31 results about "Air pollutant concentrations" patented technology

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The utility model relates to the technical field of environmental air pollutant concentration monitoring, and provides a peroxy radical chemical amplification device which comprises a sampling-amplification channel, a first acquisition control circuit module is arranged in the sampling-amplification channel and used for controlling an electric control program of a device system, and a second acquisition control circuit module is arranged in the sampling-amplification channel. An HO photolysis module is arranged in the sampling-amplification channel, a second acquisition control circuit module is arranged in the sampling-amplification channel and used for controlling an electric control program of the device system, and a gas path module is arranged in the sampling-amplification channel and used for controlling the gas flow direction of the device system; according to the utility model, the sampling-amplifying channel is arranged, so that the device is simple in structure, simple to operate, low in manufacturing cost and high in time resolution; the inhibition effect of the environment humidity on the amplification reaction is solved to a certain extent, and the actual effects of accurate measurement, simple operation and stable operation are obtained.

The invention discloses a multi-stage waste gas purification device, and belongs to the technical field of waste gas purification, the multi-stage waste gas purification device comprises a spray tower, a gas inlet pipe and a gas outlet pipe, one side of the spray tower is provided with a liquid storage cavity, a variable speed water pump is arranged between the liquid storage cavity and the spray tower, a gas quality sensor is arranged in the gas inlet pipe, and a gas outlet pipe is arranged in the gas outlet pipe. The bottom end of the spraying frame is rotationally connected with a spraying main pipe, a hydraulic driving mechanism for driving the spraying main pipe to rotate is arranged on the spraying frame, the output end of the variable-speed water pump is communicated with the hydraulic driving mechanism, and the spraying main pipe is provided with multiple layers of spraying mechanisms communicated with the spraying main pipe from top to bottom; an adjusting piston is arranged in the spraying main pipe in a sliding and sealing manner, and a centrifugal self-adjusting driving mechanism for driving the adjusting piston to slide along the spraying main pipe is arranged at the bottom end of the spraying main pipe. The multi-stage waste gas purification device provided by the invention can be used for monitoring the concentration of air pollutants and is provided with a plurality of layers of spraying mechanisms, and the spraying liquid flow and the spraying layers are automatically adjusted according to the concentration of the waste gas pollutants.

The invention relates to the technical field of data processing, and particularly discloses a data processing method for an intelligent environmental protection monitoring platform, which utilizes a gas sensor to monitor the concentration of air pollutants in real time, and introduces historical normal pollutant concentration data corresponding to the current monitoring time period as a dynamic reference system. Therefore, a dynamically changing judgment threshold value is constructed based on statistical characteristics, normal periodic pollutant concentration fluctuation is effectively filtered out, and an abnormal air pollutant concentration peak value different from a normal background is identified. Further, deep time sequence correlation analysis is carried out on pollutant concentration data and real-time meteorological data in a corresponding time period, so that the cause of an abnormal peak value of the pollutant concentration is comprehensively judged. According to the method, the pollutant concentration standard exceeding event can be accurately identified, and the causes behind the pollutant concentration standard exceeding event, such as sensor instantaneous errors, pollutant accumulation in static and stable weather or sudden pollution events, are disclosed, so that powerful support is provided for a subsequent differential management and control strategy.

The invention relates to an emergency processing system and method for atmospheric pollution source influence based on DeepSeek, and belongs to the technical field of environmental monitoring, and the method comprises the steps: collecting atmospheric pollutant concentration data, meteorological data and basic information data of surrounding buildings; preprocessing the data; carrying out deep analysis on the preprocessed data based on a DeepSeek model, and judging whether to trigger early warning or not and the early warning degree in combination with a pollutant exceeding standard knowledge base; when abnormal data is found, the constructed knowledge base is retrieved; combining the data retrieved by the knowledge base; the current atmospheric pollution and building influence conditions are retrieved and compared with existing plan cases; and a detailed alarm condition is output, and a targeted emergency plan is generated at the same time. According to the method, based on the DeepSeek data analysis and learning ability, the influence of multiple factors is fully considered, the position of the influenced building is accurately identified, the influence degree is evaluated, and a more reliable basis is provided for environment decision making.

