Three-dimensional spatial distribution modeling method, storage medium and device for air pollutants

Abstract

The present application provides a method, storage medium and device for modeling the three-dimensional spatial distribution of air pollutants, the method comprising: obtaining horizontal data and vertical data of a target area through a mobile device; wherein the horizontal data and the vertical data are obtained in the same time period; the horizontal data include the air pollutant concentration in the horizontal direction; the vertical data include the air pollutant concentration in the vertical direction; modeling the pollutants in the horizontal direction according to the horizontal data to obtain a horizontal pollutant prediction model; modeling the pollutants in the vertical direction according to the vertical data to obtain a vertical pollutant prediction model; fitting the three-dimensional spatial distribution model of pollutants according to the horizontal pollutant prediction model and the vertical pollutant prediction model. The present invention can accurately obtain the three-dimensional distribution of the pollutant concentration in the target area.

Description

Technical Field

[0001] The present application relates to the technical field of air pollutant distribution modeling, and in particular to a method, storage medium and device for modeling the three-dimensional spatial distribution of air pollutants. Background Art

[0002] The distribution of air pollutants has a great impact on people's lives. In the prior art, the distribution of pollutants is generally achieved based on atmospheric observation. However, due to the influence of distance, atmospheric observation cannot accurately obtain the distribution of pollutant concentrations in the low-altitude range where people live, and it is impossible to build a complete and accurate pollutant concentration distribution model based only on the data obtained from atmospheric observation. Therefore, how to accurately obtain the three-dimensional distribution of pollutant concentrations in the low-altitude range where people live is a technical problem to be solved. Summary of the invention

[0003] The purpose of this application is to overcome the shortcomings and deficiencies in the prior art and to provide a method, storage medium and device for modeling the three-dimensional spatial distribution of air pollutants, which can accurately obtain the three-dimensional distribution of pollutant concentrations in the target area.

[0004] An embodiment of the present application provides a method for modeling the three-dimensional spatial distribution of air pollutants, comprising:

[0005] Acquire horizontal direction data and vertical direction data of a target area through a mobile device; wherein the horizontal direction data and the vertical direction data are acquired in the same time period; the horizontal direction data include the air pollutant concentration in the horizontal direction; and the vertical direction data include the air pollutant concentration in the vertical direction;

[0006] Modeling pollutants in the horizontal direction according to the horizontal direction data to obtain a horizontal direction pollutant prediction model;

[0007] Modeling pollutants in the vertical direction according to the vertical direction data to obtain a vertical direction pollutant prediction model;

[0008] According to the horizontal pollutant prediction model and the vertical pollutant prediction model, a three-dimensional spatial distribution model of pollutants is fitted.

[0009] One embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described above.

[0010] One embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described above when executing the computer program.

[0011] Compared with the related art, the present application obtains horizontal and vertical data of the target area through a mobile device, which can improve the flexibility of data acquisition and the diversity of data acquisition locations, thereby improving the accuracy of the constructed horizontal pollutant prediction model and the vertical pollutant prediction model, and further improving the accuracy of the fitted three-dimensional spatial distribution model of pollutants, so as to accurately obtain the three-dimensional distribution of pollutant concentrations in the target area.

[0012] In order to provide a clearer understanding of the present application, the specific implementation of the present application will be described below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flow chart of a method for modeling the three-dimensional spatial distribution of air pollutants according to an embodiment of the present application.

[0014] Figure 2 This is a flowchart of steps S101 - S102 of a method for modeling the three-dimensional spatial distribution of air pollutants according to an embodiment of the present application.

[0015] Figure 3 This is a flowchart of steps S111 - S113 of a method for modeling the three-dimensional spatial distribution of air pollutants according to an embodiment of the present application.

