Traffic meteorological data fusion method based on inverse distance weight interpolation

Abstract

The invention discloses a traffic meteorological data fusion method based on inverse distance weight interpolation, and relates to the technical field of traffic meteorological data fusion. The traffic meteorological data fusion method based on inverse distance weight interpolation comprises the following steps: acquiring longitude values, latitude values and visibility measurement values of a plurality of time points of each traffic meteorological station in a set area; each traffic weather station in the set area is screened and analyzed based on the visibility measurement values of the plurality of time points to obtain a plurality of effective traffic weather stations, and the data from different time points and places are integrated and analyzed, so that the data utilization rate and accuracy are remarkably improved; the time sequence analysis of the visibility helps to understand the behavior pattern of each station changing with time, the spatial analysis ensures the continuity and consistency of data in geography, and the integration method optimizes the data processing flow, so that the visibility prediction is more accurate, and the complex traffic and meteorological condition analysis is effectively supported.

Description

Technical Field

[0001] The invention relates to the technical field of traffic meteorological data fusion, and in particular to a traffic meteorological data fusion method based on inverse distance weighted interpolation. Background Art

[0002] Traffic weather data is essential to maintaining and improving the safety, efficiency, and reliability of transportation systems. Effective traffic management systems rely on accurate weather information to predict and respond to traffic disruptions and accidents caused by severe weather conditions. Especially in complex geographical environments and changing climate conditions, accurate weather data is essential for planning routes, adjusting traffic flows, and ensuring the safety of drivers and passengers.

[0003] Although the existing traffic meteorological information system has made significant progress in data collection and processing, there are still some key technical challenges: meteorological observation sites are often uneven in geographical distribution, resulting in sparse data in some areas and difficulty in accurate prediction. The existing system often faces delays when processing and transmitting large amounts of real-time data, which reduces the timeliness and practical value of the data. Traditional data fusion methods fail to make full use of existing spatial data resources and usually cannot effectively provide high-precision meteorological information.

[0004] Based on the above scheme, it is found that the limitations of the existing technology include at least the following problems. First, the existing methods mostly rely on data analysis of static time points, fail to make full use of continuous time series data, and ignore the important impact of time changes on traffic meteorological conditions, making it difficult to accurately predict and respond to rapidly changing meteorological conditions, such as sudden haze or rainfall, which affects road safety and traffic efficiency. Secondly, the fusion processing of spatial data is usually limited to simple analysis of a single area or point-to-point, and lacks a comprehensive assessment of the interactive impact between multiple traffic meteorological stations in a wider area, which can easily lead to data in some areas being over-emphasized or ignored in a wide transportation network, resulting in uneven resource allocation and inaccurate response measures. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a traffic meteorological data fusion method based on inverse distance weighted interpolation, which solves the problems that the prior methods mostly rely on data analysis of static time points, fail to make full use of continuous time series data, and ignore the important impact of time changes on traffic meteorological conditions, making it difficult to accurately predict and respond to rapidly changing meteorological conditions, such as sudden haze or rainfall, which affects road safety and traffic efficiency. Secondly, the fusion processing of spatial data is usually limited to a single area or simple point-to-point analysis, lacking a comprehensive assessment of the interactive impact between multiple traffic meteorological stations in a wider area, which can easily lead to the data of some areas being over-emphasized or ignored in a wide traffic network, resulting in uneven resource allocation and inaccurate response measures.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a traffic meteorological data fusion method based on inverse distance weighted interpolation, comprising the following steps: obtaining the longitude value, latitude value, and visibility measurement value of each traffic meteorological station in a set area at several time points; screening and analyzing each traffic meteorological station in the set area based on the visibility measurement values ​​at several time points to obtain several valid traffic meteorological stations; establishing a visibility table based on the longitude value, latitude value, and visibility measurement value of several valid traffic meteorological stations in the set area; and fusing the visibility table based on the inverse distance weighted interpolation method.

[0007] Furthermore, the specific steps for obtaining a number of valid traffic meteorological stations are as follows: for each traffic meteorological station in the set area, a mean analysis is performed based on the visibility measurement values ​​at a number of time points and the moving exponential average method to obtain the visibility measurement mean of each traffic meteorological station in the set area; it is determined whether the visibility measurement mean of each traffic meteorological station in the set area is respectively within a preset limit threshold range, and the traffic meteorological stations whose visibility measurement mean is outside the preset limit threshold range are screened out; after the screening process, the remaining traffic meteorological stations are spatially screened to obtain a number of valid traffic meteorological stations.

