A regional atmospheric pollution source distribution and influence assessment system

Abstract

The application discloses a regional atmospheric pollution source distribution and influence evaluation system and relates to the technical field of atmospheric pollution monitoring and treatment.The system can accurately identify the spatial distribution characteristics of pollution sources by identifying the spatial distribution of agricultural waste such as straw, dry grass and livestock manure through remote sensing technology, and can comprehensively evaluate the combustion emission characteristics and diffusion influence of pollution sources based on static analysis and dynamic monitoring means.In addition, the temperature collecting unit and the inversion layer identifying unit identify the inversion phenomenon in the region, calculate the inversion layer effect factor, the vertical wind shear factor and the precipitation washing effect factor in combination with the wind speed data and the precipitation data, and calculate the dynamic diffusion coefficient classification evaluation in combination with the dimensionless processing method, and generate a targeted regulation and control strategy to further improve the accuracy of pollution diffusion prediction.

Description

Technical Field

[0001] This invention relates to the field of air pollution monitoring and control technology, specifically a regional air pollution source distribution and impact assessment system. Background Technology

[0002] With the acceleration of industrialization, pollution in the agricultural sector has gradually attracted attention. Especially during large-scale agricultural production, the disposal of straw, withered grass, and livestock manure is increasingly revealing their potential environmental impact. Particularly in intensive agricultural areas, farmers often use incineration to dispose of these agricultural wastes; however, the harmful gases and particulate matter released during incineration cause serious air pollution, affecting air quality and harming the ecological environment and human health.

[0003] However, existing technologies have many shortcomings in identifying and assessing pollution sources in agricultural areas. First, traditional pollution source monitoring relies primarily on manual inspections and ground-based monitoring stations, which cannot acquire extensive and accurate spatial data in real time, leading to incomplete identification of pollution sources. This is especially true for the burning of agricultural waste such as straw, withered grass, and livestock manure, where the spatial distribution and combustion patterns are difficult to monitor precisely. Furthermore, many agricultural areas, particularly in rural or remote regions, lack effective technological means to monitor these pollution sources in real time, making it difficult to comprehensively assess the specific impacts of burning processes on air pollution.

[0004] Meanwhile, in some regions, changes in meteorological conditions, such as the formation of temperature inversions, inhibit the diffusion of air pollutants, causing them to stagnate at low altitudes and further exacerbating the cumulative effect of pollution. However, the occurrence and impact of temperature inversions are often difficult to monitor and assess in real time. Temperature inversions cause pollutants to remain in the lower atmosphere for extended periods, preventing effective diffusion and significantly impacting the transport and diffusion behavior of air pollutants, leading to localized air quality deterioration. Therefore, identifying and analyzing the effects of temperature inversions and combining them with the distribution of air pollution sources has become a major challenge in the field of air pollution monitoring. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a regional air pollution source distribution and impact assessment system to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a regional air pollution source distribution and impact assessment system, comprising:

[0007] The remote sensing identification module is used to divide the target area into several monitoring sub-areas and identify pollution sources in the monitoring sub-areas using remote sensing technology. It obtains the spatial distribution data of pollution source aggregation points in the monitoring sub-areas, including dry grass aggregation points, straw aggregation points, and livestock manure aggregation points.

[0008] The static pollution source analysis module is used to construct a predictive pollution model using convolutional neural networks based on pollution source aggregation point data acquired by the remote sensing identification module. It analyzes the distribution characteristics of each type of pollution source, calculates the pollution potential of each type of pollution source within the monitoring sub-region based on these characteristics, generates a corresponding pollution source distribution map, simulates the pollution generated during the incineration process of each pollution source, and predicts the combustion pollution coefficient Rs for the i-th monitoring sub-region. i and for Rs i Perform classification, output the first classification result, and generate the corresponding strategy based on the first classification result;

[0009] The dynamic monitoring module, after the corresponding strategy is executed, collects temperature data at different altitudes in the i-th monitoring sub-region, plots a temperature-altitude profile of the i-th monitoring sub-region, identifies the inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r Establish a dataset of thermosphere effects;

[0010] The dynamic analysis module is used to construct the inversion stratospheric effect factor (ITEF) for the i-th monitoring sub-region based on the stratospheric effect dataset. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i The dynamic diffusion coefficient Ks of the i-th monitoring sub-region is obtained by correlation. i The system evaluates the results to output a second classification result and generates a corresponding strategy.

[0011] Preferably, the remote sensing identification module includes a region segmentation unit, a remote sensing data acquisition unit, an image preprocessing unit, and a pollution source identification unit;

[0012] The aforementioned region segmentation unit is used to collect and identify the geographical features and landforms of the target area using a GIS geographic information system, establish a three-dimensional model, and divide the target area into several monitoring sub-regions, labeled as {Zq1, Zq2, Zq3, ..., Zq...} in the three-dimensional model. n}; n represents the total number of monitored sub-regions;

[0013] The remote sensing data acquisition unit is used to acquire multi-band images of the target area using a multispectral camera mounted on a drone, and to establish a multi-band image dataset, which includes multi-band images including visible light, near infrared and short-wave infrared.

[0014] The image preprocessing unit is used to perform image registration on the multi-band image dataset, align the data of each band, perform radiometric correction, and remove noise using mean filtering, Gaussian filtering, and wavelet transform.

[0015] The pollution source identification unit is used to extract spectral index features from multi-band image datasets and generate distribution maps of different pollution types.

[0016] Preferably, the specific steps for generating distribution maps of different pollution types include:

[0017] Step Aa.1: Calculate the Normalized Difference Vegetation Index (NDVI) to distinguish between green vegetation and withered grass. The expression is as follows:

[0018]

[0019] In the formula, NIR represents the near-infrared band value, which is an indicator of plant health. Healthy vegetation has a high NIR reflectance. Red represents the infrared band value, which is the absorption characteristic of plants. Healthy vegetation has a high absorption rate in the red light band.

[0020] Step Aa.2: Preliminary screening of withered grass areas: When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.5-0.9, it is identified as a healthy vegetation area and marked as a green area;

[0021] When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.11-0.3, it is identified as a withered grass area and marked as a red area;

[0022] When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.05-0.1, it is identified as a straw area and marked as the first gray area; when the NDVI is between 0.05 and 0.1, it indicates that the vegetation has completely lost its activity, but still retains a certain organic structure.

[0023] When the Normalized Difference Vegetation Index (NDVI) is in the range of -0.2 to 0.09, it is identified as a bare soil area and marked as a brown area.

[0024] When the Normalized Difference Vegetation Index (NDVI) is less than -0.1, it is identified as a water body area and marked as an orange area.

[0025] Calculate the Normalized Difference Vegetation Index (NDVI) value for each pixel, then select the area with 0.11≤NDVI≤0.3 as the withered grass area, select the area with 0.05≤NDVI≤0.1 as the straw area, and exclude healthy vegetation points with NDVI>0.5.

[0026] Step Aa.3: Select the k-th window in the i-th monitoring sub-region of the image dataset, with a window size of 3×3 or 5×5; calculate the frequency of grayscale values ​​of each pair of pixels within the k-th window; the grayscale values ​​of each pair of pixels include the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f ;

[0027] Record the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f The frequency I appearing in the k-th window f The frequency values ​​are then normalized to probability values ​​to obtain the gray-level co-occurrence combination frequency P(I). h i f );

[0028] Step Aa.4: Based on the gray-level co-occurrence combination frequency P(I) h ,I f )Calculate and obtain the texture roughness Contrast of the k-th window k and the entropy of the k-th window. k :

[0029] Cntrast k =∑ j,f P(I h ,I f )×(I h -I f ) 2 ;

[0030] Entropy k =-∑ j,f P(I h ,I f )×logP(I h ,I f );

[0031] In the formula, (I h -I f ) 2 Used to calculate the h-th gray value I of the j-th pixel. h The trivial difference between the f-th second gray value and the gray value itself measures the gray level difference.

[0032] Step Aa.5: Set the roughness threshold and entropy threshold for withered grass texture to perform secondary filtering of withered grass areas;

[0033] When identifying the texture roughness of the k-th window Contrast k If the roughness of the withered grass texture is greater than or equal to the threshold, it is marked as the second gray area;

[0034] When identifying the texture roughness of the k-th window Contrast k <The roughness threshold for withered grass texture is not marked;

[0035] When identifying the entropy value of the k-th window... k If the value is greater than or equal to the threshold value of the withered grass entropy, it is marked as the third gray area;

[0036] When identifying the entropy value of the k-th window... k <The threshold value for withered grass entropy is not marked;

[0037] The final withered grass area is obtained by identifying the intersection area of ​​the first yellow area, the second yellow area, and the third yellow area.

[0038] The final withered grass area = first yellow area ∩ second gray area ∩ third gray area.

