Method and device for predicting agglomerate fog along highway, terminal and storage medium
By obtaining and processing meteorological data and geographical data along the expressway in real time, using the life cycle model of the mass fog for accurate prediction, solving the problem that the existing technology cannot be warned, real-time monitoring and accurate prediction of mass fog, and improving traffic Intelligent management and comprehensive data.
Patent Information
- Application Number
- CN202411143630.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology cannot give an early warning before the mass fog occurs, and it cannot monitor all highway sections in real time. The equipment costs are high and cannot be deployed on a large scale.
By obtaining real-time meteorological data, geographical data and lower surface data on both sides of the expressway, using time series rolling analysis method to process the data, form an environmental timing matrix, and input the trained mass fog life cycle model to output the mass fog generation results. Including the probability of generation, occurrence time and location, to determine the sections that will be affected by mass fog to provide early warning.
Real-time monitoring and accurate prediction of mass fog has been achieved, the accuracy of prediction results has been improved, the deep integration of the transportation field with information technology and meteorological science has been promoted, the cost of resource utilization has been reduced, and the intelligent and scalable traffic management has been enhanced. sex.
Smart Images

Figure CN118966458A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of meteorological forecasting, and in particular to a method, device, terminal and storage medium for forecasting fog along a highway. Background Art
[0002] Fog is characterized by suddenness, locality, small scale, and high concentration. In addition, visibility outside the fog is good, but visibility inside the fog is very low, only tens of meters, or even more than ten meters, which is a very strong fog. Fog is unevenly distributed, and the coverage area is inconsistent, ranging in length from 1 km to 5 km. Fog is prone to occur in late autumn and winter, generally at night and in the morning when the temperature difference between day and night is large and there is no wind. Fog is more likely to occur on relatively empty sections of highways, and some fog is generated around the highway. After generation, it moves through the highway, which is sudden and has a great impact on traffic safety.
[0003] Since the scale of fog is small and not easy to be observed by conventional ground and along-line traffic meteorological stations, there have been few studies on fog in the past, mainly focusing on heavy fog. With the rapid extension of highway mileage, the impact of fog disasters on highway driving safety has attracted more and more attention from transportation departments and scholars, and some research has been carried out in the numerical simulation of fog, meteorological characteristics analysis, impact on highway driving, process simulation, etc. In addition, there are equipment for meteorological data observation and fog warning, fog index collection equipment, and identification of fog phenomenon based on video image analysis collected by video surveillance equipment along the highway.
[0004] Existing research has been based on the analysis of the actual occurrence of fog. Through the real-time data of observation equipment such as visibility meters, the occurrence of fog can be monitored. At present, it is not possible to install equipment on all road sections, and the equipment is expensive and cannot be deployed on a large scale. In addition, the characteristics of fog are extracted based on conventional meteorological observation data and geostationary meteorological satellite remote sensing data to achieve fog recognition. This is also based on the analysis and recognition of the characteristics of fog after it occurs, and it is impossible to give a warning before the occurrence of fog. Summary of the invention
[0005] The present invention provides a method, device, terminal and storage medium for predicting fog clusters along a highway, so as to solve the problem that a prompt cannot be given before fog clusters occur.
[0006] In a first aspect, the present invention provides a method for predicting fog along a highway, comprising: Acquire real-time meteorological data, geographic data and underlying surface data within a first preset influence radius on both sides of the expressway; the real-time meteorological data includes meteorological data at the current time and within a first preset time period before the current time; The real-time meteorological data, geographic data and underlying surface data are processed using the time series rolling analysis method to obtain the environmental time series matrix; The environmental time series matrix is input into the trained fog cluster life cycle model, and the fog cluster generation results of each section within the first preset influence radius on both sides of the highway are output; the fog cluster life cycle model is used to simulate the entire life cycle of fog cluster using a neural network.
[0007] In a possible implementation, the real-time meteorological data, geographic data and underlying surface data are processed using a time series rolling analysis method to obtain an environmental time series matrix, including: Preprocessing the real-time meteorological data, geographic data and underlying surface data to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data; The preprocessed real-time meteorological data, the preprocessed geographic data and the preprocessed underlying surface data are gridded according to a second preset influence radius and a second preset time period, and a time series rolling analysis is performed to obtain real-time environmental time series data; the second preset influence radius is smaller than the first preset influence radius, and the second preset time period is smaller than the first preset time period; Based on the real-time environmental timing data, an environmental timing matrix is formed.
