A method for identifying the transmission path of ozone precursors and related equipment

Abstract

The present application relates to the technical field of ozone precursor transmission, and provides a method for identifying ozone precursor transmission paths and related equipment. The method comprises: constructing an atmospheric pollutant transmission graph network based on ozone precursor data of all grids and at all times; using a graph convolutional network to predict the ozone concentration of each grid based on the atmospheric pollutant transmission graph network and all ozone precursor data, to obtain the predicted ozone concentration of each grid at each time, and using all predicted ozone concentrations to train the graph convolutional network to obtain a trained graph convolutional network; using the trained graph convolutional network to extract features from the atmospheric pollutant transmission graph network to obtain an ozone precursor transmission intensity matrix at each time; and performing path identification based on all ozone precursor transmission intensity matrices and all grids to obtain the key transmission paths of ozone precursors in the target area. The method of the present application can improve the accuracy of identifying ozone precursor transmission paths.

Description

Technical Field

[0001] The present application relates to the technical field of ozone precursor transmission, and in particular to a method for identifying an ozone precursor transmission path and related equipment. Background Art

[0002] Ozone pollution has become a significant factor affecting urban air quality and public health. Ozone is not emitted directly into the atmosphere, but is formed through photochemical reactions between precursors such as nitrogen oxides (NOx) and volatile organic compounds (VOCs) under specific meteorological conditions. Therefore, understanding the atmospheric transport pathways, concentration variations, and spatial distribution patterns of ozone precursors is crucial for developing effective ozone pollution prevention and control measures.

[0003] Existing transmission path analysis methods mostly focus on the diffusion paths of known pollutants and their impact areas. Examples include a complex network-based method and system for identifying key nodes in atmospheric pollution transmission and a complex network-based method for analyzing regional air pollutants. However, less attention has been paid to the atmospheric propagation characteristics of ozone precursors (such as nitrogen oxides and volatile organic compounds). The transport and reaction processes of these precursors are key factors in the formation of ozone pollution. Current methods fail to effectively account for the impact of precursor propagation on secondary pollution (i.e., ozone formation), resulting in significant deviations in prediction results.

[0004] Furthermore, traditional complex network models typically focus on direct connections and transmission between nodes. This is particularly true for the spread of atmospheric pollutants, where meteorological factors such as wind speed, temperature, and humidity have a significant impact on pollutant diffusion. Complex network algorithms fail to fully account for these temporal and spatial variations. Consequently, the current identification of ozone precursor transmission pathways is inaccurate. Summary of the Invention

[0005] The present application provides a method for identifying an ozone precursor transmission path and related equipment, which can solve the problem of inaccurate identification of the ozone precursor transmission path.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying an ozone precursor transmission path, the identification method comprising:

[0007] Acquiring ozone precursor data of a target area at multiple times; the ozone precursor data includes multiple data affecting the transmission of the ozone precursor;

[0008] The target area is divided into multiple grids, and an atmospheric pollutant transmission network is constructed based on the ozone precursor data of all grids and at all times. The multiple nodes of the atmospheric pollutant transmission network correspond one-to-one to the multiple grids, and the edges between the nodes represent the adjacent transmission relationship between the corresponding two grids.

[0009] Using a graph convolutional network, the ozone concentration of each grid is predicted based on the atmospheric pollutant transport graph network and all ozone precursor data, obtaining the predicted ozone concentration of each grid at each moment. All predicted ozone concentrations are then used to train the graph convolutional network to obtain a trained graph convolutional network.

[0010] The trained graph convolutional network is used to extract features from the atmospheric pollutant transport graph network to obtain the ozone precursor transmission intensity matrix at each moment;

[0011] Path identification is performed based on the transmission intensity matrix of all ozone precursors and all grids to obtain the key transmission paths of ozone precursors in the target area.

[0012] Optionally, build an atmospheric pollutant transport map network based on ozone precursor data for all grids and all time periods, including:

[0013] For each two grids at each time, determine whether the two grids meet the adjacent transmission condition at the time. If so, it is considered that there is an adjacent transmission relationship between the two grids at the time.

[0014] A corresponding node is generated for each grid, and edges between nodes are generated based on all adjacent transmission relationships to obtain the atmospheric pollutant transmission graph network.

[0015] Optionally, the adjacent transmission condition is:

[0016]

[0017] in, Indicates in moment, The grid and The row difference between the grids, Indicates in moment, The grid and The column difference between the grids, Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates the horizontal wind speed and Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, , Indicates the number of moments, , Represents a collection of grid numbers.