[0039] Preferably, the specific steps for generating distribution maps of different pollution types also include:

[0040] Step Aa.6: Identify the surface temperature (LST);

[0041] LST = BT × (1 + W × ln(ε));

[0042] In the formula, BT represents the brightness temperature, which is the radiation temperature of the ground object measured by the sensor, in Kelvin; W represents the atmospheric water vapor influence coefficient; ε represents the surface emissivity, reflecting the ability of the ground object to absorb and emit thermal radiation; kn(ε) represents the natural logarithm of the surface reflectivity, used to correct for surface radiation errors; ground emissivity is the ability of the ground object surface to absorb and emit infrared radiation, in the range 0≤ε≤1; different ground objects such as vegetation, soil, buildings, garbage, and livestock manure have different emissivities, including: buildings: ε=0.98; vegetation: ε=0.96; soil: ε=0.92-0.95; livestock manure ε=0.89-0.91;

[0043] Step Aa.7: Identify the livestock manure area:

[0044] When the LST of the land surface is identified as 15-25℃, it is identified as soil and marked as a brown area.

[0045] When the surface temperature (LST) is identified as 30-40℃, it is identified as livestock manure and marked as a black area;

[0046] When the surface temperature (LST) is greater than 40°C, it is identified as a building area and marked as a yellow area.

[0047] Based on the markings of the final withered grass area, orange area, red area, brown area, green area, black area and yellow area in the 3D model, and extracting the final withered grass area, red area and black area, the withered grass aggregation point, straw aggregation point and livestock manure aggregation point corresponding to the i-th monitoring sub-region are generated.

[0048] Preferably, the static analysis module for pollution sources includes a first extraction unit and a model building unit;

[0049] The first extraction unit is used to identify the dry grass accumulation points, straw accumulation points, and livestock manure accumulation points in the i-th monitoring sub-region, and to count the total number of pixels N of the j-th type of pollution source in the i-th monitoring sub-region. i,j And by combining the resolution analysis of UAV images, the pixel area S is obtained. pixel The total area A of the j-th type of pollution source in the i-th monitoring sub-region is calculated using the following formula. i,j :

[0050] A i,j =N i,j ×S pixel ;

[0051] The experimental density ρ of the j-th type of pollution source j Calculate the weight per unit area M of the j-th type of pollution source within the i-th monitoring sub-region. i,j :

[0052] M i,j =A i,j ×ρ j ;

[0053] Among them, the experimental density ρ of the j-th type of pollution source j Obtained based on historical reference data, including:

[0054] Straw density: 0.5-1.2 kg / m³ 2 Dry straw density: 0.3-0.7 kg / m³ 2 Livestock manure density: 0.8-2.0 kg / m³ 2 ;

[0055] Extract the unit area weight M of the j-th type of pollution source within the i-th monitoring sub-region. i,j An incineration experiment was conducted, and the combustion emission factors and combustion time ratios of the j-th type of pollution source in the i-th monitoring sub-region during the incineration experiment were collected to establish a combustion experiment dataset.

[0056] The model establishment unit is used to construct an initial convolutional neural network model by using a convolutional neural network, simulate, test, and train the initial convolutional neural network model with a combustion experiment data set, and use the trained initial convolutional neural network model as a prediction pollution model to simulate and obtain the combustion pollution coefficient Rs of the i-th monitoring sub-region i :

[0057] The combustion pollution coefficient Rs of the i-th monitoring sub-region i is calculated and obtained by the following formula:

[0058]

[0059] In the formula, j represents the index of pollution source type, including straw, dry grass h, and livestock manure; m represents the specific number of aggregation points of the j-th pollution source;

[0060] E i,j represents the combustion emission factor of the j-th type of pollution source in the i-th monitoring sub-region, M i,j represents the unit area weight of the j-th type of pollution source in the i-th monitoring sub-region, Pr i,j represents the combustion time ratio of the j-th type of pollution source in the i-th monitoring sub-region.

[0061] Preferably, the pollution source static analysis module further includes a first evaluation unit and a first strategy unit;

[0062] The first evaluation unit is used to establish a risk threshold X, and compare and evaluate the combustion pollution coefficient Rs of the i-th monitoring sub-region i with the risk threshold X to judge the risk level of the impact of the pollution source in the i-th monitoring sub-region on air pollution after combustion, and output a first classification result, including:

[0063] The risk threshold X includes a first threshold X1 and a second threshold X2, and the first threshold X1 is greater than the second threshold X2;

[0064] When Rs i < X2, it means that the distribution of pollution sources in this monitoring sub-region is scattered, no obvious pollution aggregation area is formed, and the comprehensive impact on air pollution is limited, generating a first low-risk level;

[0065] When X2 ≤ Rs i ≤ X1, it means that the distribution of pollution sources in this monitoring sub-region is scattered, but individual pollution aggregation areas have been formed, and the comprehensive impact of the emissions on air pollution is relatively significant, generating a second medium-risk level;

[0066] When Rs i>X1 indicates that the pollution sources in the monitored sub-area are densely distributed, and the emissions from multiple pollution sources exceed expectations, requiring close attention and generating the third highest risk level;

[0067] The first strategy unit is used to summarize the monitoring sub-areas for the second medium-risk level and the third high-risk level, and generate corresponding control strategies, including:

[0068] The first strategy for the second risk level includes: returning 50-60% of the straw in the monitored sub-area to the field by mechanization or composting; converting 50-60% of the withered grass in the monitored sub-area into organic fertilizer; and using aerobic fermentation technology to convert 50-60% of the livestock manure in the monitored sub-area into organic fertilizer.

[0069] For the third highest risk level, a second strategy is generated, including: mechanized return of 61-90% of the straw in the monitored sub-area to the field or composting; conversion of 61-90% of the withered grass in the monitored sub-area into organic fertilizer and 5-10% of the withered grass into biomass energy; and conversion of 61-70% of the livestock manure in the monitored sub-area into organic fertilizer using aerobic fermentation technology and 20-30% of the livestock manure into methane energy through anaerobic microbial grading to supply biogas power generation systems.

[0070] Preferably, the dynamic monitoring module includes a temperature acquisition unit and an inversion layer identification unit;

[0071] The temperature acquisition unit is used to acquire temperature data at different heights in the i-th monitoring sub-region and draw a temperature-height profile of the i-th monitoring sub-region. Within the inversion layer, the temperature increases with increasing height, showing a positive temperature gradient and forming a region of temperature reversal.

[0072] When plotting the temperature-height profile of the i-th monitoring sub-region, the temperature on the y-axis and the height on the x-axis are correlated to obtain the relationship between temperature and height. The measured temperature values ​​of the t-th and r-th vertical height points in the i-th monitoring sub-region are extracted, and the temperature difference γ between the t-th and r-th height points is calculated using the following formula. t,r :

[0073]

[0074] In the formula, T t T represents the temperature at the t-th elevation point. rLet Δz represent the temperature at the r-th altitude point; Δz represents the altitude difference between the t-th and r-th altitude points. If the temperature gradient is negative, it indicates that the temperature decreases with increasing altitude; if the temperature gradient is positive, it indicates that the temperature increases with increasing altitude. In this case, the inversion layer identification unit identifies it as an inversion phenomenon, marks it as an inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r Establish a dataset on the thermosphere effect.

[0075] Preferably, the dynamic analysis module includes an inversion layer effect factor calculation unit, a vertical internal shear factor calculation unit, and a precipitation washing effect factor calculation unit;

[0076] The temperature layer effect factor calculation unit is used to calculate the temperature layer effect factor (ITEF) of the i-th monitoring sub-region after marking the inversion layer of the i-th monitoring sub-region using the following formula. i :

[0077]

[0078] In the formula, T env This indicates the ambient temperature (T) of the monitored sub-region. TILL This indicates the temperature within the inversion layer;

[0079] The vertical internal shear factor calculation unit is used to extract wind speed data above and below the inversion layer in the temperature stratification effect dataset after marking the inversion layer of the i-th monitoring sub-region, and calculate the vertical internal shear factor (VSCF) of the i-th monitoring sub-region using the following formula. i :

[0080]

[0081] In the formula, V wind (Z top V represents the wind speed above the inversion layer. wind (Z bottom Z represents the wind speed below the inversion layer. top and Z bottom These are the upper and lower boundary heights of the inversion layer, respectively.

[0082] The precipitation washing effect factor calculation unit is used to extract the daily average precipitation JP of the i-th monitoring sub-region in the thermosphere effect dataset. r The precipitation washing effect factor (PWEF) for the i-th monitoring sub-region is calculated using the following formula. i :

[0083] PWEF i =α×JP r ;

[0084] In the formula, α represents a constant factor, which is used to represent the average effect of precipitation on pollutant removal and is estimated through experimental data or empirical values; the precipitation washing effect refers to the ability of rainwater to wash pollutants in the air, thereby reducing the concentration of pollutants in the atmosphere; the greater the precipitation, the stronger the removal effect of pollutants in the air.

