A Method, Device, Equipment and Medium for Estimating VOCs Concentration

Abstract

The present invention relates to a method, device, equipment and medium for estimating the concentration of VOCs, belonging to the technical field of environmental monitoring. The method includes: obtaining the column concentration data of the polluting gas monitored by satellites, the profile data of the polluting gas, and the influence factor data within the target area; calculating the near-surface polluting gas concentration data with the first resolution according to the column concentration data and the profile data of the polluting gas, and performing resampling processing on the influence factor data; inputting the near-surface polluting gas concentration data with the first resolution and the processed influence factor data into a downscaling model to output the near-surface polluting gas concentration data with the second resolution, where the second resolution is greater than the first resolution; and inputting the near-surface polluting gas concentration data with the second resolution into a VOCs concentration estimation model to output the VOCs concentration data of the target area. The present invention provides a way to obtain the spatio-temporal distribution information of VOCs continuously over a large area.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring, and particularly relates to a method, device, equipment and medium for estimating the concentration of VOCs. Background Art

[0002] With the increasingly effective treatment of polluting gases such as particulate matter, sulfur dioxide, and nitrogen oxides, the pollution concentration has decreased significantly, and the ozone problem has become increasingly prominent. The treatment of ozone and its precursor VOCs has gradually become the focus of current air treatment. Timely understanding of the VOCs concentration distribution and change trend is very important for air pollution prevention and control.

[0003] In the prior art, the monitoring of VOCs mainly relies on ground equipment, which can monitor the continuous hourly changes of multiple species of VOCs. However, it also has certain limitations. On the one hand, the monitoring results only represent the concentration in a small area around the station. On the other hand, the monitoring equipment is only available in a small number of ground stations and field experiments, and it is impossible to comprehensively understand the air pollution situation. In contrast, satellite remote sensing can obtain continuous atmospheric distribution information and is an important means for monitoring air pollutants. However, satellite monitoring also has problems such as relatively coarse spatial and temporal resolutions, difficulty in achieving refined supervision at the small scale of cities, and inability to directly monitor VOCs. Therefore, there is an urgent need for a method for estimating the concentration of VOCs that can combine multi-source data. Summary of the Invention

[0004] In view of the above analysis, the embodiments of the present invention aim to provide a method, device, equipment and medium for estimating the concentration of VOCs to solve the problem that large-scale continuous monitoring of VOCs cannot be carried out in the prior art.

[0005] The object of the present invention is achieved as follows:

[0006] The first aspect of the present invention provides a method for estimating the concentration of VOCs, including:

[0007] Obtaining the column concentration data of polluting gases, the profile data of polluting gases, and the influencing factor data monitored by satellites in the target area;

[0008] Calculating the near-surface polluting gas concentration data with the first resolution according to the column concentration data and the profile data of polluting gases, and resampling the influencing factor data;

[0009] Inputting the near-surface polluting gas concentration data with the first resolution and the processed influencing factor data into a downscaling model to output the near-surface polluting gas concentration data with the second resolution, where the second resolution is greater than the first resolution;

[0010] Inputting the near-surface polluting gas concentration data with the second resolution into a VOCs concentration estimation model to output the VOCs concentration data of the target area.

[0011] Further, calculating the first-resolution near-surface pollutant gas concentration data based on the column concentration data and profile data of the pollutant gas includes:

[0012] Projecting the column concentration data into grid data, and calculating the first-resolution near-surface pollutant gas concentration data according to the grid data and the profile data, which is expressed as follows:

[0013]

[0014] where, represents the pollutant gas concentration at the grid position i and the profile height j , represents the column concentration of the pollutant gas at the grid position i , represents the type of the pollutant gas, including formaldehyde, glyoxal, and nitrogen dioxide, represents the integral of the concentration of the entire profile, represents from the ground to Hs the integral of the profile concentration at the height.

[0015] Further, the resampling process of the impact factor data includes: screening the key impact factor data that affects the pollutant gas concentration in the target area from the impact factor data using the Pearson correlation coefficient method, and resampling the key impact factors at different sampling resolutions to obtain the first-resolution grid data and the second-resolution grid data.