[0018] Optionally, a graph convolutional network is used to predict the ozone concentration of each grid based on the atmospheric pollutant transport graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each moment, including:

[0019] A node feature matrix is ​​constructed at each moment based on the atmospheric pollutant transmission network and all ozone precursor data; the elements in the node feature matrix are the ozone precursor data corresponding to each node in the atmospheric pollutant transmission network;

[0020] Constructing a dynamic adjacency matrix at each moment based on the ozone precursor data at each moment;

[0021] For each moment, the graph convolutional network is used to update the node feature matrix at the moment based on the dynamic adjacency matrix at the moment to obtain the new node feature matrix at the moment. The new node feature matrix is ​​then mapped to obtain the predicted ozone concentration of each grid at the moment.

[0022] Optionally, construct a dynamic adjacency matrix at each moment, including:

[0023] By formula:

[0024]

[0025] Calculate the The moment The grid and Adjacency parameters between grids ;

[0026] in, 、 are weight coefficients, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, , Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates the horizontal wind speed and Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates the maximum value of ozone concentration, Indicates the minimum value of ozone concentration, , Indicates the number of moments, , Represents a set of grid numbers;

[0027] Integrate the adjacency parameters corresponding to each moment into a matrix to obtain the initial adjacency matrix at each moment;

[0028] By formula:

[0029]

[0030] Calculate the Dynamic adjacency matrix at time ;

[0031] in, Indicates the The initial adjacency matrix at time t, Indicates the The initial adjacency matrix at time instant;

[0032] Using the graph convolutional network, the node feature matrix at each moment is updated based on the dynamic adjacency matrix at each moment to obtain the new node feature matrix at each moment, including:

[0033] By formula:

[0034] ;

[0035] Calculate the Output of the layer ;

[0036] in, express The degree matrix of Indicates joining the self-loop No. The dynamic adjacency matrix at each moment, , Indicates the The output of the layer, Indicates the The trainable weight matrix of the layer, , Represents the last layer, when hour, Indicates the The dynamic adjacency matrix at the moment, when hour, Indicates the The new node feature matrix at the moment.

[0037] Optionally, the trained graph convolutional network is used to extract features from the atmospheric pollutant transport graph network to obtain an ozone precursor transport intensity matrix, including:

[0038] For each moment, perform the following steps:

[0039] Using the trained graph convolutional network, the node feature matrix at each moment is updated based on the dynamic adjacency matrix at each moment to obtain the final node feature matrix at each moment.

[0040] Extract the ozone precursor-related features in the final node feature matrix and integrate them to obtain the ozone precursor transmission characteristics at that moment;

[0041] The ozone precursor transmission intensity matrix at the time is calculated based on the ozone precursor transmission characteristics.

[0042] Optionally, the ozone precursor transmission intensity matrix at the time is calculated based on the ozone precursor transmission characteristics, including:

[0043] By formula:

[0044]

[0045]

[0046] Calculate the elements of the first submatrix in the ozone precursor transport intensity matrix and the elements of the second submatrix ;

[0047] in, Indicates that nitrogen oxides The moment from The grid is transferred to the The transmission strength of the grid, Indicates that volatile organic compounds are The moment from The grid is transferred to the The transmission strength of the grid, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, represents the maximum value of the NOx-related characteristics, represents the minimum value of the NOx-related characteristics, 、 are weight coefficients, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the maximum value of the VOC-related features, Indicates the minimum value of VOC-related features, , Indicates the number of moments, , Represents a collection of grid numbers.

[0048] Optionally, path identification is performed based on all ozone precursor transport intensity matrices and all grids to obtain key transport paths of ozone precursors in the target area, including:

[0049] The grids corresponding to potential pollution source areas in all grids are used as source grids;

[0050] For each moment, according to the ozone precursor transmission intensity matrix at that moment, each source grid is used as the starting point to search for the transmission path of the source grid in all grids;

[0051] Aggregate all transmission paths at all times to obtain a collection of multiple spatiotemporal trajectories;

[0052] Calculate the similarity between every two space-time trajectories;

[0053] All spatiotemporal trajectories are clustered according to all similarities to obtain the key transmission paths.

[0054] In a second aspect, an embodiment of the present application provides a device for identifying an ozone precursor transmission path, comprising:

[0055] An acquisition module is used to acquire ozone precursor data of a target area at multiple times; the ozone precursor data includes multiple data that affect the transmission of the ozone precursor;

[0056] A partitioning module is used to divide the target area into multiple grids and construct an atmospheric pollutant transmission network based on the ozone precursor data of all grids and at all times; the multiple nodes of the atmospheric pollutant transmission network correspond one-to-one to the multiple grids, and the edges between the nodes represent the adjacent transmission relationship between the corresponding two grids;

[0057] A prediction module is used to use a graph convolutional network to predict the ozone concentration of each grid based on the atmospheric pollutant transport graph network and all ozone precursor data, thereby obtaining the predicted ozone concentration of each grid at each moment, and to train the graph convolutional network using all predicted ozone concentrations to obtain a trained graph convolutional network.

