Air quality prediction optimization method and system based on deep learning

Abstract

The invention discloses an air quality prediction optimization method and system based on deep learning, and particularly relates to the technical field of air quality prediction optimization. The method comprises the steps of (1) collecting and analyzing monitoring data of a fire area, (2) constructing a pollutant concentration prediction model, (3) correcting the pollutant concentration prediction model, and (4) predicting and optimizing the air quality of the fire area. According to the method, the monitoring data of the fire area collected in each historical fire is adopted, the deep learning technology is adopted, the prediction model of the concentration of each type of pollutants is trained, the corrected prediction model of the concentration of each type of pollutants in the fire area is obtained, and the accuracy of the prediction model of the concentration of each type of pollutants is improved. According to the method, a zoning technical means is adopted, air quality analysis and optimization treatment of risk areas with different levels of air quality are achieved, the optimization treatment effect is guaranteed, and meanwhile resources are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of air quality prediction and optimization, and in particular to an air quality prediction and optimization method and system based on deep learning. Background Art

[0002] In recent years, due to global climate change, extreme weather events around the world, such as high temperatures, droughts and strong winds, have become more frequent, resulting in a gradual increase in the frequency and intensity of fires. Fires will directly release a large amount of pollutants into the atmosphere. These pollutants not only affect the air quality in the areas surrounding the fire site, but can also spread to farther places with the influence of the wind. These pollutants can cause acute or chronic health problems to the human body. Therefore, it is necessary to study the air quality prediction and optimization technology after a fire.

[0003] The prior art, such as the invention patent application announced as CN115237896B, discloses a data pre-processing method and system for air quality forecasting based on deep learning, the method comprising: obtaining a real-time meteorological simulation data set and optimizing it using a weather forecast model to generate a meteorological forecast data set; then extracting and splicing the meteorological forecast data at the current and target forecast times in the meteorological forecast data set; then using the trained convolutional autoencoder model to reduce the spatial and temporal dimensions of the spliced ​​data and fuse them to obtain regional meteorological factors; finally, inputting the regional meteorological factors and pollutant monitoring data into the trained air quality forecast model to obtain air quality forecast results. The invention can significantly reduce the interference of noise and data outliers on the prediction process and results, improve the robustness of the model, and thus effectively improve the numerical precision and forecast accuracy of air quality forecasts for a long period in the future.

[0004] Combined with the above scheme, it is found that the prediction and optimization of air quality in the prior art is more about building a prediction model for the relationship between meteorological data and pollutants. However, it ignores that the air quality in the fire area is not only affected by meteorological data, but also includes the influence of various fire characteristic data and geographical environment data. As a result, the air quality prediction model of the prior art is difficult to adapt to the air quality prediction of the fire area, resulting in insufficient prediction and optimization of the air quality in the fire area, causing the air quality pollution in the fire area to pose a greater safety hazard to the human body and causing greater damage to the ecosystem near the fire area. On the other hand, the optimization measures for air quality in the prior art ignore the zoning and grading management according to air quality, resulting in a waste of resources and a reduction in the efficiency of the optimization process when optimizing the air quality in the fire area, resulting in poor optimization of the air quality in the fire area, and it is difficult to meet the needs of the actual air quality optimization process. Summary of the invention

[0005] The purpose of the present invention is to provide an air quality prediction optimization method and system based on deep learning, which solves the problems existing in the background technology.

[0006] To solve the above technical problems, the first aspect of the present invention provides an air quality prediction and optimization method based on deep learning, the method comprising: step one, collecting and analyzing various monitoring data of the fire area: obtaining concentration data of various types of pollutants, meteorological data, and fire characteristic data at each collection point in the fire area within the monitoring period, calculating the atmospheric stability coefficient of the fire area, obtaining various geographical environment data of the fire area, and calculating the building density coefficient of the fire area.

[0007] Step 2: Construct a pollutant concentration prediction model: Calculate the emission rate of various types of pollutants, and construct a prediction model for the concentration of various types of pollutants in the fire area based on the building density coefficient and the atmospheric stability coefficient of the fire area.

[0008] Step 3: Revise the pollutant concentration prediction model: obtain the monitoring data of the fire area collected from each historical fire, and revise the prediction model of the concentration of various types of pollutants in the fire area.