[0008] In a possible implementation, real-time meteorological data, geographic data, and underlying surface data are preprocessed to obtain preprocessed real-time meteorological data, preprocessed geographic data, and preprocessed underlying surface data, including: Establish grid data based on real-time meteorological data, geographic data and underlying surface data; The grid data is normalized according to data standard specifications to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data.
[0009] In a possible implementation, the environment timing matrix TW is expressed as:
[0010] in, T Indicates the temperature, represents the characteristic sequence of air temperature arranged in time sequence; P Indicates air pressure, A characteristic sequence representing air pressure in time order; U Indicates the humidity near the ground. A characteristic sequence representing humidity in time order; F Indicates wind speed, represents a characteristic sequence of wind speeds arranged in time order; PW represents the water vapor pressure, Represents a characteristic sequence of water vapor pressures arranged in time order; TU Indicates soil moisture, A characteristic sequence representing soil moisture in time sequence; DX Represents terrain, A sequence of features representing a terrain arranged in time sequence; PD Represents terrain slope data, A characteristic sequence representing the slope of the terrain in time sequence; XD Represents the underlying surface data, Represents a characteristic sequence of underlying surface data arranged in time sequence; ZB Indicates the vegetation type, A characteristic sequence representing vegetation types arranged in time order; SH Represents the distribution of water bodies, A characteristic sequence representing the distribution of water bodies in time order; n Represents the number of features in the environment time series matrix arranged in time order.
[0011] In a possible implementation, the real-time meteorological data includes the temperature, air pressure, humidity, wind direction, wind speed, water vapor pressure and soil humidity within a first preset influence radius on both sides of the highway; The geographic data includes the terrain, terrain slope data, underlying surface data, vegetation type and water body distribution within the first preset influence radius on both sides of the expressway.
[0012] In a possible implementation, before inputting the environmental time series matrix into the trained fog cluster life cycle model, the method for predicting fog clusters along the highway further includes: Obtain historical meteorological data within a first preset influence radius on both sides of the expressway; Based on historical meteorological data, geographic data and underlying surface data, the fog life cycle model is trained to obtain a trained fog life cycle model.
[0013] In a possible implementation, after outputting the fog cluster generation results of each road section within the first preset influence radius on both sides of the highway, the method for predicting fog clusters along the highway further includes: Obtain traffic routes within a first preset influence radius on both sides of the expressway; Based on the fog cluster generation results of each section within the preset influence radius on both sides of the expressway, traffic routes and real-time meteorological data, the target sections that will be affected by the fog cluster are determined, and early warnings are issued for the target sections; the fog cluster generation results include the probability of fog cluster occurrence, time of occurrence, location of occurrence, duration and movement trajectory.
[0014] In a second aspect, the present invention provides a device for predicting fog clusters along a highway, which uses the method for predicting fog clusters along a highway according to the first aspect, including: A data acquisition module, used to acquire real-time meteorological data, geographic data and underlying surface data within a first preset influence radius on both sides of the expressway; The data processing module is used to analyze the real-time meteorological data, geographic data and underlying surface data by rolling the time series to obtain the environmental time series matrix; The prediction and analysis module is used to input the environmental time series matrix into the trained fog group life cycle model, and output the fog group generation results of each section within the first preset influence radius on both sides of the highway; the fog group life cycle model is used to simulate the entire life cycle of fog group using a neural network.
[0015] In a third aspect, the present invention provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the first aspect or any possible implementation method of the first aspect are implemented.
[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the first aspect or any possible implementation method of the first aspect.
