Method and device for predicting airport aviation emission diffusion based on meteorological model

Abstract

The invention relates to the technical field of environmental impact assessment, in particular to a method and device for predicting airport aviation emission diffusion based on a meteorological model, and the method comprises the steps: obtaining historical meteorological data of a target airport, and carrying out the preprocessing of the historical meteorological data, and obtaining target training data meeting a preset condition; training the target long-short-term memory neural network model by using the target training data to obtain a meteorological model of the target airport; and determining target key meteorological data of the target airport according to the meteorological model, and inputting the target key meteorological data into a preset atmospheric pollutant diffusion model to obtain an airport aviation emission diffusion result predicted based on the meteorological model. Therefore, the problems that a traditional statistical model is mainly used for a univariate time sequence prediction task and has limitation, a large amount of energy needs to be consumed for data analysis work before prediction work, the complexity of weather prediction is increased, and the accuracy of airport weather information prediction is reduced in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of environmental impact assessment, and in particular to a method and device for predicting the diffusion of airport aviation emissions based on a meteorological model. Background Art

[0002] Accurate prediction of airport meteorological information is of great significance to airport operations and management. It can effectively improve flight scheduling efficiency and reduce flight delays caused by weather. At the same time, airport meteorology also has a significant impact on the diffusion of aviation emissions, thereby affecting the assessment of aviation activities on the environment around the airport. In the atmospheric pollutant diffusion model, whether the meteorological data is sufficient and accurate will directly affect the diffusion rate and direction of pollutants, thereby affecting the accuracy of pollutant simulation. Existing atmospheric pollutant models often use unified meteorological data in the diffusion model area, and assume that there will be no changes within 1 hour. Therefore, the temporal resolution of the meteorological model in the current atmospheric diffusion model is insufficient. At the same time, in terms of the spatial resolution of the meteorological model, since the main source of emissions from civil aircraft at low altitudes is the take-off stage, the spatial resolution of the meteorological model should at least be equivalent to the runway scale.

[0003] Since the weather system is affected by multiple factors, and the relationship between the various influencing factors is nonlinear and highly dynamic, the task of meteorological information forecasting is complex and challenging. In related technologies, traditional meteorological forecasting methods are statistical methods that rely on physical models. Currently, the most widely used statistical models include the autoregressive integral moving average model. The above models need to assume that the time series data is linearly separable in the forecasting task, that is, there is a linear relationship between the data. Before processing multidimensional time series data, it is necessary to manually extract features from the data in advance. Therefore, human empirical intervention is required in the feature extraction process, introducing unquantifiable deviations. At the same time, since meteorological information data contains multiple variables, traditional statistical models require a complex modeling process when processing multivariate time series.

[0004] However, traditional statistical models in related technologies, such as autoregressive models, moving average models, autoregressive integrated moving average models, etc., are mainly designed for univariate time series prediction tasks, have limitations and low applicability, and require a lot of effort to perform data analysis and extract data features before prediction, which increases the complexity of meteorological forecasts, reduces the stability of model performance, and reduces the accuracy of airport meteorological information forecasts, which needs to be urgently addressed. Summary of the invention

[0005] The present application provides a method and device for predicting the diffusion of airport aviation emissions based on a meteorological model, so as to solve the problem that the traditional statistical model in the related technology is mainly used for single variable time series prediction tasks, has limitations and low applicability, and requires a lot of effort to perform data analysis and extract data features before the prediction work, which increases the complexity of meteorological prediction, reduces the stability of model performance, and reduces the accuracy of airport meteorological information prediction.

[0006] The first aspect of the present application provides a method for predicting the diffusion of airport aviation emissions based on a meteorological model, comprising the following steps: acquiring historical meteorological data of a target airport, and preprocessing the historical meteorological data to obtain target training data that meets preset conditions; training a target long-short term memory neural network model using the target training data to obtain a meteorological model of the target airport; determining target key meteorological data of the target airport based on the meteorological model, and inputting the target key meteorological data into a pre-set atmospheric pollutant diffusion model to obtain an airport aviation emissions diffusion result predicted based on the meteorological model.