[0016] Figure 4 This is a flowchart of steps S121 - S124 of a method for modeling the three-dimensional spatial distribution of air pollutants according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0018] It should be clear that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0019] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. The singular forms of "a", "said" and "the" used in the present application and the appended claims are also intended to include the majority form, unless the context clearly indicates other meanings. The words "if" / "if" used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0020] In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0021] See also Figure 1 , which is a flow chart of a method for modeling the three-dimensional spatial distribution of air pollutants according to an embodiment of the present application, comprising:

[0022] S1: Acquire horizontal data and vertical data of a target area through a mobile device; wherein the horizontal data and the vertical data are acquired in the same time period; the horizontal data include the concentration of air pollutants in the horizontal direction; and the vertical data include the concentration of air pollutants in the vertical direction.

[0023] Optionally, the target area may be a city with dense high-rise buildings. The mobility of the mobile device may be fully utilized to flexibly collect data in the city with dense high-rise buildings to obtain horizontal and vertical data.

[0024] The horizontal data of the target area refers to the horizontal sampling data collected at the same horizontal height by the atmospheric motion monitor, for example, collected at multiple preset sampling locations at the same horizontal height, and the horizontal sampling data includes data including air pollutant concentrations. The number of pre-sampling locations is at least 10, that is, the horizontal sampling data collected at the same horizontal height includes data at at least 10 different horizontal positions.

[0025] Vertical data refers to the vertical sampling data collected by the atmospheric motion monitor at each preset sampling location along the vertical direction, for example, at multiple different heights at a preset sampling location, and the vertical sampling data includes data including air pollutant concentrations. The vertical sampling data at the same preset sampling location includes packet data at at least 4 different heights.

[0026] Air pollutants are a mixture of gaseous, volatile, semi-volatile and particulate matter (PM), and their composition varies greatly. The composition of air pollution is affected by many factors, including meteorological conditions, time of day, day of the week, industrial activity and traffic intensity.

[0027] The same time period may refer to the same hour or the same preset time period, and the preset time period includes but is not limited to the morning rush hour (08:00-09:00), afternoon (15:00-16:00) and night (21:00-22:00).

[0028] Preferably, in order to improve the accuracy of the sampling data of the atmospheric movement monitor, before performing step S1, the high-precision measuring instrument and the atmospheric movement monitor are first used to sample data at the same time and at the same location, and the atmospheric movement monitor is parameter-adjusted according to the sampling data of the high-precision measuring instrument to improve the measurement accuracy of the atmospheric movement monitor. Optionally, the horizontal direction data and the vertical direction data of step S1 can also be adjusted according to the ratio of the sampling data of the high-precision measuring instrument to the sampling data of the atmospheric movement monitor to obtain more accurate air pollutant concentration data.

[0029] S2: Modeling pollutants in the horizontal direction according to the horizontal direction data to obtain a horizontal pollutant prediction model.

[0030] Among them, the horizontal pollutant prediction model adopts the flexible Bayesian regression model.

[0031] S3: Modeling pollutants in the vertical direction according to the vertical direction data to obtain a vertical direction pollutant prediction model.

[0032] Among them, the vertical pollutant prediction model adopts an exponential model.

[0033] S4: According to the horizontal pollutant prediction model and the vertical pollutant prediction model, a three-dimensional spatial distribution model of pollutants is fitted.

[0034] Compared with the related art, the present application obtains the horizontal and vertical data of the target area through a mobile device, which can improve the flexibility of data acquisition and the diversity of data acquisition locations, thereby improving the accuracy of the constructed horizontal pollutant prediction model and the vertical pollutant prediction model, and then improving the accuracy of the three-dimensional spatial distribution model of the fitted pollutants, and can accurately obtain the three-dimensional distribution of the pollutant concentration in the target area, especially for cities with dense high-rise buildings, the corresponding three-dimensional distribution of pollutant concentration can be flexibly and accurately obtained. According to the three-dimensional distribution of pollutant concentration, it is helpful to find the source of pollutants, and it is also helpful to guide people in areas with high pollutant concentrations to take corresponding countermeasures, such as reminding people to use practical air purification equipment, wear masks, and close doors and windows during periods of high pollutant concentrations to reduce the impact of pollutants on health.

[0035] See also Figure 2 In a feasible embodiment, the step S1: the step of obtaining horizontal direction data and vertical direction data of the target area through a mobile device, comprises:

[0036] S101: Using an atmospheric motion monitor installed on a drone, data is collected above a number of preset horizontal sampling points to obtain air pollutant concentrations at multiple heights at each horizontal sampling point.

