Road meteorological environment monitoring intelligent early warning system

Abstract

The invention relates to the technical field of intelligent traffic and environment monitoring, and discloses a road meteorological environment monitoring intelligent early warning system, which comprises a sensor integration module, a task planning and flight control module, a data acquisition and transmission module, a data analysis application, an early warning mechanism and map superposition and GIS integration, a plurality of meteorological sensors, a high-definition camera and an infrared imaging and multispectral sensor are carried on the unmanned aerial vehicle and are used for collecting meteorological data and obtaining earth surface features in real time, and the task planning and flight control module comprises automatic flight planning and real-time monitoring adjustment. And the data acquisition and transmission module comprises real-time data sharing transmission and data storage and processing. According to the invention, the unmanned aerial vehicle carries a plurality of meteorological sensors and imaging sensors, the real-time data acquisition capability can quickly reflect the meteorological change on the road, the timeliness and accuracy of monitoring are improved, and the potential safety hazard caused by information lag is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation and environmental monitoring, and in particular to an intelligent early warning system for road meteorological environment monitoring. Background Art

[0002] With the acceleration of urbanization and the continuous increase in transportation demand, the importance of road meteorological environment monitoring has become increasingly prominent. Effective road meteorological environment monitoring can not only improve traffic safety, but also optimize traffic management and reduce the accident rate.

[0003] At present, the main road meteorological environment monitoring methods include the following: Fixed weather station monitoring: Fixed weather stations are set up on major roads and intersections to collect real-time meteorological data such as temperature, humidity, wind speed, and precipitation. This method has high monitoring accuracy, but due to the limitations of fixed stations, it is difficult to fully cover the vast road network.

[0004] Mobile monitoring equipment: Use mobile devices (such as patrol cars) equipped with meteorological sensors to collect data. This method can make up for the shortcomings of fixed monitoring stations and provide dynamic and flexible monitoring data. However, the monitoring frequency and coverage of mobile devices are limited, making it difficult to ensure continuity and comprehensiveness.

[0005] The application number 202010124808.6 disclosed a road meteorological environment monitoring intelligent early warning system, including a road information collection system, a central server and an information release system. The road information collection system and the information release system are connected to the central server through a network; the road information collection system transmits the collected data to the central server, and the central server performs classification, format conversion, decoding and decoding processing on the collected data, and performs geographic information fusion processing, data visualization processing and data calculation. The real-time monitoring data and analysis and forecast data are stored in the database, and information query, display and early warning forecast are performed through the information release system. This solution can provide road managers with minute-level and kilometer-level near-term weather forecasts, comprehensive disaster information warnings, trend forecasts and quantifiable accurate data, providing a decision-making basis for traffic control to achieve comprehensive monitoring and dynamic management of highway weather, and to achieve the purpose of deploying disposal strategies in advance and reducing the accident rate of roads.

[0006] In the existing technology and the above-mentioned technical solutions, road meteorological environment monitoring is achieved by combining fixed weather station monitoring with mobile monitoring equipment. Fixed weather station monitoring and mobile monitoring equipment have multiple defects in road meteorological environment monitoring. Fixed weather stations are limited by their locations and it is difficult to fully cover the vast road network, especially in remote areas. Although mobile monitoring equipment has a certain degree of flexibility, its patrol routes still limit the comprehensiveness of the data. Secondly, fixed weather stations usually collect data at fixed time intervals and cannot capture rapidly changing meteorological phenomena. The data updates of fixed weather stations are not timely enough, especially when extreme weather events occur, and changes may not be reflected quickly. In summary, the traditional monitoring method has obvious deficiencies in coverage, data collection frequency, and timeliness.

[0007] To this end, we propose an intelligent early warning system for road meteorological environment monitoring. Summary of the invention

[0008] The present invention mainly solves the above-mentioned technical problems and provides an intelligent early warning system for monitoring the road meteorological environment.

[0009] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an intelligent early warning system for road meteorological environment monitoring, including a sensor integration module, a mission planning and flight control module, a data acquisition and transmission module, a data analysis application, an early warning mechanism, and map overlay and GIS integration. A variety of meteorological sensors, high-definition cameras, infrared imaging and multi-spectral sensors are carried on the unmanned aerial vehicle for real-time collection of meteorological data and acquisition of surface features. The mission planning and flight control module includes automatic flight planning and real-time monitoring and adjustment, the data acquisition and transmission module includes real-time data sharing transmission and data storage and processing, the data analysis application includes data fusion and pattern recognition, the early warning mechanism includes automatic early warning triggering and decision support triggering, and the map overlay and GIS integration is to overlay the unmanned aerial vehicle monitoring data on the GIS map.