[0009] Step 4. Predict and optimize the air quality in the fire area: Based on the revised prediction model for the concentration of each type of pollutant, obtain the concentration data of each type of pollutant at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, construct the judgment area and divide the air quality risk level of the judgment area, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area.

[0010] In a second aspect of the present invention, an air quality prediction and optimization system based on deep learning is provided, and the system specifically includes: a data acquisition and analysis module, a prediction model construction module, a prediction model correction module, an air quality prediction and optimization module and a terminal display module.

[0011] The data collection and analysis module is used to obtain concentration data, meteorological data and fire characteristic data of various types of pollutants at various collection points in the fire area during the monitoring period, obtain geographical environment data of the fire area, and calculate the atmospheric stability coefficient and building density coefficient of the fire area.

[0012] The prediction model building module is used to build a prediction model for the concentration of various types of pollutants in the fire area according to the building density coefficient and the atmospheric stability coefficient of the fire area.

[0013] The prediction model correction module is used to obtain various monitoring data of the fire area collected from various historical fires, and to correct the prediction model of the concentration of various types of pollutants in the fire area.

[0014] The air quality prediction and optimization module is used to obtain the concentration data of various types of pollutants at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, divide the risk areas into different levels of air quality, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area.

[0015] The terminal display module is used to display the air quality compliance level of each judgment area and the air quality optimization measures of each judgment area.

[0016] Compared with the prior art, the benefits of the present invention are as follows: 1. The present invention constructs a prediction model for the concentration of various types of pollutants in the fire area by analyzing the building density and atmospheric stability coefficient in the fire area, fully considering the impact of meteorological data and geographical environment data on the diffusion movement of pollutants in the fire area, and improving the reliability of the actual scene application of the prediction model for the concentration of various types of pollutants.

[0017] 2. The present invention uses the monitoring data of the fire area collected from various historical fires, and adopts the idea of ​​deep learning to train the prediction model of the concentration of various types of pollutants, so as to obtain the revised prediction model of the concentration of various types of pollutants in the fire area, thereby achieving the accuracy of the prediction model of the concentration of various types of pollutants, and providing data support for the subsequent optimization processing of air quality in risk areas with different levels of air quality.

[0018] 3. The present invention adopts the technical means of zoning to analyze the air quality risk coefficients of different judgment areas, so as to determine the risk levels of different judgment areas, and realize the analysis and optimization of air quality in risk areas with different air quality levels, thereby ensuring the effect of the optimization processing and saving resources at the same time, reflecting the practicality and scientificity of the air quality prediction and optimization system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0021] Figure 2 It is a system structure connection diagram of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] For ease of understanding, some professional terms involved in the present invention are explained below: Satellite remote sensing technology refers to the technology of remotely detecting the ground, ocean, atmosphere, etc. and collecting various data through sensors carried on satellites, such as optical, infrared, radar and other sensors. These data are usually used in many fields such as environmental monitoring, natural disaster assessment, climate research, resource exploration, urban planning, etc.

[0024] Deep learning refers to the ability to automatically learn features in data through large-scale data and powerful computing power without the need to manually design features.

[0025] The vertical temperature change index is an important indicator used in meteorology to describe the change of temperature in the atmosphere with altitude. It indicates the rate of change of temperature in the atmosphere with altitude and is used to assess atmospheric stability.

[0026] Wind shear index refers to an indicator used to measure the degree of change of wind speed with height, that is, the speed at which wind speed changes with height, which is used to assess atmospheric stability.

[0027] The lateral diffusion coefficient refers to a statistic of the degree of diffusion of a substance in a fluid along the lateral direction, which is affected by the building density and atmospheric stability.

[0028] The vertical diffusion coefficient refers to a statistic of the degree of vertical diffusion of a substance in a fluid, which is affected by building density and atmospheric stability.

[0029] Combustion intensity refers to an important parameter used to quantify the intensity or heat release rate of the combustion process, which helps describe the speed and efficiency of heat release during the combustion process.