[0016] Further, inputting the first-resolution near-surface pollutant gas concentration data and the processed impact factor data into the downscaling model to output the second-resolution near-surface pollutant gas concentration data includes:

[0017] Using the trend surface function to predict the first-resolution near-surface pollutant gas concentration value based on the first-resolution grid data, and calculating the first-resolution residual between the first-resolution predicted value of the near-surface pollutant gas concentration and the first-resolution near-surface pollutant gas concentration data, which is expressed as:

[0018]

[0019] where, represents the first-resolution predicted value of the near-surface pollutant gas concentration, represents the trend surface function, represents the key impact factor data in the first-resolution grid data, represents the first-resolution residual, represents the first-resolution near-surface pollutant gas concentration data;

[0020] Predict the concentration value of near - surface pollution gas at the second resolution using a trend - surface function, interpolate the first - resolution residual to obtain the second - resolution residual, and calculate the second - resolution near - surface pollution gas concentration data based on the predicted value of the second - resolution near - surface pollution gas concentration and the second - resolution residual, which is expressed as:

[0021]

[0022] Among them, represents the predicted value of the near - surface pollution gas concentration at the second resolution, represents the key influencing factor data in the second - resolution grid data, represents the second - resolution near - surface pollution gas concentration data, represents the second - resolution residual.

[0023] Furthermore, the trend - surface function is obtained by training a random forest model, and the training process includes: collecting the near - surface pollution gas concentration data and the influencing factor grid data of the target area as the first training set; training the random forest model with the influencing factor grid data as the model input and the near - surface pollution gas concentration data as the model output;

[0024] Taking the atmospheric diffusion equation as the loss function of the random forest model, which is expressed as follows:

[0025]

[0026] Among them, represents the near - surface pollution gas concentration data, u represents the vector wind speed, D represents the diffusion coefficient, represents the spatial gradient of the near - surface pollution gas concentration data, represents the Laplace operator of the near - surface pollution gas concentration data.

[0027] Furthermore, it also includes dynamically partitioning the target area according to the second - resolution near - surface pollution gas concentration data, specifically including: calculating the ratio R of the formaldehyde concentration to the nitrogen dioxide concentration in the second - resolution near - surface pollution gas concentration data, setting the area where R is less than the first threshold in the target area as the anthropogenic - source influence area, setting the area where R is greater than or equal to the first threshold and less than the second threshold as the transition area, and setting the area where R is greater than or equal to the second threshold as the natural - source influence area.

[0028] Further, the training process of the VOCs concentration estimation model includes: collecting historical data of VOCs concentration monitored by ground stations in the target area, and forming a second training set with the historical data of near-surface pollutant gas concentration; dividing the second training set into three groups according to the dynamic partitioning rule, and each group is trained with the historical data of near-surface pollutant gas concentration and relevant influencing factor data as inputs and the historical data of VOCs concentration as the output to obtain three VOCs concentration estimation models. The near-surface pollutant gas at least includes formaldehyde, and the relevant influencing factors at least include air temperature, humidity, and normalized difference vegetation index.

[0029] In a second aspect of the embodiments of the present invention, a VOCs concentration estimation device is provided, including:

[0030] A data acquisition module, configured to acquire column concentration data of pollutant gases, profile data of pollutant gases, and influencing factor data monitored by satellites in the target area;

[0031] A data processing module, configured to calculate near-surface pollutant gas concentration data with a first resolution according to the column concentration data and profile data of the pollutant gases, and perform resampling processing on the influencing factor data;

[0032] A downscaling module, configured to input the near-surface pollutant gas concentration data with the first resolution and the processed influencing factor data into a downscaling model, and output near-surface pollutant gas concentration data with a second resolution, where the second resolution is greater than the first resolution;

[0033] A concentration estimation module, configured to input the near-surface pollutant gas concentration data with the second resolution into a VOCs concentration estimation model, and output VOCs concentration data of the target area.

[0034] In a third aspect of the embodiments of the present invention, an electronic device is provided, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the VOCs concentration estimation method described in any embodiment is implemented.

[0035] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the VOCs concentration estimation method described in any embodiment is implemented.

[0036] Compared with the prior art, the present invention can at least achieve one of the following beneficial effects:

[0037] The VOCs concentration estimation method provided by the present invention calculates the near-surface polluting gas concentration data with a lower resolution by combining the column concentration data monitored by satellites and the profile data monitored by ground monitoring stations. Then, a downscaling model is used to obtain the near-surface polluting gas concentration data with a higher resolution based on the near-surface polluting gas concentration data with a lower resolution and the influencing factor data. Subsequently, a VOCs concentration estimation model is utilized to convert the near-surface polluting gas concentration data with a higher resolution into spatially continuous VOCs concentration data, thereby overcoming the drawbacks of relying solely on ground station monitoring or satellite monitoring, achieving a more comprehensive monitoring of the air pollution situation, and providing an implementation approach for obtaining large-scale continuous VOCs spatio-temporal distribution information. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the embodiments of this specification. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a flowchart of the VOCs concentration estimation method provided in Embodiment 1 of the present invention;