[0058] The feature extraction module is used to extract features from the atmospheric pollutant transmission graph network using the trained graph convolutional network to obtain the ozone precursor transmission intensity matrix at each moment;

[0059] The path identification module is used to identify the path based on the transmission intensity matrix of all ozone precursors and all grids to obtain the key transmission path of ozone precursors in the target area.

[0060] In a third aspect, an embodiment of the present application provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying the transmission path of ozone precursors when executing the above-mentioned computer program.

[0061] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the above-mentioned method for identifying the transmission path of ozone precursors when executed by a processor.

[0062] The above solution of the present application has the following beneficial effects:

[0063] In an embodiment of the present application, ozone precursor data of a target area at multiple times are obtained, the target area is divided into multiple grids, and an atmospheric pollutant transmission graph network is constructed based on the ozone precursor data of all grids and all times. Then, a graph convolutional network is used to predict the ozone concentration of each grid according to the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each time. The graph convolutional network is trained using all predicted ozone concentrations to obtain a trained graph convolutional network. The trained graph convolutional network is then used to perform feature extraction on the atmospheric pollutant transmission graph network to obtain an ozone precursor transmission intensity matrix at each time. Finally, path identification is performed based on all ozone precursor transmission intensity matrices and all grids to obtain the key transmission paths of ozone precursors in the target area. Among them, an atmospheric pollutant transmission map network is constructed based on ozone precursor data including multiple data, taking into account multiple factors affecting the transmission of ozone precursors, improving the comprehensiveness of information in the atmospheric pollutant transmission map network, and performing feature extraction and path identification on the atmospheric pollutant transmission map network with comprehensive information. It can effectively capture the transmission paths of ozone precursors in space, identify dynamic propagation characteristics, improve the accuracy of key transmission paths of ozone precursors, and thereby improve the accuracy of identifying the transmission paths of ozone precursors.

[0064] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0066] Figure 1 A flowchart of a method for identifying an ozone precursor transmission path according to an embodiment of the present application;

[0067] Figure 2 A schematic diagram of the structure of an ozone precursor transmission path identification device provided in one embodiment of the present application;

[0068] Figure 3 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0069] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0070] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0071] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0072] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0073] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0074] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0075] In response to the problem of inaccurate identification of existing ozone precursor transmission paths, an embodiment of the present application provides a method for identifying ozone precursor transmission paths. The identification method obtains ozone precursor data of a target area at multiple times, then divides the target area into multiple grids, and constructs an atmospheric pollutant transmission graph network based on the ozone precursor data of all grids and all times. Then, a graph convolutional network is used to predict the ozone concentration of each grid based on the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each time. The graph convolutional network is trained using all predicted ozone concentrations to obtain a trained graph convolutional network. The trained graph convolutional network is then used to perform feature extraction on the atmospheric pollutant transmission graph network to obtain an ozone precursor transmission intensity matrix at each time. Finally, path identification is performed based on all ozone precursor transmission intensity matrices and all grids to obtain the key transmission paths of ozone precursors in the target area. Among them, an atmospheric pollutant transmission map network is constructed based on ozone precursor data including multiple data, taking into account multiple factors affecting the transmission of ozone precursors, improving the comprehensiveness of information in the atmospheric pollutant transmission map network, and performing feature extraction and path identification on the atmospheric pollutant transmission map network with comprehensive information. It can effectively capture the transmission paths of ozone precursors in space, identify dynamic propagation characteristics, improve the accuracy of key transmission paths of ozone precursors, and thereby improve the accuracy of identifying the transmission paths of ozone precursors.

[0076] Next, the method for identifying the ozone precursor transmission path provided in this application is exemplified.

[0077] like Figure 1 As shown, the method for identifying the transmission path of ozone precursors provided in this application includes the following steps:

[0078] Step 11: Acquire ozone precursor data of the target area at multiple times.

[0079] The aforementioned ozone precursor data includes multiple data that affect the transmission of ozone precursors, such as surface ozone concentration data, precursor emission data (including NOx and VOCs emissions), meteorological data (including surface temperature, atmospheric humidity, solar radiation intensity, wind speed and direction, boundary layer height, etc.), and geographic information data (including regional terrain elevation). The aforementioned target area is the area where ozone precursor transmission paths need to be identified, such as a county or township. The multiple time points are multiple time points within the time period in which the ozone precursor transmission paths need to be analyzed. For example, if the ozone precursor transmission paths in the target area need to be identified and analyzed between January 1 and February 1, the multiple time points could be January 1, January 10, January 20, and February 1.