[0017] The present invention provides a method, device, terminal and storage medium for predicting fog clusters along highways, which ensure the timeliness and accuracy of model input data by acquiring and processing meteorological data, geographic data and underlying surface data along highways in real time. Compared with video image analysis that can only identify fog conditions that have already occurred, the fog cluster life cycle model accurately simulates the generation and disappearance process of fog clusters through neural networks and deep learning, and outputs detailed results of fog cluster generation in each section of road, including generation probability and specific conditions, thereby improving the accuracy of prediction results. The present invention has shown obvious advantages in data comprehensiveness and accuracy, prediction ability and accuracy, automation and intelligence, resource utilization and cost control, as well as scalability and adaptability, and has promoted the deep integration of the transportation field with information technology and meteorological science, promoted the application and innovation of new technologies in traffic management, and laid the foundation for building a smart transportation system. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0019] Figure 1 This is an application scenario diagram of the method for predicting fog clusters along highways provided by an embodiment of the present invention; Figure 2 It is a flow chart of the implementation of the method for predicting fog clusters along highways provided by an embodiment of the present invention; Figure 3 is a flow chart of fog cluster prediction and model training provided by an embodiment of the present invention; Figure 4 It is a flowchart for implementing the method of obtaining a trained cluster fog life cycle model provided by an embodiment of the present invention; Figure 5 is a flowchart for implementing the time series rolling analysis provided by an embodiment of the present invention; Figure 6 is a schematic diagram of part of the grid data corresponding to the real-time meteorological data provided by an embodiment of the present invention; Figure 7 It is a schematic diagram of a portion of grid data corresponding to static geographic data and underlying surface data provided by an embodiment of the present invention; Figure 8 is a schematic diagram of the structure of a device for predicting fog along a highway provided by an embodiment of the present invention; Fig. 9 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0020] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0021] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.
[0022] Figure 1 This is an application scenario diagram of the method for predicting fog along a highway provided by an embodiment of the present invention. Figure 1 As shown: Some geographic data can be obtained by searching for published information on terrain, vegetation coverage, water distribution and other data on the websites of public institutions. In addition, meteorological data, geographic data and traffic flow data on both sides of the highway can be collected in real time through meteorological observation stations, sensors and other equipment installed along the highway, and stored in database 101. Database 101 is the core data storage center of the fog prediction system.
[0023] The server 102 obtains various data from the database 101, uses neural network algorithms and models to predict fog clusters, and sends the prediction results to user terminals such as traffic management departments and drivers through the router 103 so that they can take timely countermeasures.
[0024] Through such application scenarios, the fog cluster prediction system along the highway can realize real-time monitoring and accurate prediction of fog clusters, providing strong support for traffic management and driving safety.
[0025] See also Figure 2 and Figure 3 , Figure 2 The following is a flowchart of a method for predicting fog clusters along a highway according to an embodiment of the present invention. Figure 3 The following is a flowchart of fog cluster prediction and model training. The following is a detailed description of the fog cluster prediction method along the highway: Step 201, obtaining real-time meteorological data, geographic data and underlying surface data within a first preset influence radius on both sides of the expressway.
[0026] For example, the central and eastern regions are densely populated areas of my country's expressways, and fog is also prevalent. According to statistics, among the expressway sections with more than 10 fogs per year, the most are located in Hunan and Sichuan, with more than 100. Hubei, Fujian, Shandong, and Shanxi are also relatively common. In general, the Yangtze River and the Jiangnan region are more prone to fog. During the peak period, among the expressway sections with more than 50 fogs per year, the peak period for fog is from 22:00 to 8:00 the next day, and November-December and January-March from late autumn to winter are the peak months, which generally occur at night and in the early morning when the temperature difference between day and night is large or there is no wind.
[0027] At the same time, it was found that fog clusters are closely related to the local microclimate environment (temperature, air pressure, humidity, wind), underlying surface water supply, ground roughness, dust, etc. For example, fog clusters are more likely to occur in suburbs and rural areas than in cities. The probability of fog clusters is very high in low-lying areas, near rivers and lakes, mountainous areas after rain, and empty sections of highways. Fog clusters are more likely to occur when the underlying surface data is swamps, water bodies, etc. than when the underlying surface data is land surfaces such as concrete. Therefore, the influence of the underlying surface on fog clusters cannot be ignored.
[0028] The duration of fog clusters usually varies from 1 to 6 hours, and the movement trend is related to the wind and slope. Only when the fog clusters move through transportation facilities such as roads during their existence will they affect traffic, etc., then, the real-time meteorological data includes meteorological data at the current time and within the first preset time period before the current time. The first preset impact radius can be a section of the highway, such as 50km, and the first preset time period can be 6 hours.
[0029] In step 101, the real-time meteorological data includes the temperature, air pressure, humidity, wind direction, wind speed, water vapor pressure and soil moisture within a first preset influence radius on both sides of the highway.
[0030] The geographic data includes the terrain, terrain slope data, vegetation type and water body distribution within the first preset influence radius on both sides of the expressway.