The invention relates to the technical field of atmosphere quality monitoring, and discloses an underway atmosphere quality monitoring method and system, and the method comprises the steps: constructing a vehicle-mounted underway atmosphere quality monitoring system based on a front-end sensor assembly, a data collection module, a wireless transmission unit, a positioning system and a power supply system, and generating an underway monitoring execution scheme; driving the vehicle to collect atmospheric pollutant concentration and meteorological parameter data; performing timestamp matching and fusion processing with the original GPS position data to obtain atmospheric pollutant spatial distribution data; transmitting to an environment monitoring cloud platform in real time, and generating an atmospheric pollutant concentration distribution thermodynamic diagram; and performing air quality grading evaluation and pollution source identification on the monitored area, and generating an area air quality risk grade map and pollution early warning information, thereby realizing stable acquisition of environmental parameters in the mobile monitoring process, effectively eliminating interference of vehicle vibration and environmental change on monitoring data, and improving the monitoring accuracy. And the accuracy of atmosphere quality monitoring is improved.

The embodiment of the invention provides an environment data processing method, device and equipment. The method comprises the following steps: acquiring a plurality of environment data packets of each preset grid of a target area in a target time period; wherein each environment data packet comprises at least one kind of air pollutant concentration data collected by the vehicle; for each preset grid, determining initial environment data of the preset grid in the target time period according to the air pollutant concentration data in the environment data packet of the preset grid in the target time period; acquiring environment monitoring data of an environment monitoring station to which the preset grid belongs in a target time period; based on the environment monitoring data of the target time period, performing correction processing on the initial environment data of the preset grid in the target time period to obtain target environment data of the preset grid in the target time period; and determining an environment pollution area of the target area according to the target environment data of each preset grid in the target time period. The method is used for achieving the effect of improving the accuracy of the environmental data.

The embodiment of the invention provides an air pollutant concentration three-dimensional modeling method, and belongs to the technical field of data processing, and the method specifically comprises the steps: setting a cruise region, and dividing the cruise region into initial grids; setting a global cruise path strategy and a local cruise path strategy; all the initial grids are traversed, and the pollutant concentration is collected at the end point of each initial grid; calculating a real-time gradient mode of two end points and calculating an average gradient mode of each initial grid according to the real-time gradient mode; die-cutting a next initial grid according to the average gradient; traversing all the global grids according to a hierarchical cruise path strategy, uniformly collecting pollutant concentrations of a plurality of points on each edge of each global grid, and performing PCHIP interpolation fitting; obtaining point cloud data corresponding to the global grid and establishing a transition layer between grids with different densities according to the point cloud data; and constructing a three-dimensional space contour surface concentration field model according to the point cloud data and the concentration interpolation curve and outputting the three-dimensional space contour surface concentration field model. Through the scheme disclosed by the invention, the modeling efficiency and accuracy are improved.

This invention discloses an air quality prediction method based on a deep learning model using potential source contribution analysis. Applied to the field of air quality prediction technology, it addresses the problem that existing technologies only consider the geographical distance of the research object, lacking a deeper exploration of its spatial diffusion impact. This invention utilizes potential source contribution analysis based on airflow trajectories to construct a spatial impact map to represent the spatial correlation between cities. Then, by using a graph convolution algorithm, it extracts effective spatial features from the spatial impact map in conjunction with the pollution status of each city. Furthermore, it employs a long short-term memory model to learn the temporal characteristics of past air pollutant concentration data, generating prediction results. First, the results of potential source contribution analysis are applied to a graph convolutional network, and then combined with the long short-term memory model to predict urban air pollution data. The method of this invention can accurately predict urban air pollutants on both spatiotemporal scales.

The invention discloses an air pollutant concentration prediction method and device, equipment and a medium, and relates to the technical field of deep learning, and the method comprises the steps: obtaining site monitoring data and site longitude and latitude, carrying out the missing value filling and normalization processing of the site monitoring data, obtaining a time sequence, and constructing a geographic relation graph; performing trend feature extraction and feature processing on the time sequence by using an exponential moving average method and based on a gating circulation unit to obtain trend component features; performing periodic feature extraction on the time sequence; performing batch normalization processing, function activation and vector splicing on the noise sequence to obtain noise component features; splicing and fusing the trend component feature, the periodic component feature and the noise component feature to obtain a first prediction feature; solving and coding the time sequence to obtain a second prediction feature; and performing gating fusion and graph attention fusion on the first prediction feature and the second prediction feature based on a geographic relation graph to obtain an air pollutant concentration prediction result.