[0080] In some embodiments of the present application, ozone precursor data may be acquired through sensors, theodolites, and other equipment.

[0081] Step 12: Divide the target area into multiple grids, and construct an atmospheric pollutant transport map network based on the ozone precursor data of all grids and all times.

[0082] The multiple nodes in the aforementioned atmospheric pollutant transmission network correspond one-to-one to multiple grids, and the edges between nodes represent the adjacent transmission relationships between the corresponding two grids. After the target area is gridded, the resulting grids are arranged in rows and columns, with rows representing the horizontal divisions of the target area and columns representing the vertical divisions. The horizontal and vertical directions of the target area are set based on the actual geographic location of the target area, such as setting latitude as the horizontal direction and longitude as the vertical direction.

[0083] In some embodiments of the present application, the steps of dividing the target area into a plurality of grids and constructing an atmospheric pollutant transmission map network based on ozone precursor data of all grids and at all times include:

[0084] The first step is to determine whether each pair of grids at each moment meets the proximity transmission condition. If so, it is considered that there is a proximity transmission relationship between the two grids at that moment. If the two grids do not meet the proximity transmission condition at that moment, it is considered that there is no proximity transmission relationship between the two grids at that moment.

[0085] Specifically, the adjacent transmission conditions are:

[0086]

[0087] in, Indicates in moment, The grid and The row difference between the grids, Indicates in moment, The grid and The column difference between the grids, Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates the horizontal wind speed and Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, , Indicates the number of moments, , Represents a collection of grid numbers.

[0088] It should be noted that the row difference is the difference in row numbers of the two grids (for example, if one grid is in row 2 and the other is in row 3, the row difference is 1), and the column difference is the difference in column numbers of the two grids (for example, if one grid is in column 6 and the other is in column 2, the column difference is 4). Grid to The horizontal wind speed of each grid is unidirectional. When analyzing the adjacent transmission relationship through the above process, it is necessary to consider the other propagation direction between the two grids. For example, when considering the Grid to When the horizontal wind speed of the grid is less than 1, the adjacent transmission condition is not met, but when the horizontal wind speed of the grid is less than 1, the adjacent transmission condition is not met. Grid to When the horizontal wind speed of the grid meets the adjacent propagation conditions, then it is still considered that the The grid and There is a neighboring propagation relationship between the grids.

[0089] In the second step, a corresponding node is generated for each grid, and edges between nodes are generated based on all adjacent transmission relationships to obtain the atmospheric pollutant transmission graph network.

[0090] It should be noted that at each moment, if a neighboring transmission relationship exists between the two grids corresponding to the two nodes at that moment, an edge is generated, and this edge is directed (determined by the direction of the horizontal wind speed considered when the neighboring transmission relationship exists in the previous step. The direction of the horizontal wind speed determines the direction of the directed edge. If a neighboring transmission relationship exists in both directions, the edge is bidirectional). If a neighboring transmission relationship does not exist between the two grids corresponding to the two nodes at that moment, no edge is generated. For example, if a neighboring relationship exists between the two grids at both the first and third moments, two edges exist between the two nodes corresponding to the two grids, representing the neighboring transmission relationship between the two grids at the first and third moments, respectively. The data corresponding to the node in all ozone precursor data is used as the attribute of the node.

[0091] Step 13: Using a graph convolutional network, the ozone concentration of each grid is predicted based on the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each moment, and all predicted ozone concentrations are used to train the graph convolutional network to obtain a trained graph convolutional network.

[0092] In some embodiments of the present application, the above-mentioned steps of using a graph convolutional network to predict the ozone concentration of each grid based on the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each moment, and training the graph convolutional network using all predicted ozone concentrations to obtain the trained graph convolutional network include:

[0093] In the first step, a node feature matrix at each moment is constructed based on the atmospheric pollutant transport graph network and all ozone precursor data.

[0094] The elements in the above node feature matrix are the ozone precursor data corresponding to each node in the atmospheric pollutant transmission graph network.

[0095] Specifically, for each moment, the data corresponding to each node in the ozone precursor data at that moment is extracted, and the data of all nodes are integrated into a matrix to obtain a node feature matrix.

[0096] If the expression is:

[0097]

[0098] in, 、 is a node In the NOx emissions and VOCs emissions at each moment, 、 、 、 、 、 Represents nodes respectively In the Wind speed, temperature, humidity, solar radiation intensity, boundary layer height, and terrain elevation data at each moment.

[0099] In the second step, a dynamic adjacency matrix is ​​constructed at each moment based on the ozone precursor data at each moment.

[0100] First, through the formula:

[0101]

[0102] Calculate the The moment The grid and Adjacency parameters between grids .

