutant emission and diffusion trends in the city's historical multi-source heterogeneous emission data, obtain emission trend indicators for different vehicle types on various road sections in the city, and construct a time-series distribution map of urban pollutant emissions and diffusion; Obtain the urban traffic road network, analyze the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluate the dynamic emission indicators of mobile sources in the urban traffic road network; Obtain urban non-road mobile machinery data, identify the execution conditions corresponding to the operation modes of the construction machinery in the non-road mobile machinery data, and evaluate the dynamic emission indicators of urban non-road mobile sources; Using the dynamic emission indicators of mobile sources on the urban road network and the dynamic emission indicators of mobile sources on urban non-roads, the emission trend indicators of different vehicle types on various sections of the city are corrected to obtain a real-time distribution map of urban pollutant emissions. Among them, the dynamic emission indicators of mobile sources of urban traffic road network and urban non-road mobile sources are used to revise the emission trend indicators of different vehicle types in various sections of the city. Specifically: ； in, is the emission trend correction index of the i-th vehicle type on the k-th road section in the city, is the total emission of the i-th vehicle type on the k-th road section in the city, is the dynamic emission index of the i-th vehicle type in urban non-road mobility; Among them, based on the urban historical multi-source heterogeneous emission database, the pollutant emission and diffusion trends in the urban historical multi-source heterogeneous emission data are analyzed, and the time series distribution map of urban pollutant emission diffusion is constructed. Specifically, the following are included: Based on the city's historical multi-dimensional heterogeneous emission database, data is divided according to several dimensions of urban pollutants to obtain a data array of urban historical multi-dimensional emission factors; the multi-dimensional emission factors include: vehicle dimension, environmental dimension, oil dimension, and road dimension; Based on the vehicle emission test data in the city's historical multi-dimensional emission factor data array, several categories of emission factors for different vehicle types are determined, and a basic emission factor list for different vehicle types is determined; Based on the meteorological data in the city's historical multi-dimensional emission factor data array and the comparison table of environmental factors affecting pollutant emissions, the comprehensive environmental correction factor is determined; Based on the city's oil product data in the city's historical multi-dimensional emission factor data array and the oil product factor comparison table affecting pollutant emissions, the comprehensive oil product correction factor is determined; Based on the road network data and road traffic flow data in the city's historical multi-dimensional emission factor data array, and the road grade correction factor comparison table and speed correction factor comparison table that affect pollutant emissions, the comprehensive road correction factor is determined; Based on the basic emission factor list of different vehicle types, comprehensive environmental correction factors, comprehensive oil correction factors, and comprehensive road correction factors, we align them with time attributes, establish a time sliding window, and obtain time series data on multi-dimensional factors affecting historical pollutants in the city; Based on the multi-dimensional time series data of historical pollutant impact factors in the city, a MOBILE neural network model was established to generate emission trend indicators for different vehicle types on various road sections in the city and construct a time series distribution map of urban pollutant emissions. The MOBILE neural network model is specifically: ； Where, is the total emission of the i-th vehicle type on the k-th road section in the city, BEF ij is the jth basic emission factor of the i-th vehicle type, γ is the comprehensive environmental correction factor, φ is the comprehensive oil correction factor, λ k is the comprehensive correction factor of the kth road section, P i is the number of vehicles of type i in the city, VKT i is the average mileage of the i-th vehicle type, n is the total number of vehicle types, and m is the total number of road sections in the urban road network.

2. The method for constructing a mobile source pollution data visualization platform according to claim 1, characterized in that: Obtain the urban traffic road network, analyze the mobile source pollutant emission status in the real-time traffic flow information of the traffic road network, and evaluate the dynamic emission indicators of mobile sources in the urban traffic road network, including: Based on urban road network data and road traffic flow data, the historical urban road traffic flow data is obtained, and the vehicle type composition information and road traffic flow information of the road section are divided and extracted to obtain the historical road vehicle type composition data and historical road section flow data; Based on historical road vehicle composition data, a BP neural network is trained. Taking vehicle composition data, road type, and spatial characteristics from the historical road vehicle composition data as input, the BP neural network is used to fit the complex function between vehicle proportions and road section characteristics to predict future road vehicle composition data. Based on historical urban road traffic flow data, an LSTM urban road network vehicle type flow prediction model is trained. The flow data of sections with detectors in the historical road section flow data is used to drive the spatial topological flow of sections without detectors. The upstream and downstream traffic flows and spatial feature influence coefficients are combined as input to predict future road section flow data. Based on the predicted future road vehicle composition data, predicted future road section traffic data, and a list of basic emission factors for different vehicle types, dynamic prediction and calculation are performed on the emissions of vehicle types in each section of the urban road network to obtain the dynamic emission indicators of mobile sources in the urban traffic road network.

3. The method for constructing a mobile source pollution data visualization platform according to claim 2, characterized in that: The dynamic emission indicators of mobile sources in the urban traffic road network are specifically: ； Where, is the dynamic emission of the i-th vehicle type on the k-th road segment in the urban road network, is the traffic volume of the i-th type of vehicle on the k-th road section in the urban road network, is the travel time of the i-th vehicle type on the k-th road section in the urban road network, is the total number of vehicles of type i on the kth road section in the urban road network.

4. The method for constructing a mobile source pollution data visualization platform according to claim 3, characterized in that: Obtain urban non-road mobile machinery data, identify the execution conditions corresponding to the operation modes of the construction machinery in the non-road mobile machinery data, and evaluate the dynamic emission indicators of urban non-road mobile sources, including: Based on the non-road mobile machinery data, according to the operation modes of engineering machinery of different non-road mobile vehicle types, an original data set of the operation modes of engineering machinery of non-road mobile vehicle types is established; Determine the operating parameters corresponding to the operation mode of the construction machinery of the non-road mobile vehicle type; Based on the original data set of engineering machinery operation modes of non-road mobile vehicle types, a C-SVC vector machine is trained, with the engineering machinery operation modes corresponding to the original data of the engineering machinery operation modes as input and the operating condition parameters of the engineering machinery operation modes of non-road mobile vehicle types as output; Converting the operating condition parameters of the non-road mobile vehicle type engineering machinery operation mode by using a linear mapping to obtain an operating condition parameter vector of the non-road mobile vehicle type engineering machinery operation mode; Calculate the linear regression coefficient between the operating condition parameter vector of the non-road mobile vehicle type construction machinery operation mode and the pollutant emissions as the pollutant emission impact coefficient of the non-road mobile vehicle type construction machinery operation mode; Based on the pollutant emission impact coefficient of the engineering machinery operation mode of non-road mobile vehicle types and real-time urban non-road mobile machinery data, the dynamic emission indicators of urban non-road mobile vehicle types are calculated, and the dynamic emission indicators of urban non-road mobile sources are determined.

5. The method for constructing a mobile source pollution data visualization platform according to claim 4, characterized in that: The dynamic emission index for calculating urban non-road mobile vehicle types is specifically as follows: ； Where, is the dynamic emission index of the i-th vehicle type in the city’s non-road mobility, E i is the emission index of the i-th vehicle type in urban non-road mobility, is the pollutant emission impact coefficient of the vth construction machinery operation mode of the i-th non-road mobile vehicle type, X iv The operating condition parameters of the vth construction machinery operation mode of the i-th non-road mobile vehicle type.

Images