[0030] Embodiment 1 Reference Figure 1 As shown, in the first aspect of the present invention, a deep learning-based air quality prediction and optimization method is provided, and the method comprises: step one, collecting and analyzing various monitoring data of the fire area: obtaining concentration data of various types of pollutants, meteorological data, and fire characteristic data of each collection point in the fire area within the monitoring period, calculating the atmospheric stability coefficient of the fire area, obtaining various geographical environment data of the fire area, and calculating the building density coefficient of the fire area.

[0031] Step 2: Construct a pollutant concentration prediction model: Calculate the emission rate of various types of pollutants, and construct a prediction model for the concentration of various types of pollutants in the fire area based on the building density coefficient and the atmospheric stability coefficient of the fire area.

[0032] Step 3: Revise the pollutant concentration prediction model: obtain the monitoring data of the fire area collected from each historical fire, and revise the prediction model of the concentration of various types of pollutants in the fire area.

[0033] Step 4. Predict and optimize the air quality in the fire area: Based on the revised prediction model for the concentration of each type of pollutant, obtain the concentration data of each type of pollutant at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, construct the judgment area and divide the air quality risk level of the judgment area, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area.

[0034] In a specific embodiment of the present invention, the specific analysis method for calculating the building density coefficient of the fire area is as follows: taking the center point of the fire area as the center of the circle, Construct an analysis area for the radius and extract a planar geographic feature image of the analysis area from the database, where Represents the radius of the preset analysis area extracted from the database.

[0035] Based on the planar geographic feature images of the analysis area, the plane outlines of each building are extracted, and the actual area and size of each building in the analysis area are obtained through computer image processing technology. .

[0036] It should be noted that, in a specific embodiment, the specific analysis method for obtaining the actual floor area and the total floor area of ​​each building in the analysis area is: based on the plane feature image of the analysis area, the feature area blocks of each building are automatically identified by computer deep learning technology, and the total number of pixels of the feature area blocks of each building is counted. , based on the area of ​​each pixel , through the formula: , calculate the area of ​​the characteristic area block of the building in the plane characteristic image of the analysis area , obtain the enlargement ratio of the plane feature image of the analysis area obtained by satellite remote sensing technology , through the formula: , calculate the actual floor space and .

[0037] By formula: , calculate the building density coefficient ,in Represents pi.

[0038] In a specific embodiment of the present invention, the atmospheric stability coefficient of the fire area is calculated by a specific analysis method: based on the meteorological data of each collection point in the fire area during the monitoring period, the meteorological data include: the temperature at each height , wind speed at each height ,in Indicates the temperature of each collection point in the fire area, represents the wind speed at each collection point in the fire area, Indicates the height of each collection point in the fire area, , Indicates the number of each collection point in the fire area, Represents the total number of collection points in the fire area.

[0039] It should be noted that, in a specific embodiment, the acquisition points are different coordinates in a three-dimensional spatial coordinate system.

[0040] It should be noted that, in a specific embodiment, the temperature at different heights and the wind speed at different heights are determined by considering the temperature and wind speed at different coordinates on the Z axis when the x-axis and y-axis coordinates are determined. The height collection points are set in a discrete form by setting the height growth scale of the collection points. For example, the height growth scale is 2 meters, and the temperature is collected by a temperature sensor at positions of 0, 2, 4, 6 on the Z axis height, and the wind speed is collected by a wind speed sensor.

[0041] By formula: , calculate the vertical temperature transformation index , through the formula: , the wind speed shear index is calculated .

[0042] By formula: , the atmospheric stability coefficient is calculated ,in represents the standard vertical temperature variation index extracted from the database, Represents the standard wind speed shear index extracted from the database.

[0043] In a specific embodiment of the present invention, the prediction model for the concentration of various types of pollutants in the fire area is constructed, and its specific analysis method is as follows: the wind direction of the fire area is obtained by a wind direction sensor, and a three-dimensional spatial coordinate system is established with the center point of the fire area as the coordinate origin, the vertical direction as the Z axis, the wind direction of the fire area as the X axis, and the direction horizontally and perpendicular to the X axis as the Y axis.

[0044] Using the Gaussian gas diffusion model: , we get the prediction model of the concentration of various types of pollutants in the fire area, where Represents the emission rate of each type of pollutant, Indicates at the collection point The wind speed at Indicates Types of pollutants at the collection point The concentration at represents the diffusion coefficient of pollutants in the lateral direction, represents the diffusion coefficient of pollutants in the vertical direction, represents a natural constant, ,in The numbers representing the types of pollutants. Indicates the total number of pollutant types.