[0103] in, 、 are weight coefficients, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, , Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates the horizontal wind speed and Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates the maximum value of ozone concentration, Indicates the minimum value of ozone concentration, , Indicates the number of moments, , Represents a collection of grid numbers.

[0104] Then, the adjacency parameters corresponding to each moment are integrated into a matrix to obtain the initial adjacency matrix at each moment.

[0105] Finally, through the formula:

[0106]

[0107] Calculate the Dynamic adjacency matrix at time .

[0108] in, Indicates the The initial adjacency matrix at time t, Indicates the The initial adjacency matrix at time instant.

[0109] In the third step, for each moment, the graph convolutional network is used to update the node feature matrix at that moment based on the dynamic adjacency matrix at that moment to obtain the new node feature matrix at that moment, and the new node feature matrix is ​​mapped to obtain the predicted ozone concentration of each grid at that moment.

[0110] Specifically, through the formula:

[0111]

[0112] Calculate the Output of the layer .

[0113] in, express The degree matrix of Indicates joining the self-loop No. The dynamic adjacency matrix at each moment, , Indicates the The output of the layer, Indicates the The trainable weight matrix of the layer, , Represents the last layer, when hour, Indicates the The dynamic adjacency matrix at the moment, when hour, Indicates the The new node feature matrix at the moment.

[0114] For example, a fully connected layer can be used to map the new node feature matrix to obtain the predicted ozone concentration of each grid at the time.

[0115] It is understandable that the above calculation The output formula of the layer is the first Expression of layer graph convolution.

[0116] The fourth step is to use all predicted ozone concentrations to train the graph convolutional network to obtain the trained graph convolutional network.

[0117] Specifically, a loss function is constructed based on all predicted ozone concentrations, and then the parameters of the graph convolutional network are optimized through the back propagation algorithm to minimize the loss function. , update the weight matrix using gradient descent method .

[0118] The above loss function is:

[0119]

[0120] in, 、 Grid In the The actual and predicted ozone concentrations at the time is the total number of grids, is the length of the time series.

[0121] Step 14: Use the trained graph convolutional network to extract features from the atmospheric pollutant transmission graph network to obtain the ozone precursor transmission intensity matrix at each moment.

[0122] In some embodiments of the present application, the step of extracting features from the atmospheric pollutant transmission graph network using the trained graph convolutional network to obtain the ozone precursor transmission intensity matrix at each moment includes:

[0123] For each moment, perform the following steps:

[0124] In the first step, the trained graph convolutional network is used to update the node feature matrix at each moment based on the dynamic adjacency matrix at each moment to obtain the final node feature matrix at each moment.

[0125] Specifically, the dynamic adjacency matrix is ​​substituted into the trained graph convolutional network for operation to obtain the final node feature matrix.

[0126] In the second step, the features related to ozone precursors in the final node feature matrix are extracted and integrated to obtain the ozone precursor transmission characteristics at that moment.

[0127] The final node feature matrix includes multiple features of each node (such as the characteristics of surface ozone concentration, the characteristics of precursor emission data, the characteristics of meteorological data, and the characteristics of geographic information data). All features related to ozone precursors are selected and integrated to obtain the ozone precursor transmission characteristics.

[0128] The third step is to calculate the ozone precursor transmission intensity matrix at that moment based on the ozone precursor transmission characteristics.

[0129] The ozone precursor transmission intensity matrix includes a first sub-matrix and a second sub-matrix. The first sub-matrix is ​​used to describe the transmission intensity of nitrogen oxides between every two grids, and the second sub-matrix is ​​used to describe the transmission intensity of ozone precursors between every two grids.

[0130] Specifically, through the formula:

[0131]

[0132]

[0133] Calculate the elements of the first submatrix in the ozone precursor transport intensity matrix and the elements of the second submatrix ;

[0134] in, Indicates that nitrogen oxides The moment from The grid is transferred to the The transmission strength of the grid, Indicates that volatile organic compounds are The moment from The grid is transferred to the The transmission strength of the grid, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, represents the maximum value of the NOx-related feature, represents the minimum value of the NOx-related characteristics, 、 are weight coefficients, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the maximum value of the VOC-related features, Indicates the minimum value of VOC-related features, , Indicates the number of moments, , Represents a collection of grid numbers.

[0135] Step 15: Perform path identification based on all ozone precursor transmission intensity matrices and all grids to obtain key transmission paths of ozone precursors in the target area.

[0136] In some embodiments of the present application, the step of performing path identification based on all ozone precursor transmission intensity matrices and all grids to obtain key transmission paths of ozone precursors in the target area includes:

[0137] In the first step, all grids corresponding to potential pollution source areas are used as source grids.