[0040] Figure 2 It is a schematic diagram of the VOCs concentration estimation device provided in Embodiment 2 of the present invention;

[0041] Figure 3 It is a schematic diagram of the electronic device architecture provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. It should be noted that, without conflict, the implementation manners and features in the present disclosure can be combined, separated, interchanged, and / or rearranged. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] Embodiment 1

[0044] A specific embodiment of the present invention, as Figure 1 shown, discloses a VOCs concentration estimation method, including the following steps:

[0045] S1. Obtain the column concentration data of the polluting gases monitored by satellites, the profile data of the polluting gases, and the influencing factor data within the target area;

[0046] Specifically, the polluting gases include formaldehyde, glyoxal, and nitrogen dioxide. The hourly column concentration data thereof is obtained through geostationary satellites such as Himawari and GeoKompsat 2B; the profile data of the polluting gas concentration is obtained through ground monitoring stations or atmospheric chemistry numerical model simulations; the influencing factor data is the influencing factor data of human activities and the natural environment, including but not limited to population density, road network density, night light index, normalized difference vegetation index, surface reflectance, geographical elevation, surface type data, air temperature, relative humidity, air pressure, wind speed, wind direction, and boundary layer height.

[0047] S2. Calculate the near-surface polluting gas concentration data at the first resolution based on the column concentration data and the profile data of the polluting gases, and perform resampling processing on the influencing factor data;

[0048] In this embodiment, step S2 specifically includes:

[0049] S201. Project the column concentration data into raster data, and calculate the near-surface polluting gas concentration data at the first resolution according to the raster data and the profile data, which is expressed as follows:

[0050]

[0051] Among them, represents the polluting gas concentration at the raster position i and the profile height is j ; represents the column concentration of the polluting gas at the raster position i ; represents the type of the polluting gas, including formaldehyde, glyoxal, and nitrogen dioxide, represents the integral of the concentration of the entire profile, represents from the ground to Hs the integral of the profile concentration at the height.

[0052] S202. Use the Pearson correlation coefficient method to screen the key influencing factor data that affects the polluting gas concentration within the target area from the influencing factor data, and resample the key influencing factors at different sampling resolutions to obtain the raster data at the first resolution and the raster data at the second resolution.

[0053] Exemplarily, the key influencing factors screened by the Pearson correlation coefficient method are air temperature, pressure, humidity, light index, normalized difference vegetation index, surface type, and road network density. Then, the least squares interpolation method is used to sample the key influencing factors at different resolutions, obtaining first-resolution grid data (such as 7km×8km) with the same resolution as the column concentration data, and second-resolution grid data (such as 1km×1km) with a resolution greater than that of the column concentration data. Among them, meteorological factor data can be obtained from the China Meteorological Data Network; normalized difference vegetation index data can be generated using Moderate Resolution Imaging Spectroradiometer (MODIS) data and the maximum value composite method to produce monthly products; night light index data can be obtained using the VIIRS / DNB night lighting product, including continuous or low-intensity lights from urban lights, small residential areas, and traffic flow; surface type data can be obtained using the global geographic information public product GlobalLand30, which assigns numbers to different surface types; road network density data can be obtained from the road network density dataset of the Earth System Science Data Center.

[0054] S3. Input the first-resolution near-surface pollutant gas concentration data and the processed influencing factor data into the downscaling model, and output second-resolution near-surface pollutant gas concentration data, where the second resolution is greater than the first resolution.

[0055] In this embodiment, step S3 specifically includes:

[0056] S301. Use the trend surface function to predict the first-resolution near-surface pollutant gas concentration value based on the first-resolution grid data, and calculate the first-resolution residual between the first-resolution near-surface pollutant gas concentration prediction value and the first-resolution near-surface pollutant gas concentration data, expressed as:

[0057]

[0058] Where, represents the first-resolution near-surface pollutant gas concentration prediction value, represents the trend surface function, represents the key influencing factor data in the first-resolution grid data, represents the first-resolution residual, represents the first-resolution near-surface pollutant gas concentration data.