The invention provides a welding fume collecting device which comprises a pipeline truss arranged on a ship body; the first walking mechanism is connected to the pipeline truss in a sliding mode and slides along the pipeline truss in a reciprocating mode; the second walking mechanism is connected to the pipeline truss in a sliding mode, the second walking mechanism and the first walking mechanism are arranged in a spaced mode, and the second walking mechanism slides along the pipeline truss in a reciprocating mode; the environment detection assembly is connected to the first walking mechanism and used for detecting the concentration of pollutants in the air; the dust collection pipeline is connected to the second walking mechanism; and the purification mechanism is connected with the dust collection pipeline and used for absorbing pollutants through the dust collection pipeline and purifying the pollutants. The device is suitable for purifying regional welding fume with unfixed operation points.

A graph attention network-bidirectional recurrent interpolation network (GAI-BRI)-based air pollutant concentration interpolation prediction method, a device, and a medium. The method comprises: on the basis of the extracted air pollutant concentrations, meteorological data and satellite data from multiple distributed sites within a given time range and region, constructing an air pollutant concentration map for describing pollutant conditions within the given time range and region; and inputting numerical values in the air pollutant concentration map into a GAT-BRI prediction model to obtain an air pollutant concentration interpolation prediction result for a future time period, wherein the GAT-BRI prediction model comprises a GAT that is arranged at the bottom layer and used for extracting spatial features from the air pollutant concentration map, a BRI that is arranged at the middle layer and used for extracting temporal features from the spatial features outputted by the GAT, and a feedforward network that is arranged at the top layer and used for outputting an interpolation prediction result. The method fully exploits the spatial and temporal dependencies among multiple cities, achieving high prediction accuracy.

The present disclosure relates to a method, device and electronic equipment for determining a monitoring station position, the method comprising: obtaining first meteorological information and first concentration information of an air pollutant of N target sub-regions at T time, and second meteorological information and second concentration information of an air pollutant of M preset sub-regions at T time; determining the concentration information of the air pollutant of a second target sub-region at a first time according to the first meteorological information and the first concentration information; determining the concentration information of the air pollutant of a first target sub-region at the first time according to the second meteorological information and the second concentration information; and determining a monitoring station of the air pollutant from the N target sub-regions according to the concentration information of the air pollutant of the N target sub-regions at the first time. Through the above technical solution, the influence of the air pollutant outside the target region on the boundary is considered, and the accuracy and rationality of the determined monitoring station are improved.

The utility model discloses a peroxide radical chemical amplification module, which relates to the technical field of environmental air pollutant concentration monitoring and comprises a four-way valve, three gas storage tanks are arranged at the bottom end of the side surface of the four-way valve, and a source intensity three-way valve and a gas mixing three-way valve II are arranged at the top end of the four-way valve. A first gas mixing three-way valve is arranged on the side, away from the gas storage tank, of the bottom end of the four-way valve, and the first gas mixing three-way valve, the four-way valve, the source intensity three-way valve and the second gas mixing three-way valve are used for controlling circulation and entering of gas. According to the utility model, the flow of a detection instrument is directly controlled through an integral module to realize accurate flow control in sampling and amplification processes, and an experimenter is helped to carry out deeper research and analysis. The module is simple in structure, easy to operate, low in manufacturing cost and high in time resolution, and the inhibition effect of the environment humidity on the amplification reaction is achieved to a certain extent.

The application discloses a range hood purification control method and device and a range hood, and belongs to the technical field of kitchen appliances. The method comprises the following steps: acquiring the working state of the range hood; in the case that the working state is a start-up state, acquiring the air pollutant concentration at the current time and predicting the change trend of the air pollutant concentration at a future target time; and controlling the operation mode of the auxiliary air purification device according to the air pollutant concentration at the current time and the change trend. The application further acquires the air pollutant concentration at the current time and predicts the change trend of the pollutant concentration at the future target time in the start-up state, realizes dynamic perception and prediction of the kitchen air quality, makes the purification function no longer dependent on manual operation or fixed timing of the user, but matches the generation rule and diffusion trend of pollutants in the actual cooking process, thereby reducing the technical problem that the purification function is disconnected from the real demand, and improving the air purification effect of the kitchen environment.