[0010] Preferably, in the mission planning and flight control module, automatic flight planning is to use software to plan the flight path of the UAV, dynamically adjust the route according to the area, weather conditions and historical data that need to be monitored, and real-time monitoring and adjustment is to monitor the flight status of the UAV in real time through a ground control station.

[0011] Preferably, in the data collection and transmission module, real-time data sharing transmission transmits the data collected by the drone to the cloud platform and the ground control center in real time through wireless communication technology. Data storage and processing are performed in the ground control center and the cloud to store, process and analyze the data to form a meteorological monitoring report.

[0012] Preferably, in the data analysis application, data fusion is to fuse the data collected by the drone with the meteorological monitoring data, and pattern recognition is to use machine learning and artificial intelligence technology to analyze data, identify meteorological patterns and trends, and provide early warning of extreme weather.

[0013] Preferably, the specific steps of the automatic early warning triggering include: step one, threshold setting based on model and historical data, step two, false positive and false negative processing and step three, real-time data and feedback mechanism.

[0014] Preferably, the threshold setting in step one is based on the model and historical data, historical meteorological data is collected and analyzed, a machine learning model is used to establish the relationship between meteorological parameters and weather events, a preliminary threshold is set based on the distribution of historical data and the frequency of extreme weather events, and the impact of different thresholds on the warning effect is tested.

[0015] Preferably, the steps 2 and 3 implement a multi-condition triggering warning mechanism, set a lag time to ensure that meteorological conditions are not short-term fluctuations that cause false alarms, combine real-time monitoring data with historical event patterns, use machine learning methods to identify potential extreme weather characteristics, and automatically adjust trigger conditions according to changes in real-time data. After the warning mechanism is triggered, monitor actual weather conditions through a feedback mechanism, record the results under the triggering conditions, accumulate data for subsequent model improvements, establish cooperation with meteorological experts, and regularly review and adjust thresholds and trigger conditions.

[0016] Preferably, the map overlay and GIS integration includes the following implementation steps: S1: Data preparation; S2: Data processing and analysis; S3: Visual display.

[0017] Preferably, the map overlay is integrated with GIS, and the data collected by the drone during the monitoring process is sorted and formatted into a format compatible with the GIS platform. For image data, geocoding is required to ensure that each image is accompanied by accurate geographic coordinate information. A GIS base map is selected as the basic data for overlay. Through GIS software, the data collected by the drone is integrated with the basic geographic information to form a comprehensive data set. Spatial analysis tools are applied to identify and extract meteorological and environmental features in a specific area. The coordinate data collected by the drone is matched with the GIS map to achieve accurate positioning of the location.

[0018] Preferably, the map overlay is integrated with GIS. On the GIS platform, the drone data is superimposed on the basic map, different layers are used to represent different types of data, and symbolization and graded coloring methods are used to clearly display the distribution and changes of the data.

[0019] Beneficial Effects The present invention provides an intelligent early warning system for road meteorological environment monitoring. It has the following beneficial effects: (1) This is an intelligent early warning system for road weather environment monitoring. It uses software to plan the flight path of the drone by carrying multiple meteorological sensors and imaging sensors, and dynamically adjusts the route according to the area, meteorological conditions and historical data that need to be monitored. Real-time monitoring and adjustment is achieved by monitoring the flight status of the drone in real time through a ground control station, adjusting the flight path and altitude when necessary to ensure that the required data is obtained. The system can realize real-time monitoring of environmental and meteorological conditions. This real-time data collection capability can quickly reflect meteorological changes on the road, improve the timeliness and accuracy of monitoring, help relevant departments to grasp the current weather conditions in a timely manner, and reduce safety hazards caused by information lags.

[0020] (2) An intelligent early warning system for monitoring the road meteorological environment. The early warning mechanism in the system uses automated triggering and machine learning analysis to quickly identify potential extreme weather events and issue timely alerts to decision makers. The efficient early warning capability can effectively reduce the impact of extreme weather on traffic safety and public safety, and ensure the safety of road users, especially in severe weather conditions.

[0021] (3) This is an intelligent early warning system for road meteorological environment monitoring. Map overlay and GIS integration is to overlay drone monitoring data on the GIS map. On the GIS platform, drone data is overlaid on the basic map, and different layers are used to represent different types of data (such as temperature distribution, precipitation, air quality, etc.). Using symbolization and graded coloring methods, the system visualizes the monitoring data through GIS integration, intuitively showing the relationship between meteorological information and road location. The visualization capability enhances the readability of the data, supports relevant departments in making scientific decisions, and helps formulate relevant policies such as traffic management and environmental protection to better respond to the challenges brought about by meteorological changes.

