Method and system for predicting and evaluating spatial and temporal distribution of atmospheric pollutant concentration in park
Through deep learning technology combined with meteorological simulation and air quality model, the problem of lack of timely analysis and analysis in the prevention and control of atmospheric environmental pollution in the park is solved, and accurate prediction of the spatiotemporal distribution characteristics of pollutants is achieved, and the effect of pollution prevention and control is improved.
Patent Information
- Application Number
- CN202411987140.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-05-27
AI Technical Summary
The existing technology lacks timely analysis and prevention management in the prevention and control of atmospheric environmental pollution in the park, making it difficult to achieve targeted pre-control work, and the impact of meteorological fields on the diffusion of pollutants has not been fully considered.
Deep learning technology is used to combine meteorological simulation and air quality model to construct spatial and temporal distribution prediction and evaluation methods for atmospheric pollutant concentration in the park, and improve prediction accuracy through the fusion and optimization of multi-source data.
Accurate prediction of the spatial and temporal distribution characteristics of air pollutants in the park has been achieved, providing strong support for the park's air quality assessment and pollution prevention and control, dynamically adjusting the model to improve prediction performance, and helping to formulate effective environmental protection policies and response measures.
Smart Images
Figure CN120046770A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of prevention and control of atmospheric environmental pollution in industrial parks, and specifically to a method and system for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in a park. Background Art
[0002] The prediction of the spatio-temporal distribution characteristics of atmospheric environmental pollutants in a park is crucial for the prevention and control of atmospheric pollution in the park. In the past, the governance work of the atmospheric environment in the park was mostly based on the historical over-standard degree, lacking timely research and judgment analysis and preventive management, so it was difficult to achieve targeted pre-treatment work.
[0003] With the progress of science and technology, information technologies such as the Internet of Things and artificial intelligence have been applied to the process of atmospheric environment management in the park. Among them, the Internet of Things technology can be used to store and manage various pollutant indicators in the park, and the artificial intelligence technology can analyze the distribution, characteristics and trends of pollutants. However, as an external factor, the meteorological field has a certain impact on the diffusion of pollutants, and it is necessary to pay attention to the meteorological field factors when using the deep learning technology in artificial intelligence to carry out the concentration of atmospheric pollutants.
[0004] In addition, the prediction effect of the spatio-temporal distribution characteristics of atmospheric pollutant concentrations depends on the lag of the observed data. It is of certain guiding significance to carry out the simulation of the diffusion analysis of pollutant concentrations in the park by using an air quality model such as CALPUFF. To better carry out the prediction and evaluation of the spatio-temporal distribution of atmospheric pollutant concentrations in the park, it is urgent to construct a technical method system integrating deep learning and numerical models. Summary of the Invention
[0005] In view of this, the present invention provides a method and system for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in a park, aiming to use deep learning technology to carry out the prediction of the spatio-temporal distribution concentration of atmospheric environmental pollutants in the park, and evaluate the prediction effect through a numerical model, so as to provide effective decision-making support for the later prevention and control of atmospheric environmental pollution in the park.
[0006] According to the first aspect of the embodiments of the present invention, a method for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in a park is provided, including: collecting the original data set of the park through each atmospheric environmental quality observation station, and constructing a spatio-temporal distribution feature map of the atmospheric environmental quality in the park according to the site locations of each atmospheric environmental quality observation station; constructing a meteorological numerical model based on the original data set, performing parametric sensitivity analysis based on the meteorological numerical model, and generating meteorological field data as the meteorological simulation results of the park; constructing a deep learning algorithm based on the meteorological simulation results of the park and the original data set, performing atmospheric environmental pollutant prediction based on the deep learning algorithm, and obtaining the spatio-temporal distribution prediction results of the atmospheric environmental pollutant concentrations; constructing an air quality model based on the meteorological simulation results of the park and the original data set, performing air quality simulation based on the air quality model, and obtaining the spatio-temporal distribution feature simulation results of the air quality; combining the spatio-temporal distribution feature map of the atmospheric environmental quality in the park, comparing and analyzing the spatio-temporal distribution prediction results of the atmospheric environmental pollutant concentrations and the spatio-temporal distribution feature simulation results of the air quality, and optimizing the deep learning algorithm and the air quality model by combining the comparison and analysis results with the new observation data obtained by each atmospheric environmental quality observation station to improve the prediction performance of the spatio-temporal distribution of the atmospheric environmental pollutant concentrations.
[0007] In one implementation, the original data set includes background station observation data, air quality observation data, pollution source emission data, and other data within the park, and the other data includes terrain data and land use type data.