[0031] The underlying surface data include water surface, land surface and agricultural land.
[0032] Step 202, using a time series rolling analysis method to process real-time meteorological data, geographic data and underlying surface data to obtain an environmental time series matrix.
[0033] Establish multivariate time series data from 6 hours before the occurrence to the end of fog cluster, set a fixed time window, for example 12 hours, with a sliding time interval of 30 minutes. After every 30 minutes, add real-time meteorological data to the time series and remove old data points that exceed the time window range to track the entire change process of dynamic data. At the same time, set the weight of each influencing factor and apply it to the subsequent fog cluster life cycle model prediction.
[0034] Step 203, input the environmental time series matrix into the trained fog cluster life cycle model, and output the fog cluster generation results of each road section within the first preset influence radius on both sides of the highway.
[0035] The fog life cycle model is used to simulate the entire life cycle of fog using neural networks.
[0036] This embodiment ensures the timeliness and accuracy of the model input data by acquiring and processing the meteorological data, geographic data and underlying surface data along the highway in real time. Compared with video image analysis that can only identify fog conditions that have already occurred, the fog life cycle model accurately simulates the generation and disappearance process of fog clusters through neural networks and deep learning, and outputs detailed results of fog cluster generation in each section of the road, including generation probability and specific circumstances, thereby improving the accuracy of the prediction results. The present invention has shown obvious advantages in data comprehensiveness and accuracy, prediction ability and accuracy, degree of automation and intelligence, resource utilization and cost control, as well as scalability and adaptability. It has promoted the deep integration of the transportation field with information technology and meteorological science, promoted the application and innovation of new technologies in traffic management, and laid the foundation for building a smart transportation system.
[0037] Figure 4 The following is a flowchart of obtaining a trained cluster fog life cycle model provided by an embodiment of the present invention, which is described in detail as follows: Exemplarily, before inputting the environmental time series matrix into the trained fog cluster life cycle model, the method for predicting fog clusters along the highway further includes: Step 301, obtaining historical meteorological data within a first preset influence radius on both sides of the highway.
[0038] Step 302 trains the fog life cycle model based on historical meteorological data, geographic data and underlying surface data to obtain a trained fog life cycle model.
[0039] In step 302, target real-time meteorological data and target geographic data within the range of the first preset time before the occurrence of fog clusters to the disappearance time are screened from the real-time meteorological data. Grid data is established based on the target historical meteorological data and target geographic data. The grid data is normalized according to the data standard specification to obtain pre-processed historical meteorological data, pre-processed geographic data and pre-processed underlying surface data.
[0040] Exemplarily, relevant data within the range of 6 hours before the occurrence of fog clusters to the time of their disappearance are screened, including the road section where the fog clusters occur, the time of occurrence, the duration, and the real-time data of historical temperature, air pressure, relative humidity, wind speed, water vapor pressure, soil moisture, etc. within 50 km of the surrounding area from 6 hours before the occurrence to the end of the occurrence; static data such as terrain, terrain slope data, underlying surface data, and water body distribution within 50 km on both sides of the research section are collected to establish grid data with a grid unit length of 100m. According to the file content format of various types of data, the grid data is designed into a special data list and data format for fog cluster prediction, and metadata descriptions and data standard specifications are formed. Data cleaning, data standardization, and data dimension reduction are carried out on real-time data such as meteorology and soil, and static underlying surface ecological environment data such as terrain and vegetation types according to data standard specifications, and the data are converted into data files with the same time and space scales to establish a data file set for the process of fog cluster formation and disappearance.
[0041] The pre-processed real-time meteorological data is divided into grid data according to the second preset influence radius and the second preset time period, and a time series rolling analysis is performed to obtain historical environmental time series data. Based on the historical environmental time series data, a historical environmental time series matrix is formed.
[0042] According to the model training requirements, the historical environmental time series matrix and the data set of the fog cluster formation and disappearance process are divided into training set, test set and validation set to train the fog cluster life cycle model.
[0043] Unsupervised learning can be used to establish a fog life cycle model using the Long Short-Term Memory (LSTM) network, the Generative Adversarial Networks (GAN) framework + Wasserstein distance method. Based on historical meteorological data, geographic data and underlying surface data of the historical fog generation and disappearance process, the GAN generator and discriminator are generated for training, and the evaluation index can be constructed using reconstruction loss and prediction difference. The model is evaluated using the root mean square error method. By repeatedly evaluating and optimizing the model, better unsupervised learning results can be obtained until the fog life cycle model meets the evaluation accuracy requirements, for example, the evaluation accuracy can reach 80% or above.