[0037] The atmospheric movement detection device is arranged at the bottom of the UAV, and its sampling port extends to 50 cm above the UAV. Optionally, a meteorological parameter measuring device is also arranged on the top of the UAV, and the sampling port of the meteorological parameter measuring device also extends to 50 cm above the UAV. This can prevent the sampling ports of the atmospheric movement detection device and the meteorological parameter measuring device from being affected by the rotor airflow of the UAV.

[0038] S102: Determine the air pollutant concentrations at multiple heights of the same horizontal sampling point as the vertical direction data.

[0039] In this embodiment, accurate vertical direction data can be acquired through steps S101 - S102 .

[0040] See also Figure 3 In a feasible embodiment, the step S1: the step of obtaining horizontal direction data and vertical direction data of the target area through a mobile device, comprises:

[0041] S111: Data is collected on the ground range of several preset horizontal sampling points by using an atmospheric movement monitor installed on a ground moving object to obtain the air pollutant concentration of the ground range of each horizontal sampling point; wherein the ground range refers to a position whose height is lower than a preset height value.

[0042] Among them, ground moving objects can be cars, motorcycles, bicycles or even pedestrians. The ground range refers to the position below 2 meters in height.

[0043] S112: Determine the air pollutant concentration at each preset horizontal sampling point as the horizontal direction data.

[0044] In this embodiment, accurate horizontal direction data can be acquired through steps S111 - S112 .

[0045] See also Figure 4 In a feasible embodiment, the step S1: the step of obtaining horizontal direction data and vertical direction data of the target area through a mobile device, comprises:

[0046] S121: When acquiring the horizontal direction data and the vertical direction data of the target area, shooting the environment is performed to obtain an environment image.

[0047] The environment image can be a photo or a video.

[0048] S122: Determine the data in the horizontal direction data and the vertical direction data, in which the concentration of air pollutants is greater than a preset abnormal threshold, as suspicious data.

[0049] Among them, the preset abnormal threshold refers to the sum of the average value of the air pollutant concentration and three times the standard deviation of the air pollutant concentration.

[0050] S123: Performing image detection on the environment image corresponding to the suspicious data to identify the suspicious data with unnatural influence as abnormal data.

[0051] Among them, suspicious data of unnatural influences include abnormally high concentrations of air pollutants caused by unnatural conditions such as smoking and fire.

[0052] S124: Deleting the abnormal data from the horizontal direction data and the vertical direction data.

[0053] In this embodiment, through steps S121 - S124 , abnormal data can be deleted from the horizontal direction data and the vertical direction data to prevent the abnormal data from affecting the accuracy of the three-dimensional spatial distribution model of pollutants.

[0054] In a feasible embodiment, the step S2: performing horizontal pollutant modeling according to the horizontal data to obtain a horizontal pollutant prediction model includes:

[0055] S21: Calculate the mean data and variance data of the horizontal pollutant model according to the horizontal data.

[0056] Specifically, the step S21 includes:

[0057] The mean data of the horizontal pollutant model is calculated by the following formula:

[0058] μ(X,s,t)=η * (x)+mean(Y s )+mean(Y t );

[0059] Among them, μ(X, s, t) is the mean data of the horizontal pollutant model; η * (x) is the fitting parameter; mean(Y s ) is the mean value of the pollutant concentration at the horizontal position s; mean(Y t ) is the mean value of the pollutant concentration in the horizontal direction at time t.

[0060] The variance data of the horizontal pollutant model is calculated by the following formula:

[0061] logσ(X,s,t)=η * (x)+std(Y s )+std(Y t );

[0062] Among them, logσ(X, s, t) is the variance data of the horizontal pollutant model; std(Y s ) is the standard deviation of the pollutant concentration at the horizontal position s; std(Y t ) is the standard deviation of the pollutant concentration in the horizontal direction at time t.