[0085] Preferably, the dynamic analysis module further includes an association unit, a second evaluation unit, and a second strategy unit;

[0086] The association unit is used to extract the inversion layer effect factor ITEF of the i-th monitoring sub-region i , the vertical shear factor VSCF i and the precipitation washing effect factor PWEF i . After dimensionless processing, the dynamic diffusion coefficient Ks of the i-th monitoring sub-region is calculated through the following formula i :

[0087]

[0088] In the formula, b1, b2, and b3 respectively represent the inversion layer effect factor ITEF i , the vertical shear factor VSCF i and the precipitation washing effect factor PWEF i weight coefficients, and the sum of the weights is 1; the precipitation washing effect factor is in an inverse relationship.

[0089] Preferably, the second evaluation unit is used to preset a diffusion threshold Y, and compare the dynamic diffusion coefficient Ks of the i-th monitoring sub-region i with the diffusion threshold Y to judge the diffusion influence level of the pollution source in the i-th monitoring sub-region on the adjacent region after combustion, and output a second classification result, including:

[0090] The diffusion threshold Y includes a first diffusion threshold Y1 and a second diffusion threshold Y2, and the first diffusion threshold Y1 is greater than the second diffusion threshold Y2;

[0091] When Ks i < Y2, it means that during the incineration process of the pollution source in this monitoring sub-region, the pollution source has stagnated in the inversion layer within the region and there is no diffusion risk, forming a first stagnation risk region level, and a third strategy is generated through the second strategy unit, including: when identifying that the pollution source is burning, 1-2 drones equipped with spray dust suppression equipment are arranged above the inversion layer in the upwind direction of the pollution source burning for 15-20 minutes of operation; the spray interval is set to once every 20 minutes, and the spray duration is 5 minutes;

[0092] When Y2 ≤ Ks i≤Y1 indicates that the pollution source in the monitored sub-area has a risk of diffusion during the incineration process, but the risk is within expectations. This generates a second low diffusion risk area level, and a fourth strategy is generated through the second strategy unit. This strategy includes: when the pollution source is identified and incinerated, deploying three drones equipped with spray dust suppression equipment at a height of 26-50 meters above the ground in the upwind direction of the pollution source incineration, to carry out operations for 21-30 minutes; the spray interval is set to once every 15 minutes, and the spray duration is 5 minutes.

[0093] When Ks i >Y1 indicates that the pollution source in the monitored sub-area has a risk of spreading during the incineration process, and the risk of spreading can reach a far range in a short period of time, generating the third highest risk area level; and the fifth strategy is generated through the second strategy unit, including: when the pollution source is identified and incinerated, deploy 4-5 drones equipped with spray dust suppression equipment at a height of 40-50 meters above the ground in the upwind direction of the pollution source incineration, and carry out operation for 31-40 minutes; the spray interval is set to once every 10 minutes, and the spray duration is 10 minutes.

[0094] This invention provides a system for assessing the distribution and impact of regional air pollution sources. It offers the following advantages:

[0095] (1) By combining remote sensing technology with deep learning models, the system can accurately identify the spatial distribution of agricultural waste such as straw, withered grass, and livestock manure. This identification method can efficiently cover a wide range of target areas, especially suitable for remote areas and densely agricultural areas, overcoming the limitations of traditional methods that rely on manual inspections and ground stations. The remote sensing identification module can provide real-time and accurate data on the location and type of pollution sources, providing solid data support for subsequent pollution assessments. The remote sensing data acquisition unit uses a UAV equipped with a multispectral camera to acquire images, which can obtain image data in multiple bands, including visible light, near-infrared, and short-wave infrared. These multi-band images have strong spatial and spectral information, and can provide the reflectance characteristics of different pollution sources (such as straw, withered grass, and livestock manure) in different bands, making it easier to identify pollution sources and their distribution more accurately.

[0096] (2) By marking each region in the 3D model and combining it with the aforementioned steps (NDVI, texture analysis, LST identification, etc.), the spatial distribution map of various pollution sources can be accurately drawn. For example, pollution types such as healthy vegetation, withered grass, straw, livestock manure, and bare land can be visualized using different color markers (such as green, red, black, brown, etc.). By extracting and drawing monitoring sub-regions, the aggregation points of different pollution types (such as withered grass, straw, livestock manure, etc.) can intuitively show the distribution trend of pollution sources, facilitating further analysis and decision-making.

[0097] (3) This regional air pollution source distribution and impact assessment system utilizes a predictive pollution model constructed with a convolutional neural network (CNN) to deeply learn and analyze the distribution characteristics of different types of pollution sources. Through detailed calculations of pollution sources within each monitoring sub-region, the system can accurately assess the pollution potential of each type of pollution source, thereby generating an accurate pollution source distribution map. This method has significant advantages over traditional manual analysis, enabling rapid and efficient processing and analysis of large-scale data. The static pollution source analysis module, by combining remote sensing image analysis with deep learning technology, achieves accurate identification, quantification, and prediction of pollution sources (dried grass, straw, livestock manure, etc.). This improves the accuracy of pollution source identification and provides an important basis for subsequent pollution source management and prevention measures; by training the incineration experimental data with a convolutional neural network, the combustion pollution coefficient Rs of the pollution source is accurately simulated. i This effectively supports environmental protection and governance efforts.

[0098] (4) The dynamic monitoring module collects temperature, wind speed, and daily average precipitation data at different altitudes to create temperature-altitude profiles and performs real-time monitoring in conjunction with the inversion layer effect. This enables the system to promptly identify the presence of inversion layers and assess their impact on pollutant diffusion. Under the influence of inversion layers, pollutants often stagnate at low altitudes, allowing the system to adjust its monitoring strategy in real time. This avoids ignoring the inversion layer effect in traditional methods and enhances the system's responsiveness to dynamic changes in air pollution. Attached Figure Description

[0099] Figure 1 This is a schematic diagram of the process of a regional air pollution source distribution and impact assessment system according to the present invention. Detailed Implementation

[0100] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0101] Example 1

[0102] This invention provides a system for assessing the distribution and impact of regional air pollution sources. Please refer to [link / reference]. Figure 1 ,include:

[0103] The remote sensing identification module is used to divide the target area into several monitoring sub-areas and identify pollution sources in the monitoring sub-areas using remote sensing technology. It obtains the spatial distribution data of pollution source aggregation points in the monitoring sub-areas, including dry grass aggregation points, straw aggregation points, and livestock manure aggregation points.

[0104] The static pollution source analysis module is used to construct a predictive pollution model using convolutional neural networks based on pollution source aggregation point data acquired by the remote sensing identification module. It analyzes the distribution characteristics of each type of pollution source, calculates the pollution potential of each type of pollution source within the monitoring sub-region based on these characteristics, generates a corresponding pollution source distribution map, simulates the pollution generated during the incineration process of each pollution source, and predicts the combustion pollution coefficient Rs for the i-th monitoring sub-region. i and for Rs i Perform classification, output the first classification result, and generate the corresponding strategy based on the first classification result;

[0105] The dynamic monitoring module, after the corresponding strategy is executed, collects temperature data at different altitudes in the i-th monitoring sub-region, plots a temperature-altitude profile of the i-th monitoring sub-region, identifies the inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r Establish a dataset of thermosphere effects;

[0106] The dynamic analysis module is used to construct the inversion stratospheric effect factor (ITEF) for the i-th monitoring sub-region based on the stratospheric effect dataset. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i The dynamic diffusion coefficient Ks of the i-th monitoring sub-region is obtained by correlation. i The system evaluates the results to output a second classification result and generates a corresponding strategy.

[0107] In this embodiment, remote sensing technology enables the system to accurately identify the spatial distribution of agricultural waste such as straw, withered grass, and livestock manure. This identification method can efficiently cover a wide target area, especially suitable for remote areas and densely agricultural areas, overcoming the limitations of traditional methods that rely on manual inspections and ground stations. The remote sensing identification module provides real-time and accurate data on the location and type of pollution sources, providing solid data support for subsequent pollution assessments. A predictive pollution model built using a convolutional neural network (CNN) can deeply learn and analyze the distribution characteristics of different types of pollution sources. Through detailed calculations of pollution sources within each monitoring sub-region, the system can accurately assess the pollution potential of each type of pollution source, thereby generating an accurate pollution source distribution map. This method has significant advantages over traditional manual analysis, enabling rapid and efficient processing and analysis of large-scale data. The dynamic monitoring module collects temperature, wind speed, and daily average precipitation data at different altitudes to create temperature-altitude profiles and combines this with real-time monitoring of the inversion layer effect. This allows the system to promptly identify the existence of inversion layers and assess their impact on pollutant diffusion. Due to the influence of the inversion layer, pollutants tend to stagnate at low altitudes. The system can adjust its monitoring strategy in real time, avoiding the neglect of the inversion layer effect in traditional methods and improving its ability to respond to dynamic changes in air pollution.

[0108] Example 2

[0109] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the remote sensing identification module includes a region segmentation unit, a remote sensing data acquisition unit, an image preprocessing unit, and a pollution source identification unit;

[0110] The aforementioned region segmentation unit is used to collect and identify the geographical features and landforms of the target area using a GIS geographic information system, establish a three-dimensional model, and divide the target area into several monitoring sub-regions, labeled as {Zq1, Zq2, Zq3, ..., Zq...} in the three-dimensional model. n}; n represents the total number of monitored sub-regions;

[0111] The remote sensing data acquisition unit is used to acquire multi-band images of the target area using a multispectral camera mounted on a drone, and to establish a multi-band image dataset, which includes multi-band images including visible light, near infrared and short-wave infrared.