[0045] Through satellite remote sensing monitoring technology, the burning intensity of the fire area is obtained. , through the formula: , calculate the emission rate of each type of pollutant ,in Represents the emission factors of each type of pollutant extracted from the database.

[0046] It should be noted that, in a specific embodiment, the emission factor of each type of pollutant refers to the emission amount of a certain type of pollutant generated per unit time.

[0047] By formula: , the lateral diffusion coefficient of the pollutant is calculated, where Represents the correction factor in the horizontal direction.

[0048] By formula: , the diffusion coefficient of pollutants in the vertical direction is calculated, where Represents the correction factor in the vertical direction.

[0049] It should be noted that, in a specific embodiment, the diffusion coefficient of the pollutant in the lateral direction and the diffusion coefficient in the vertical direction are affected by the building density coefficient and the atmospheric stability coefficient.

[0050] The present invention constructs a prediction model for the concentration of various types of pollutants in the fire area by analyzing the building density and atmospheric stability coefficient in the fire area, fully considering the influence of meteorological data and geographical environment data on the diffusion movement of pollutants in the fire area, and improving the reliability of the actual scene application of the prediction model for the concentration of various types of pollutants.

[0051] In a specific embodiment of the present invention, the prediction model for the concentration of various types of pollutants in the fire area is corrected, and its specific analysis method is as follows: various monitoring data of the fire area collected from various historical fires are extracted from the database, and first the emission rate of various types of pollutants collected from the first historical fire, the concentration of various types of pollutants at each collection point and the wind speed at each collection point are substituted into the prediction model for the concentration of various types of pollutants in the fire area, and the lateral diffusion coefficient and the vertical diffusion coefficient of each collection point of the first historical fire are obtained.

[0052] The atmospheric stability coefficient and building density coefficient of the fire area collected from the first fire in history are substituted into the lateral diffusion coefficient of each collection point of the first fire in history to obtain the correction factor of the lateral diffusion coefficient of each collection point of the first fire in history. The correction factors of the lateral diffusion coefficient of each collection point of the first fire in history are averaged, and the average result is used as the correction factor of the lateral diffusion coefficient of the first fire in history.

[0053] According to the calculation method of the correction factor of the lateral diffusion coefficient of the first fire in history, the correction factors of the lateral diffusion coefficient of each fire in history are obtained, and the correction factors of the lateral diffusion coefficient of each fire in history are averaged to obtain the correction factors of the lateral diffusion coefficient.

[0054] The correction factor of the diffusion coefficient in the vertical direction is processed according to the calculation method of the correction factor of the diffusion coefficient in the horizontal direction to obtain the correction factor of the diffusion coefficient in the vertical direction.

[0055] Substituting the correction factor of the diffusion coefficient in the lateral direction and the correction factor of the diffusion coefficient in the vertical direction into the prediction model of the concentration of each type of pollutant in the fire area, a corrected prediction model of the concentration of each type of pollutant in the fire area is obtained.

[0056] The present invention adopts the monitoring data of the fire area collected from various historical fires and the idea of ​​deep learning to train the prediction model of the concentration of various types of pollutants, so as to obtain the revised prediction model of the concentration of various types of pollutants in the fire area, thereby achieving the accuracy of the prediction model of the concentration of various types of pollutants, and providing data support for the subsequent optimization processing of air quality in risk areas with different levels of air quality.

[0057] In a specific embodiment of the present invention, the concentration data of each type of pollutant at each monitoring point in the judgment area is obtained, and the specific analysis method is: extracting the judgment radius from the database , with the coordinate origin as the center and the xy axis as the plane, a judgment area is constructed, and the coordinates of each monitoring point are obtained by using a uniformly distributed random number generation technique within the judgment area. , , Indicates the number of each monitoring point. Indicates the total number of monitoring points.