[0138] For example, industrial areas, natural source emission areas, etc. are regarded as potential pollution source areas, and the grids corresponding to the potential pollution source areas are regarded as source grids.

[0139] In the second step, for each moment, based on the ozone precursor transmission intensity matrix at that moment, each source grid is used as the starting point to search for the transmission path of the source grid in all grids.

[0140] Specifically, the source grid is used as the current grid, all elements related to the current grid in the ozone precursor transmission intensity matrix are obtained, and it is determined whether there is an element greater than 0 among all the elements;

[0141] If so, the grid corresponding to the element with the largest value is used as the transmission grid, and the transmission grid is used as the current grid, and the step of obtaining all elements related to the current grid in the ozone precursor transmission intensity matrix is ​​returned;

[0142] Otherwise, end the search and integrate the source grid and all transmission grids into one transmission path ,in, represents the source mesh, represents the transmission grid determined based on the source grid, Represents the last propagation grid.

[0143] It should be noted that the grid corresponding to the ozone pollution core area in the target area can also be used as the target grid, and the target grid can be used as the starting point. According to the search process of the source grid mentioned above, reverse tracing can be performed to gradually find the possible transmission source of the precursor and obtain the propagation path. ,in, represents the target grid, A grid representing the start of propagation of the reverse-traced precursor.

[0144] The third step is to aggregate all transmission paths at all times to obtain a collection of multiple spatiotemporal trajectories.

[0145] Specifically, the set of multiple space-time trajectories is:

[0146]

[0147]

[0148] in, is the geographic coordinate (i.e. the coordinate of the grid center point in the transmission path), Space-time trajectory length, represents the number of space-time trajectories (i.e., the total number of all transmission paths at all times within a cycle).

[0149] Exemplary, space-time trajectory Corresponding to a transmission path among all propagation paths at all times, the space-time trajectory The geographic coordinates in the transmission path correspond to the grid, space-time trajectory The length of is the number of grids in the transmission path.

[0150] The fourth step is to calculate the similarity between every two spatiotemporal trajectories.

[0151] For example, the dynamic time warping (DTW) algorithm can be used to calculate the similarity between spatiotemporal trajectories, and the expression is:

[0152]

[0153] in, Representing space-time trajectories and space-time trajectories The similarities between Representing space-time trajectories and space-time trajectories The cumulative distance between them is calculated as follows:

[0154] ;

[0155] ;

[0156] ;

[0157] in, express No. Node and No. The cumulative distance of the node, express No. Node and No. The distance between nodes, express No. Node and No. The cumulative distance of the node, express No. Node and No. The cumulative distance of the node, express No. Node and No. The cumulative distance of the node, express The first node and No. The cumulative distance of the node, express No. Node and The cumulative distance to the first node of .

[0158] In the fifth step, all spatiotemporal trajectories are clustered according to all similarities to obtain the key transmission paths.

[0159] For example, the K-medoids algorithm can be used to cluster all spatiotemporal trajectories based on all similarities to obtain multiple clusters. A spatiotemporal trajectory is randomly selected from each cluster as the key transmission path of the cluster (the key transmission path of the cluster can be updated). The process of the K-medoids algorithm is as follows:

[0160] Randomly select K representative trajectories (medoids), Represents a set of medoids. Each trajectory is assigned to the nearest medoid:

[0161]

[0162] Then for each cluster , select a new medoid , such that:

[0163]

[0164] Repeat the assignment and update until the medoids are stable or the maximum number of iterations is reached. At this point, the final cluster is obtained: , clustering trajectory: , each cluster Include Trajectories:

[0165]

[0166] in, It is clustering The number of samples, is the total number of trajectories identified in the period, is the indicator function, when the trajectory Belong to cluster , the function value is 1, otherwise it is 0.

[0167] It is worth mentioning that an atmospheric pollutant transmission map network is constructed based on ozone precursor data including multiple data, taking into account multiple factors that affect the transmission of ozone precursors, improving the comprehensiveness of information in the atmospheric pollutant transmission map network, and performing feature extraction and path identification on the atmospheric pollutant transmission map network with comprehensive information. It can effectively capture the spatial transmission paths of ozone precursors, identify dynamic propagation characteristics, improve the accuracy of key transmission paths of ozone precursors, and thereby improve the accuracy of identifying the transmission paths of ozone precursors.

[0168] The following is an exemplary description of the device for identifying the ozone precursor transmission path provided in this application.