[0112] The image preprocessing unit is used to perform image registration on the multi-band image dataset, align the data of each band, perform radiometric correction, and remove noise using mean filtering, Gaussian filtering, and wavelet transform.

[0113] The pollution source identification unit is used to extract spectral index features from multi-band image datasets and generate distribution maps of different pollution types.

[0114] In this embodiment, the region segmentation unit utilizes GIS technology to accurately divide the target area into multiple sub-regions based on its geographical features and topographic information, and annotates them in a 3D model, forming a detailed division of the distribution of air pollution sources. In this way, the system can achieve accurate region division and spatial analysis, providing fundamental data for subsequent pollution source identification and assessment. The remote sensing data acquisition unit uses a UAV equipped with a multispectral camera to acquire images, obtaining image data in multiple bands, including visible light, near-infrared, and short-wave infrared. These multi-band images possess strong spatial and spectral information, providing the reflectance characteristics of different pollution sources (such as straw, withered grass, and livestock manure) in different bands, facilitating more accurate identification of pollution sources and their distribution.

[0115] Example 3

[0116] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically, the steps for generating distribution maps of different pollution types include:

[0117] Step Aa.1: Calculate the Normalized Difference Vegetation Index (NDVI) to distinguish between green vegetation and withered grass. The expression is as follows:

[0118]

[0119] In the formula, NIR represents the near-infrared band value, which is an indicator of plant health. Healthy vegetation has a high NIR reflectance. Red represents the infrared band value, which is the absorption characteristic of plants. Healthy vegetation has a high absorption rate in the red light band.

[0120] Step Aa.2: Preliminary screening of withered grass areas: When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.5-0.9, it is identified as a healthy vegetation area and marked as a green area; the chlorophyll of green plants absorbs red light (Red) and strongly reflects near-infrared light (NIR), resulting in a high NDVI; NDVI > 0.5 indicates that → the chlorophyll content is high, the plants are healthy, and the growth is vigorous.

[0121] When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.11-0.3, it is identified as a withered grass area and marked as a red area. Although withered grass has decayed, it still has some structurally intact cells. Withered grass is vegetation that has decayed but still retains some cellular structure. The chlorophyll content is significantly reduced, resulting in an NDVI of 0.11-0.3. Near-infrared reflectance is reduced and red light absorption is weakened, so the NDVI value decreases. Withered grass usually has a lower NDVI than healthy vegetation, but it is still higher than bare soil or straw.

[0122] When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.05-0.1, it is identified as a straw area and marked as the first gray area. Straw is the residue after crop harvesting and has almost no chlorophyll. Its NDVI is slightly higher than that of bare land but lower than that of dead grass because its internal fibrous structure can still reflect some infrared light. An NDVI between 0.05 and 0.1 indicates that the vegetation has completely lost its activity but still retains some organic structure.

[0123] When the Normalized Difference Vegetation Index (NDVI) is in the range of -0.2 to 0.09, it is identified as a bare soil area and marked as a brown area. Bare soil, sandy soil, rocks, etc., do not contain vegetation and reflect visible and infrared light relatively evenly, resulting in an NDVI close to 0 or a negative value. An NDVI between -0.2 and 0.09 indicates that there is basically no vegetation cover.

[0124] When the Normalized Difference Vegetation Index (NDVI) is less than -0.1, it is identified as a water body and marked as an orange area. Water bodies strongly absorb infrared light (NIR), causing the calculated NDVI value to become negative. NDVI < -0.1 indicates that the area is a water body, such as a lake, river, or wetland.

[0125] Calculate the Normalized Difference Vegetation Index (NDVI) value for each pixel, then select the area with 0.11≤NDVI≤0.3 as the withered grass area, select the area with 0.05≤NDVI≤0.1 as the straw area, and exclude healthy vegetation points with NDVI>0.5.

[0126] Step Aa.3: Select the k-th window in the i-th monitoring sub-region of the image dataset, with a window size of 3×3 or 5×5; calculate the frequency of grayscale values ​​of each pair of pixels within the k-th window; the grayscale values ​​of each pair of pixels include the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f ;

[0127] Record the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f The frequency I appearing in the k-th window f The frequency values ​​are then normalized to probability values ​​to obtain the gray-level co-occurrence combination frequency P(I). h ,I f This method can effectively describe the texture features in an image. This helps in understanding the spatial distribution and texture differences of different types of pollution (such as withered grass, straw, etc.).

[0128] Step Aa.4: Calculate the texture roughness Contrast of the k-th window based on the gray-level co-occurrence combination frequency P(i,j). k and the entropy of the k-th window. k :

[0129] Contrast k =∑ j,f P(I j ,I f )×(I j -I f ) 2 ;

[0130] Entropy k =-∑ j,f P(I j ,I f )×logP(I j ,I f );

[0131] In the formula, (I j -I f ) 2 Used to calculate the trivial difference between the first gray value of the h-th pixel and the second gray value of the f-th pixel, to measure the gray value difference;

[0132] Contrast texture roughness of the k-th window k High numerical values ​​result in coarse textures (like withered grass);

[0133] Contrast texture roughness of the k-th window k Low values ​​indicate smooth textures (such as healthy vegetation);

[0134] The entropy of the k-th window. k High numerical values ​​→ high texture complexity (such as withered grass);

[0135] The entropy of the k-th window. k Low values ​​indicate uniform texture (e.g., healthy vegetation);

[0136] Step Aa.5: Set the roughness threshold and entropy threshold for withered grass texture to perform secondary filtering of withered grass areas;

[0137] When identifying the texture roughness of the k-th window Contrast k If the roughness of the withered grass texture is greater than or equal to the threshold, it is marked as the second gray area;

[0138] When identifying the texture roughness of the k-th window Contrast k <The roughness threshold for withered grass texture is not marked;

[0139] When identifying the entropy value of the k-th window... k If the value is greater than or equal to the threshold value of the withered grass entropy, it is marked as the third gray area;

[0140] When identifying the entropy value of the k-th window... k <The threshold value for withered grass entropy is not marked;

[0141] The final withered grass area is obtained by identifying the intersection area of ​​the first yellow area, the second yellow area, and the third yellow area.

[0142] The final withered grass area = first yellow area ∩ second gray area ∩ third gray area.

[0143] In this embodiment, by calculating the Normalized Difference Vegetation Index (NDVI), different types of ground cover such as green vegetation, withered grass, straw, and bare soil can be effectively distinguished. The NDVI value reflects the health status of vegetation, providing an efficient and non-contact monitoring method that facilitates the processing of remote sensing data and the identification of pollution sources.

[0144] Screening based on NDVI value range can accurately distinguish different categories such as healthy vegetation, withered grass, straw, bare land and water, forming different area markers (such as green, red, gray, etc.). This screening can improve the accuracy of subsequent pollution source identification and promote the accurate identification of withered grass and straw areas in agricultural waste monitoring.

[0145] By calculating texture features, the system can distinguish complex regions (such as withered grass and straw) from smooth regions (such as healthy vegetation) in an image, providing data support for subsequent texture analysis. The choice of window size (such as 3×3 or 5×5) allows for flexible adjustment of the analysis accuracy, enhancing the adaptability and processing capabilities of remote sensing data.

[0146] By calculating texture roughness and entropy, we can gain a deeper understanding of the texture complexity and uniformity of different regions. For example, the texture of withered grass and straw is typically rough and complex, while healthy vegetation is relatively smooth and uniform. This method can identify pollution source types through image texture features, further improving the accuracy of pollution source identification, especially in complex environments. By setting thresholds for texture roughness and entropy, regions that match specific texture characteristics (such as withered grass areas) can be effectively filtered out. This filtering method can further refine the identification of pollution sources, eliminate some interfering factors, and improve identification accuracy.

[0147] Example 4

[0148] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically, the steps for generating distribution maps of different pollution types also include:

[0149] Step Aa.6: Identify the surface temperature (LST);

[0150] LST = BT × (1 + W × ln(ε));

[0151] In the formula, BT represents brightness temperature, which is the radiation temperature of ground objects measured by the sensor, in Kelvin; W represents the atmospheric water vapor influence coefficient; W is obtained by inverting the atmospheric water vapor content from remote sensing images. Generally, this requires combining ground meteorological station data or global climate models to estimate the water vapor content in the atmosphere. Using the relationship between water vapor content and remote sensing image data, the atmospheric water vapor influence coefficient can be derived.