[0059] S302. Use the trend surface function to predict the second-resolution near-surface pollutant gas concentration value based on the second-resolution grid data, interpolate the first-resolution residual to obtain the second-resolution residual, and calculate the second-resolution near-surface pollutant gas concentration data based on the second-resolution near-surface pollutant gas concentration prediction value and the second-resolution residual, expressed as:

[0060]

[0061] Among them, represents the predicted value of the near-surface pollutant gas concentration at the second resolution, represents the key influencing factor data in the grid data at the second resolution, represents the near-surface pollutant gas concentration data at the second resolution, represents the residual at the second resolution.

[0062] In this embodiment, the trend surface function is obtained by training a random forest model, and the training process includes:

[0063] (I) Collect the near-surface pollutant gas concentration data and the influencing factor grid data of the target area as the first training set;

[0064] (II) Train the random forest model with the influencing factor grid data as the model input and the near-surface pollutant gas concentration data as the model output;

[0065] Take the atmospheric diffusion equation as the loss function of the random forest model, which is expressed as follows:

[0066]

[0067] Among them, represents the near-surface pollutant gas concentration data, u represents the vector wind speed, D represents the diffusion coefficient, represents the spatial gradient of the near-surface pollutant gas concentration data, represents the Laplace operator of the near-surface pollutant gas concentration data.

[0068] In some embodiments, between steps S3 and S4, it further includes dynamically partitioning the target area according to the near-surface pollutant gas concentration data at the second resolution, specifically including:

[0069] Calculate the ratio R of the formaldehyde concentration to the nitrogen dioxide concentration in the near-surface pollutant gas concentration data at the second resolution. Set the area where R is less than the first threshold in the target area as the anthropogenic source influence area, the area where R is greater than or equal to the first threshold and less than the second threshold as the transition area, and the area where R is greater than or equal to the second threshold as the natural source influence area.

[0070] Specifically, the study area is divided into human activity areas and areas with high vegetation coverage such as forests and grasslands by combining surface types, night light index, and normalized difference vegetation index (NDVI). Areas with a night light index greater than 1 are considered human activity areas, and areas with an NDVI greater than 0.4 are considered areas with high vegetation coverage. The m% and n% quantiles (Q1m, Q2n) of the R values for the two types are calculated. m and n can be set to 90 and 10 respectively, and the set initial thresholds are: A1 = Q190, A2 = Q210; where A1 is the first threshold and A2 is the second threshold. The thresholds are spatially smoothed using a sliding window (window size 3 km) to eliminate the interference of local outliers. The recommended range for A1 is 1 - 3.5, and the recommended range for A2 is 3 - 7.

[0071] If the nitrogen dioxide data is missing, the target area can also be partitioned according to the ratio R2 of glyoxal concentration to formaldehyde concentration in the near-surface pollutant gas concentration data at the second resolution. Combining the surface type data, dynamic thresholds B1 and B2 are set. Areas where R2 < B1 are the areas mainly affected by anthropogenic sources, areas where R2 ≥ B2 are the areas mainly affected by natural sources, and areas where B1 ≤ R2 < B2 are the transition areas.

[0072] Compared with the method of partitioning solely based on surface types, using the ratio method for partitioning can more comprehensively consider the key variable of atmospheric movement. As an important factor affecting the distribution and transport of pollutants, the dynamic changes of atmospheric movement are often difficult to accurately capture through static surface type data. By calculating the concentration ratio of specific pollutants, the sources and diffusion of pollutants in the atmosphere can be indirectly reflected, providing a better partitioning basis for subsequent calculations.

[0073] S4. Input the near-surface pollutant gas concentration data at the second resolution into the VOCs concentration estimation model to output the VOCs concentration data of the target area.

[0074] Specifically, existing research has shown that there is a linear relationship between the concentrations of formaldehyde, glyoxal, etc. and the VOCs concentration. Therefore, the spatially continuous VOCs concentration can be estimated based on the discrete near-surface formaldehyde and glyoxal concentrations. For example, it can be achieved using a multiple linear regression equation or a random forest model. The specific structure of the VOCs concentration estimation model is not limited in this embodiment and can be flexibly applied according to the data scale.

[0075] Compared with the prior art, the VOCs concentration estimation method provided in this embodiment calculates the near-surface polluted gas concentration data with lower resolution by combining the column concentration data monitored by satellites and the profile data monitored by ground monitoring stations. Then, a downscaling model is used to obtain the near-surface polluted gas concentration data with higher resolution based on the near-surface polluted gas concentration data with lower resolution and the influencing factor data. Subsequently, a VOCs concentration estimation model is utilized to convert the near-surface polluted gas concentration data with higher resolution into spatially continuous VOCs concentration data. Thereby, it overcomes the drawbacks of relying solely on ground station monitoring or satellite monitoring, realizes a relatively comprehensive monitoring of the atmospheric pollution situation, and provides an implementation approach for obtaining large-scale continuous VOCs spatio-temporal distribution information.