[0008] In another implementation, constructing a deep learning algorithm based on the meteorological simulation results of the park and the original data set includes: cleaning the air quality observation data in the original data to obtain the cleaned air quality observation data; fusing the cleaned air quality observation data and the meteorological field data to obtain the fused data; constructing a deep learning algorithm according to the fused data to perform atmospheric environmental pollutant prediction.
[0009] In another implementation, constructing an air quality model based on the meteorological simulation results of the park and the original data set includes: converting the data format of the meteorological simulation results of the park to obtain the park meteorological simulation results with the format converted; constructing an air quality model according to the park meteorological simulation results with the format converted and the made model inventory file.
[0010] In another implementation, the model inventory file includes an emission inventory, a terrain data inventory, and a land use type data inventory, where the emission inventory is obtained according to the pollution source emission data, the terrain data inventory is obtained according to the terrain data, and the land use type data inventory is obtained according to the land use type data.
[0011] In another implementation, the air quality model adopts the CALPUFF model.
[0012] In another implementation, the meteorological numerical model adopts the WRF model.
[0013] According to the second aspect of the embodiments of the present invention, a system for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in a park is provided, including: a collection module for collecting an original data set of the park through each atmospheric environmental quality observation station and constructing a spatio-temporal distribution feature map of the atmospheric environmental quality in the park according to the site locations of each atmospheric environmental quality observation station; a meteorological numerical model module for constructing a meteorological numerical model based on the original data set, performing parametric sensitivity analysis based on the meteorological numerical model, and generating meteorological field data as the meteorological simulation result of the park; a deep learning algorithm module for constructing a deep learning algorithm based on the meteorological simulation result and the original data set of the park, and performing atmospheric environmental pollutant prediction based on the deep learning algorithm to obtain a spatio-temporal distribution prediction result of the atmospheric environmental pollutant concentration; an air quality model module for constructing an air quality model based on the meteorological simulation result and the original data set of the park, and performing air quality simulation based on the air quality model to obtain a spatio-temporal distribution feature simulation result of the air quality; a comparative analysis and optimization module for combining the spatio-temporal distribution feature map of the atmospheric environmental quality in the park, comparing and analyzing the spatio-temporal distribution prediction result of the atmospheric environmental pollutant concentration and the spatio-temporal distribution feature simulation result of the air quality, and optimizing the deep learning algorithm and the air quality model by combining the comparative analysis result with new observation data obtained by each atmospheric environmental quality observation station to improve the spatio-temporal distribution prediction performance of the atmospheric environmental pollutant concentration.
[0014] According to the third aspect of the embodiments of the present invention, an electronic device is provided, including a processor and a memory storing a program. Among them, the program includes instructions that, when executed by the processor, cause the processor to execute the steps performed by the method in the first aspect as described above.
[0015] According to the fourth aspect of the embodiments of the present invention, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, it implements the method in the first aspect as described above.
[0016] In summary, by combining meteorological simulation, deep learning algorithms, and air quality models, the present invention can accurately predict the spatio-temporal distribution characteristics of atmospheric pollutants in the park, providing strong support for air quality assessment and pollution prevention and control in the park. Through the fusion and optimization of multi-source data, the prediction accuracy is improved, the model can be dynamically adjusted, the prediction performance of atmospheric pollutant concentrations is enhanced, and it helps the park formulate effective environmental protection policies and response measures, thereby realizing real-time monitoring and optimized management of environmental quality. Description of the Drawings
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.
[0018] Figure 1 It is a step flow chart of the method for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in the park of the present invention.
[0019] Figure 2 For Figure 1 The specific flow chart of the method for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in the park of the present invention corresponding to. Specific implementation manners
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.
[0021] See Figure 1 、 2 The main steps of the method for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in the park of the present invention include:
[0022] S1. Collect the original data set of the park through each atmospheric environmental quality observation station, and construct a spatio-temporal distribution feature map of the atmospheric environmental quality in the park according to the site locations of each atmospheric environmental quality observation station;
[0023] S2. Construct a meteorological numerical model based on the original data set, perform parametric sensitivity analysis based on the meteorological numerical model, and generate meteorological field data as the meteorological simulation result of the park;
[0024] S3. Construct a deep learning algorithm based on the meteorological simulation result of the park and the original data set, perform atmospheric environmental pollutant prediction based on the deep learning algorithm, and obtain the spatio-temporal distribution prediction result of the atmospheric environmental pollutant concentration;
[0025] S4. Construct an air quality model based on the meteorological simulation result of the park and the original data set, perform air quality simulation based on the air quality model, and obtain the spatio-temporal distribution feature simulation result of the air quality;
[0026] S5. Combine with the spatio-temporal distribution characteristic map of the atmospheric environment quality in the park, compare and analyze the spatio-temporal distribution prediction results of atmospheric environment pollutant concentrations and the simulation results of the spatio-temporal distribution characteristics of air quality, and optimize the deep learning algorithm and air quality model by combining the comparison and analysis results with the new observation data obtained from each atmospheric environment quality observation station to improve the spatio-temporal distribution prediction performance of atmospheric environment pollutant concentrations.