[0007] Optionally, in one embodiment of the present application, the historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

[0008] Optionally, in one embodiment of the present application, the historical meteorological data is preprocessed to obtain target training data that meets preset conditions, including: obtaining a comma-separated value file of each historical meteorological data changing over time; using the comma-separated value file to standardize each historical meteorological data to obtain standardized meteorological data, and determining the target correlation degree between each historical meteorological data; based on the target correlation degree and the standardized meteorological data, determining the target input data-label value pairs, and dividing the target input data-label value pairs to obtain the target training data that meets the preset conditions.

[0009] Optionally, in one embodiment of the present application, obtaining a comma-separated value file of each historical meteorological data changing over time includes: using a time axis to fuse each historical meteorological data to obtain fused meteorological data; determining a target moment that meets a missing condition based on the fused meteorological data, and obtaining meteorological data at the previous moment and the next moment of the target moment; using the meteorological data at the previous moment and the meteorological data at the next moment to determine the meteorological data corresponding to the target moment, so as to generate the comma-separated value file of each historical meteorological data changing over time.

[0010] Optionally, in one embodiment of the present application, the target key meteorological data of the target airport is determined according to the meteorological model, and the target key meteorological data is input into a pre-set atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted by the meteorological model, including: based on the meteorological model, obtaining multi-location key meteorological data within the target time; inputting the multi-location key meteorological data, the target pollution source emission inventory model, the target simulation area terrain information and the target boundary background concentration into the pre-set atmospheric pollutant diffusion model to obtain the spatial distribution results and time evolution results of the pollutant concentration of the target airport.

[0011] The second aspect of the present application provides a device for predicting the diffusion of airport aviation emissions based on a meteorological model, including: an acquisition module, used to acquire historical meteorological data of a target airport, and preprocess the historical meteorological data to obtain target training data that meets preset conditions; a determination module, used to train a target long-short term memory neural network model using the target training data to obtain a meteorological model of the target airport; a prediction module, used to determine target key meteorological data of the target airport based on the meteorological model, and input the target key meteorological data into a pre-set atmospheric pollutant diffusion model to obtain the airport aviation emissions diffusion results predicted based on the meteorological model.

[0012] Optionally, in one embodiment of the present application, the historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

[0013] Optionally, in one embodiment of the present application, the acquisition module includes: an acquisition unit, used to obtain a comma-separated value file of each historical meteorological data changing over time; a first determination unit, used to use the comma-separated value file to standardize each historical meteorological data to obtain standardized meteorological data, and determine the target correlation degree between each historical meteorological data; a second determination unit, used to determine the target input data-label value pairs based on the target correlation degree and the standardized meteorological data, and divide the target input data-label value pairs to obtain the target training data that meets the preset conditions.

[0014] Optionally, in one embodiment of the present application, the acquisition unit includes: a first acquisition sub-unit, used to use the time axis to fuse each of the historical meteorological data to obtain the fused meteorological data; a second acquisition sub-unit, used to determine the target moment that meets the missing condition based on the fused meteorological data, and obtain the meteorological data of the previous moment and the meteorological data of the next moment of the target moment; a generation sub-unit, used to use the meteorological data of the previous moment and the meteorological data of the next moment to determine the meteorological data corresponding to the target moment, so as to generate the comma-separated value file of each historical meteorological data changing over time.

[0015] Optionally, in one embodiment of the present application, the prediction module includes: a third determination unit, used to obtain key meteorological data of multiple locations within the target time based on the meteorological model; a processing unit, used to input the key meteorological data of multiple locations, the target pollution source emission inventory model, the target simulation area terrain information and the target boundary background concentration into the pre-set atmospheric pollutant diffusion model to obtain the spatial distribution results and time evolution results of the pollutant concentration of the target airport.

[0016] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting the diffusion of airport aviation emissions based on a meteorological model as described in the above embodiment.

[0017] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above method for predicting the diffusion of airport aviation emissions based on meteorological models.

[0018] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above method for predicting the diffusion of airport aviation emissions based on meteorological models.