[0008] Furthermore, the specific formula for calculating the mean visibility measurement value of each traffic meteorological station in the set area is as follows: Among them, NjJ i is the mean visibility measurement value of the ith traffic meteorological station in the set area, NjC iu is the visibility measurement value of the i-th traffic meteorological station in the set area at the u-th time point, α iu1 is the weighting coefficient of the visibility measurement value at the i-th traffic meteorological station in the set area at the u-th time point, NjC i(u+1) is the visibility measurement value of the i-th traffic meteorological station in the set area at the u+1th time point, αiu2 is the weighting coefficient of the visibility measurement value at the i-th traffic meteorological station in the set area at the u+1th time point, α iu1 +α iu2 =1, i=1, 2, 3, ..., i0, i0 is the number of traffic meteorological stations in the set area, u=1, 2, 3, ..., u0, u0 is the number of acquired time points.

[0009] Furthermore, after the screening process, the specific steps of spatial screening of the remaining traffic meteorological stations are as follows: for each remaining traffic meteorological station, the number of traffic meteorological stations within the set analysis area is counted respectively, and the visibility analysis mean is analyzed; the visibility measurement mean of each remaining traffic meteorological station is difference analyzed with the visibility analysis mean, and the visibility difference value of each remaining traffic meteorological station is obtained; it is determined whether the visibility difference value of each remaining traffic meteorological station is lower than the visibility difference threshold, and the remaining traffic meteorological stations whose visibility difference values ​​are not lower than the visibility difference threshold are screened out to obtain a number of valid traffic meteorological stations.

[0010] Furthermore, the specific formula for calculating the visibility analysis mean and visibility difference value of each remaining traffic meteorological station is as follows: Among them, NjF r is the mean value of visibility analysis of the remaining rth traffic meteorological station, NjJ rt is the mean visibility measurement value of the t-th traffic meteorological station within the set analysis area of ​​the remaining r-th traffic meteorological station, Q rt is the weight coefficient of the mean visibility measurement value of the tth traffic meteorological station within the set analysis area of ​​the remaining rth traffic meteorological station, NjY r is the visibility difference value of the remaining rth traffic meteorological station, NjJ r is the mean visibility measurement value of the remaining rth traffic meteorological station, r = 1, 2, 3, ..., r0, r0 is the number of remaining traffic meteorological stations, t = 1, 2, 3, ..., t0, t0 is the number of traffic meteorological stations within the set analysis area.

[0011] Furthermore, the specific steps of establishing a visibility table are as follows: establishing an initial visibility table with longitude as the horizontal coordinate and latitude as the vertical coordinate; based on the longitude and latitude values ​​of each valid traffic meteorological station, finding the actual position coordinate point of each valid traffic meteorological station in the initial visibility table; obtaining the detection range of each valid traffic meteorological station, and marking the detection range corresponding to the actual position coordinate point of each valid traffic meteorological station in the initial visibility table with the visibility measurement mean, so as to obtain the visibility table.

[0012] Furthermore, the specific steps of fusing the visibility table based on the inverse distance weighted interpolation method are as follows: the visibility table is gridded based on a preset interpolation grid size to obtain a number of visibility grids; for each visibility grid, the visibility measurement mean of a number of adjacent visibility grids within a preset interpolation grid area is analyzed by combining the mean method and the inverse distance weighted interpolation method to obtain a first visibility interpolation value and a second visibility interpolation value of each visibility grid; the first visibility interpolation value and the second visibility interpolation value of each visibility grid are comprehensively analyzed to obtain a visibility fusion value of each visibility grid.

[0013] Furthermore, the specific formula for calculating the first visibility interpolation value and the second visibility interpolation value of each visibility grid is as follows: Among them, YnC a is the first visibility interpolation of the ath visibility grid, NjJ ab is the average visibility measurement value of the bth adjacent visibility grid in the preset interpolation grid area of ​​the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, JL ab is the grid distance value between the ath visibility grid and the bth adjacent visibility grid in the preset interpolation grid area, k is the weight attenuation parameter, a=1, 2, 3, ..., a0, a0 is the number of visibility grids, b=1, 2, 3, ..., b0, b0 is the number of adjacent visibility grids in the preset interpolation grid area.