[0152] ε represents the surface emissivity, reflecting the ability of ground features to absorb and emit thermal radiation; ln(ε) represents the natural logarithm of the surface reflectivity, used to correct for surface radiation errors; ground emissivity is the ability of a ground feature's surface to absorb and emit infrared radiation, ranging from 0 ≤ ε ≤ 1; different ground features such as vegetation, soil, buildings, garbage, and livestock manure have different emissivities, including: buildings: ε = 0.98; vegetation: ε = 0.96; soil: ε = 0.92-0.95; livestock manure: ε = 0.89-0.91;

[0153] Step Aa.7: Identify the livestock manure area:

[0154] When the LST of the land surface is identified as 15-25℃, it is identified as soil and marked as a brown area.

[0155] When the surface temperature (LST) is identified as 30-40℃, it is identified as livestock manure and marked as a black area;

[0156] When the surface temperature (LST) is greater than 40°C, it is identified as a building area and marked as a yellow area.

[0157] Based on the markings of the final withered grass area, orange area, red area, brown area, green area, black area and yellow area in the 3D model, and extracting the final withered grass area, red area and black area, the withered grass aggregation point, straw aggregation point and livestock manure aggregation point corresponding to the i-th monitoring sub-region are generated.

[0158] In this embodiment, surface temperature (LST) identification provides a detailed understanding of the ground's thermal state. Through the combined calculation of brightness temperature (BT) and atmospheric water vapor influence coefficient (W), it accurately reflects the thermal radiation characteristics of different ground cover materials (such as soil, buildings, vegetation, livestock manure, etc.). This step, by measuring the surface radiation temperature, can effectively identify different types of ground cover, especially those associated with pollution, such as livestock manure and buildings.

[0159] By marking various regions in the 3D model and combining this with the aforementioned steps (NDVI, texture analysis, LST identification, etc.), the spatial distribution map of various pollution sources can be accurately drawn. For example, pollution types such as healthy vegetation, withered grass, straw, livestock manure, and bare land can be visualized using different color markers (such as green, red, black, brown, etc.). By extracting and drawing monitoring sub-regions, the aggregation points of different pollution types (such as withered grass, straw, livestock manure, etc.) can intuitively show the distribution trend of pollution sources, facilitating further analysis and decision-making.

[0160] Example 5

[0161] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the pollution source static analysis module includes a first extraction unit and a model building unit;

[0162] The first extraction unit is used to identify the dry grass accumulation points, straw accumulation points, and livestock manure accumulation points in the i-th monitoring sub-region, and to count the total number of pixels N of the j-th type of pollution source in the i-th monitoring sub-region. i,j And by combining the resolution analysis of UAV images, the pixel area S is obtained. pixel The total area A of the j-th type of pollution source in the i-th monitoring sub-region is calculated using the following formula. i,j :

[0163] A i,j =N i,j ×S pixel ;

[0164] The experimental density ρ of the j-th type of pollution source j Calculate the weight per unit area M of the j-th type of pollution source within the i-th monitoring sub-region. i,j :

[0165] M i,j =A i,j ×ρ j ;

[0166] Among them, the experimental density ρ of the j-th type of pollution source j Obtained based on historical reference data, including:

[0167] Straw density: 0.5-1.2 kg / m³ 2 Dry straw density: 0.3-0.7 kg / m³ 2 Livestock manure density: 0.8-2.0 kg / m³ 2 ;

[0168] Extract the unit area weight M of the j-th type of pollution source within the i-th monitoring sub-region. i,jAn incineration experiment was conducted, and the combustion emission factors and combustion time ratios of the j-th type of pollution source in the i-th monitoring sub-region during the incineration experiment were collected to establish a combustion experiment dataset.

[0169] The model building unit is used to construct an initial convolutional neural network model using a convolutional neural network, and to simulate, test, and train the initial convolutional neural network model using a combustion experiment dataset. The trained initial convolutional neural network model is then used as a pollution prediction model to simulate and obtain the combustion pollution coefficient Rs of the i-th monitoring sub-region. i :

[0170] The combustion pollution coefficient Rs of the i-th monitoring sub-region i Calculated using the following formula:

[0171]

[0172] In the formula, j represents the pollution source type index, including straw, dry grass h and livestock manure; m represents the number of specific aggregation points of the j-th pollution source;

[0173] E i,j M represents the combustion emission factor of the j-th pollution source in the i-th monitoring sub-region. i,j Pr represents the weight per unit area of ​​the j-th type of pollution source within the i-th monitoring sub-region. i,j This represents the ratio of the combustion time of the j-th type of pollution source within the i-th monitoring sub-region.

[0174] The pollutant combustion emission factors were determined by experimental data, and typical values ​​for different pollution sources are shown in the following table (unit: g / kg):

[0175] Pollution source categories <![CDATA[CO2(g / kg)]]> NOx (g / kg) <![CDATA[SO2(g / kg)]]> PM2.5 (g / kg) straw burning 1512 4.2 0.8 12.6 Burning dry grass 1385 3.6 0.7 10.2 Livestock manure burning 1205 2.9 1.4 14.8

[0176] The following is the combustion pollution coefficient Rs in the simulated Zq1 monitoring sub-region. i Experimental charts:

[0177]

[0178] Assume that the following occurred in monitoring sub-area Zq1: 500 kg of straw was burned over a period of 30 minutes, with a pollution source burning time ratio of 0.5.

[0179] Dry grass: Burning 300 kg for 20 minutes, the pollution source combustion time ratio is 0.33;

[0180] Livestock manure: Burning 200 kg for 40 minutes, the pollution source combustion time ratio is 0.67;

[0181] This indicates that within the 60-minute monitoring period, straw burned for 50% of the time, dry grass burned for 33% of the time, and livestock manure burned for 67% of the time.

[0182] Calculate CO2 emissions:

[0183] FCO2,5=(1512×500×0.5)+(1385×300×0.33)+(1205×200×0.67)=676.585g=676.6kg;

[0184] Calculate PM2.5 emissions:

[0185] PM2.5,5=(12.6×500×0.5)+(10.2×300×0.33)+(14.8×200×0.67)=6.143g=6.14kg;

[0186] Finally, the total emissions of various pollutants can be calculated, and the combustion pollution coefficient Rs can be obtained. i .

[0187] In this embodiment, the static pollution source analysis module, by combining remote sensing image analysis and deep learning technology, achieves accurate identification, quantification, and prediction of pollution sources (dried grass, straw, livestock manure, etc.). This improves the accuracy of pollution source identification and provides an important basis for subsequent pollution source management and prevention measures. Furthermore, by training the incineration experimental data using a convolutional neural network, the combustion pollution coefficient Rs of the pollution source is accurately simulated. i This effectively supports environmental protection and governance efforts.

[0188] Example 6

[0189] This embodiment is an explanation based on Embodiment 5. Please refer to it. Figure 1 Specifically, the pollution source static analysis module further includes a first assessment unit and a first strategy unit;

[0190] The first assessment unit is used to establish a risk threshold X and to set the combustion pollution coefficient Rs of the i-th monitoring sub-region. i The risk level of the pollution source in the i-th monitoring sub-region after combustion is compared and evaluated with the risk threshold X to determine the risk level of the pollution source's impact on air pollution. The first classification result is output, including:

[0191] The risk threshold X includes a first threshold X1 and a second threshold X2, and the first threshold X1 is greater than the second threshold X2.

[0192] When Rs i<X2 indicates that the distribution of pollution sources in this monitoring sub-region is scattered, and no obvious pollution aggregation area is formed, so the comprehensive impact on air pollution is limited, and the first low-risk level is generated; the pollution sources in this monitoring sub-region are sparse, and the mutual influence between pollution sources is small, so the overall air pollution risk is low;

[0193] When X2 ≤ Rs i ≤ X1 indicates that the distribution of pollution sources in this monitoring sub-region is scattered, but individual pollution aggregation areas have been formed, and the comprehensive impact of emissions on air pollution is relatively significant, generating the second medium-risk level; although the distribution of pollution sources in this monitoring sub-region is relatively scattered, the emissions of local pollution sources are relatively high, resulting in a certain risk of air pollution;

[0194] When Rs i > X1 indicates that the distribution of pollution sources in this monitoring sub-region is intensive, and the emissions of multiple pollution sources exceed expectations, with a relatively high overall air pollution risk, which needs to be focused on, generating the third high-risk level; the distribution of pollution sources in this monitoring sub-region is very intensive, and the emissions of multiple pollution sources are relatively high, with a significant impact on air pollution and a high risk level;

[0195] The first strategy unit is used to summarize the monitoring sub-regions of the second medium-risk level and the third high-risk level, and generate corresponding regulation strategies, including:

[0196] Generate the first strategy for the second medium-risk level, including: returning 50 - 60% of the straw in this monitoring sub-region to the field by mechanization or composting; converting 50 - 60% of the dry grass in this monitoring sub-region into organic fertilizer, and converting 50 - 60% of the livestock manure in this monitoring sub-region into organic fertilizer by aerobic fermentation technology;

[0197] Generate the second strategy for the third high-risk level, including: returning 61 - 90% of the straw in this monitoring sub-region to the field by mechanization or composting; converting 61 - 90% of the dry grass in this monitoring sub-region into organic fertilizer, and converting 5 - 10% of the dry grass into biomass energy; converting 61 - 70% of the livestock manure in this monitoring sub-region into organic fertilizer by aerobic fermentation technology, and grading 20 - 30% of the livestock manure through anaerobic microorganisms to generate methane energy for supplying the biogas power generation system.