[0019] The embodiment of the present application can pre-process the historical meteorological data of the target airport to obtain target training data that meets certain conditions, thereby training the target long-short term memory neural network model to obtain the meteorological model of the target airport, determine the target key meteorological data of the target airport according to the meteorological model, and input it into the pre-set atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted by the meteorological model, effectively reduce the complexity of meteorological forecasting, and improve the accuracy of airport meteorological information forecasting. Thus, the problem that the traditional statistical model in the related art is mainly used for single variable time series forecasting tasks, has limitations and low applicability, and requires a lot of effort for data analysis before the forecasting work, increases the complexity of meteorological forecasting, and reduces the accuracy of airport meteorological information forecasting is solved.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A flowchart of a method for predicting the diffusion of airport aviation emissions based on a meteorological model according to an embodiment of the present application;

[0023] Figure 2 This is a schematic diagram of the correlation analysis results of a certain airport's one-year historical meteorological data in a specific embodiment of the present application;

[0024] Figure 3 A schematic diagram of the division of input values ​​and label values ​​of a long short-term memory neural network model according to a specific embodiment of the present application;

[0025] Figure 4 This is a schematic diagram of the change of the loss function based on a year of meteorological data of a certain airport with the number of training cycles in a specific embodiment of the present application;

[0026] Figure 5 This is a schematic diagram of the wind speed prediction capability of a meteorological model based on one year's meteorological data of a certain airport in a specific embodiment of the present application;

[0027] Figure 6 This is a schematic diagram of the NO emission distribution results in aircraft exhaust gas in a certain airport area according to a specific embodiment of the present application;

[0028] Figure 7 A schematic diagram of the structure of a device for predicting the diffusion of airport aviation emissions based on a meteorological model according to an embodiment of the present application;

[0029] Figure 8 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] The following describes a method and device for predicting the diffusion of airport aviation emissions based on a meteorological model according to an embodiment of the present application with reference to the accompanying drawings. In view of the fact that the traditional statistical model in the related art mentioned in the above background technology is mainly used for single variable time series prediction tasks, has limitations and low applicability, and requires a lot of effort to perform data analysis before the prediction work, which increases the complexity of meteorological prediction and reduces the accuracy of airport meteorological information prediction, the present application provides a method for predicting the diffusion of airport aviation emissions based on a meteorological model, in which the historical meteorological data of the target airport can be preprocessed to obtain target training data that meets certain conditions, thereby training the target long short-term memory neural network model to obtain the meteorological model of the target airport, determine the target key meteorological data of the target airport according to the meteorological model, and input it into the pre-set atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion result predicted based on the meteorological model, effectively reduce the complexity of meteorological prediction, and improve the accuracy of airport meteorological information prediction. Thus, the problem that the traditional statistical model in the related art is mainly used for single variable time series prediction tasks, has limitations and low applicability, and requires a lot of effort to perform data analysis before the prediction work, increases the complexity of meteorological prediction, and reduces the accuracy of airport meteorological information prediction is solved.

[0032] Specifically, Figure 1 A schematic flow chart of a method for predicting the diffusion of airport aviation emissions based on a meteorological model provided in an embodiment of the present application.

[0033] like Figure 1 As shown, the method for predicting the diffusion of airport aviation emissions based on a meteorological model includes the following steps:

[0034] In step S101, historical meteorological data of the target airport is obtained, and the historical meteorological data is preprocessed to obtain target training data that meets preset conditions.

[0035] In the embodiment of the present application, the target airport is the airport for which weather information is to be predicted.

[0036] It can be understood that the embodiments of the present application can obtain historical meteorological data of the target airport. For example, the embodiments of the present application can obtain historical meteorological data of the airport whose meteorological information is to be predicted, such as precipitation, fog, etc., and pre-process the historical meteorological data in the following steps to obtain target training data that meets certain conditions, thereby effectively improving the feasibility of predicting airport meteorological information.

[0037] In one embodiment of the present application, the historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

[0038] During the actual implementation process, the meteorological data that need to be regularly recorded and saved at the airport to be predicted in the embodiment of the present application mainly include wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena, such as precipitation, thunderstorms, fog, frost and ice, etc., so as to predict the airport's instantaneous temperature, instantaneous relative humidity, instantaneous wind speed, instantaneous wind direction, instantaneous air pressure, instantaneous visibility value, 1-minute average precipitation intensity, cloud base height and other meteorological information, effectively improving the comprehensiveness of meteorological information forecasting.