[0027] Optionally, the original data set includes background station observation data, air quality observation data, pollution source emission data, and other data within the park area. The other data includes terrain data and land use type data.
[0028] Optionally, based on the park meteorological simulation results and the original data set, construct a deep learning algorithm, including: cleaning the air quality observation data in the original data to obtain the cleaned air quality observation data; fusing the cleaned air quality observation data and the meteorological field data to obtain fused data; constructing a deep learning algorithm based on the fused data to predict atmospheric environment pollutants.
[0029] Optionally, based on the park meteorological simulation results and the original data set, construct an air quality model, including: converting the data format of the park meteorological simulation results to obtain the park meteorological simulation results with the format converted; constructing an air quality model based on the park meteorological simulation results with the format converted and the prepared model inventory file.
[0030] Optionally, the model inventory file includes an emission inventory, a terrain data inventory, and a land use type data inventory. The emission inventory is obtained from the pollution source emission data, the terrain data inventory is obtained from the terrain data, and the land use type data inventory is obtained from the land use type data.
[0031] Optionally, the air quality model uses the CALPUFF model.
[0032] It should be understood that the CALPUFF ("California Puff") model is a three-dimensional time-resolved model for the diffusion of atmospheric pollutants, mainly used to simulate the diffusion process of aerosol and gas pollutants, especially suitable for the diffusion of pollutants under complex terrain and atmospheric boundary layer conditions, and is often used for air quality assessment, environmental impact assessment, and pollution warning.
[0033] Optionally, the meteorological numerical model uses the WRF model.
[0034] It should be understood that the WRF (Weather Research and Forecasting) model is a numerical weather prediction model widely used in weather simulation and climate research. It is a high-resolution finite difference model specifically used for short-term weather forecasting, meteorological analysis, and studying the changes of meteorological processes.
[0035] Figure 2 Among them, (1) Original dataset: mainly includes background station observation data, air quality observation data, pollution source emission data, other data, etc. within the park area. Among them, other data mainly includes topographic data, land use type data and other operation data for driving the air quality model.
[0036] (2) Prediction of atmospheric environmental pollutants: mainly includes cleaning of air observation data, fusion data generated by meteorological numerical models, and construction and prediction analysis of deep learning algorithms.
[0037] (3) Generation of meteorological field data: Using public meteorological numerical models, such as WRF, to carry out parametric sensitivity analysis to obtain the meteorological simulation results of the park, and to realize the driving work of data fusion and air quality model operation in the prediction and analysis of atmospheric environmental pollutants.
[0038] (4) Air quality model: Combining factors such as the dynamic characteristics of pollutant diffusion at the park scale, using the CALPUFF model to carry out simulation analysis of the spatio-temporal distribution characteristics of regional air quality.
[0039] (5) Prediction and evaluation of the spatio-temporal distribution of atmospheric pollutant concentrations: Comparing and analyzing the spatio-temporal distribution results of the predicted atmospheric environmental pollutants with the simulated characteristics. At the same time, combining the new observation data obtained from each observation station to carry out optimization analysis of the algorithm and model, so as to continuously improve the prediction performance of the spatio-temporal distribution of atmospheric pollutant concentrations.
[0040] A technique for predicting and evaluating the spatio-temporal distribution of atmospheric pollutant concentrations in a park provided by the present invention. First, collect air quality data at each moment by each atmospheric environmental quality observation station and store it in the database, and construct a spatio-temporal distribution characteristic map of the atmospheric environmental quality of the park through the positions of each station for analysis. Secondly, use the meteorological numerical model to further enrich the meteorological field data of the park to increase more influencing factors of the atmospheric environmental pollutants in the park. This has a crucial impact on the diffusion of atmospheric environmental pollutants in the park area and can improve the accuracy of model prediction. Then, carry out air quality numerical model analysis work through the sorted pollutant emission source data of the park. This scheme uses the CALPUFF model, which can better carry out the simulation work of the spatio-temporal distribution characteristics of atmospheric environmental pollutants at the park scale. Finally, compare and analyze the spatio-temporal distribution results of the atmospheric environmental pollutants predicted by deep learning with the results simulated by CALPUUF, and better carry out the optimization and improvement of the model to achieve better prediction of the spatio-temporal distribution characteristics of atmospheric environmental pollutants, providing more timely decision-making support for the later atmospheric environmental pollution control work in the park.