[0198] In this embodiment, through the collaborative work of the first evaluation unit and the first strategy unit, the pollution source static analysis module realizes the accurate evaluation and effective regulation of different pollution sources. By establishing reasonable risk thresholds and evaluation methods, the monitoring sub-regions can be risk-graded, and targeted regulation strategies can be proposed for different risk levels. This method not only helps to control and reduce air pollution, but also improves the sustainability of agricultural production and promotes the protection of the ecological environment by converting waste into organic fertilizer or biomass energy.

[0199] Example 7

[0200] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the dynamic monitoring module includes a temperature acquisition unit and an inversion layer identification unit;

[0201] The temperature acquisition unit is used to acquire temperature data at different heights in the i-th monitoring sub-region and draw a temperature-height profile of the i-th monitoring sub-region. Within the inversion layer, the temperature increases with increasing height, showing a positive temperature gradient and forming a region of temperature reversal.

[0202] When plotting the temperature-height profile of the i-th monitoring sub-region, the temperature on the y-axis and the height on the x-axis are correlated to obtain the relationship between temperature and height. The measured temperature values ​​of the t-th and r-th vertical height points in the i-th monitoring sub-region are extracted, and the temperature difference γ between the t-th and r-th height points is calculated using the following formula. t,r :

[0203]

[0204] In the formula, T t T represents the temperature at the t-th elevation point. r Let represent the temperature at the r-th elevation point; Δz represents the elevation difference between the t-th and r-th elevation points.

[0205] If the temperature gradient is negative, it indicates that the temperature decreases with increasing altitude, which is a normal phenomenon. If the temperature gradient is positive, it indicates that the temperature increases with increasing altitude. In this case, the inversion layer identification unit identifies it as a temperature inversion phenomenon, marks it as an inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r A thermosphere effect dataset was established, acquired using a strategy of temperature sensors, wind speed sensors, and rainfall sensors; the daily average precipitation JP of the i-th monitoring sub-region was also measured. r It can also be obtained by analyzing historical rainfall data.

[0206] In this embodiment, the dynamic monitoring module, through the coordinated operation of the temperature acquisition unit and the inversion layer identification unit, accurately depicts the relationship between temperature and altitude, promptly identifies temperature inversion phenomena, and provides crucial information for air pollution management by combining data such as wind speed and precipitation. Through the monitoring and analysis of this module, environmental meteorological changes can be effectively understood, pollution source monitoring and control strategies can be optimized, and the effectiveness of environmental management and pollution prevention and control can be improved.

[0207] Example 8

[0208] This embodiment is an explanation based on Embodiment 7. Please refer to it. Figure 1 Specifically, the dynamic analysis module includes an inversion layer effect factor calculation unit, a vertical internal shear factor calculation unit, and a precipitation washing effect factor calculation unit.

[0209] The temperature layer effect factor calculation unit is used to calculate the temperature layer effect factor (ITEF) of the i-th monitoring sub-region after marking the inversion layer of the i-th monitoring sub-region using the following formula. i :

[0210]

[0211] In the formula, T env This indicates the ambient temperature (T) of the monitored sub-region. TILL This indicates the temperature within the inversion layer. If the temperature of the inversion layer is high, pollutants will remain in this area, their diffusion ability will be inhibited, resulting in a higher concentration of pollutants.

[0212] The vertical internal shear factor calculation unit is used to extract wind speed data above and below the inversion layer in the temperature stratification effect dataset after marking the inversion layer of the i-th monitoring sub-region, and calculate the vertical internal shear factor (VSCF) of the i-th monitoring sub-region using the following formula. i :

[0213]

[0214] In the formula, V wind (Z top V represents the wind speed above the inversion layer. wind (Z bottom Z represents the wind speed below the inversion layer. top and Z bottom These are the upper and lower boundary heights of the inversion layer, respectively; if the vertical wind speed changes significantly (strong shear), the vertical diffusion capacity of pollutants is stronger.

[0215] The precipitation washing effect factor calculation unit is used to extract the daily average precipitation JP of the i-th monitoring sub-region in the thermosphere effect dataset. r The precipitation washing effect factor (PWEF) for the i-th monitoring sub-region is calculated using the following formula. i :

[0216] PWEF i =α×JP r ;

[0217] In the formula, α represents a constant factor used to represent the average effect of precipitation on pollutant removal, which is estimated through experimental data or empirical values; the precipitation washing effect refers to the ability of rainwater to clean pollutants in the air, thereby reducing the concentration of pollutants in the atmosphere; the greater the precipitation, the stronger the removal effect on pollutants in the air.

[0218] In this embodiment, the inversion layer effect is quantified: by calculating this factor, the effect of the inversion layer on pollutant retention can be quantified, thereby helping to predict the impact of temperature inversion on regional air pollution. The introduction of the inversion layer effect factor makes the environmental prediction system more accurate, capable of reflecting the impact of temperature reversal on pollutant distribution in real time, providing important basis for pollution management. The introduction of the vertical internal shear factor helps to assess the impact of wind speed changes on the vertical diffusion capacity of pollutants. If the wind speed change is large, pollutants may diffuse more easily to higher or lower altitudes, reducing the accumulation of local pollution concentrations.

[0219] By calculating the precipitation washing effect factor, the removal effect of precipitation on pollutants can be quantitatively analyzed, helping to assess the impact of precipitation on air pollution. This factor enables environmental monitoring and air pollution prediction models to take the role of precipitation into account, providing a dynamic adjustment basis for environmental management.

[0220] Example 8

[0221] This embodiment is an explanation based on Embodiment 7. Please refer to it. Figure 1 Specifically, the dynamic analysis module further includes an association unit, a second evaluation unit, and a second strategy unit;

[0222] The associated unit is used to extract the inversion layer effect factor (ITEF) of the i-th monitoring sub-region. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i After dimensionless processing, the dynamic diffusion coefficient Ks of the i-th monitoring sub-region is calculated using the following formula. i :

[0223]

[0224] In the formula, b1, b2, and b3 represent the inversion layer effect factor (ITEF) of the i-th monitoring sub-region, respectively. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i The weighting coefficients are equal to 1; the precipitation washing effect factor is inversely proportional.

[0225] Example 2 is an explanation of Example 1. Please refer to the example provided. Figure 1, specifically, the second evaluation unit is used to preset a diffusion threshold Y and compare the dynamic diffusion coefficient Ks of the i-th monitoring sub-region i with the diffusion threshold Y to determine the diffusion impact level of the pollution source in the i-th monitoring sub-region on adjacent regions after combustion, and output a second classification result, including:

[0226] The diffusion threshold Y includes a first diffusion threshold Y1 and a second diffusion threshold Y2, and the first diffusion threshold Y1 is greater than the second diffusion threshold Y2;

[0227] When Ks i < Y2, it means that during the incineration of the pollution source in this monitoring sub-region, the pollution source has stagnated in the temperature inversion layer within the region and there is no diffusion risk, forming a first stagnant risk region level, and a third strategy is generated through the second strategy unit, including: when identifying the incineration of the pollution source, 1-2 drones equipped with spray dust suppression equipment are arranged along the upper part of the temperature inversion layer in the upwind direction of the pollution source incineration for 15-20 minutes of operation; the spray interval is set to once every 20 minutes, and the spray duration is 5 minutes;

[0228] When Y2 ≤ Ks i ≤ Y1, it means that during the incineration of the pollution source in this monitoring sub-region, there is a diffusion risk, but the risk is within the expected range, generating a second low diffusion risk region level, and a fourth strategy is generated through the second strategy unit, including: when identifying the incineration of the pollution source, 3 drones equipped with spray dust suppression equipment are arranged at a height of 26-50 meters from the ground in the upwind direction of the pollution source incineration for 21-30 minutes of operation; the spray interval is set to once every 15 minutes, and the spray duration is 5 minutes;

[0229] When Ks i > Y1, it means that during the incineration of the pollution source in this monitoring sub-region, there is a diffusion risk, and the diffusion risk will reach a relatively far range in a short time, generating a third high diffusion risk region level; and a fifth strategy is generated through the second strategy unit, including: when identifying the incineration of the pollution source, 4-5 drones equipped with spray dust suppression equipment are arranged at a height of 40-50 meters from the ground in the upwind direction of the pollution source incineration for 31-40 minutes of operation; the spray interval is set to once every 10 minutes, and the spray duration is 10 minutes.

[0230] In this embodiment, accurate response strategies are generated according to different diffusion risk levels to ensure that effective pollution control measures can be taken in a timely manner when the pollution source is incinerated. The strategy of drones equipped with spray equipment can dynamically adjust the time, interval and duration of spray operations, effectively reduce pollution diffusion, and improve the flexibility and efficiency of air quality management.