[0039] Among them, in one embodiment of the present application, historical meteorological data are preprocessed to obtain target training data that meets preset conditions, including: obtaining a comma-separated value file of each historical meteorological data changing over time; using the comma-separated value file to standardize each historical meteorological data to obtain standardized meteorological data, and determining the target correlation between each historical meteorological data; based on the target correlation and the standardized meteorological data, determining the target input data-label value pairs, and dividing the target input data-label value pairs to obtain the target training data that meets the preset conditions.

[0040] For example, since the format of historical meteorological data records needs to comply with standard regulations, it is necessary to pre-process the historical meteorological data. First, the embodiment of the present application can summarize the historical meteorological data recorded by different sensors, and interpolate the meteorological data of the previous and next moments to obtain the missing meteorological information at certain moments, forming a comma-separated value file of different meteorological data changing over time. Since the values ​​of different meteorological data vary greatly, the different meteorological data are first standardized to obtain standardized meteorological data, and then the covariance calculation is performed to obtain the correlation between the different meteorological data, such as Figure 2 As shown in Figure 1, the correlation analysis results of a certain airport's historical meteorological data for one year are shown. When the correlation coefficient is greater than 0.1, it is considered that there is a certain implicit correlation between the two.

[0041] Next, the embodiment of the present application can divide the input value and the corresponding label value based on the correlation degree and the standardized meteorological data, such as Figure 3As shown, first, in order to speed up the training speed of the model in the following steps, time resampling can be performed according to the characteristics of meteorological information. For example, for meteorological information recorded once a minute, for meteorological data such as temperature, pressure, relative humidity, etc., the frequency of change in time is relatively small, and resampling can be performed every 10 minutes; for meteorological information with a large change frequency such as wind speed and wind direction, resampling can be performed every 2 minutes or no resampling operation can be performed; at the same time, when defining the size of the observation window (input data), it is also necessary to change it according to the characteristics of meteorological information. For example, the frequency of change of meteorological data such as temperature, pressure, relative humidity is relatively small, and it is more affected by historical data. Therefore, the observation window can be larger, such as 720 minutes, and the corresponding future moment of the label value can also be longer, such as 120 minutes; while for meteorological information with a large change frequency such as wind speed and wind direction, it is not obviously affected by historical data, and the observation window can be smaller, such as 360 minutes, and the corresponding future moment of the label value can also be shorter, such as 60 minutes.

[0042] Secondly, after dividing the corresponding input data-label value pairs, the data can be randomly shuffled in time to prevent the model from falling into the local area optimum. Then all the data can be divided into training set, validation set and test set according to the ratio of 0.5:0.3:0.2. At the same time, multiple data pairs can be packaged and trained simultaneously. For example, 128 data pairs can be packaged into a data packet, which can speed up the training speed of the model in the following steps and avoid overfitting of the model in the following steps.

[0043] Optionally, in one embodiment of the present application, a comma-separated value file of each historical meteorological data changing over time is obtained, including: using a time axis to fuse each historical meteorological data to obtain fused meteorological data; determining a target moment that meets the missing condition based on the fused meteorological data, and obtaining meteorological data at the previous moment and the next moment of the target moment; using the meteorological data at the previous moment and the meteorological data at the next moment to determine the meteorological data corresponding to the target moment, so as to generate a comma-separated value file of each historical meteorological data changing over time.

[0044] As a possible implementation method, the embodiment of the present application can summarize the historical meteorological data recorded by different sensors and fuse them according to the time axis. For the meteorological information missing at certain moments, the meteorological data before and after the missing moment can be interpolated to obtain it, forming a comma-separated value file of different meteorological data changing over time, which effectively improves the accuracy of meteorological information forecasts.

[0045] In step S102, the target long short-term memory neural network model is trained using the target training data to obtain a meteorological model of the target airport.