[0022] (4) This road weather environment monitoring intelligent early warning system can improve the accuracy and reliability of data by integrating the data collected by drones with other meteorological monitoring data (such as fixed weather stations and satellite remote sensing data). The data fusion capability helps to identify meteorological patterns and trends and supports more in-depth environmental analysis. It uses machine learning and artificial intelligence technology to analyze data, identify meteorological patterns and trends, and achieve the effect of early warning of extreme weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the implementation of the present invention or the technical solution in the prior art, the following is a brief introduction to the drawings required for the implementation or the prior art description. Obviously, the drawings described below are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0024] The structures, proportions, sizes, etc. disclosed in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0025] Figure 1 This is the overall architecture diagram of the intelligent early warning system for road meteorological environment monitoring; Figure 2 It is a guide map for data analysis application in the intelligent early warning system for road meteorological environment monitoring; Figure 3 This is a flowchart of the early warning mechanism in the intelligent early warning system for road meteorological environment monitoring; Figure 4 It is a flowchart of GIS integration in the intelligent early warning system for road meteorological environment monitoring; Figure 5 This is a framework diagram for data analysis applications in the road meteorological environment monitoring intelligent early warning system. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Embodiment: A road weather environment monitoring intelligent early warning system includes a sensor integration module, a mission planning and flight control module, a data acquisition and transmission module, a data analysis application, an early warning mechanism, and map overlay and GIS integration; Sensor integration module: The drone is equipped with a variety of meteorological sensors, such as temperature, humidity, air pressure, wind speed, precipitation sensors, etc., to collect meteorological data in real time. High-definition cameras, infrared imaging and multi-spectral sensors are used to obtain visual data of surface features and meteorological phenomena (such as clouds, precipitation distribution, etc.). The combination of hyperspectral imaging and lidar technology further improves the accuracy and comprehensiveness of monitoring. The mission planning and flight control module includes automatic flight planning and real-time monitoring and adjustment. Automatic flight planning is to use software to plan the flight path of the UAV and dynamically adjust the route according to the area, weather conditions and historical data to be monitored. Real-time monitoring and adjustment is to monitor the flight status of the UAV in real time through the ground control station, and adjust the flight path and altitude when necessary to ensure the acquisition of the required data. The data collection and transmission module includes real-time data sharing transmission and data storage and processing. Real-time data sharing transmission transmits the data collected by the drone to the cloud platform or ground control center in real time through wireless communication technology. Data storage and processing is to store, process and analyze the data in the ground control center or cloud to form a meteorological monitoring report. Data analysis applications include data fusion and pattern recognition. Data fusion is the fusion of data collected by drones with other meteorological monitoring data (such as fixed weather stations and satellite remote sensing data) to improve the accuracy and reliability of data. Pattern recognition uses machine learning and artificial intelligence technology to analyze data, identify meteorological patterns and trends, and provide early warning of extreme weather. The early warning mechanism includes automatic early warning triggering and decision support triggering. When a specific meteorological parameter is detected to exceed the threshold, an alarm is automatically sent to the early warning mechanism. Combined with the data collected by the drone in real time, the early warning mechanism can make more accurate decision analysis. The specific steps of automatic early warning triggering are as follows: Step 1: Threshold setting based on model and historical data: Collect and analyze historical meteorological data, including temperature, humidity, wind speed, precipitation, etc., to identify normal and abnormal weather patterns; The relationship between meteorological parameters and weather events is established using a machine learning model, specifically through the gradient boosted decision tree (GBDT) algorithm. A strong learner is constructed by combining multiple weak learners (usually decision trees) to achieve better prediction results. The objective function formula of XGBoost is as follows:

[0028] Loss function, measuring the true value and predicted values Depending on the problem type (classification or regression), common loss functions include: For classification tasks (such as rain / no rain): Log Loss:

[0029] For regression tasks (such as predicting precipitation): Squared loss ; In each iteration, XGBoost updates the model through gradient and Hessian: ; in, represents the gradient (first-order derivative) of the loss function with respect to the predicted value, Hessian (second-order derivative) of the loss function with respect to the predicted value; When combining meteorological parameters with weather events, the input feature X contains various meteorological parameters, such as: X=[temperature,humidity,wind_speed,pressure,previous_precipitation,…], and the target variable is either binary (rainfall yes or no) or continuous (precipitation amount); In summary, after substituting the relationship between meteorological parameters and weather events, the objective function of XGBoost is: ,in, Actual weather events, The predicted value calculated by the meteorological parameter X; Set preliminary thresholds based on the distribution of historical data and the frequency of extreme weather events; Conduct sensitivity analysis to test the impact of different thresholds on warning effects, and optimize threshold settings through methods such as cross-validation; Step 2: False positive and false negative processing: Implement a multi-condition trigger warning mechanism, that is, multiple meteorological parameters must reach the threshold at the same time to trigger the warning, so as to reduce false alarms; Set a hysteresis time (if it lasts for more than a certain period of time) to ensure that meteorological conditions are not short-term fluctuations that trigger false alarms. Combine real-time monitoring data with historical event patterns and use machine learning methods to identify potential extreme weather characteristics to improve the sensitivity of the early warning mechanism and automatically adjust the trigger conditions according to changes in real-time data; Step 3: Real-time data and feedback mechanism: After the early warning mechanism is triggered, the actual weather conditions are monitored through the feedback mechanism, the results under the triggering conditions are recorded, data is accumulated for subsequent model improvements, cooperation with meteorological experts is established, thresholds and triggering conditions are regularly reviewed and adjusted, and optimization is carried out in combination with professional knowledge and field experience; Such integration not only improves the real-time and accuracy of meteorological monitoring, but also provides strong support for the early warning and response of extreme weather events. By effectively linking drones with early warning mechanisms, the monitoring capabilities of complex meteorological environments can be significantly improved, and public safety can be enhanced. Map overlay and GIS integration is to overlay the drone monitoring data on the GIS map, which can not only intuitively display the road location, but also provide rich environmental information. The implementation steps of map overlay and GIS integration mainly include: S1: Data preparation; The meteorological data, high-definition images, infrared imaging, multispectral data, etc. collected by drones during the monitoring process all need to be sorted and formatted to be compatible with the GIS platform. For image data, geocoding is required to ensure that each image is accompanied by accurate geographic coordinate information. The second step is GIS base map selection. Choose a suitable GIS base map, including topographic maps, satellite images, traffic maps, etc., as the basic data for overlay.

[0030] S2: Data processing and analysis; Through GIS software, the data collected by drones are integrated with basic geographic information (such as road networks, terrain elevations, land use types, etc.) to form a comprehensive data set. Spatial analysis tools are used to identify and extract meteorological and environmental characteristics in specific areas. The coordinate data collected by drones (such as the location of meteorological monitoring points) are matched with GIS maps to achieve accurate positioning.

[0031] S3: Visual display; On the GIS platform, drone data is superimposed on the basic map, and different layers are used to represent different types of data (such as temperature distribution, precipitation, air quality, etc.). Symbolization and graded coloring methods are used to clearly display the distribution and changes of data and enhance readability.

[0032] When extreme weather events occur, superimposed monitoring data can quickly identify affected areas, support emergency decision-making and resource allocation, and through superimposed environmental information, evaluate the meteorological impact of specific roads and help formulate environmental protection measures and traffic management strategies.

[0033] The mission planning and flight control modules of the drone are closely linked to the early warning mechanism through real-time data sharing, dynamic mission adjustment, and information feedback and response. Such integration not only improves the real-time and accuracy of meteorological monitoring, but also provides strong support for the early warning and response of extreme weather events. By achieving effective linkage between drones and early warning mechanisms, the monitoring capability of complex meteorological environments can be significantly improved, thereby enhancing public safety protection.

[0034] By carrying a variety of meteorological sensors and imaging sensors on drones, using software to plan the flight path of drones, the flight route can be dynamically adjusted according to the area, meteorological conditions and historical data that need to be monitored. Real-time monitoring and adjustment is achieved by monitoring the flight status of drones in real time through ground control stations, adjusting the flight path and altitude when necessary to ensure the acquisition of required data. The system can achieve real-time monitoring of environmental and meteorological conditions. The real-time data collection capability can quickly reflect meteorological changes on the road and improve the timeliness and accuracy of monitoring. The early warning mechanism in the system uses automated triggering and machine learning analysis to quickly identify potential extreme weather events and issue alerts to decision makers in a timely manner. The efficient early warning capability can effectively reduce the impact of extreme weather on traffic safety and public safety, and ensure the safety of road users; By fusing the data collected by drones with other meteorological monitoring data (such as fixed weather stations and satellite remote sensing data), the system can improve the accuracy and reliability of the data. The data fusion capability helps identify meteorological patterns and trends, supports more in-depth environmental analysis, and uses machine learning and artificial intelligence technology to analyze data and identify meteorological patterns and trends. Map overlay and GIS integration is to overlay UAV monitoring data on GIS maps. On the GIS platform, UAV data is overlaid on the basic map, and different layers are used to represent different types of data (such as temperature distribution, precipitation, air quality, etc.). Using symbolization and graded coloring methods, the system visualizes the monitoring data through GIS integration, intuitively showing the relationship between meteorological information and road location. The visualization capability enhances the readability of the data.