This invention discloses a quasi-bi-weekly lifecycle identification method for air pollution based on Fourier filtering, comprising the following steps: S1, acquiring daily observation data of air pollutant concentrations in the target area, and screening and confirming periods where pollutant concentrations continuously exceed a threshold as independent pollution events; S2, performing Fourier transform on the daily observation data and calculating the power spectrum to verify the existence of a significant quasi-bi-weekly periodic signal; S3, based on the confirmation of a significant quasi-bi-weekly periodic signal, performing Fourier filtering on the original concentration sequence to extract the quasi-bi-weekly scale component sequence; S4, for each pollution event, performing phase localization to achieve quasi-bi-weekly lifecycle identification of pollutant events. This invention can objectively extract oscillation signals at the quasi-bi-weekly scale and accurately determine the phase of a single pollution event within its quasi-bi-weekly cycle, thereby achieving quantitative identification of its lifecycle.

The invention relates to a method for determining individual air pollutant levels in specific regions using an electronic device (30) with a processor (32). The method comprises the following steps: - Calculating an individual respiratory volume of a person taking into account the duration of stay and mode of movement of the person in a measurement region (22, 24), - Obtaining a prevailing air pollutant concentration in the measurement region (22, 24) via a network, - Determining the individual air pollutant exposure of the person, taking into account the calculated individual breathing volume and the obtained air pollutant concentration, - Output of a signal based on the individual air pollution level.

The invention designs an air quality pollution single-factor prediction method based on a neural network, and the method is used for predicting the PM2.5 concentration in the next 24 hours. The model combines a residual network (ResNet), a graph convolutional network (GCN), an attention mechanism and a long short-term memory network (LSTM) so as to learn the space-time dependence of the air pollutant concentration. The AR-LSTM model can effectively improve the prediction accuracy of the PM2.5 concentration by integrating the meteorological data, the geographic position information of the monitoring station and the historical data of PM2.5. A research result shows that compared with a traditional statistical model and a single deep learning model, AR-LSTM shows higher accuracy and a lower error rate on multiple evaluation indexes.

A utility model for air quality monitoring is presented, which incorporates a modified conventional unmanned aerial vehicle (UAV) with a retractable mechanical extension for spaced environmental sensors. This allows the air pollutant concentration sensors and meteorological parameter sensors to be positioned in an area free from air turbulence caused by the movement of the UAV's propellers during air pollutant concentration measurements. This invention addresses the negative impact of air turbulence produced by the movement of the UAV's propellers.

The present application relates to the technical field of intelligent transportation and Internet of Vehicles, in particular to a traffic and atmospheric pollution two-way coupling flow prediction method based on double-path dynamic fusion. The method comprises the following steps: collecting traffic flow and air pollutant concentration data, and performing spatio-temporal alignment and reversible instance normalization; dividing the data into two branches, extracting time-dependent features through gated convolution and probabilistic sparse self-attention in the first branch, and obtaining variable interaction features through dimension reshaping, context extraction and reversible coupling transformation in the second branch; performing two-way feature interaction through cross-attention, dynamically generating weights based on channel attention, and performing residual connection after weighted fusion; linearly mapping the fused features and performing inverse normalization to obtain traffic flow prediction values. The present application significantly improves the prediction accuracy and robustness in pollution-sensitive scenarios.

The invention relates to the technical field of intelligent control, and discloses an air purification equipment control method and device, air purification equipment and a medium. After entering a set purification operation time period, a target gear is determined by obtaining the total amount of pollutants in a current closed area and combining the first duration needed by purification of the highest gear; and after a first preset operation duration, the total amount of pollutants is updated, a second duration is calculated, and the gear is updated circularly until the cut-off moment. Therefore, through dynamic and staged gear regulation and control, resource waste or insufficient purification caused by traditional fixed gear operation is avoided. And by matching the total amount of pollutants and the purification gear in real time, rapid purification at a proper gear during high pollution is ensured, timely adjustment can be performed after the pollutants are reduced, the optimal purification efficiency is realized in the purification operation time period, the problem that the concentration of the air pollutants still exceeds the standard after purification is avoided, the actual air purification requirement of a user is met, and the user experience is improved. The purification effect and energy consumption optimization are considered, and resource waste is avoided.