[0041] In summary, compared with the prior art, the beneficial effects of the present invention are:
[0042] By combining meteorological simulation, deep learning algorithms, and air quality models, the present invention can accurately predict the spatio-temporal distribution characteristics of atmospheric pollutants in the park, providing strong support for air quality assessment and pollution prevention in the park. Through the fusion and optimization of multi-source data, the prediction accuracy is improved, the model can be dynamically adjusted, and the prediction performance of atmospheric pollutant concentration is enhanced, helping the park formulate effective environmental protection policies and response measures, thereby realizing real-time monitoring and optimized management of environmental quality.
[0043] The embodiment of the present invention also provides a spatio-temporal distribution prediction and evaluation system for atmospheric pollutant concentration in the park, including:
[0044] A collection module, configured to collect the original data set of the park through each atmospheric environmental quality observation station, and construct a spatio-temporal distribution characteristic map of the atmospheric environmental quality in the park according to the site locations of each atmospheric environmental quality observation station;
[0045] A meteorological numerical model module, which constructs a meteorological numerical model based on the original data set, performs parametric sensitivity analysis based on the meteorological numerical model, and generates meteorological field data as the meteorological simulation result of the park;
[0046] A deep learning algorithm module, configured to construct a deep learning algorithm based on the meteorological simulation result and the original data set of the park, and perform prediction of atmospheric environmental pollutants based on the deep learning algorithm to obtain the spatio-temporal distribution prediction result of the atmospheric environmental pollutant concentration;
[0047] An air quality model module, configured to construct an air quality model based on the meteorological simulation result and the original data set of the park, and perform air quality simulation based on the air quality model to obtain the spatio-temporal distribution characteristic simulation result of the air quality;
[0048] A comparative analysis and optimization module, configured to combine the spatio-temporal distribution characteristic map of the atmospheric environmental quality in the park, compare and analyze the spatio-temporal distribution prediction result of the atmospheric environmental pollutant concentration and the spatio-temporal distribution characteristic simulation result of the air quality, and optimize the deep learning algorithm and the air quality model by combining the comparative analysis result with the new observation data obtained by each atmospheric environmental quality observation station to improve the spatio-temporal distribution prediction performance of the atmospheric environmental pollutant concentration.
[0049] It should be understood that a spatio-temporal distribution prediction and evaluation system for atmospheric pollutant concentration in the park of this embodiment is used to implement the corresponding methods in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments.
[0050] As another example, the present invention also provides an electronic device. Now, the electronic device that can be used as the server or client of the present invention will be described, which is an example of the hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.
[0051] The electronic device may include: a processor, a communications interface, a memory, and a communication bus.
[0052] The processor, the communications interface, and the memory communicate with each other through the communication bus. The communications interface is used to communicate with other electronic devices or servers.
[0053] The processor is used to execute a program, specifically, it can execute the relevant steps in the above method embodiments.
[0054] Specifically, the program may include program code, and the program code includes computer operation instructions.
[0055] The processor may be a processor CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the intelligent device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.
[0056] The memory is used to store the program. The memory may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.
[0057] When the program is executed by the processor, it is used to enable the electronic device to execute a method for predicting and evaluating the spatio-temporal distribution of the concentration of atmospheric pollutants in a park of the present invention.
[0058] In addition, for the specific implementation of each step in the program, reference may be made to the corresponding steps and descriptions in the corresponding units in the foregoing method embodiments, which will not be elaborated herein. Those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the devices and modules described above can refer to the corresponding process descriptions in the foregoing method embodiments, which will not be elaborated herein again.
[0059] An exemplary embodiment of the present invention further provides a computer storage medium storing a computer program, wherein when the computer program is executed by a processor, the methods of the embodiments of the present invention are implemented. Reference may be made to the corresponding process descriptions in the foregoing method embodiments, which will not be elaborated herein again.
[0060] The methods according to the embodiments of the present invention described above can be implemented in hardware, firmware, or be implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or be implemented as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and downloaded through a network and to be stored in a local recording medium, so that the methods described herein can be stored in such software processes on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or an FPGA). It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component (such as a RAM, a ROM, a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods described herein are implemented. In addition, when a general-purpose computer accesses the code for implementing the methods shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the methods shown herein.
[0061] So far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.