[0046] In the embodiment of the present application, the long short-term memory neural network is a special recursive neural network, which overcomes the long-term dependency problem of the traditional recursive neural network by introducing "memory cells" and gate mechanisms (input gate, forget gate, output gate), and captures the implicit nonlinear relationship between meteorological information. First, given the number of neurons ("memory cells") of the long short-term memory network, generally speaking, the more neurons, the more complex the model, and the appropriate number of neurons can be selected according to cross-validation; practice has proved that 64 neurons are enough to accurately predict meteorological data; secondly, given the shape of the input data of the network, this is related to the number of data pairs in the single data packet preprocessed in the above steps; in order to reduce the mutual dependence between neurons, a random inactivation algorithm can be used, the loss ratio is 20%, and the tanh activation function is used, and the structure of the output layer of the neural network is given at the end, and a certain kind of meteorological information is output here, so the long short-term memory neural network models of different meteorological information are independent of each other, wherein the loss function uses the mean square error function, therefore, the target long short-term memory neural network in the embodiment of the present application can be dynamically modified according to the training effect to improve the applicability of the long short-term memory neural network model.

[0047] It can be understood that the embodiment of the present application can use the target training data to train the target long short-term memory neural network model. During the training process, the number of data training times is set to 10, but in order to avoid overfitting of the model, the early stopping method is adopted, that is, the training is stopped when the loss function of the validation set has not improved for 4 consecutive times; because the data has been disrupted and packaged again during the data preprocessing process, the meteorological model of the target airport obtained by training has better generalization characteristics, which effectively improves the accuracy of meteorological information prediction.

[0048] For example, based on the historical meteorological data of a domestic airport from March 2023 to March 2024, Figure 4 It shows how the loss function of the training set and the validation set changes with the number of training cycles. Figure 5 The trained model is shown to be able to predict the wind speed for the airport in May 2023. It can be seen that the meteorological model obtained by training the long short-term memory neural network model can effectively capture the changing trend and range of wind speed, and provide accurate meteorological information for the atmospheric pollutant diffusion model.

[0049] In step S103, target key meteorological data of the target airport are determined according to the meteorological model, and the target key meteorological data are input into a preset atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted by the meteorological model.

[0050] It can be understood that the embodiment of the present application can determine the target key meteorological data of the target airport according to the meteorological model in the following steps, and input the target key meteorological data into the pre-set atmospheric pollutant diffusion model, so as to obtain the airport aviation emission diffusion results predicted by the meteorological model, such as the spatial distribution results and time evolution results of pollutant concentrations, etc., effectively reduce the complexity of meteorological forecasts, and improve the accuracy of airport meteorological information forecasts.

[0051] Among them, in one embodiment of the present application, target key meteorological data of the target airport are determined according to the meteorological model, and the target key meteorological data are input into a pre-set atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted by the meteorological model, including: based on the meteorological model, obtaining multi-location key meteorological data within the target time; inputting the multi-location key meteorological data, the target pollution source emission inventory model, the target simulation area terrain information and the target boundary background concentration into the pre-set atmospheric pollutant diffusion model to obtain the spatial distribution results and time evolution results of the pollutant concentration of the target airport.

[0052] In some embodiments, since the meteorological model is one of the important components of the pollutant atmospheric diffusion model, for example, in city-chem, the pollution source emission inventory model, the simulation area terrain information and the boundary background concentration information together constitute the input conditions of the atmospheric diffusion model. In the simulation of pollutant atmospheric diffusion, based on the meteorological model, the key meteorological data parameters of multiple locations within a certain period of time after training, such as wind speed, temperature, humidity, etc., can be used as input conditions to predict and calculate the pollutant diffusion parameters (including but not limited to turbulence scale and intensity, mixing height, dry and wet deposition rate, etc.) under the influence of different meteorological conditions; at the same time, Figure 6 As shown, the NO emission distribution result in aircraft exhaust in a certain airport area, the embodiment of the present application can be combined with other data such as the aircraft exhaust pollution emission inventory to numerically solve the convection and diffusion control equations of the corresponding pollution emission components (such as NOx), and then realize the simulation calculation of the spatiotemporal distribution process of different pollutants in the simulation area. Among them, in the above-mentioned atmospheric diffusion simulation process, the time resolution of meteorological data determines the simulation time resolution. The embodiment of the present application has the characteristics of high prediction accuracy and small calculation amount, and the time resolution of the meteorological model can reach minute level, which can be used as the input condition of the atmospheric pollution diffusion model to realize the accurate prediction of the airport area diffusion of aviation emissions.