[0014] Furthermore, the specific formula for calculating the visibility fusion value of each visibility grid is as follows: NhZ a =ω a1 *YnC a +ω a2 *EnC a Among them, NhZ a is the visibility fusion value of the ath visibility grid, YnC a is the first visibility interpolation of the ath visibility grid, ω a1 is the scale factor of the first visibility interpolation of the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, ω a2 is the scale factor of the second visibility interpolation of the ath visibility grid, ω a1 +ω a2 =1, a=1,2,3,…,a0, a0 is the number of visibility grids.

[0015] The present invention has the following beneficial effects:

[0016] (1) This traffic and meteorological data fusion method based on inverse distance weighted interpolation significantly improves data utilization and accuracy by integrating and analyzing data from different time points and locations. The time series analysis of visibility helps to understand the behavior patterns of each station over time, while spatial analysis ensures the geographical continuity and consistency of the data. This integrated method optimizes the data processing process, making visibility prediction more accurate and effectively supporting the analysis of complex traffic and meteorological conditions.

[0017] (2) This traffic and meteorological data fusion method based on inverse distance weighted interpolation is crucial in traffic management and meteorological monitoring, as it is able to accurately predict and respond to adverse weather conditions in real time. This data fusion technology based on inverse distance weighted interpolation provides highly reliable visibility information, enabling emergency management teams to make data-based decisions quickly, which not only reduces traffic accidents and delays caused by weather, but also significantly improves road use efficiency and safety.

[0018] (3) This traffic meteorological data fusion method based on inverse distance weighted interpolation, accurate visibility information allows traffic management departments to allocate resources more effectively, for example, adjusting the working mode of traffic lights or deploying emergency services to deal with low visibility conditions. In addition, by identifying possible areas with poor visibility in advance, preventive maintenance and intervention can be carried out, thereby reducing operational disruptions and maintenance costs caused by sudden weather conditions. This method improves overall operational efficiency and reduces additional costs incurred by emergency response.

[0019] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The present invention is a flow chart of a traffic meteorological data fusion method based on inverse distance weighted interpolation.

[0021] Figure 2 The present invention is a flowchart of the specific steps of obtaining a plurality of effective traffic meteorological sites in a traffic meteorological data fusion method based on inverse distance weighted interpolation.

[0022] Figure 3 The present invention is a schematic diagram of a grid that requires interpolation calculation in a traffic meteorological data fusion method based on inverse distance weighted interpolation. DETAILED DESCRIPTION

[0023] The embodiment of the present application uses a traffic meteorological data fusion method based on inverse distance weighted interpolation to solve the problems that the existing methods mostly rely on data analysis of static time points, fail to fully utilize continuous time series data, and ignore the important impact of time changes on traffic meteorological conditions, making it difficult to accurately predict and respond to rapidly changing meteorological conditions, such as sudden haze or rainfall, which affects road safety and traffic efficiency. Secondly, the fusion processing of spatial data is usually limited to simple analysis of a single area or point-to-point, and lacks a comprehensive assessment of the interactive impact between multiple traffic meteorological stations in a wider area, which can easily lead to data in some areas being over-emphasized or ignored in a wide transportation network, resulting in uneven resource allocation and inaccurate response measures.

[0024] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0025] First, comprehensive data collection is carried out, including obtaining longitude, latitude and visibility measurements at multiple time points from each traffic meteorological station. Using these data, the moving exponential average method is used to calculate the mean visibility measurement for each station. The visibility measurement mean is screened according to the preset threshold to exclude those stations that do not meet the standards. For the qualified stations, further spatial screening is carried out to determine which stations’ data are relevant and reliable for subsequent data fusion processing. The screened station data are fused using the inverse distance weighted interpolation method to establish a detailed visibility table. This table not only reflects the location and visibility of each station, but also creates a continuous spatial data model through interpolation for final decision support and application.