The invention provides an oxygen production method, device and system and a vehicle. The method comprises the following steps: acquiring first environment data, wherein the first environment data comprises at least one of a first environment temperature outside a first space, a first environment humidity outside the first space and a first air pollutant concentration outside the first space; based on the first environment data, determining that the air inlet amount of the first air inlet is a first air inlet amount and the air inlet amount of the second air inlet is a second air inlet amount; based on the first air inflow and the second air inflow, air entering the first air inlet and air entering the second air inlet are controlled to flow into the oxygen generation module, so that the oxygen generation module outputs prepared oxygen, the first air inlet is used for inputting external air from the outside of the first space, and the second air inlet is used for inputting internal air from the inside of the first space. The air inlet proportion can be intelligently adjusted, the oxygen generation efficiency is improved, the service life of oxygen generation equipment and a system is prolonged, in-vehicle air health is guaranteed in a complex environment, and driving comfort and safety of a user are guaranteed.

The application discloses an air quality forecasting method fusing monitoring image data, comprising the following steps: constructing an LSTM single-channel deep learning network for extracting features of historical air quality data, meteorological data and time data; constructing a CNN-LSTM single-channel deep learning network for extracting features of monitoring images; integrating the two single-channel networks to construct a double-channel integrated deep learning model for air quality forecasting; collecting monitoring images, air quality and meteorological data and other multi-source data to construct an air quality multi-source data set; using a sliding window method and a 'T1:T2' mode to generate sequence samples from the constructed air quality multi-source data set; training the double-channel integrated deep learning model by using a sequence sample training set to obtain a regression model with multi-step and multi-variable output forecasting capability; and inputting to-be-detected sequence sample data into the regression model to output forecasting results of multiple air quality indexes at multiple future time points. The application combines two single-channel neural networks to construct a relationship model between air pollutant concentration and monitoring images, meteorological data and time, realizes time sequence forecasting of air quality, and integrates outdoor monitoring image data to improve the forecasting precision of air quality.

Embodiments of the present disclosure provide a machine learning correction method based on low-cost atmospheric particulate matter sensor measurement, applied to the technical field of meteorological data processing. The method comprises obtaining a CSV file of low-cost atmospheric particulate matter sensor measurement data, and performing data preprocessing and feature engineering to construct an input feature set; dividing the input feature set into a training set and a test set according to the site identification in the CSV file; based on the preset model parameters, using the DART-LightGBM model, performing training according to the training set and early stopping with the early stopping set, evaluating on the test set, and saving the trained air pollutant concentration correction model, performing feature importance analysis and multi-dimensional evaluation on the model; and outputting deployment support files including a site mapping file and a feature list file. Based on this, the DART-LightGBM model can be trained and output, the site mapping and the feature list can be formed, and a closed-loop process from preprocessing to deployment is formed, which is convenient for consistent deployment of multiple sites.

The invention relates to a method and device for determining the position of a monitoring station, and electronic equipment, and the method comprises the steps: obtaining the first meteorological information of N target sub-regions at T time, and the first concentration information of air pollutants, obtaining second meteorological information and second concentration information of air pollutants of the M preset sub-regions at the T moment; according to the first weather information and the first concentration information, determining air pollutant concentration information of the second target sub-region at the first moment; according to the second weather information and the second concentration information, determining air pollutant concentration information of the first target sub-region at the first moment; and according to the air pollutant concentration information of the N target sub-regions at the first moment, determining air pollutant monitoring stations from the N target sub-regions. According to the technical scheme, the influence of air pollutants outside the target area on the boundary is considered, and the accuracy and rationality of the determined monitoring site are improved.