[0058] It should be noted that, in a specific embodiment, the specific analysis method for obtaining the coordinates of each monitoring point is: by using a uniformly distributed random number generation technology, randomly generate the coordinates on the x-axis and y-axis in the judgment area, and it is necessary to ensure that the range of the generated x-axis and y-axis coordinates does not exceed , using random number generation technology to obtain the coordinates of the z-axis, it is necessary to ensure that the range of the obtained z-axis coordinates does not exceed the judgment radius .

[0059] The combustion intensity of the fire area is obtained through satellite remote sensing, the emission rate of various types of pollutants is calculated, and the wind speed at each monitoring point is obtained through wind speed detection sensors.

[0060] Substitute the coordinates of each monitoring point, the wind speed of each monitoring point and the emission rate of each type of pollutant into the revised prediction model of each type of pollutant concentration to obtain the predicted concentration of each type of pollutant at each monitoring point in the judgment area. .

[0061] In a specific embodiment of the present invention, the air quality risk coefficient of each monitoring point in the calculation judgment area is specifically analyzed by: based on the predicted concentration of each type of pollutant at each monitoring point in the judgment area , through the formula: , calculate the abnormal judgment value of the predicted concentration of each type of pollutant at each monitoring point in the judgment area ,in The standard interval of concentration of each type of pollutant extracted from the database is expressed by the formula: , calculate the air quality risk coefficient of each monitoring point in the judgment area .

[0062] In a specific embodiment of the present invention, the specific analysis method of dividing the air quality risk level of the judgment area is: based on the air quality risk coefficient of each monitoring point in the judgment area, Each monitoring point is recorded as an abnormal monitoring point, and the number of abnormal monitoring points is obtained by counting ,in Represents the judgment threshold of the air quality risk factor extracted from the database, through the formula: , calculate the non-compliance rate of air quality in the judgment area ,like , the judgment area is divided into the first-level air quality risk area.

[0063] like , the judgment area will be divided into the secondary air quality risk area.

[0064] like , the judgment area is divided into three levels of air quality risk areas, among which Represents the air quality first-level risk area judgment threshold extracted from the database, represents the judgment threshold of the third-level air quality risk area extracted from the database, and the The air quality compliance level of the judgment area is determined by the radius.

[0065] It should be noted that, in a specific embodiment, the division of the air quality risk areas at various levels is manually set by technical personnel based on a comprehensive analysis of the impact of the actual air quality coefficient of each area on the human body and the ecosystem, and is stored in a database.

[0066] Extract the radius growth scale from the database ,by As the radius, the coordinate origin is the center of the circle, and we get To determine the radius of the judgment area and The non-intersecting parts of the circle with a radius of 1 constitute a new judgment area, and the operation of dividing the air quality risk level in the judgment area is performed.

[0067] Growth scale Increase the judgment radius to obtain a new judgment area, perform the operation of dividing the air quality risk level in the judgment area, and obtain risk areas with different air quality levels.

[0068] It should be noted that, in a specific embodiment, the judgment radius increases sequentially, but does not exceed the judgment radius threshold of the preset value extracted from the database. For example, the judgment radius that increases in sequence shall not exceed rice.

[0069] In a specific embodiment of the present invention, the air quality optimization measures corresponding to the air quality risk level of the implementation judgment area are specifically analyzed by: extracting the coverage area of ​​each level of mobile air purifier from the database ,in , A number indicating each level of mobile air purifier.

[0070] It should be noted that, in a specific embodiment, the strength levels of the mobile air purifiers are sequentially reduced according to their numbers.

[0071] The optimization measures for the first-level air quality risk area are: select the first-level mobile air purifiers, extract the area of ​​the first-level air quality risk area , through the formula: , calculate the distribution number of mobile air purifiers of the first level in the air quality level 1 risk area ,in represents the rounding up function, then in the first-level air quality risk area, First-class mobile air purifiers are deployed to optimize air quality.

[0072] It should be noted that, in a specific embodiment, the specific analysis method for extracting the area of ​​the first-level air quality risk area is: if the judgment radius of the judgment area is the initial , then the area of ​​the first-level air quality risk area is , if the judgment radius of the judgment area is increased, then the formula is: , and calculate the area of ​​the first-level air quality risk zone.

[0073] According to the analysis method of optimization measures for air quality level 1 risk areas, air quality level 2 risk areas and level 3 risk areas are processed to obtain optimization measures for air quality level 2 risk areas and level 3 risk areas.