[0169] like Figure 2 As shown, an embodiment of the present application provides an ozone precursor transmission path identification device, and the ozone precursor transmission path identification device 200 includes:

[0170] An acquisition module 201 is configured to acquire ozone precursor data of a target area at multiple times; the ozone precursor data includes multiple data that affect the transmission of the ozone precursor;

[0171] A partitioning module 202 is configured to divide the target area into a plurality of grids and construct an atmospheric pollutant transmission network based on the ozone precursor data of all grids and at all times; the plurality of nodes in the atmospheric pollutant transmission network correspond one-to-one to the plurality of grids, and the edges between the nodes represent the adjacent transmission relationships between the corresponding two grids;

[0172] Prediction module 203 is configured to use a graph convolutional network to predict the ozone concentration of each grid based on the atmospheric pollutant transport graph network and all ozone precursor data, thereby obtaining the predicted ozone concentration of each grid at each moment, and to train the graph convolutional network using all the predicted ozone concentrations to obtain a trained graph convolutional network.

[0173] A feature extraction module 204 is configured to extract features from the atmospheric pollutant transport graph network using the trained graph convolutional network to obtain an ozone precursor transport intensity matrix at each moment;

[0174] The path identification module 205 is used to perform path identification based on all ozone precursor transmission intensity matrices and all grids to obtain key transmission paths of ozone precursors in the target area.

[0175] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0176] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0177] like Figure 3 As shown, an embodiment of the present application provides a terminal device. The terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 3 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.

[0178] Specifically, when the processor D100 executes the computer program D102, it obtains the ozone precursor data of the target area at multiple times, then divides the target area into multiple grids, and constructs an atmospheric pollutant transmission graph network based on the ozone precursor data of all grids and all times, and then uses the graph convolution network to predict the ozone concentration of each grid according to the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each time, and uses all predicted ozone concentrations to train the graph convolution network to obtain the trained graph convolution network, and then uses the trained graph convolution network to extract features from the atmospheric pollutant transmission graph network to obtain the ozone precursor transmission intensity matrix at each time, and finally performs path identification based on all ozone precursor transmission intensity matrices and all grids to obtain the key transmission path of ozone precursors in the target area. Among them, an atmospheric pollutant transmission map network is constructed based on ozone precursor data including multiple data, taking into account multiple factors affecting the transmission of ozone precursors, improving the comprehensiveness of information in the atmospheric pollutant transmission map network, and performing feature extraction and path identification on the atmospheric pollutant transmission map network with comprehensive information. It can effectively capture the transmission paths of ozone precursors in space, identify dynamic propagation characteristics, improve the accuracy of key transmission paths of ozone precursors, and thereby improve the accuracy of identifying the transmission paths of ozone precursors.

[0179] The processor D100 may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0180] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device D10. Furthermore, the memory D101 may include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory D101 may also be used to temporarily store data that has been output or is about to be output.

[0181] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0182] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0183] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the ozone precursor transmission path identification method device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. Examples include a USB flash drive, removable hard drive, magnetic disk, or optical disk.

[0184] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0185] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0186] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying an ozone precursor transmission path, characterized in that: include: Obtain ozone precursor data in the target area at multiple times; The ozone precursor data includes a plurality of data affecting the transmission of ozone precursors; Dividing the target area into a plurality of grids, and constructing an atmospheric pollutant transmission graph network based on ozone precursor data of all grids and at all times; wherein the plurality of nodes of the atmospheric pollutant transmission graph network correspond one-to-one to the plurality of grids, and the edges between the nodes represent the adjacent transmission relationships between the corresponding two grids; Using a graph convolutional network, predicting the ozone concentration of each grid according to the atmospheric pollutant transport graph network and all ozone precursor data, to obtain a predicted ozone concentration of each grid at each moment, and training the graph convolutional network using all predicted ozone concentrations to obtain a trained graph convolutional network; Using the trained graph convolutional network to perform feature extraction on the atmospheric pollutant transmission graph network to obtain an ozone precursor transmission intensity matrix at each moment; Path identification is performed based on all ozone precursor transmission intensity matrices and all grids to obtain key transmission paths of ozone precursors in the target area.

2. The identification method according to claim 1, characterized in that The method of constructing an atmospheric pollutant transmission map network based on ozone precursor data of all grids and at all times includes: For each two grids at each moment, determine whether the two grids meet a neighboring transmission condition at the moment; if so, consider that a neighboring transmission relationship exists between the two grids at the moment; A corresponding node is generated for each grid, and edges between nodes are generated based on all adjacent transmission relationships to obtain the atmospheric pollutant transmission graph network.

3. The identification method according to claim 2, characterized in that The adjacent transmission condition is: in, Indicates in moment, The grid and The row difference between the grids, Indicates in moment, The grid and The column difference between the grids, Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates that the horizontal wind speed is Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, , Indicates the number of moments, , Represents a collection of grid numbers.