[0062] It should be understood that although this specification is described according to various embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.
[0063] Finally, it should be noted that the above embodiments are only used to illustrate the embodiments of the present invention, rather than limiting the embodiments of the present invention. Those of ordinary skill in the relevant technical field can also make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present invention, and the patent protection scope of the embodiments of the present invention shall be defined by the claims.
Claims
1. A method for predicting and evaluating the spatiotemporal distribution of atmospheric pollutant concentration in a park, characterized in that: include: The original data set of the park is collected through each air environment quality observation station, and the spatiotemporal distribution characteristic map of the park's air environment quality is constructed according to the site location of each air environment quality observation station; Build a meteorological numerical model based on the original data set, perform parameterized sensitivity analysis based on the meteorological numerical model, and generate meteorological field data as the park meteorological simulation results; Based on the park's meteorological simulation results and original data sets, a deep learning algorithm was constructed to predict atmospheric environmental pollutants and obtain the prediction results of the spatiotemporal distribution of atmospheric environmental pollutant concentrations; Based on the park's meteorological simulation results and the original data set, an air quality model is constructed, and air quality simulation is performed based on the air quality model to obtain simulation results of the spatiotemporal distribution characteristics of air quality; Combined with the spatiotemporal distribution characteristic map of the park's atmospheric environment quality, the prediction results of the spatiotemporal distribution of atmospheric pollutant concentrations and the simulation results of the spatiotemporal distribution characteristics of air quality are compared and analyzed. The comparative analysis results are combined with the new observation data obtained from each atmospheric environment quality observation station to optimize the deep learning algorithm and air quality model, so as to improve the prediction performance of the spatiotemporal distribution of atmospheric pollutant concentrations.
2. The method according to claim 1, characterized in that The original data set includes background station observation data, air quality observation data, pollution source emission data and other data within the park, including terrain data and land use type data.
3. The method according to claim 2, characterized in that Based on the park's meteorological simulation results and original data sets, a deep learning algorithm is constructed, including: Cleaning the air quality observation data in the original data to obtain cleaned air quality observation data; The cleaned air quality observation data and meteorological field data are fused to obtain fused data; A deep learning algorithm is constructed based on the fused data to predict atmospheric environmental pollutants.
4. The method according to claim 2, characterized in that: Based on the park's meteorological simulation results and original data sets, an air quality model is constructed, including: Performing data format conversion on the park meteorological simulation results to obtain the park meteorological simulation results after format conversion; An air quality model is constructed based on the format-converted park meteorological simulation results and the produced model inventory file.
5. The method according to claim 4, characterized in that The model inventory file includes an emission inventory, a terrain data inventory, and a land use type data inventory, wherein the emission inventory is obtained based on pollution source emission data, the terrain data inventory is obtained based on terrain data, and the land use type data inventory is obtained based on land use type data.
6. The method according to claim 2, characterized in that The air quality model adopts the CALPUFF model.
7. The method according to claim 2, characterized in that The meteorological numerical model adopts the WRF model.
8. A system for predicting and evaluating the spatiotemporal distribution of atmospheric pollutant concentration in a park, characterized in that: include: The collection module is used to collect the original data set of the park through each air environment quality observation station, and construct the spatiotemporal distribution characteristic map of the park's air environment quality according to the site location of each air environment quality observation station; Meteorological numerical model module, which builds a meteorological numerical model based on the original data set, performs parameterized sensitivity analysis based on the meteorological numerical model, and generates meteorological field data as the park meteorological simulation results; The deep learning algorithm module is used to build a deep learning algorithm based on the park's meteorological simulation results and the original data set, and to predict atmospheric pollutants based on the deep learning algorithm to obtain the prediction results of the spatiotemporal distribution of atmospheric pollutant concentrations; The air quality model module is used to build an air quality model based on the park's meteorological simulation results and the original data set, and to simulate the air quality based on the air quality model to obtain the simulation results of the spatiotemporal distribution characteristics of the air quality; The comparative analysis and optimization module is used to compare and analyze the prediction results of the spatiotemporal distribution of atmospheric pollutant concentrations and the simulation results of the spatiotemporal distribution characteristics of air quality in combination with the spatiotemporal distribution characteristic map of the park's atmospheric environment quality. The comparative analysis results are combined with the new observation data obtained from each atmospheric environment quality observation station to optimize the deep learning algorithm and air quality model, so as to improve the prediction performance of the spatiotemporal distribution of atmospheric pollutant concentrations.
9. An electronic device, characterized in that: include: processor; A memory for storing programs; The program includes instructions, which, when executed by the processor, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.
10. A computer storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.