[0044] This embodiment can significantly improve the prediction accuracy of the occurrence, development and disappearance of fog along the highway by training the fog life cycle model based on historical meteorological data, geographic data and underlying surface data, and using advanced machine learning techniques (such as LSTM and GAN framework + Wasserstein distance method). This helps to reduce traffic accidents caused by fog and improve road safety. Through the screening and gridding of real-time meteorological data, as well as time series rolling analysis, the solution can timely detect precursor information of fog and provide traffic management departments with earlier and more accurate warnings, so that there is enough time to take countermeasures, such as limiting vehicle speed, turning on fog lights, etc., to ensure driving safety.
[0045] Figure 5 The following is a flowchart of implementing the time series rolling analysis provided by an embodiment of the present invention, which is described in detail as follows: Exemplarily, step 202 may include: Step 2021, preprocessing the real-time meteorological data, geographic data and underlying surface data to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data.
[0046] In step 221, based on real-time meteorological data, geographic data and underlying surface data, grid data is established, such as Figure 6 The real-time meteorological data shown corresponds to some grid data and Figure 7 The static geographic data and partial grid data corresponding to the underlying surface data shown; the grid data is normalized according to the data standard specification to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data.
[0047] Step 2022, the preprocessed real-time meteorological data, the preprocessed geographic data and the preprocessed underlying surface data are gridded according to the second preset influence radius and the second preset time period, and a time series rolling analysis is performed to obtain real-time environmental time series data.
[0048] The pre-processed real-time meteorological data, pre-processed geographic data, and pre-processed underlying surface data are still the data of the first preset influence radius and the first preset time period on both sides of the expressway. In order to improve the efficiency of data processing, the grid data is segmented according to the second preset influence radius and the second preset time for analysis. Therefore, the second preset influence radius is smaller than the first preset influence radius, the second preset time period is smaller than the first preset time period, and the first preset influence radius is an integer multiple of the second preset influence radius, and the first preset time period is an integer multiple of the second preset time period.
[0049] For example, the first preset influence radius can be set to 50km. If the second preset influence radius can be set to 5km, there are 10 groups of grid data on both sides of the highway, for a total of 20 groups. If the second preset influence radius can be set to 1km, there are 50 groups of grid data on both sides of the highway, for a total of 100 groups. Each group of grid data can form corresponding real-time environmental time series data.
[0050] Step 2023, forming an environment timing matrix based on the real-time environment timing data.
[0051] Exemplarily, the environment timing matrix TW can be expressed as:
[0052] in, T Indicates the temperature, represents the characteristic sequence of air temperature arranged in time sequence; P Indicates air pressure, A characteristic sequence representing air pressure in time order; U Indicates the humidity near the ground. A characteristic sequence representing humidity in time order; F Indicates wind speed, represents a characteristic sequence of wind speeds arranged in time order; PW represents the water vapor pressure, Represents a characteristic sequence of water vapor pressures arranged in time order; TU Indicates soil moisture, A characteristic sequence representing soil moisture in time sequence; DX Represents terrain, A sequence of features representing a terrain arranged in time sequence; PD Represents terrain slope data, A characteristic sequence representing the slope of the terrain in time sequence; XD Represents the underlying surface data, Represents a characteristic sequence of underlying surface data arranged in time sequence; ZB Indicates the vegetation type, A characteristic sequence representing vegetation types arranged in time order; SH Represents the distribution of water bodies, A characteristic sequence representing the distribution of water bodies in time order; n Represents the number of features in the environment time series matrix arranged in time order.
[0053] Of course, the characteristic elements in the above-mentioned environment timing matrix may increase as the acquired data type increases.
[0054] The embodiment of the present invention normalizes the grid data according to the data standard specification to ensure that data of different dimensions and ranges can be compared and analyzed on the same scale, thereby improving the accuracy and efficiency of data analysis. The preprocessed data is sliced according to the second preset influence radius and the second preset time period to reduce the amount of data processed at a single time and improve processing efficiency. At the same time, this slicing method also conforms to the characteristics of time series data and is convenient for capturing the time change trend in the data. Time series analysis is performed on each data slice to extract characteristic information in the time series, such as trends, periodicity, outliers, etc., to form real-time environmental time series data, effectively extract characteristic information in the data, and provide a basis for subsequent advanced analysis such as prediction and modeling. The data structure in matrix form makes subsequent data analysis simpler and more efficient.