[0063] Among them, the fitting parameters are affected by meteorological data, sampling period and various horizontal prediction variables, such as building environment data, street type data, land use type data, weekly change data and seasonal change data. The fitting parameters can be constructed by sampling the pollutant concentration, meteorological data, building environment data, street type data, land use type data, weekly change data and seasonal change data to construct a generalized additive model, thereby calculating the intercept of the generalized additive model and the coefficient of meteorological data, and then according to the intercept of the generalized additive model, the coefficient of meteorological data and various other horizontal prediction variables, the fitting parameters of different positions are inverted, that is, the calculation formula of the fitting parameters is as follows:

[0064] η * (x) = α0 + α1·x mgteo +β+f1(x h );

[0065] Among them, α0 is the intercept; α1 is the coefficient of meteorological data; x meteois the meteorological data; β represents the data of the predictor variables in various horizontal directions; f1(x h ) is the sampling period.

[0066] S22: Constructing the horizontal pollutant prediction model according to the mean data and the variance data.

[0067] The step S22 comprises:

[0068] The horizontal pollutant prediction model is constructed by the following formula:

[0069] Y(s,t)=μ(x,s,t)±σ(x,s,t);

[0070] Wherein, Y(s, t) is the predicted ground concentration value of the pollutant at the horizontal position s at time t; μ(x, s, t) is the mean data of the horizontal position s at time t; σ(x, s, t) is the variance data of the horizontal position s at time t.

[0071] In this embodiment, a horizontal pollutant prediction model is constructed through steps S21-S22, and the horizontal pollutant prediction model can be used to predict the ground predicted concentration value of pollutants at a certain horizontal position at a certain moment.

[0072] In a feasible embodiment, the step S3: performing vertical pollutant modeling according to the vertical data to obtain a vertical pollutant prediction model includes:

[0073] The following formula is used to calculate the k(t) corresponding to the pollutant concentration observation at each location, time and height according to the following exponential model:

[0074] C h (t) = C0(t) × e k(t)×h ;

[0075] Among them, C h (t) is the concentration value at time t and height h; C0(t) is the ground concentration value of the pollutant at time t; k(t) is the vertical attenuation coefficient at time t; h is the height.

[0076] Next, we need to build a second model to fit k(t) corresponding to each observation. Since the vertical attenuation coefficient is affected by the prediction variables in the vertical direction, which include terrain data, land use data, meteorological data, traffic data, and socio-economic data, the input data for simulating the vertical attenuation coefficient include but are not limited to meteorological station observation data (station data such as temperature, precipitation, and solar radiation intensity), land use data (obtained through ground remote sensing data identification), building environment data (such as Amap building height data and sky openness data obtained from remote sensing images), socio-economic data (including population density data, GDP and other grid data), and road data (vector data such as road network). The input data can also be found in the following table:

[0077] Table 1: Examples of data to be collected and predictor variables

[0078]

[0079] The process of obtaining the vertical attenuation coefficient includes:

[0080] S301: Perform univariate regression on various vertical prediction variables to calculate the determination coefficients corresponding to the various vertical prediction variables. The determination coefficients are used to evaluate the fitting effect of the regression model. The higher the value of the determination coefficient, the better the fitting effect of the regression model.

[0081] S302: adding the prediction variable with the highest coefficient of determination to the initial model of the vertical attenuation coefficient, and calculating the coefficient of determination of the vertical attenuation coefficient model after the prediction variable is added;

[0082] The calculation formula of the coefficient of determination is:

[0083]

[0084] R 2 is the coefficient of determination, is the vertical attenuation coefficient corresponding to the i-th vertical prediction variable, and k is the initial vertical attenuation coefficient.

[0085] S303: adding the next vertical prediction variable to the vertical attenuation coefficient model according to a preset order, and calculating the coefficient of determination at this time;

[0086] S304: judging the validity of the added prediction variables according to the determination coefficient of the vertical attenuation coefficient model before the prediction variables are added and the determination coefficient of the vertical attenuation coefficient model after the prediction variables are added, and judging is specifically performed by the following judgment formula:

[0087]

[0088] Among them, R 2 is the coefficient of determination of the vertical attenuation coefficient model before adding the predictor variables, is the coefficient of determination of the vertical attenuation coefficient model after adding the predictor variables.