[0074] The optimization measures for the air quality level 1 risk areas, level 2 risk areas and level 3 risk areas constitute the air quality optimization measures corresponding to the air quality risk level of the judgment area.

[0075] Embodiment 2 Reference Figure 2 As shown, in the second aspect of the present invention, there is provided an air quality prediction and optimization system based on deep learning, the system comprising: a data acquisition and analysis module, a prediction model construction module, a prediction model correction module, an air quality prediction and optimization module, a terminal display module and a database: the data acquisition and analysis module is used to obtain the concentration data, meteorological data and fire characteristic data of various types of pollutants at each collection point in the fire area within the monitoring period, obtain the geographical environment data of the fire area, and calculate the atmospheric stability coefficient and building density coefficient of the fire area.

[0076] The prediction model building module is used to build a prediction model for the concentration of various types of pollutants in the fire area according to the building density coefficient and the atmospheric stability coefficient of the fire area.

[0077] The prediction model correction module is used to obtain various monitoring data of the fire area collected from various historical fires, and to correct the prediction model of the concentration of various types of pollutants in the fire area.

[0078] The air quality prediction and optimization module is used to obtain the concentration data of various types of pollutants at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, divide the risk areas into different levels of air quality, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area.

[0079] The terminal display module is used to display the air quality compliance level of each judgment area and the air quality optimization measures of each judgment area.

[0080] The database is used to store planar geographic feature images of the analysis area, store standard vertical temperature change index, standard wind speed shear index, store emission factors of various types of pollutants, fire duration, store standard ranges of concentrations of various types of pollutants, store judgment thresholds of air quality risk coefficients, store judgment thresholds of air quality first-level risk areas, store judgment thresholds of air quality third-level risk areas, store judgment radius, and judgment radius growth scale.

[0081] It should be noted that in a specific embodiment, in an air quality prediction and optimization system based on deep learning, the data acquisition and analysis module is connected to the prediction model construction model, the prediction model construction module is connected to the prediction model correction module, the prediction model correction module is connected to the air quality prediction and optimization module, the air quality prediction and optimization module is connected to the terminal display module, and the database is connected to the data acquisition and analysis module, the prediction model construction module, the prediction model correction module and the air quality prediction and optimization module.

[0082] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A deep learning-based air quality prediction and optimization method, characterized in that: The method comprises: Step 1: Collect and analyze various monitoring data of the fire area: obtain the concentration data of various types of pollutants, meteorological data, and fire characteristics data of each collection point in the fire area during the monitoring period, calculate the atmospheric stability coefficient of the fire area, obtain the geographical environment data of the fire area, and calculate the building density coefficient of the fire area; Step 2: Construct a pollutant concentration prediction model: Calculate the emission rate of various types of pollutants, and construct a prediction model for the concentration of various types of pollutants in the fire area based on the building density coefficient and the atmospheric stability coefficient of the fire area; Step 3: Correct the pollutant concentration prediction model: obtain the monitoring data of the fire area collected from each historical fire, and correct the prediction model of the concentration of each type of pollutant in the fire area; Step 4. Predict and optimize the air quality in the fire area: Based on the revised prediction model for the concentration of each type of pollutant, obtain the concentration data of each type of pollutant at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, construct the judgment area and divide the air quality risk level of the judgment area, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area.

2. The air quality prediction optimization method based on deep learning according to claim 1, characterized in that: The specific analysis method for calculating the building density coefficient of the fire area is as follows: With the center of the fire area as the center of the circle, Construct an analysis area for the radius and extract a planar geographic feature image of the analysis area from the database, where represents the radius of the preset analysis area extracted from the database; Based on the planar geographic feature images of the analysis area, the plane outlines of each building are extracted, and the actual area and size of each building in the analysis area are obtained through computer image processing technology. ; By formula: , calculate the building density coefficient ,in Represents pi.