[0076] In this embodiment, the training process of the VOCs concentration estimation model includes:

[0077] Collect the measured VOCs concentration data of the target area during the specific historical period, and form a second training set with the near-surface polluted gas concentration data of the second resolution in the first training set;

[0078] According to the dynamic partitioning rule, divide the second training set into three groups. Each group is trained with the near-surface polluted gas concentration data of the second resolution and the relevant influencing factors as the model input and the measured VOCs concentration data as the model output to obtain three VOCs concentration estimation models. The near-surface polluted gas includes at least formaldehyde, and the relevant influencing factors include at least air temperature, humidity, and normalized difference vegetation index.

[0079] Specifically, air temperature is the most important factor affecting the relationship between VOCs and formaldehyde. During training, the data within each partition is further grouped according to the ambient air temperature (such as with a step of 7°C). If the number of samples within a group is less than a certain threshold, a multiple linear regression model is trained as the VOCs concentration estimation model; otherwise, a random forest regression model is trained as the VOCs concentration estimation model. Considering that there are usually few ground stations and there is often a lack of ground monitoring data in the transition area, a weighted method can be used to obtain the concentration estimation model.

[0080] Embodiment 2

[0081] This embodiment provides a VOCs concentration estimation device, as Figure 2 shown, including:

[0082] A data acquisition module, configured to acquire the column concentration data of the polluted gas, the profile data of the polluted gas, and the influencing factor data monitored by satellites within the target area;

[0083] A data processing module, configured to calculate the near-surface polluted gas concentration data of the first resolution according to the column concentration data and the profile data of the polluted gas, and perform resampling processing on the influencing factor data;

[0084] A downscaling module, configured to input the near-surface pollutant gas concentration data at the first resolution and the processed influencing factor data into a downscaling model, and output near-surface pollutant gas concentration data at a second resolution, where the second resolution is greater than the first resolution;

[0085] A concentration estimation module, configured to input the near-surface pollutant gas concentration data at the second resolution into a VOCs concentration estimation model, and output VOCs concentration data of a target area.

[0086] Embodiment 3

[0087] This embodiment provides an electronic device, as Figure 3 shown, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, it implements the VOCs concentration estimation method described in any of the foregoing embodiments.

[0088] Embodiment 4

[0089] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the VOCs concentration estimation method described in any of the foregoing embodiments.

[0090] The computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory media such as modulated data signals and carrier waves.

[0091] Those skilled in the art should further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0092] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0093] The specific embodiments described above have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for estimating the concentration of VOCs, characterized in that Including: Obtaining column concentration data of polluting gases, profile data of polluting gases, and impact factor data monitored by satellites within a target area, where the impact factor data is human activity and natural environment impact factor data; Calculating near-surface polluting gas concentration data at a first resolution based on the column concentration data and profile data of polluting gases, including: projecting the column concentration data into raster data, and calculating the near-surface polluting gas concentration data at the first resolution according to the raster data and the profile data, expressed as follows: Among them, represents the grid position as i the contour height is j the concentration of polluted gas, represents the grid position as i the column concentration of polluted gas, represents the type of polluted gas, including formaldehyde, glyoxal and nitrogen dioxide, represents the integral of the concentration of the entire contour, represents from the ground to Hs the integral of the contour concentration at the height; Performing resampling processing on the impact factor data, including: using the Pearson correlation coefficient method to screen out key impact factor data affecting the polluting gas concentration within the target area from the impact factor data, and resampling the key impact factors at different sampling resolutions to obtain raster data at the first resolution and raster data at the second resolution; Inputting the near-surface polluting gas concentration data at the first resolution and the processed impact factor data into a downscaling model to output near-surface polluting gas concentration data at a second resolution, where the second resolution is greater than the first resolution; Inputting the near-surface polluting gas concentration data at the second resolution into a VOCs concentration estimation model to output VOCs concentration data of the target area.