[0055] In one embodiment, after outputting the fog cluster generation results of each road section within the first preset influence radius on both sides of the highway, the method for predicting fog clusters along the highway further includes: The traffic routes within the first preset influence radius on both sides of the expressway are obtained, wherein the adjacent routes or county roads or national roads and other related traffic routes within 50km along the expressway are obtained.
[0056] Based on the fog cluster generation results of each section within the preset influence radius along the expressway, traffic routes and real-time meteorological data, the target sections that will be affected by the fog cluster are determined, and early warnings are issued for the target sections; the fog cluster generation results include the probability of fog cluster occurrence, time of occurrence, location of occurrence, duration and movement trajectory.
[0057] Among them, the target section includes not only a section of the highway affected by the fog, but also the adjacent lines or county roads or national highways and other related traffic routes within 50km along the highway affected by the fog. In this way, it is possible to locate the section of the highway affected by the fog, and also help the nearby traffic sections to provide warnings before the fog reaches the traffic facilities, thereby reducing the incidence of traffic accidents.
[0058] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0059] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.
[0060] Figure 8 The schematic diagram of the structure of the device for predicting fog clusters along highways provided by an embodiment of the present invention is shown. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows: like Figure 8 As shown, a device 4 for predicting fog along a highway includes a data acquisition module 41 , a data processing module 42 and a prediction and analysis module 43 .
[0061] The data acquisition module 41 is used to acquire real-time meteorological data, geographical data and underlying surface data within a first preset influence radius on both sides of the expressway; The data processing module 42 is used to analyze the real-time meteorological data, geographic data and underlying surface data by rolling using the time series to obtain the environmental time series matrix; The prediction and analysis module 43 is used to input the environmental time series matrix into the trained fog group life cycle model, and output the fog group generation results of each section within the first preset influence radius on both sides of the highway; the fog group life cycle model is used to simulate the entire life cycle of fog group using a neural network.
[0062] The embodiments of the present invention ensure the timeliness and accuracy of the model input data by acquiring and processing the meteorological data, geographic data and underlying surface data along the highway in real time. Compared with the video image analysis that can only identify the fog conditions that have already occurred, the fog life cycle model accurately simulates the generation and disappearance process of fog clusters through neural networks and deep learning, and outputs detailed results of fog cluster generation in each section of the road, including generation probability and specific circumstances, thereby improving the accuracy of the prediction results. The present invention has shown obvious advantages in data comprehensiveness and accuracy, prediction ability and accuracy, automation and intelligence, resource utilization and cost control, as well as scalability and adaptability. It has promoted the deep integration of the transportation field with information technology and meteorological science, promoted the application and innovation of new technologies in traffic management, and laid the foundation for building a smart transportation system.
[0063] In a possible implementation, the device for predicting fog clusters along highways further includes a model training module. The model training module is specifically used for: Before inputting the environment time series matrix into the trained cluster fog life cycle model: Obtain historical meteorological data within a first preset influence radius on both sides of the expressway; Based on historical meteorological data, geographic data and underlying surface data, the fog life cycle model is trained to obtain a trained fog life cycle model.
[0064] In a possible implementation, the analysis module 42 is specifically used for: Preprocessing the real-time meteorological data, geographic data and underlying surface data to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data; The preprocessed real-time meteorological data, the preprocessed geographic data and the preprocessed underlying surface data are gridded according to a second preset influence radius and a second preset time period, and a time series rolling analysis is performed to obtain real-time environmental time series data; the second preset influence radius is smaller than the first preset influence radius, and the second preset time period is smaller than the first preset time period; Based on the real-time environmental timing data, an environmental timing matrix is formed.
[0065] In a possible implementation, real-time meteorological data, geographic data, and underlying surface data are preprocessed to obtain preprocessed real-time meteorological data, preprocessed geographic data, and preprocessed underlying surface data, including: Establish grid data based on real-time meteorological data, geographic data and underlying surface data; The grid data is normalized according to data standard specifications to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data.