[0035] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent early warning system for road meteorological environment monitoring, characterized in that: It includes a sensor integration module, a mission planning and flight control module, a data acquisition and transmission module, a data analysis application, an early warning mechanism, and map overlay and GIS integration. The UAV is equipped with a variety of meteorological sensors, high-definition cameras, infrared imaging and multi-spectral sensors for real-time collection of meteorological data and acquisition of surface features. The mission planning and flight control module includes automatic flight planning and real-time monitoring and adjustment, the data acquisition and transmission module includes real-time data sharing transmission and data storage and processing, the data analysis application includes data fusion and pattern recognition, the early warning mechanism includes automatic early warning triggering and decision support triggering, and the map overlay and GIS integration is to overlay the UAV monitoring data on the GIS map.

2. The intelligent early warning system for road meteorological environment monitoring according to claim 1 is characterized in that: In the mission planning and flight control module, automatic flight planning is to use software to plan the flight path of the UAV, and dynamically adjust the route according to the area, weather conditions and historical data that need to be monitored. Real-time monitoring and adjustment is to monitor the flight status of the UAV in real time through the ground control station.

3. The intelligent early warning system for road meteorological environment monitoring according to claim 1 is characterized in that: In the data collection and transmission module, real-time data sharing transmission transmits the data collected by the drone to the cloud platform and the ground control center in real time through wireless communication technology. Data storage and processing are the storage, processing and analysis of data in the ground control center and the cloud to form a meteorological monitoring report.

4. The intelligent early warning system for road meteorological environment monitoring according to claim 1 is characterized in that: In the data analysis application, data fusion is the fusion of data collected by drones with meteorological monitoring data, and pattern recognition is the use of machine learning and artificial intelligence technology to analyze data, identify meteorological patterns and trends, and provide early warning of extreme weather.

5. The intelligent early warning system for road meteorological environment monitoring according to claim 1 is characterized in that: The specific steps of the automatic early warning triggering include: step one, threshold setting based on model and historical data, step two, false positive and false negative processing and step three, real-time data and feedback mechanism.

6. The intelligent early warning system for road meteorological environment monitoring according to claim 5 is characterized in that: The step 1 threshold setting is based on the model and historical data, collects and analyzes historical meteorological data, uses a machine learning model to establish the relationship between meteorological parameters and weather events, sets preliminary thresholds based on the distribution of historical data and the frequency of extreme weather events, and tests the impact of different thresholds on the warning effect.

7. The intelligent early warning system for road meteorological environment monitoring according to claim 5 is characterized in that: The above steps 2 and 3 implement a multi-condition triggering early warning mechanism, set a lag time to ensure that meteorological conditions are not short-term fluctuations that cause false alarms, combine real-time monitoring data with historical event patterns, use machine learning methods to identify potential extreme weather characteristics, and automatically adjust trigger conditions according to changes in real-time data. After the early warning mechanism is triggered, the actual weather conditions are monitored through a feedback mechanism, the results under the triggering conditions are recorded, and data are accumulated for subsequent model improvements. Cooperation with meteorological experts is established to regularly review and adjust thresholds and trigger conditions.

8. The intelligent early warning system for road meteorological environment monitoring according to claim 1 is characterized in that: The map overlay and GIS integration includes the following implementation steps: S1: Data preparation; S2: Data processing and analysis; S3: Visual display.

9. The intelligent early warning system for road meteorological environment monitoring according to claim 8 is characterized in that: The map overlay is integrated with GIS. The data collected by the drone during the monitoring process is sorted and formatted into a format compatible with the GIS platform. For image data, geocoding is required to ensure that each image is accompanied by accurate geographic coordinate information. The GIS base map is selected as the basic data for overlay. Through GIS software, the data collected by the drone is integrated with the basic geographic information to form a comprehensive data set. Spatial analysis tools are applied to identify and extract meteorological and environmental characteristics in a specific area. The coordinate data collected by the drone is matched with the GIS map to achieve accurate positioning of the location.

10. The intelligent early warning system for road meteorological environment monitoring according to claim 8, characterized in that: The map overlay is integrated with GIS. On the GIS platform, drone data is overlaid on the basic map, different layers are used to represent different types of data, and symbolization and graded coloring methods are used to clearly display the distribution and changes of data.

Images