[0089] If the above judgment formula is met, it means that the added prediction variable is valid data, and jump to step S302. If the above judgment formula is not met, it means that the added prediction variable is invalid data, and jump to step S305;

[0090] S305: Calculate the variance inflation factor of the added predictor variables, and remove the predictor variables whose variance inflation factor is greater than a preset factor threshold;

[0091] VIF=1 / (1-R 2 )

[0092] Where VIF is the variance inflation factor, and the preset factor threshold is 3.

[0093] S306: According to the model obtained in step S305, determine the final vertical attenuation coefficient:

[0094] k=β0+β1×v1+…+β n ×v n .

[0095] Among them, β0 represents the initial preset variable coefficient; β1 represents the variable coefficient of the predicted variable v1; β n Denotes the predictor variable v n The variable coefficient of .

[0096] In this embodiment, through the above formula, a model of the vertical attenuation coefficient k(t) of vertical pollutants can be constructed, the fitting model of k(t) can be brought into the vertical distribution prediction model, and the concentration value of pollutants at a certain height at a certain time can be predicted through the vertical pollutant prediction model.

[0097] In a feasible embodiment, the step S4: the step of fitting a three-dimensional spatial distribution model of pollutants according to the horizontal pollutant prediction model and the vertical pollutant prediction model, comprises:

[0098] Among them, according to the horizontal pollutant prediction model and the vertical pollutant prediction model, the three-dimensional spatial distribution model of pollutants is fitted, which means that the prediction output result of the horizontal pollutant prediction model is used as the input of the vertical pollutant prediction model to obtain a model that can predict the three-dimensional spatial distribution of pollutants.

[0099] The three-dimensional spatial distribution model of pollutants is constructed using the following formula:

[0100] C h (s ， t)′=Y(s,t)×e k(t)×h ;

[0101] Among them, C h (s, t)′ is the predicted pollutant concentration value at the horizontal position s and the height h at time t; Y(s, t) is the predicted ground concentration value of the pollutant at the horizontal position S at time t; k(t) is the vertical attenuation coefficient at time t; h is the height.

[0102] In this embodiment, by fitting the horizontal pollutant prediction model and the vertical pollutant prediction model, a three-dimensional spatial distribution model of pollutants is obtained, and the air pollutant concentration at any height at any horizontal position in the corresponding target area can be predicted, thereby accurately obtaining the three-dimensional distribution of pollutant concentration in the target area.

[0103] One embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described above.

[0104] One embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described above when executing the computer program.

[0105] The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. Ordinary technicians in this field can understand and implement it without creative work.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the function selected in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 function selected in a box or multiple boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 steps for the function selected in a box or multiple boxes.