[0066] In a possible implementation, the environment timing matrix TW is expressed as:
[0067] in, T Indicates the temperature, represents the characteristic sequence of air temperature arranged in time sequence; P Indicates air pressure, A characteristic sequence representing air pressure in time order; U Indicates the humidity near the ground. A characteristic sequence representing humidity in time order; F Indicates wind speed, represents a characteristic sequence of wind speeds arranged in time order; PW represents the water vapor pressure, Represents a characteristic sequence of water vapor pressures arranged in time order; TU Indicates soil moisture, A characteristic sequence representing soil moisture in time sequence; DX Represents terrain, A sequence of features representing a terrain arranged in time sequence; PD Represents terrain slope data, A characteristic sequence representing the slope of the terrain in time sequence; XD Represents the underlying surface data, Represents a characteristic sequence of underlying surface data arranged in time sequence; ZB Indicates the vegetation type, A characteristic sequence representing vegetation types arranged in time order; SH Represents the distribution of water bodies, A characteristic sequence representing the distribution of water bodies in time order; n Represents the number of features in the environment time series matrix arranged in time order.
[0068] In a possible implementation, in the data acquisition module 41, the real-time meteorological data includes the temperature, air pressure, humidity, wind direction, wind speed, water vapor pressure and soil humidity within a first preset influence radius on both sides of the highway; The geographic data includes the terrain, terrain slope data, underlying surface data, vegetation type and water body distribution within the first preset influence radius on both sides of the expressway.
[0069] In a possible implementation, the device for predicting fog along a highway further includes an early warning module. The early warning module is specifically used for: After outputting the fog cluster generation results of each road section within the first preset influence radius on both sides of the highway: Obtain traffic routes within a first preset influence radius on both sides of the expressway; Based on the fog cluster generation results of each section within the preset influence radius along the expressway, traffic routes and real-time meteorological data, the target sections that will be affected by the fog cluster are determined, and early warnings are issued for the target sections; the fog cluster generation results include the probability of fog cluster occurrence, time of occurrence, location of occurrence, duration and movement trajectory.
[0070] Fig. 9 is a schematic diagram of a terminal provided by an embodiment of the present invention. Fig. 9 As shown, the terminal 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above-mentioned various highway fog prediction method embodiments are implemented, for example Figure 2 Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 8 Functions of the modules / units 41 to 43 are shown.
[0071] Exemplarily, the computer program 52 may be divided into one or more modules / units, one or more modules / units are stored in the memory 51 and executed by the processor 50 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the terminal 5. For example, the computer program 52 may be divided into Figure 8 Modules / units 41 to 43 are shown.
[0072] The terminal 5 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Fig. 9 It is only an example of terminal 5 and does not constitute a limitation on terminal 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0073] The processor 50 may be a central processing unit (CPU), a graphics processing unit (GPU) or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0074] The memory 51 may be an internal storage unit of the terminal 5, such as a hard disk or memory of the terminal 5. The memory 51 may also be an external storage device of the terminal 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 5. Further, the memory 51 may also include both an internal storage unit of the terminal 5 and an external storage device. The memory 51 is used to store computer programs and other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.
[0075] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0076] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0077] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0078] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0080] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0081] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned embodiments of the method for predicting fog clusters along the highway can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.
[0082] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for predicting fog along a highway, characterized in that: include: Obtain real-time meteorological data, geographic data and underlying surface data within the first preset influence radius on both sides of the expressway; The real-time meteorological data includes meteorological data at the current time and within a first preset time period before the current time; Processing the real-time meteorological data, geographic data and underlying surface data using a time series rolling analysis method to obtain an environmental time series matrix; Input the environmental time series matrix into the trained fog cluster life cycle model, and output the fog cluster generation result within the first preset influence radius on both sides of the highway; The fog cluster life cycle model is used to simulate the entire life cycle of fog clusters using a neural network.
2. The method for predicting fog along a highway according to claim 1, characterized in that: The real-time meteorological data, geographic data and underlying surface data are processed by the time series rolling analysis method to obtain an environmental time series matrix, including: Preprocessing the real-time meteorological data, the geographic data and the underlying surface data to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data; The preprocessed real-time meteorological data, the preprocessed geographic data and the preprocessed underlying surface data are gridded according to a second preset influence radius and a second preset time period, and a time series rolling analysis is performed to obtain real-time environmental time series data; the second preset influence radius is smaller than the first preset influence radius, and the second preset time period is smaller than the first preset time period; Based on the real-time environmental timing data, an environmental timing matrix is formed.