The invention discloses an air pollutant concentration precise monitoring system, and belongs to the technical field of air pollutant concentration monitoring. The system comprises a coupling prediction module which is used for generating a topographic change vector based on the current topography, the meteorological data and the topographic data at the previous moment, obtaining a corrected airflow field by combining the topographic change vector with the current meteorological data, and generating predicted pollutant concentration; the state evaluation module is used for generating a model prediction deviation index and a sensor degradation state index based on the predicted pollutant concentration, the actually measured concentration of the sensor and the historical state data of the sensor; the comprehensive diagnosis module combines the model prediction deviation index and the sensor degradation state index to generate a system comprehensive mismatch factor; and the adaptive correction module generates a correction instruction according to the factor, and adjusts parameters of the coupling prediction module to realize closed-loop correction. According to the method, the problem of prediction misalignment caused by terrain mismatching of a traditional static model is solved, the source accuracy of pollutant diffusion prediction is improved, and continuous self-evaluation and correction can be realized.

The invention relates to an atmospheric pollutant concentration monitoring and early warning method and system, and belongs to the technical field of environmental protection informatization and environmental pollution prevention and control. The system comprises a multivariate data acquisition module, an analysis and early warning module, a linkage control module and a remote monitoring platform; the multivariate data acquisition module comprises an infrared spectrum absorption type gas sensor, an electrochemical gas sensor, a temperature and humidity sensor and a wind speed and direction sensor, and the multivariate data acquisition module is deployed in a monitoring area in a distributed manner and is used for acquiring pollutant concentration and environmental data. According to the invention, comprehensive and accurate monitoring can be realized, through cooperation of multi-principle sensors and dynamic weight fusion, limitation of a single sensor is overcome, accurate and reliable monitoring of multiple pollutants in a full concentration range is realized, monitoring blind areas are significantly reduced, advanced early warning and efficient closed-loop management and control can be realized, and the system has good application prospects. And the speed and the accurate management and control capability of the environmental pollution emergency response are greatly improved.

The application belongs to the technical field of air pollution assessment, and relates to a city air pollutant change range assessment and ranking method and system, the method comprising: 1) obtaining multiple city air pollutant concentrations in different time dimensions and standardizing the air pollutant concentrations; 2) performing multi-dimensional time series analysis on the air pollutant concentrations to obtain multi-dimensional time series analysis results; 3) calculating the comprehensive score of each city according to the air pollutant concentrations and the multi-dimensional time series analysis results; 4) calculating the dynamic assessment score of each city and dynamically ranking the multiple cities according to the dynamic assessment score; and 5) assessing the change range of the pollutant concentration of each city and ranking the multiple cities according to the multi-dimensional time series analysis results and the change range to obtain the risk level of each city. The application is evaluated based on multi-dimensional time series analysis results and dynamic weights, and the evaluation results are comprehensive and accurate.

The application discloses a multistage waste gas purification device, and belongs to the technical field of waste gas purification, which comprises a spraying tower, an air inlet pipe and an air outlet pipe, a liquid storage cavity is arranged on one side of the spraying tower, a variable speed water pump is arranged between the liquid storage cavity and the spraying tower, a gas quality sensor is arranged in the air inlet pipe, a spraying main pipe is rotatably connected to the bottom end of a spraying frame, a hydraulic drive mechanism for driving the spraying main pipe to rotate is arranged on the spraying frame, the output end of the variable speed water pump is communicated with the hydraulic drive mechanism, a plurality of spraying mechanisms are arranged in the spraying main pipe from top to bottom, the spraying mechanisms are respectively communicated with the spraying main pipe, an adjusting piston is slidably arranged in the spraying main pipe, and a centrifugal self-adjusting drive mechanism for driving the adjusting piston to slide along the spraying main pipe is arranged at the bottom end of the spraying main pipe. The multistage waste gas purification device can monitor the concentration of air pollutants, and a plurality of spraying mechanisms are arranged, the spraying liquid flow and spraying levels are automatically adjusted according to the concentration of waste gas pollutants.

The application provides a traffic flow prediction method fusing air pollution factors, which comprises the following steps: acquiring traffic topology structure, historical traffic flow and air pollutant concentration data, constructing a traffic feature matrix, an adjacency matrix, a related pollutant concentration attribute matrix and a mapping function, and fusing the air pollutant concentration data through an attribute enhancement unit; adopting K-means clustering to screen the pollutants with the highest correlation with traffic flow, and using the attribute enhancement unit to integrate the pollutants into traffic flow features; and building and training a deep learning model to predict traffic flow. The method overcomes the limitation of the prior art which only depends on traffic flow data by combining the correlation between traffic flow spatiotemporal features and air pollutants, and effectively improves the prediction accuracy.