3. The air quality prediction optimization method based on deep learning according to claim 2 is characterized in that: The specific analysis method for calculating the atmospheric stability coefficient of the fire area is as follows: Based on the meteorological data of each collection point in the fire area during the monitoring period, the meteorological data include: temperature at each height , wind speed at each height ,in Indicates the temperature of each collection point in the fire area, represents the wind speed at each collection point in the fire area, Indicates the height of each collection point in the fire area, , Indicates the number of each collection point in the fire area, Represents the total number of collection points in the fire area; By formula: , the vertical temperature transformation index is calculated , through the formula: , the wind speed shear index is calculated ; By formula: , the atmospheric stability coefficient is calculated ,in represents the standard vertical temperature variation index extracted from the database, Represents the standard wind speed shear index extracted from the database.

4. The air quality prediction and optimization method based on deep learning according to claim 3 is characterized in that: The prediction model for the concentration of various types of pollutants in the fire area is constructed, and the specific analysis method is as follows: The wind direction of the fire area is obtained through the wind direction sensor, and a three-dimensional spatial coordinate system is established with the center point of the fire area as the coordinate origin, the vertical direction as the Z axis, the wind direction of the fire area as the X axis, and the direction perpendicular to the X axis as the Y axis; Using the Gaussian gas diffusion model: , we get the prediction model of the concentration of various types of pollutants in the fire area, where Represents the emission rate of each type of pollutant, Indicates at the collection point The wind speed at Indicates Types of pollutants at the collection point The concentration at represents the diffusion coefficient of pollutants in the lateral direction, represents the diffusion coefficient of pollutants in the vertical direction, represents a natural constant, ,in The numbers representing the types of pollutants. Indicates the total number of pollutant types; Through satellite remote sensing monitoring technology, the burning intensity of the fire area is obtained. , through the formula: , calculate the emission rate of each type of pollutant ,in It represents the emission factors of each type of pollutant extracted from the database; By formula: , the lateral diffusion coefficient of the pollutant is calculated, where represents the correction factor in the lateral direction; By formula: , the diffusion coefficient of pollutants in the vertical direction is calculated, where Represents the correction factor in the vertical direction.

5. The air quality prediction and optimization method based on deep learning according to claim 4 is characterized in that: The specific analysis method for correcting the prediction model of the concentration of various types of pollutants in the fire area is as follows: The monitoring data of the fire area collected from each historical fire are extracted from the database. First, the emission rate of each type of pollutant collected from the first historical fire, the concentration of each type of pollutant at each collection point and the wind speed at each collection point are substituted into the prediction model of the concentration of each type of pollutant in the fire area to obtain the horizontal diffusion coefficient and the vertical diffusion coefficient of each collection point of the first historical fire. Substitute the atmospheric stability coefficient and building density coefficient of the fire area collected during the first fire in history into the lateral diffusion coefficient of each collection point of the first fire in history, obtain the correction factor of the lateral diffusion coefficient of each collection point of the first fire in history, average the correction factors of the lateral diffusion coefficient of each collection point of the first fire in history, and use the average result as the correction factor of the lateral diffusion coefficient of the first fire in history; According to the calculation method of the correction factor of the horizontal diffusion coefficient of the first fire in history, the correction factors of the horizontal diffusion coefficient of each fire in history are obtained, and the correction factors of the horizontal diffusion coefficient of each fire in history are averaged to obtain the correction factors of the horizontal diffusion coefficient; The correction factor of the diffusion coefficient in the vertical direction is processed according to the calculation method of the correction factor of the diffusion coefficient in the horizontal direction to obtain the correction factor of the diffusion coefficient in the vertical direction; Substituting the correction factor of the diffusion coefficient in the lateral direction and the correction factor of the diffusion coefficient in the vertical direction into the prediction model of the concentration of each type of pollutant in the fire area, a corrected prediction model of the concentration of each type of pollutant in the fire area is obtained.

6. The air quality prediction and optimization method based on deep learning according to claim 5, characterized in that: The concentration data of each type of pollutant at each monitoring point in the determination area are obtained, and the specific analysis method is as follows: Extract the judgment radius from the database , with the origin of the coordinate as the center of the circle and the xy axis as the plane, a judgment area is constructed, and the coordinates of each monitoring point are obtained by using a uniformly distributed random number generation technique within the judgment area. , , Indicates the number of each monitoring point. Indicates the total number of monitoring points; The burning intensity of the fire area is obtained through satellite remote sensing, the emission rate of various types of pollutants is calculated, and the wind speed at each monitoring point is obtained through wind speed detection sensors; Substitute the coordinates of each monitoring point, the wind speed of each monitoring point and the emission rate of each type of pollutant into the revised prediction model of each type of pollutant concentration to obtain the predicted concentration of each type of pollutant at each monitoring point in the judgment area. .