[0109] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0110] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0111] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0112] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0113] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for modeling the three-dimensional spatial distribution of air pollutants, characterized in that: include: Acquire horizontal direction data and vertical direction data of a target area through a mobile device; wherein the horizontal direction data and the vertical direction data are acquired in the same time period; the horizontal direction data include the air pollutant concentration in the horizontal direction; and the vertical direction data include the air pollutant concentration in the vertical direction; Modeling pollutants in the horizontal direction according to the horizontal direction data to obtain a horizontal direction pollutant prediction model; Modeling pollutants in the vertical direction according to the vertical direction data to obtain a vertical direction pollutant prediction model; According to the horizontal pollutant prediction model and the vertical pollutant prediction model, a three-dimensional spatial distribution model of pollutants is fitted; The step of modeling pollutants in the horizontal direction according to the horizontal direction data to obtain a horizontal pollutant prediction model includes: Calculating the mean data and variance data of the horizontal pollutant model according to the horizontal data; Constructing the horizontal pollutant prediction model according to the mean data and the variance data; The step of calculating the mean data and variance data of the horizontal pollutant model according to the horizontal data includes: The mean data of the horizontal pollutant model is calculated by the following formula: μ(X,s,t)=η * (x)+mean(Y s )+mean(Y t ); Among them, μ(X, s, t) is the mean data of the horizontal pollutant model; η * (x) is the fitting parameter; mean(Y s ) is the mean value of the pollutant concentration at the horizontal position s; mean(Y t ) is the mean value of the pollutant concentration in the horizontal direction at time t; The variance data of the horizontal pollutant model is calculated by the following formula: logσ(X,s,t)=η * (x)+std(Y s )+std(Y t ): Among them, logσ(X, s, t) is the variance data of the horizontal pollutant model; std(Y s ) is the standard deviation of the pollutant concentration at the horizontal position s; std(Y t ) is the standard deviation of the pollutant concentration in the horizontal direction at time t; The step of constructing the horizontal pollutant prediction model according to the mean data and the variance data comprises: The horizontal pollutant prediction model is constructed by the following formula: Y(s,t)=μ(x,s,t)±σ(x,s,t); Among them, Y(s, t) is the predicted ground concentration value of the pollutant at the horizontal position s at time t; μ(x, s, t) is the mean data of the horizontal position s at time t; σ(x, s, t) is the variance data of the horizontal position s at time t; The pollutant modeling in the vertical direction is performed according to the vertical direction data to obtain a vertical direction pollutant prediction model, including: The vertical pollutant prediction model is constructed by the following formula: C h (t)=C0(t)×e k(t)×h ; Among them, C h (t) is the concentration value at time t and height h; c0(t) is the ground concentration value of the pollutant at time t; k(t) is the vertical attenuation coefficient at time t; h is the height.

2. The method for modeling the three-dimensional spatial distribution of air pollutants according to claim 1, characterized in that: The step of fitting a three-dimensional spatial distribution model of pollutants according to the horizontal pollutant prediction model and the vertical pollutant prediction model comprises: The three-dimensional spatial distribution model of pollutants is constructed using the following formula: C h (s,t)′=Y(s,t)×e k(t)×h ; Among them, C h (s, t)′ is the predicted pollutant concentration value at the horizontal position s and the height h at time t; Y(s, t) is the predicted ground concentration value of the pollutant at the horizontal position s at time t; k(t) is the vertical attenuation coefficient at time t; h is the height.

3. The method for modeling the three-dimensional spatial distribution of air pollutants according to claim 1, characterized in that: The step of obtaining horizontal direction data and vertical direction data of the target area through the mobile device includes: When acquiring the horizontal direction data and the vertical direction data of the target area, performing environmental photography to obtain an environmental image; Determine the data in the horizontal direction data and the vertical direction data, in which the concentration of air pollutants is greater than a preset abnormal threshold, as suspicious data; Performing image detection on the environment image corresponding to the suspicious data to identify the suspicious data with unnatural influence as abnormal data; The abnormal data is deleted from the horizontal direction data and the vertical direction data.

4. The method for modeling the three-dimensional spatial distribution of air pollutants according to claim 1, characterized in that: The step of obtaining horizontal direction data and vertical direction data of the target area through the mobile device includes: The atmospheric mobile monitor installed on the drone collects data above several preset horizontal sampling points to obtain the concentration of air pollutants at multiple heights at each horizontal sampling point; The air pollutant concentrations at multiple heights of the same horizontal sampling point are determined as the vertical direction data.

5. The method for modeling the three-dimensional spatial distribution of air pollutants according to claim 1, characterized in that: The step of obtaining horizontal direction data and vertical direction data of the target area through the mobile device includes: By means of an atmospheric movement monitor installed on a ground moving object, data is collected on the ground range of a number of preset horizontal sampling points to obtain the concentration of air pollutants in the ground range of each horizontal sampling point; wherein the ground range refers to a position whose height is lower than a preset height value; The air pollutant concentration at each preset horizontal sampling point is determined as the horizontal direction data.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described in any one of claims 1 to 5 are implemented.

7. A computer device, characterized in that: The method comprises a storage device, a processor, and a computer program stored in the storage device and executable by the processor. When the processor executes the computer program, the steps of the method for modeling the three-dimensional spatial distribution of air pollutants as described in any one of claims 1 to 5 are implemented.

Images