[0231] This dynamic analysis module, through multi-level assessment and strategy generation, can accurately identify and respond to the risk of pollution source diffusion. Its core advantages include: providing dynamic and accurate assessments of pollution diffusion by integrating the effects of temperature inversion, wind shear, and precipitation washing; accurately classifying diffusion risk levels based on the comparison of diffusion coefficients with preset thresholds and adjusting response strategies in a timely manner; and flexibly configuring drones and spray equipment according to different risk levels to optimize pollution control effectiveness and ensure that air quality is not affected by pollution source diffusion.

[0232] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0233] The above formulas are all derived from software simulation using a large amount of data and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the protection scope of the present invention.

Claims

1. A regional air pollution source distribution and impact assessment system, characterized in that, include: The remote sensing identification module is used to divide the target area into several monitoring sub-areas and identify pollution sources in the monitoring sub-areas using remote sensing technology. It obtains the spatial distribution data of pollution source aggregation points in the monitoring sub-areas, including dry grass aggregation points, straw aggregation points, and livestock manure aggregation points. The static pollution source analysis module is used to construct a predictive pollution model using convolutional neural networks based on pollution source aggregation point data acquired by the remote sensing identification module. It analyzes the distribution characteristics of each type of pollution source, calculates the pollution potential of each type of pollution source within the monitoring sub-region based on these characteristics, generates a corresponding pollution source distribution map, simulates the pollution generated during the incineration process of each pollution source, and predicts the combustion pollution coefficient Rs for the i-th monitoring sub-region. i and for Rs i Perform classification, output the first classification result, and generate the corresponding strategy based on the first classification result; The dynamic monitoring module, after the corresponding strategy is executed, collects temperature data at different altitudes in the i-th monitoring sub-region, plots a temperature-altitude profile of the i-th monitoring sub-region, identifies the inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r Establish a dataset of thermosphere effects; The dynamic analysis module is used to construct the inversion stratospheric effect factor (ITEF) for the i-th monitoring sub-region based on the stratospheric effect dataset. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i The dynamic diffusion coefficient Ks of the i-th monitoring sub-region is obtained by correlation. i The system evaluates the results to output a second classification result and generates a corresponding strategy.

2. The regional air pollution source distribution and impact assessment system according to claim 1, characterized in that, The remote sensing identification module includes a region segmentation unit, a remote sensing data acquisition unit, an image preprocessing unit, and a pollution source identification unit; The aforementioned region segmentation unit is used to collect and identify the geographical features and landforms of the target area using a GIS geographic information system, establish a three-dimensional model, and divide the target area into several monitoring sub-regions, labeled as {Zq1, Zq2, Zq3, ..., Zq...} in the three-dimensional model. n }; n represents the total number of monitored sub-regions; The remote sensing data acquisition unit is used to acquire multi-band images of the target area using a multispectral camera mounted on a drone, and to establish a multi-band image dataset, which includes multi-band images including visible light, near infrared and short-wave infrared. The image preprocessing unit is used to perform image registration on the multi-band image dataset, align the data of each band, perform radiometric correction, and remove noise using mean filtering, Gaussian filtering, and wavelet transform. The pollution source identification unit is used to extract spectral index features from multi-band image datasets and generate distribution maps of different pollution types.

3. The regional air pollution source distribution and impact assessment system according to claim 2, characterized in that, The specific steps for generating distribution maps of different pollution types include: Step Aa.1: Calculate the Normalized Difference Vegetation Index (NDVI) to distinguish between green vegetation and withered grass. The expression is as follows: In the formula, NIR represents the near-infrared band value, which is an indicator of plant health. Healthy vegetation has high NIR reflectance. Red indicates the infrared band value, plant absorption characteristics, and healthy vegetation has a high absorption rate in the red light band. Step Aa.2: Preliminary screening of withered grass areas: When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.5-0.9, it is identified as a healthy vegetation area and marked as a green area; When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.11-0.3, it is identified as a withered grass area and marked as a red area; When the Normalized Difference Vegetation Index (NDVI) is in the range of 0.05-0.1, it is identified as a straw area and marked as the first gray area; when the NDVI is between 0.05 and 0.1, it indicates that the vegetation has completely lost its activity, but still retains a certain organic structure. When the Normalized Difference Vegetation Index (NDVI) is in the range of -0.2 to 0.09, it is identified as a bare soil area and marked as a brown area. When the Normalized Difference Vegetation Index (NDVI) is less than -0.1, it is identified as a water body area and marked as an orange area. The NDVI value of each pixel is calculated, and then the area with 0.11 ≤ NDVI ≤ 0.3 is selected as the withered grass area, the area with 0.05 ≤ NDVI ≤ 0.1 is selected as the straw area, and healthy vegetation points with NDVI > 0.5 are excluded. Step Aa.3: Select the k-th window in the i-th monitoring sub-region of the image dataset, with a window size of 3×3 or 5×5; calculate the frequency of grayscale values ​​of each pair of pixels within the k-th window; the grayscale values ​​of each pair of pixels include the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f ; Record the first grayscale value I of the h-th pixel. h and the second grayscale value I of the f-th pixel f The frequency I appearing in the k-th window f The frequency values ​​are then normalized to probability values ​​to obtain the gray-level co-occurrence combination frequency P(I). h ,I f ); Step Aa.4: Based on the gray-level co-occurrence combination frequency P(I) h ,I f )Calculate and obtain the texture roughness Contrast of the k-th window k and the entropy of the k-th window. k : Contrast k =∑ j,f P(I h ,I f )×(I h -I f ) 2 ; Entropy k =-∑ j,f P(I h ,I f )×logP(I h ,I f ); In the formula, (I h -I f ) 2 Used to calculate the h-th gray value I of the j-th pixel. h The trivial difference between the f-th second gray value and the gray value itself measures the gray level difference. Step Aa.5: Set the roughness threshold and entropy threshold for withered grass texture to perform secondary filtering of withered grass areas; When identifying the texture roughness of the k-th window Contrast k If the roughness of the withered grass texture is greater than or equal to the threshold, it is marked as the second gray area; When identifying the texture roughness of the k-th window Contrast k <The roughness threshold for withered grass texture is not marked; When identifying the entropy value of the k-th window... k If the value is greater than or equal to the threshold value of the withered grass entropy, it is marked as the third gray area; When identifying the entropy value of the k-th window... k <The threshold value for withered grass entropy is not marked; The final withered grass area is obtained by identifying the intersection area of ​​the first yellow area, the second yellow area, and the third yellow area. The final withered grass area = first yellow area ∩ second gray area ∩ third gray area.

4. The regional air pollution source distribution and impact assessment system according to claim 3, characterized in that, The specific steps for generating distribution maps of different pollution types also include: Step Aa.6: Identify the surface temperature (LST); LST = BT × (1 + W × ln(ε)); In the formula, BT represents the brightness temperature, which is the radiation temperature of the ground object measured by the sensor, in Kelvin; W represents the atmospheric water vapor influence coefficient; ε represents the surface emissivity, reflecting the ability of the ground object to absorb and emit thermal radiation; ln(ε) represents the natural logarithm of the surface reflectivity, used to correct for surface radiation errors; ground emissivity is the ability of the ground object surface to absorb and emit infrared radiation, in the range 0≤ε≤1; different ground objects such as vegetation, soil, buildings, garbage, and livestock manure have different emissivities, including: buildings: ε=0.98; vegetation: ε=0.96; soil: ε=0.92-0.95; livestock manure ε=0.89-0.91; Step Aa.7: Identify the livestock manure area: When the LST of the land surface is identified as 15-25℃, it is identified as soil and marked as a brown area. When the surface temperature (LST) is identified as 30-40℃, it is identified as livestock manure and marked as a black area; When the surface temperature (LST) is greater than 40°C, it is identified as a building area and marked as a yellow area. Based on the markings of the final withered grass area, orange area, red area, brown area, green area, black area and yellow area in the 3D model, and extracting the final withered grass area, red area and black area, the withered grass aggregation point, straw aggregation point and livestock manure aggregation point corresponding to the i-th monitoring sub-region are generated.