7. The air quality prediction and optimization method based on deep learning according to claim 6 is characterized in that: The specific analysis method of calculating and judging the air quality risk coefficient of each monitoring point in the area is as follows: Based on the predicted concentration of each type of pollutant at each monitoring point in the judgment area , through the formula: , calculate the abnormal judgment value of the predicted concentration of each type of pollutant at each monitoring point in the judgment area ,in The standard interval of concentration of each type of pollutant extracted from the database is expressed by the formula: , calculate the air quality risk coefficient of each monitoring point in the judgment area .

8. The air quality prediction and optimization method based on deep learning according to claim 7, characterized in that: The specific analysis method for the air quality risk level of the division and judgment area is as follows: Based on the air quality risk factor of each monitoring point in the judgment area, Each monitoring point is recorded as an abnormal monitoring point, and the number of abnormal monitoring points is obtained by counting ,in Represents the judgment threshold of the air quality risk factor extracted from the database, through the formula: , calculate the non-compliance rate of air quality in the judgment area ,like , the judgment area is divided into the first-level air quality risk area; like , then the judgment area is divided into the secondary air quality risk area; like , the judgment area is divided into three levels of air quality risk areas, among which Represents the air quality first-level risk area judgment threshold extracted from the database, represents the judgment threshold of the third-level air quality risk area extracted from the database, and the To determine the air quality compliance level in the radius judgment area; Extract the radius growth scale from the database ,by As the radius, the coordinate origin is the center of the circle, and we get To determine the radius of the judgment area and The non-intersecting parts of the circle with the radius of the new judgment area are used to perform the air quality risk level classification operation in the judgment area; Growth scale Increase the judgment radius to obtain a new judgment area, perform the operation of dividing the air quality risk level in the judgment area, and obtain risk areas with different air quality levels.

9. The air quality prediction and optimization method based on deep learning according to claim 8, characterized in that: The specific analysis method of the air quality optimization measures corresponding to the air quality risk level of the implementation judgment area is as follows: Extract the coverage area of ​​mobile air purifiers of various levels from the database ,in , Indicates the number of each level of mobile air purifier; The optimization measures for the first-level air quality risk area are: select the first-level mobile air purifiers, extract the area of ​​the first-level air quality risk area , through the formula: , calculate the distribution number of mobile air purifiers of the first level in the air quality level 1 risk area ,in represents the rounding up function, then in the first-level air quality risk area, First-class mobile air purifiers are deployed to optimize air quality; According to the analysis method of optimization measures for air quality level 1 risk areas, the air quality level 2 risk areas and level 3 risk areas are processed to obtain optimization measures for air quality level 2 risk areas and level 3 risk areas; The optimization measures for the air quality level 1 risk areas, level 2 risk areas and level 3 risk areas constitute the air quality optimization measures corresponding to the air quality risk level of the judgment area.

10. A system for executing the air quality prediction optimization method based on deep learning according to any one of claims 1 to 9, characterized in that: The system comprises: The data collection and analysis module is used to obtain the concentration data of various types of pollutants, meteorological data and fire characteristics data of each collection point in the fire area during the monitoring period, obtain the geographical environment data of the fire area, and calculate the atmospheric stability coefficient and building density coefficient of the fire area; A prediction model building module is used to build a prediction model for the concentration of various types of pollutants in the fire area based on the building density coefficient and the atmospheric stability coefficient; The prediction model correction module is used to obtain the monitoring data of the fire area collected from each historical fire and correct the prediction model of the concentration of various types of pollutants in the fire area; The air quality prediction and optimization module is used to obtain the concentration data of various types of pollutants at each monitoring point in the judgment area, calculate the air quality risk coefficient of each monitoring point in the judgment area, divide the risk areas of different air quality levels, and implement air quality optimization measures corresponding to the air quality risk level of the judgment area; The terminal display module is used to display the air quality compliance level of each judgment area and the air quality optimization measures of each judgment area.

Images