[0053] According to the method for predicting the diffusion of airport aviation emissions based on a meteorological model proposed in the embodiment of the present application, the historical meteorological data of the target airport can be preprocessed to obtain target training data that meets certain conditions, thereby training the target long-short term memory neural network model to obtain the meteorological model of the target airport, determine the target key meteorological data of the target airport according to the meteorological model, and input it into the pre-set atmospheric pollutant diffusion model to obtain the airport aviation emissions diffusion results predicted based on the meteorological model, effectively reducing the complexity of meteorological forecasting and improving the accuracy of airport meteorological information forecasting. Thus, the problem that the traditional statistical model in the related art is mainly used for single variable time series forecasting tasks, has limitations and low applicability, and requires a lot of effort for data analysis before the forecasting work, increases the complexity of meteorological forecasting, and reduces the accuracy of airport meteorological information forecasting is solved.

[0054] Next, a device for predicting the diffusion of airport aviation emissions based on a meteorological model according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0055] Figure 7 It is a block diagram of an apparatus for predicting the diffusion of airport aviation emissions based on a meteorological model according to an embodiment of the present application.

[0056] like Figure 7 As shown, the device 10 for predicting the diffusion of airport aviation emissions based on a meteorological model includes: an acquisition module 100 , a determination module 200 and a prediction module 300 .

[0057] Specifically, the acquisition module 100 is used to acquire historical meteorological data of the target airport and pre-process the historical meteorological data to obtain target training data that meets preset conditions.

[0058] The determination module 200 is used to train the target long short-term memory neural network model using the target training data to obtain the meteorological model of the target airport.

[0059] The prediction module 300 is used to determine the target key meteorological data of the target airport according to the meteorological model, and input the target key meteorological data into a preset atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted based on the meteorological model.

[0060] Optionally, in one embodiment of the present application, the historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

[0061] Optionally, in one embodiment of the present application, the acquisition module 100 includes: an acquisition unit, a first determination unit and a second determination unit.

[0062] The acquisition unit is used to obtain a comma-separated value file of each historical meteorological data changing over time.

[0063] The first determination unit is used to perform standardization processing on each historical meteorological data using a comma separated value file to obtain standardized meteorological data, and determine the target correlation degree between each historical meteorological data.

[0064] The second determination unit is used to determine the target input data-label value pairs based on the target relevance and the standardized meteorological data, and divide the target input data-label value pairs to obtain target training data that meets preset conditions.

[0065] Optionally, in one embodiment of the present application, the acquisition unit includes: a first acquisition subunit, a second acquisition subunit and a generation subunit.

[0066] The first acquisition subunit is used to perform fusion processing on each historical meteorological data using the time axis to obtain fused meteorological data.

[0067] The second acquisition subunit is used to determine the target time that meets the missing condition based on the fused meteorological data, and to acquire the meteorological data of the previous moment and the next moment of the target time.

[0068] The generation subunit is used to determine the meteorological data corresponding to the target moment by using the meteorological data of the previous moment and the meteorological data of the next moment, so as to generate a comma-separated value file of each historical meteorological data changing with time.

[0069] Optionally, in one embodiment of the present application, the prediction module 300 includes: a third determination unit and a processing unit.

[0070] The third determination unit is used to obtain key meteorological data of multiple locations within a target time based on a meteorological model.

[0071] The processing unit is used to input the key meteorological data of multiple locations, the emission inventory model of the target pollution source, the terrain information of the target simulation area and the target boundary background concentration into the pre-set atmospheric pollutant diffusion model to obtain the spatial distribution results and time evolution results of the pollutant concentration of the target airport.

[0072] It should be noted that the aforementioned explanation of the embodiment of the method for predicting the diffusion of airport aviation emissions based on a meteorological model is also applicable to the device for predicting the diffusion of airport aviation emissions based on a meteorological model in this embodiment, and will not be repeated here.