[0026] See also Figure 1 The embodiment of the present invention provides a technical solution: a traffic meteorological data fusion method based on inverse distance weighted interpolation, comprising the following steps: obtaining the longitude value, latitude value, and visibility measurement value of each traffic meteorological station in a set area at several time points (continuously obtained), obtaining the longitude and latitude values ​​through a global positioning system (GPS) device, and obtaining the visibility measurement value through a meteorological sensor, such as a visibility meter (for example, a laser scatter meter or a forward scatter meter); screening and analyzing each traffic meteorological station in the set area based on the visibility measurement values ​​at several time points to obtain several valid traffic meteorological stations; establishing a visibility table based on the longitude value, latitude value, and visibility measurement values ​​of several valid traffic meteorological stations in the set area; and fusing the visibility table based on the inverse distance weighted interpolation method.

[0027] Specifically, Figure 2As shown, the specific steps for obtaining a number of valid traffic meteorological stations are as follows: for each traffic meteorological station in the set area, a mean analysis is performed based on the visibility measurement values ​​at a number of time points and the moving exponential average method to obtain the visibility measurement mean of each traffic meteorological station in the set area; it is determined whether the visibility measurement mean of each traffic meteorological station in the set area is respectively within the preset limit threshold range, and the traffic meteorological stations whose visibility measurement mean is outside the preset limit threshold range (for example, the visibility range is 0 meters to 30,000 meters) are screened out; after the screening process, the remaining traffic meteorological stations are spatially screened to obtain a number of valid traffic meteorological stations.

[0028] The specific formula for calculating the mean visibility measurement value for each traffic weather station in a set area is as follows: Among them, NjJ i is the mean visibility measurement value of the ith traffic meteorological station in the set area, NjC iu is the visibility measurement value of the i-th traffic meteorological station in the set area at the u-th time point, α iu1 is the weighting coefficient of the visibility measurement value at the i-th traffic meteorological station in the set area at the u-th time point, NjC i(u+1) is the visibility measurement value of the i-th traffic meteorological station in the set area at the u+1th time point, α iu2 is the weighting coefficient of the visibility measurement value at the i-th traffic meteorological station in the set area at the u+1th time point, α iu1 +α iu2 =1, i=1, 2, 3, ..., i0, i0 is the number of traffic meteorological stations in the set area, u=1, 2, 3, ..., u0, u0 is the number of acquired time points.

[0029] It needs to be explained that α iu1 , α iu2 The specific calculation process of is: summing up and analyzing the visibility measurement values ​​of the i-th traffic meteorological station in the set area at the u-th and u+1-th time points to obtain the u-th group of visibility measurement and value of the i-th traffic meteorological station in the set area, and then performing ratio analysis on the visibility measurement values ​​of the i-th traffic meteorological station in the set area at the u-th and u+1-th time points with the u-th group of visibility measurement and value, and the ratio analysis result is the corresponding weighting coefficient.

[0030] In this implementation scheme, by performing moving exponential averaging analysis on the visibility measurements of each traffic meteorological station at different time points, this method can more accurately reflect the average visibility level of the station. Moving exponential averaging is a technology that provides smooth data output and can effectively reduce the errors caused by random fluctuations, thereby providing more stable and reliable data. This method is particularly suitable for processing meteorological data with time series characteristics because it can emphasize the weight of recent observations, thereby more accurately reflecting the latest changes in meteorological conditions. By setting a limit threshold to screen out stations with qualified visibility measurement averages, it can ensure that resources and attention are only focused on those stations that provide valuable data. This process helps to filter out data with poor quality or that do not meet analysis requirements. stations, thereby reducing the interference of invalid or misleading data on the overall analysis. As a result, decision makers can make more informed strategic and operational decisions based on higher quality and more relevant data sets, such as traffic control and emergency response measures for specific areas. After preliminary data cleaning and screening, the spatial screening processing of the remaining traffic meteorological stations allows for comprehensive coverage and evaluation of the meteorological conditions in the entire set area. This spatial screening not only enhances the geographical representativeness of the data, but also ensures the continuity and consistency of the data in spatial distribution. In addition, by further fusing these data through the inverse distance weighted interpolation method, a coherent visibility analysis map can be formed in the entire region, providing a solid data foundation for regional-level weather condition monitoring and traffic safety management.