4. The identification method according to claim 1, wherein: The method of using a graph convolutional network to predict the ozone concentration of each grid according to the atmospheric pollutant transmission graph network and all ozone precursor data to obtain the predicted ozone concentration of each grid at each moment includes: Constructing a node feature matrix at each moment based on the atmospheric pollutant transmission graph network and all ozone precursor data; the elements in the node feature matrix are the ozone precursor data corresponding to each node in the atmospheric pollutant transmission graph network; Constructing a dynamic adjacency matrix at each moment based on the ozone precursor data at each moment; For each moment, the graph convolutional network is used to update the node feature matrix at the moment based on the dynamic adjacency matrix at the moment to obtain a new node feature matrix at the moment, and the new node feature matrix is ​​mapped to obtain the predicted ozone concentration of each grid at the moment.

5. The identification method according to claim 4, characterized in that: The construction of the dynamic adjacency matrix at each moment includes: By formula: Calculate the The moment The grid and Adjacency parameters between grids ; in, 、 are weight coefficients, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, , Indicates in moment, Grid to The horizontal wind speed of the grid, Indicates that the horizontal wind speed is Grid to The angle between the horizontal transmission direction of the lines connecting the grids is, Indicates the The grid and The terrain correction angle between grids, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates in The ozone precursor data at the moment The ozone concentration of each grid, Indicates the maximum value of ozone concentration, Indicates the minimum value of ozone concentration, , Indicates the number of moments, , Represents a set of grid numbers; Integrate the adjacency parameters corresponding to each moment into a matrix to obtain the initial adjacency matrix at each moment; By formula: Calculate the Dynamic adjacency matrix at time ; in, Indicates the The initial adjacency matrix at time t, Indicates the The initial adjacency matrix at time instant; The method of using the graph convolutional network to update the node feature matrix at the moment based on the dynamic adjacency matrix at the moment to obtain a new node feature matrix at the moment includes: By formula: ； Calculate the Output of the layer ; in, express The degree matrix of Indicates joining the self-loop No. The dynamic adjacency matrix at each moment, , Indicates the The output of the layer, Indicates the The trainable weight matrix of the layer, , Represents the last layer, when hour, Indicates the The dynamic adjacency matrix at the moment, when hour, Indicates the The new node feature matrix at the moment.

6. The identification method according to claim 4, characterized in that: The method of using the trained graph convolutional network to perform feature extraction on the atmospheric pollutant transmission graph network to obtain an ozone precursor transmission intensity matrix includes: For each moment, perform the following steps: Using the trained graph convolutional network, updating the node feature matrix at the moment based on the dynamic adjacency matrix at the moment to obtain a final node feature matrix at the moment; Extracting and integrating features related to ozone precursors in the final node feature matrix to obtain ozone precursor transmission features at that moment; An ozone precursor transmission intensity matrix at the moment is calculated based on the ozone precursor transmission characteristics.

7. The identification method according to claim 6, characterized in that: The calculating of the ozone precursor transmission intensity matrix at the moment based on the ozone precursor transmission characteristics includes: By formula: Calculate the elements of the first submatrix in the ozone precursor transport intensity matrix and the elements of the second submatrix ; in, Indicates that nitrogen oxides The moment from The grid is transferred to the The transmission strength of the grid, Indicates that volatile organic compounds are The moment from The grid is transferred to the The transmission strength of the grid, Indicates in The moment The grid is transferred to the The terrain-corrected wind speed for each grid cell, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment NOx-related features of the grid, Indicates the minimum value of terrain-corrected wind speed, represents the maximum value of the terrain-corrected wind speed, represents the maximum value of the NOx-related characteristics, represents the minimum value of the NOx-related characteristics, 、 are weight coefficients, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the The transport characteristics of ozone precursors at the moment The VOC-related features of the grid, Indicates the maximum value of the VOC-related features, Indicates the minimum value of VOC-related features, , Indicates the number of moments, , Represents a collection of grid numbers.

8. The identification method according to claim 1, characterized in that The path identification is performed based on all ozone precursor transmission intensity matrices and all grids to obtain the key transmission paths of ozone precursors in the target area, including: The grids corresponding to potential pollution source areas in all grids are used as source grids; For each moment, based on the ozone precursor transmission intensity matrix at the moment, each source grid is used as a starting point, and a transmission path of the source grid is searched in all grids; Aggregate all transmission paths at all times to obtain a collection of multiple spatiotemporal trajectories; Calculate the similarity between every two space-time trajectories; All spatiotemporal trajectories are clustered according to all similarities to obtain the key transmission paths.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for identifying the ozone precursor transmission path according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying the ozone precursor transmission path according to any one of claims 1 to 8 is implemented.

Images