5. The regional air pollution source distribution and impact assessment system according to claim 1, characterized in that, The static analysis module for pollution sources includes a first extraction unit and a model building unit; The first extraction unit is used to identify the dry grass accumulation points, straw accumulation points, and livestock manure accumulation points in the i-th monitoring sub-region, and to count the total number of pixels N of the j-th type of pollution source in the i-th monitoring sub-region. i,j And by combining the resolution analysis of UAV images, the pixel area S is obtained. pixel The total area A of the j-th type of pollution source in the i-th monitoring sub-region is calculated using the following formula. i,j : A i,j =N i,j ×S pixel ; The experimental density ρ of the j-th type of pollution source j Calculate the weight per unit area M of the j-th type of pollution source within the i-th monitoring sub-region. i,j : M i,j =A i,j ×ρ j ; Among them, the experimental density ρ of the j-th type of pollution source j Obtained based on historical reference data, including: Straw density: 0.5-1.2 kg / m³ 2 Dry straw density: 0.3-0.7 kg / m³ 2 Livestock manure density: 0.8-2.0 kg / m³ 2 ; Extract the unit area weight M of the j-th type of pollution source within the i-th monitoring sub-region. i,j An incineration experiment was conducted, and the combustion emission factors and combustion time ratios of the j-th type of pollution source in the i-th monitoring sub-region during the incineration experiment were collected to establish a combustion experiment dataset. The model building unit is used to construct an initial convolutional neural network model using a convolutional neural network, and to simulate, test, and train the initial convolutional neural network model using a combustion experiment dataset. The trained initial convolutional neural network model is then used as a pollution prediction model to simulate and obtain the combustion pollution coefficient Rs of the i-th monitoring sub-region. i : The combustion pollution coefficient Rs of the i-th monitoring sub-region i Calculated using the following formula: In the formula, j represents the pollution source type index, including straw, dry grass h and livestock manure; m represents the number of specific aggregation points of the j-th pollution source; E i,j M represents the combustion emission factor of the j-th pollution source in the i-th monitoring sub-region. i,j Pr represents the weight per unit area of ​​the j-th type of pollution source within the i-th monitoring sub-region. i,j This represents the ratio of the combustion time of the j-th type of pollution source within the i-th monitoring sub-region.

6. The regional air pollution source distribution and impact assessment system according to claim 1, characterized in that, The static analysis module for pollution sources also includes a first assessment unit and a first strategy unit; The first assessment unit is used to establish a risk threshold X and to set the combustion pollution coefficient Rs of the i-th monitoring sub-region. i The risk level of the pollution source in the i-th monitoring sub-region after combustion is compared and evaluated with the risk threshold X to determine the risk level of the pollution source's impact on air pollution. The first classification result is output, including: The risk threshold X includes a first threshold X1 and a second threshold X2, and the first threshold X1 is greater than the second threshold X2. When Rs i <X2, it indicates that the pollution sources in the monitoring sub-region are distributed dispersedly and no obvious pollution aggregation area is formed, generating the first low-risk level; when X2 ≤ Rs i ≤ X1, it indicates that the pollution sources in the monitoring sub-region are distributed dispersedly but individual pollution aggregation areas have been formed, generating the second medium-risk level; when Rs i > X1, it indicates that the pollution sources in the monitoring sub-region are densely distributed and the emissions of multiple pollution sources exceed expectations, which need to be focused on, generating the third high-risk level; The first strategy unit is used to summarize the monitoring sub-areas for the second medium-risk level and the third high-risk level, and generate corresponding control strategies, including: The first strategy for the second risk level includes: returning 50-60% of the straw in the monitored sub-area to the field by mechanization or composting; converting 50-60% of the withered grass in the monitored sub-area into organic fertilizer; and using aerobic fermentation technology to convert 50-60% of the livestock manure in the monitored sub-area into organic fertilizer. For the third highest risk level, a second strategy is generated, including: mechanized return of 61-90% of the straw in the monitored sub-area to the field or composting; conversion of 61-90% of the withered grass in the monitored sub-area into organic fertilizer and 5-10% of the withered grass into biomass energy; and conversion of 61-70% of the livestock manure in the monitored sub-area into organic fertilizer using aerobic fermentation technology and 20-30% of the livestock manure into methane energy through anaerobic microbial grading to supply biogas power generation systems.

7. The regional air pollution source distribution and impact assessment system according to claim 1, characterized in that, The dynamic monitoring module includes a temperature acquisition unit and an inversion layer identification unit; The temperature acquisition unit is used to acquire temperature data at different heights in the i-th monitoring sub-region and draw a temperature-height profile of the i-th monitoring sub-region. Within the inversion layer, the temperature increases with increasing height, showing a positive temperature gradient and forming a region of temperature reversal. When plotting the temperature-height profile of the i-th monitoring sub-region, the temperature on the y-axis and the height on the x-axis are correlated to obtain the relationship between temperature and height. The measured temperature values ​​of the t-th and r-th vertical height points in the i-th monitoring sub-region are extracted, and the temperature difference γ between the t-th and r-th height points is calculated using the following formula. t,r : In the formula, T t T represents the temperature at the t-th elevation point. r Let Δz represent the temperature at the r-th altitude point; Δz represents the altitude difference between the t-th and r-th altitude points. If the temperature gradient is negative, it indicates that the temperature decreases with increasing altitude; if the temperature gradient is positive, it indicates that the temperature increases with increasing altitude. In this case, the inversion layer identification unit identifies it as an inversion phenomenon, marks it as an inversion layer, and collects wind speed data above and below the inversion layer and the daily average precipitation JP of the i-th monitoring sub-region. r Establish a dataset on the thermosphere effect.

8. The regional air pollution source distribution and impact assessment system according to claim 7, characterized in that, The dynamic analysis module includes a calculation unit for inversion layer effect factors, a calculation unit for vertical internal shear factors, and a calculation unit for precipitation washing effect factors. The temperature layer effect factor calculation unit is used to calculate the temperature layer effect factor (ITEF) of the i-th monitoring sub-region after marking the inversion layer of the i-th monitoring sub-region using the following formula. i : In the formula, T env This indicates the ambient temperature (T) of the monitored sub-region. TILL This indicates the temperature within the inversion layer; The vertical internal shear factor calculation unit is used to extract wind speed data above and below the inversion layer in the temperature stratification effect dataset after marking the inversion layer of the i-th monitoring sub-region, and calculate the vertical internal shear factor (VSCF) of the i-th monitoring sub-region using the following formula. i : In the formula, V wind (Z top V represents the wind speed above the inversion layer. wind (Z bottom Z represents the wind speed below the inversion layer. top and Z bottom These are the upper and lower boundary heights of the inversion layer, respectively. The precipitation washing effect factor calculation unit is used to extract the daily average precipitation JP of the i-th monitoring sub-region in the thermosphere effect dataset. r The precipitation washing effect factor (PWEF) for the i-th monitoring sub-region is calculated using the following formula. i : PWEF i =α×JP r ; In the formula, α represents a constant factor, which is used to represent the average effect of precipitation on pollutant removal.

9. A regional air pollution source distribution and impact assessment system according to claim 8, characterized in that, The dynamic analysis module also includes an association unit, a second evaluation unit, and a second strategy unit; The associated unit is used to extract the inversion layer effect factor (ITEF) of the i-th monitoring sub-region. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i After dimensionless processing, the dynamic diffusion coefficient Ks of the i-th monitoring sub-region is calculated using the following formula. i : In the formula, b1, b2, and b3 represent the inversion layer effect factor (ITEF) of the i-th monitoring sub-region, respectively. i Vertical internal shear factor VSCF i and precipitation washing effect factor PWEF i The weighting coefficients are equal to 1; the precipitation washing effect factor is inversely proportional.

10. A regional air pollution source distribution and impact assessment system according to claim 9, characterized in that, The second evaluation unit is used to preset the diffusion threshold Y and to set the dynamic diffusion coefficient Ks of the i-th monitoring sub-region. i The impact level of the pollution source in the i-th monitoring sub-region on the diffusion of adjacent areas after combustion is determined by comparing it with the diffusion threshold Y, and the second classification result is output, including: The diffusion threshold Y includes a first diffusion threshold Y1 and a second diffusion threshold Y2, and the first diffusion threshold Y1 is greater than the second diffusion threshold Y2; When Ks i <Y2, indicating that during the incineration of the pollution source in this monitoring sub-region, the pollution source has stagnated in the temperature inversion layer within the region and there is no diffusion risk, forming the first stagnation risk area level. And the third strategy is generated through the second strategy unit, including: when identifying the incineration of the pollution source, 1-2 drones equipped with spray dust suppression equipment are arranged above the temperature inversion layer in the upwind direction of the pollution source incineration for 15-20 minutes of operation; the spray interval is set to once every 20 minutes, and the spray duration is 5 minutes; When Y2≤Ks i ≤Y1 indicates that the pollution source in the monitored sub-area has a risk of diffusion during the incineration process, but the risk is within expectations. This generates a second low diffusion risk area level, and a fourth strategy is generated through the second strategy unit. This strategy includes: when the pollution source is identified and incinerated, deploying three drones equipped with spray dust suppression equipment at a height of 26-50 meters above the ground in the upwind direction of the pollution source incineration, to carry out operations for 21-30 minutes; the spray interval is set to once every 15 minutes, and the spray duration is 5 minutes. When Ks i >Y1 indicates that the pollution source in the monitored sub-area has a risk of spreading during the incineration process, and the risk of spreading can reach a far range in a short period of time, generating the third highest risk area level; and the fifth strategy is generated through the second strategy unit, including: when the pollution source is identified and incinerated, deploy 4-5 drones equipped with spray dust suppression equipment at a height of 40-50 meters above the ground in the upwind direction of the pollution source incineration, and carry out operation for 31-40 minutes; the spray interval is set to once every 10 minutes, and the spray duration is 10 minutes.

Images