[0031] Specifically, after the screening process, the specific steps for spatial screening of the remaining traffic meteorological stations are as follows: for each remaining traffic meteorological station, the number of traffic meteorological stations within the set analysis area is counted respectively, and the visibility analysis mean is analyzed (calculated by the visibility measurement mean of each traffic meteorological station within the set analysis area); the visibility measurement mean of each remaining traffic meteorological station is difference analyzed with the visibility analysis mean, and the visibility difference value of each remaining traffic meteorological station is obtained; it is determined whether the visibility difference value of each remaining traffic meteorological station is lower than the visibility difference threshold (for example, 7500 meters, that is, when the difference value is 7500 meters and above, the station value is suspected to be erroneous, and the national station instrument adopts DNQ3 equipment, which has been subjected to a large number of experiments and verifications on stability and quality control rate), and the remaining traffic meteorological stations whose visibility difference values ​​are not lower than the visibility difference threshold are screened out to obtain a number of valid traffic meteorological stations.

[0032] The specific formula for calculating the visibility analysis mean and visibility difference value of each remaining traffic meteorological station is as follows: Among them, NjF r is the mean value of visibility analysis of the remaining rth traffic meteorological station, NjJ rtis the mean visibility measurement value of the t-th traffic meteorological station within the set analysis area of ​​the remaining r-th traffic meteorological station, Q rt is the weight coefficient of the mean visibility measurement value of the tth traffic meteorological station within the set analysis area of ​​the remaining rth traffic meteorological station, NjY r is the visibility difference value of the remaining rth traffic meteorological station, NjJ r is the mean visibility measurement value of the remaining rth traffic meteorological station, r=1, 2, 3, …, r0, r0 is the number of remaining traffic meteorological stations, t=1, 2, 3, …, t0, t0 is the number of traffic meteorological stations within the set analysis area, and r0≤i0, t0≤i0.

[0033] It needs to be explained that Q rt The specific calculation process is as follows: summing up and analyzing the mean visibility measurement values ​​of each traffic meteorological station within the set analysis area of ​​the remaining r-th traffic meteorological station to obtain the visibility measurement analysis sum value of the remaining r-th traffic meteorological station, and then performing a ratio analysis on the visibility measurement mean value of the t-th traffic meteorological station within the set analysis area of ​​the remaining r-th traffic meteorological station and the visibility measurement analysis sum value, and the ratio analysis result is the corresponding weight coefficient.

[0034] In this implementation scheme, by analyzing the visibility difference values ​​of the remaining traffic meteorological stations and comparing them with the set difference threshold, this step ensures that only the most accurate and reliable data are used for further analysis and decision making. In this way, those stations that may have data deviations due to equipment failure, environmental interference or other non-meteorological factors can be effectively excluded. This screening mechanism enhances the overall quality of the data set and provides a solid data foundation for traffic safety and meteorological response plans. Using the difference between the mean visibility measurement and the regional average as a screening criterion not only helps to identify and maintain those stations that provide high-quality data, but also can effectively optimize the allocation of monitoring resources. For example, it can reduce the number of stations that continue to This approach reduces investment in poorly performing sites and focuses resources and attention on sites with high data quality that are more critical to the overall network analysis. This approach helps reduce operating costs and improve service quality by improving the efficiency of data collection and analysis. Through spatial screening processing, it ensures that the distribution of the final selected sites can represent the entire monitoring area, thereby enhancing the spatial continuity and coverage of the data. This not only helps to provide more accurate regional meteorological analysis, but also provides more comprehensive support when forecasting large-scale meteorological events and formulating response strategies. For example, when planning traffic control and emergency response measures for extreme meteorological conditions such as haze and heavy rain, data with high spatial representativeness can ensure the pertinence and effectiveness of the measures.

[0035] Specifically, the specific steps for establishing a visibility table are as follows: establish an initial visibility table with longitude as the horizontal coordinate and latitude as the vertical coordinate (this grid covers the geographical locations of all stations, and each grid point corresponds to a longitude and latitude); based on the longitude and latitude values ​​of each valid traffic meteorological station, find the actual location coordinate point of each valid traffic meteorological station in the initial visibility table; obtain the detection range of each valid traffic meteorological station (for example, a circular detection range, obtained from the technical specification manual provided by the equipment manufacturer), and mark the detection range corresponding to the actual location coordinate point of each valid traffic meteorological station in the initial visibility table with the mean visibility measurement value, so as to obtain a visibility table (if the ranges of valid traffic meteorological stations overlap, then for the overlapping part, the visibility measurement means of the valid traffic meteorological stations corresponding to the overlap are averaged, and marked based on the mean processing result).