3. The method for predicting fog along a highway according to claim 2, characterized in that: The preprocessing of the real-time meteorological data, the geographic data and the underlying surface data to obtain the preprocessed real-time meteorological data, the preprocessed geographic data and the preprocessed underlying surface data comprises: Establishing grid data based on the real-time meteorological data, the geographic data and the underlying surface data; The grid data is normalized according to data standard specifications to obtain preprocessed real-time meteorological data, preprocessed geographic data and preprocessed underlying surface data.
4. The method for predicting fog along a highway according to claim 2, characterized in that: The environment timing matrix TW is expressed as: in, T Indicates the temperature, represents the characteristic sequence of air temperature arranged in time sequence; P Indicates air pressure, A characteristic sequence representing air pressure in time order; U Indicates the humidity near the ground. A characteristic sequence representing humidity in time order; F Indicates wind speed, represents a characteristic sequence of wind speeds arranged in time order; PW represents the water vapor pressure, Represents a characteristic sequence of water vapor pressures arranged in time order; TU Indicates soil moisture, A characteristic sequence representing soil moisture in time sequence; DX Represents terrain, A sequence of features representing a terrain arranged in time sequence; PD Represents terrain slope data, A characteristic sequence representing the slope of the terrain in time sequence; XD Represents the underlying surface data, Represents a characteristic sequence of underlying surface data arranged in time sequence; ZB Indicates the vegetation type, A characteristic sequence representing vegetation types arranged in time order; SH Represents the distribution of water bodies, A characteristic sequence representing the distribution of water bodies in time order; n It represents the number of each feature arranged in time sequence in the environment time sequence matrix.
5. The method for predicting fog along a highway according to any one of claims 1 to 4, characterized in that: The real-time meteorological data includes the temperature, air pressure, humidity, wind direction, wind speed, water vapor pressure and soil humidity within a first preset influence radius on both sides of the expressway; The geographic data includes the terrain, terrain slope data, vegetation type and water body distribution within a first preset influence radius on both sides of the expressway; The underlying surface data includes water surface, land surface and agricultural land.
6. The method for predicting fog along a highway according to claim 1, characterized in that: Before inputting the environmental time series matrix into the trained fog cluster life cycle model, the method for predicting fog clusters along the highway further includes: Obtain historical meteorological data within a first preset influence radius on both sides of the expressway; Based on the historical meteorological data, the geographical data and the underlying surface data, the fog life cycle model is trained to obtain a trained fog life cycle model.
7. The method for predicting fog along a highway according to claim 1, characterized in that: After outputting the fog cluster generation results of each road section within the first preset influence radius on both sides of the expressway, the method for predicting fog clusters along the expressway further includes: Obtain traffic routes within a first preset influence radius on both sides of the expressway; Based on the fog cluster generation results of each section within the preset influence radius on both sides of the expressway, the traffic routes and the real-time meteorological data, the target sections that will be affected by the fog cluster are determined, and early warnings are issued for the target sections; the fog cluster generation results include the probability of fog cluster occurrence, the time of occurrence, the location of occurrence, the duration and the movement trajectory; the fog cluster generation results are used to calculate the affected expressway sections, the affected time and the visibility level.
8. A device for predicting fog along a highway, characterized in that: The method for predicting fog clusters along a highway as claimed in any one of claims 1 to 7 is applied, comprising: A data acquisition module, used to acquire real-time meteorological data, geographic data and underlying surface data within a first preset influence radius on both sides of the expressway; A data processing module is used to analyze the real-time meteorological data, geographic data and underlying surface data by rolling using a time series to obtain an environmental time series matrix; The prediction and analysis module is used to input the environmental time series matrix into the trained fog group life cycle model, and output the fog group generation results of each section within the first preset influence radius on both sides of the highway; the fog group life cycle model is used to simulate the entire life cycle of fog group using a neural network.
9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for predicting fog clusters along highways as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting fog clusters along a highway as described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Highway agglomerate fog prediction method based on multi-source data fusion and electronic equipment
CN121747337A
Strait agglomerate fog full-life-cycle advanced maneuver forecasting method
CN122283981A