2. The VOCs concentration estimation method according to claim 1, wherein The step of inputting the near-surface polluting gas concentration data at the first resolution and the processed impact factor data into a downscaling model to output near-surface polluting gas concentration data at a second resolution includes: Using a trend surface function to predict the near-surface polluting gas concentration value at the first resolution based on the raster data at the first resolution, and calculating the first resolution residual between the predicted value of the near-surface polluting gas concentration at the first resolution and the near-surface polluting gas concentration data at the first resolution, expressed as: Among them, represents the predicted value of the near-surface polluted gas concentration at the first resolution, represents the trend surface function, represents the key influencing factor data in the grid data at the first resolution, represents the residual at the first resolution, represents the near-surface polluted gas concentration data at the first resolution; Using a trend surface function to predict the near-surface polluting gas concentration value at the second resolution based on the raster data at the second resolution, interpolating the first resolution residual to obtain the second resolution residual, and calculating the near-surface polluting gas concentration data at the second resolution according to the predicted value of the near-surface polluting gas concentration at the second resolution and the second resolution residual, expressed as: Among them, represents the predicted value of the near-surface polluted gas concentration at the second resolution, represents the key influencing factor data in the grid data at the second resolution, represents the near-surface polluted gas concentration data at the second resolution, represents the residual at the second resolution.

3. The VOCs concentration estimation method according to claim 2, wherein The trend surface function is obtained by training a random forest model, and the training process includes: Collecting near-surface polluting gas concentration data and impact factor raster data of the target area as a first training set; Training the random forest model with the impact factor raster data as the model input and the near-surface polluting gas concentration data as the model output; Using the atmospheric diffusion equation as the loss function of the random forest model, expressed as follows: Among them, represents the near-surface polluted gas concentration data, u represents the vector wind speed, D represents the diffusion coefficient, represents the spatial gradient of the near-surface polluted gas concentration data, represents the Laplace operator of the near-surface polluted gas concentration data.

4. The VOCs concentration estimation method according to any one of claims 1-3, characterized in that It further includes dynamically partitioning the target area according to the near-surface polluting gas concentration data at the second resolution, specifically including: Calculating the ratio R of the formaldehyde concentration to the nitrogen dioxide concentration in the near-surface polluting gas concentration data at the second resolution, setting the area within the target area where R is less than a first threshold as the area affected by anthropogenic sources, setting the area where R is greater than or equal to the first threshold and less than a second threshold as the transition area, and setting the area where R is greater than or equal to the second threshold as the area affected by natural sources.

5. The VOCs concentration estimation method according to claim 4, characterized in that The training process of the VOCs concentration estimation model includes: Collecting historical VOCs concentration data monitored by ground stations in the target area and forming a second training set with the historical near-surface polluting gas concentration data; The second training set is divided into three groups according to the dynamic partitioning rules. Each group is trained with historical data of near-surface pollution gas concentrations and relevant influencing factor data as inputs and historical VOCs concentration data as outputs to obtain three VOCs concentration estimation models. The near-surface pollution gas at least includes formaldehyde, and the relevant influencing factors at least include air temperature, humidity, and normalized difference vegetation index.

6. A VOCs concentration estimation device, characterized in that, The device includes: A data acquisition module for acquiring column concentration data of pollution gases, profile data of pollution gases, and influencing factor data monitored by satellites in the target area. The influencing factor data is human activity and natural environment influencing factor data; A data processing module for calculating near-surface pollution gas concentration data at the first resolution based on the column concentration data and profile data of the pollution gas, including: projecting the column concentration data into raster data, and calculating the near-surface pollution gas concentration data at the first resolution according to the raster data and the profile data, expressed as follows: Among them, indicates that the grid position is i the contour height is j the concentration of polluted gas, indicates that the grid position is i the column concentration of polluted gas, indicates the type of polluted gas, including formaldehyde, glyoxal and nitrogen dioxide, indicates the integral of the concentration of the whole contour, indicates from the ground to Hs the integral of the contour concentration at the height; Performing resampling processing on the influencing factor data, including: screening key influencing factor data that affects the pollution gas concentration in the target area from the influencing factor data using the Pearson correlation coefficient method, and resampling the key influencing factors at different sampling resolutions to obtain raster data at the first resolution and raster data at the second resolution; A downscaling module for inputting the near-surface pollution gas concentration data at the first resolution and the processed influencing factor data into a downscaling model and outputting near-surface pollution gas concentration data at the second resolution, where the second resolution is greater than the first resolution; A concentration estimation module for inputting the near-surface pollution gas concentration data at the second resolution into the VOCs concentration estimation model and outputting the VOCs concentration data of the target area.

7. An electronic device, characterized in that, It includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the VOCs concentration estimation method according to any one of claims 1-5.

8. A storage medium, characterized in that, Stored thereon is a computer program, and when the program is executed by the processor, it implements the VOCs concentration estimation method according to any one of claims 1-5.

Images