[0036] In this implementation scheme, by establishing a visibility table based on longitude and latitude, the method provides an intuitive way to visualize and analyze the geographical distribution of meteorological data. This spatial representation not only facilitates the viewing and understanding of the data, but also makes it possible to directly mark the visibility of each station on the map, providing a very effective visual aid. Such visualization support helps to more quickly identify possible problem areas, such as hot spots with low visibility, thereby providing immediate decision support for traffic management and emergency response departments. By obtaining the detection range of each effective traffic meteorological station and marking it in the visibility table, this method ensures dynamic coverage of the data, especially when the detection ranges of the stations overlap, by measuring the visibility of the overlapping parts. This processing not only improves the overall quality of the data, but also ensures that the information in the table is optimized and integrated, which is especially important for dealing with complex or changing meteorological conditions. The established visibility table can help transportation departments and meteorological agencies allocate resources and adjust strategies more effectively. For example, when extreme weather events are predicted or actually occur, with clear geographic data support, the response team can more accurately locate areas that need special attention, such as sections of road where visibility suddenly drops. In addition, visibility tables can also be used as a basis for evaluating and optimizing existing traffic signals and information systems, such as adjusting traffic light operations or highway information board displays according to visibility changes to improve road use efficiency and safety.

[0037] Specifically, the specific steps for fusing the visibility table based on the inverse distance weighted interpolation method are as follows: the visibility table is gridded based on a preset interpolation grid size (such as 5km×5km) to obtain a number of visibility grids (the size is consistent with the interpolation grid size); for each visibility grid, the visibility measurement mean of a number of adjacent visibility grids within the preset interpolation grid area is analyzed by combining the mean method and the inverse distance weighted interpolation method to obtain a first visibility interpolation value and a second visibility interpolation value of each visibility grid; the first visibility interpolation value and the second visibility interpolation value of each visibility grid are comprehensively analyzed to obtain a visibility fusion value of each visibility grid.

[0038] The specific formulas for calculating the first visibility interpolation and the second visibility interpolation of each visibility grid are as follows: Among them, YnC a is the first visibility interpolation of the ath visibility grid, NjJ ab is the average visibility measurement value of the bth adjacent visibility grid in the preset interpolation grid area of ​​the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, JL ab is the grid distance value between the ath visibility grid and the bth adjacent visibility grid in the preset interpolation grid area (calculated by the Euclidean distance formula), k is the weight attenuation parameter (this is a positive number, the commonly used value is 2, its purpose is to control the influence of distance on the weight, the larger the k value, the smaller the influence of data far away from the interpolation point on the interpolation result, and vice versa), a=1, 2, 3, …, a0, a0 is the number of visibility grids, b=1, 2, 3, …, b0, b0 is the number of adjacent visibility grids in the preset interpolation grid area.

[0039] It should be explained that the preset interpolation grid area in this example is in the range of 3*3, that is, the value of b0 is 8, because the number of adjacent visibility grids of its visibility grid is 8.

[0040] To calculate a surrounding grid, you need to use the 8 surrounding grids as control points, such as Figure 3 As shown in the figure, when calculating the coordinate (x-1,y-1), the eight surrounding grids [(x-2,y-2),(x-1,y-2),(x,y-2),(x-2,y-1),(x,y-1),(x-2,y),(x-1,y),(x,y)] are required to participate in the interpolation calculation.

[0041] The specific formula for calculating the visibility fusion value of each visibility grid is as follows: NhZ a =ω a1 -YnC a +ωa2 *EnC a Among them, NhZ a is the visibility fusion value of the ath visibility grid, YnC a is the first visibility interpolation of the ath visibility grid, ω a1 is the scale factor of the first visibility interpolation of the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, ω a2 is the scale factor of the second visibility interpolation of the ath visibility grid, ω a1 +ω a2 =1, a=1, 2, 3, …, a0, a0 is the number of visibility grids.

[0042] It needs to be explained that ω a1 ,ω a2 The specific calculation formula is: sum and analyze the first visibility interpolation value and the second visibility interpolation value of the a-th visibility grid to obtain the interpolation sum value of the a-th visibility grid, and then perform ratio analysis on the first visibility interpolation value and the second visibility interpolation value of the a-th visibility grid and the interpolation sum value of the a-th visibility grid, and the ratio analysis result is the corresponding proportional coefficient.