[0073] According to the device for predicting the diffusion of airport aviation emissions based on a meteorological model proposed in the embodiment of the present application, the historical meteorological data of the target airport can be preprocessed to obtain target training data that meets certain conditions, thereby training the target long-short term memory neural network model to obtain the meteorological model of the target airport, determine the target key meteorological data of the target airport according to the meteorological model, and input it into the pre-set atmospheric pollutant diffusion model to obtain the airport aviation emissions diffusion results predicted based on the meteorological model, effectively reducing the complexity of meteorological forecasting and improving the accuracy of airport meteorological information forecasting. Thus, the problem that the traditional statistical model in the related art is mainly used for single variable time series forecasting tasks, has limitations and low applicability, and requires a lot of effort for data analysis before the forecasting work, increases the complexity of meteorological forecasting, and reduces the accuracy of airport meteorological information forecasting is solved.

[0074] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0075] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0076] When the processor 802 executes the program, the method for predicting the diffusion of airport aviation emissions based on a meteorological model provided in the above embodiment is implemented.

[0077] Furthermore, the electronic device further comprises:

[0078] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0079] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0080] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0081] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0082] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0083] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0084] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above method for predicting the diffusion of airport aviation emissions based on a meteorological model.

[0085] This embodiment also provides a computer program product, including a computer program. When the computer program is executed, it is used to implement the above method for predicting the diffusion of airport aviation emissions based on a meteorological model.

[0086] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0088] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0090] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0091] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0092] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0093] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting the dispersion of airport aviation emissions based on a meteorological model, characterized in that: The following steps are involved: Acquire historical meteorological data of the target airport, and preprocess the historical meteorological data to obtain target training data that meets preset conditions; Using the target training data to train a target long short-term memory neural network model to obtain a meteorological model of the target airport; The target key meteorological data of the target airport are determined according to the meteorological model, and the target key meteorological data are input into a preset atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted based on the meteorological model.

2. The method according to claim 1, characterized in that: The historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

3. The method according to claim 1, characterized in that The preprocessing of the historical meteorological data to obtain target training data that meets preset conditions includes: Get a comma-separated value file of each historical weather data change over time; Using the comma separated value file to perform standardization processing on each of the historical meteorological data to obtain standardized meteorological data, and determining the target correlation degree between each of the historical meteorological data; Based on the target relevance and the standardized meteorological data, target input data-label value pairs are determined, and the target input data-label value pairs are divided to obtain the target training data that meets the preset conditions.

4. The method according to claim 3, characterized in that The comma-separated value file of each historical meteorological data changing over time is obtained, including: Using the time axis to fuse each of the historical meteorological data, to obtain fused meteorological data; Determine a target time that meets the missing condition according to the fused meteorological data, and obtain meteorological data of a moment before and a moment after the target time; The meteorological data at the previous moment and the meteorological data at the next moment are used to determine the meteorological data corresponding to the target moment, so as to generate the comma-separated value file of each historical meteorological data changing with time.

5. The method according to claim 1, characterized in that The step of determining the target key meteorological data of the target airport according to the meteorological model, and inputting the target key meteorological data into a preset atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted based on the meteorological model, includes: Based on the meteorological model, obtaining key meteorological data of multiple locations within a target time; The multi-location key meteorological data, target pollution source emission inventory model, target simulation area terrain information and target boundary background concentration are input into the pre-set atmospheric pollutant diffusion model to obtain the spatial distribution results and time evolution results of the pollutant concentration of the target airport.

6. A device for predicting the diffusion of airport aviation emissions based on a meteorological model, characterized in that: include: An acquisition module is used to acquire historical meteorological data of a target airport and preprocess the historical meteorological data to obtain target training data that meets preset conditions; A determination module, used to train a target long short-term memory neural network model using the target training data to obtain a meteorological model of the target airport; The prediction module is used to determine the target key meteorological data of the target airport according to the meteorological model, and input the target key meteorological data into a pre-set atmospheric pollutant diffusion model to obtain the airport aviation emission diffusion results predicted based on the meteorological model.

7. The device according to claim 6, characterized in that The historical meteorological data includes at least one of wind speed, wind direction, visibility, cloud conditions, temperature, humidity, air pressure and weather phenomena.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting the diffusion of airport aviation emissions based on a meteorological model as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for predicting the diffusion of airport aviation emissions based on a meteorological model as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed by a processor to implement the method for predicting airport aviation emission dispersion based on a meteorological model as described in any one of claims 1 to 5.

Images