[0043] In this implementation scheme, the use of inverse distance weighted interpolation for data fusion can significantly improve the spatial resolution of visibility data. By combining the mean visibility measurements of adjacent grids and weighting them according to their distance from the target grid, the spatial variation of visibility can be more accurately depicted. This method is particularly suitable for processing meteorological data that vary smoothly or have gradient variations in space, ensuring the continuity and accuracy of the data, thereby providing more reliable decision support for traffic management and weather forecasting. In practical applications, meteorological stations are often unevenly distributed due to terrain or other factors. The inverse distance weighted interpolation method naturally enhances the influence of neighboring stations on the target area estimation through weighted processing, while the influence of distant stations is smaller, which not only It improves the performance of data in complex terrain or sparsely populated areas, and optimizes the overall data quality and application effects, especially in mountainous areas or urban-rural fringe areas, which can effectively enhance the application value of data. By adopting a preset interpolation grid size, such as 5km×5km, and performing data fusion in each grid, this standardized processing method not only unifies the data format, but also increases the consistency of the entire data set. In addition, by calculating the first visibility interpolation and the second visibility interpolation of each grid, and performing a comprehensive analysis to obtain the fusion value, the final data output has both statistical support and is easy for users to understand and apply. The transparency and interpretability of this method are extremely important for users who need to rely on accurate data for operational decisions.

[0044] In summary, this application has at least the following effects:

[0045] By integrating and analyzing data from different time points and locations, data utilization and accuracy are significantly improved. Time series analysis of visibility helps understand the behavioral patterns of each site over time, while spatial analysis ensures the geographical continuity and consistency of the data. This integrated approach optimizes the data processing process, making visibility forecasts more accurate and effectively supporting the analysis of complex traffic and meteorological conditions.

[0046] In traffic management and meteorological monitoring, it is crucial to be able to accurately predict and respond to adverse weather conditions in real time. This data fusion technology based on inverse distance weighted interpolation provides highly reliable visibility information, enabling emergency management teams to make data-based decisions quickly, which not only reduces traffic accidents and delays caused by weather, but also significantly improves road use efficiency and safety.

[0047] Accurate visibility information allows traffic management departments to allocate resources more effectively, for example, adjusting the working mode of traffic lights or deploying emergency services to deal with low visibility conditions. In addition, by identifying possible areas of poor visibility in advance, preventive maintenance and intervention can be carried out, thereby reducing operational disruptions and maintenance costs caused by unexpected weather conditions. This approach improves overall operational efficiency and reduces additional costs incurred due to emergency response.

[0048] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A traffic and meteorological data fusion method based on inverse distance weighted interpolation, characterized in that: The following steps are involved: Obtain the longitude, latitude and visibility measurement values ​​of each traffic meteorological station in the set area at several time points; Based on the visibility measurement values ​​at several time points, each traffic meteorological station in the set area is screened and analyzed to obtain several valid traffic meteorological stations; A visibility table is established based on the longitude values, latitude values, and visibility measurement values ​​of several valid traffic meteorological stations within the set area; The visibility tables are fused based on the inverse distance weighted interpolation method.

2. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 1 is characterized in that: The specific steps to obtain several valid traffic meteorological stations are as follows: For each traffic meteorological station in the set area, a mean analysis is performed based on the visibility measurement values ​​at several time points and the moving exponential average method to obtain the mean visibility measurement value of each traffic meteorological station in the set area; Determine whether the visibility measurement mean value of each traffic meteorological station in the set area is within the preset limit threshold range, and screen out the traffic meteorological stations whose visibility measurement mean value is outside the preset limit threshold range; After the screening process, the remaining traffic meteorological stations are spatially screened to obtain several valid traffic meteorological stations.

3. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 2 is characterized in that: The specific formula for calculating the mean visibility measurement value for each traffic weather station in a set area is as follows: Among them, NjJ i is the mean visibility measurement value of the ith traffic meteorological station in the set area, NjC iu is the visibility measurement value of the i-th traffic meteorological station in the set area at the u-th time point, α iu1 is the weighting coefficient of the visibility measurement value at the i-th traffic meteorological station in the set area at the u-th time point, NjC i(u+1) is the visibility measurement value of the i-th traffic meteorological station in the set area at the u+1th time point, α iu2 is the weighting coefficient of the visibility measurement value at the u+1th time point of the first traffic meteorological station in the set area, α iu1 +α iu2 =1, i=1.2.3,…,i0, i0 is the number of traffic meteorological stations in the set area, u=1,2,3,…,u0, u0 is the number of acquired time points.

4. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 2 is characterized in that: After the screening process, the specific steps for spatial screening of the remaining traffic meteorological stations are as follows: For each remaining traffic meteorological station, the number of traffic meteorological stations within the set analysis area is counted, and the mean value of visibility analysis is analyzed; Perform difference analysis on the visibility measurement mean of each remaining traffic meteorological station and the visibility analysis mean, and obtain the visibility difference value of each remaining traffic meteorological station; It is determined whether the visibility difference value of each remaining traffic meteorological station is lower than the visibility difference threshold, and the remaining traffic meteorological stations whose visibility difference values ​​are not lower than the visibility difference threshold are screened out to obtain several valid traffic meteorological stations.

5. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 4 is characterized in that: The specific formula for calculating the visibility analysis mean and visibility difference value of each remaining traffic meteorological station is as follows: Among them, NjF r is the mean value of visibility analysis of the remaining rth traffic meteorological station, NjJ rt is the mean visibility measurement value of the t-th traffic meteorological station within the set analysis area of ​​the remaining r-th traffic meteorological station, Q rt is the weight coefficient of the mean visibility measurement value of the tth traffic meteorological station within the set analysis area of ​​the remaining rth traffic meteorological station, NjY r is the visibility difference value of the remaining rth traffic meteorological station, NjJ r is the mean visibility measurement value of the remaining rth traffic meteorological station, r=1.2,3.…,r0, r0 is the number of remaining traffic meteorological stations, t=1,2,3,…,t0, t0 is the number of traffic meteorological stations within the set analysis area.

6. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 1 is characterized in that: The specific steps to create a visibility table are as follows: Establish an initial visibility table with longitude as the horizontal coordinate and latitude as the vertical coordinate; Based on the longitude and latitude values ​​of each valid traffic meteorological station, find the actual location coordinate point of each valid traffic meteorological station in the initial visibility table; The detection range of each valid traffic meteorological station is obtained, and the detection range corresponding to the actual position coordinate point of each valid traffic meteorological station in the initial visibility table is marked with the mean value of visibility measurement, so as to obtain the visibility table.

7. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 6 is characterized in that: The specific steps for fusing the visibility table based on the inverse distance weighted interpolation method are as follows: The visibility table is meshed based on a preset interpolation grid size to obtain a plurality of visibility grids; For each visibility grid, the visibility measurement averages of several adjacent visibility grids in the preset interpolation grid area are analyzed by combining the mean method and the inverse distance weighted interpolation method to obtain the first visibility interpolation value and the second visibility interpolation value of each visibility grid; The first visibility interpolation and the second visibility interpolation of each visibility grid are comprehensively analyzed to obtain the visibility fusion value of each visibility grid.

8. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 7 is characterized in that: The specific formulas for calculating the first visibility interpolation and the second visibility interpolation of each visibility grid are as follows: Among them, YnC a is the first visibility interpolation of the ath visibility grid, NjJ ab is the average visibility measurement value of the bth adjacent visibility grid in the preset interpolation grid area of ​​the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, JL ab is the grid distance value between the ath visibility grid and the bth adjacent visibility grid in the preset interpolation grid area, k is the weight attenuation parameter, a=1, 2, 3, …, a0, a0 is the number of visibility grids, b=1, 2, 3, …, b0, b0 is the number of adjacent visibility grids in the preset interpolation grid area.

9. The traffic and meteorological data fusion method based on inverse distance weighted interpolation according to claim 7 is characterized in that: The specific formula for calculating the visibility fusion value of each visibility grid is as follows: NhZ a =ω a1 *YnC a +ω a2 *EnC a ; Among them, NhZ a is the visibility fusion value of the ath visibility grid, YnC a is the first visibility interpolation of the ath visibility grid, ω a1 is the scale factor of the first visibility interpolation of the ath visibility grid, EnC a is the second visibility interpolation of the ath visibility grid, ω a2 is the scale factor of the second visibility interpolation of the ath visibility grid, ω a1 +ω a2 =1, a=1, 2, 3,…, a0, a0 is the number of visibility grids.

Images