Meteorological-assisted forest fire efficient early warning and scheduling system

Abstract

The invention relates to the technical field of forest fire early warning, in particular to a meteorological-assisted forest fire efficient early warning and scheduling system which comprises a meteorological data analysis module, a rescue resource scheduling module, a real-time path planning module and a fire behavior mode prediction module. According to the invention, through the application of real-time monitoring and data analysis, the response speed and accuracy of forest fire early warning are greatly improved, the real-time measurement and analysis of meteorological variables enable fire early warning not to only depend on a traditional probability model, but can dynamically adjust the early warning threshold based on real-time data, so that early warning is more timely and highly targeted, and the early warning efficiency is improved. The problem of data updating delay is solved, accurate risk assessment is provided, instant fire alarm issuing and real-time optimization of a rescue path are ensured, rescue resources can be ensured to quickly respond through the shortest path, the success rate and efficiency of rescue actions are directly influenced, and a fire behavior prediction model utilizes continuous data training to improve the rescue efficiency. And the adaptability and prediction capability to the fire change are further enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of mountain fire early warning, and in particular to a meteorologically assisted mountain fire efficient early warning and dispatching system. Background Art

[0002] Wildfire warning technology is used to identify and respond to wildfire threats in advance. It combines remote sensing technology, geographic information system (GIS) and meteorological data analysis to monitor fire conditions and environmental conditions. Through real-time or near real-time data monitoring, it can predict the probability of fire, spread path and impact range, thereby helping relevant departments to prepare in advance and achieve rapid response.

[0003] Among them, the meteorological-assisted efficient wildfire warning and dispatch system is a technical solution that uses meteorological information to improve the efficiency of wildfire warning. The system integrates meteorological data and wildfire behavior models, and analyzes meteorological conditions such as temperature, humidity, wind speed and other factors in real time to predict the risk and spread of wildfires. Its main purpose is to provide accurate fire warnings and dispatch decision support to relevant departments, emergency management agencies and fire departments, ensure the rapid and effective deployment of rescue resources, minimize casualties and property losses, and improve the response speed and processing capabilities to wildfires.

[0004] Data processing in existing systems is based on updates at predetermined time points rather than event-driven real-time analysis, which leads to delayed responses in sudden extreme weather conditions. The limitation is that its early warning system cannot be adjusted in time and the response time is long, especially when wind speed or temperature changes dramatically. In addition, the scheduling of rescue resources lacks dynamic optimization capabilities, making it impossible to adapt quickly to complex road conditions or changing fire conditions, thereby affecting rescue efficiency and the deployment of rescue teams, resulting in the inability to maximize the efficiency of rescue resource use at critical moments, increasing the difficulty of fire control and the overall risk of responding to wildfires. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a meteorological-assisted high-efficiency mountain fire early warning and dispatching system.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a meteorologically assisted high-efficiency early warning and dispatching system for wildfires, the system comprising:

[0007] The meteorological data analysis module collects key climate variables based on regional meteorological information, measures temperature, humidity, wind speed and rainfall, calculates the change rate of historical data and the abnormal value of current data, identifies abnormal data points, and adjusts the fire risk warning threshold according to the identification results to obtain the climate variation warning index;

[0008] The rescue resource scheduling module evaluates the matching degree between the currently available rescue resources and the demand based on the climate variability early warning index, calculates the distance between the location of the rescue team and equipment and the fire point, and updates the resource status and fire situation in real time, adjusts the resource allocation, and obtains the optimal configuration of the rescue deployment;

[0009] The real-time path planning module collects real-time traffic and fire dynamics based on the rescue deployment optimization configuration, uses GIS technology to analyze road conditions in real time, calculates the optimal path from the rescue vehicle to the fire scene, and adjusts the rescue path in real time according to changes in road conditions, and obtains rescue path update information;

[0010] The fire pattern prediction module collects fire data in different areas based on the rescue path update information, extracts fire source image features by comparing the fire pattern with the current data, builds a fire model, and continuously trains the model with the newly added data to obtain the fire response judgment result.

[0011] The present invention is improved in that the steps for calculating the historical data change rate and the current data abnormal value are specifically as follows:

[0012] Based on regional meteorological information, historical temperature, humidity, wind speed and rainfall data in the region are collected, and the annual average values ​​are calculated to obtain the historical annual average data set;

[0013] Based on the historical annual average data set, the formula is used:

[0014]

[0015] Determine the historical data change rate R, where x i Represents data for a certain year. represents the average value of all years’ data, and n represents the number of years’ data;

[0016] An outlier analysis is performed on the real-time data of the current year. Based on the change rate of the historical data, the Z-score method is used to calculate the degree of deviation of each meteorological variable from the historical annual average data, and identify the outliers of the current data.

[0017] The present invention is improved in that the step of obtaining the climate change early warning index is specifically as follows:

[0018] Readjusting fire danger warning thresholds based on the identified results, including current and historical abnormal climate data;

[0019] Based on the fire risk warning threshold, the formula is adopted:

[0020] Calculate the climate variability early warning index IG, where xs i represents the adjusted threshold of the ith meteorological variable, ws irepresents the weight of the ith meteorological variable, and ns is the total number of meteorological variables.

[0021] The present invention is improved in that the step of evaluating the matching degree between the currently available rescue resources and the demand is specifically as follows:

[0022] Collect and organize the data of currently available rescue resources, including lists of personnel, equipment and supplies, to obtain a list of rescue resources;

[0023] Based on the climate variability early warning index, analyze the needs of the current fire risk area, including the number of rescue teams and types of rescue equipment required, and obtain a demand assessment record;

[0024] Compare the rescue resource list and demand assessment records to calculate resource matching using the formula:

[0025]

[0026]

[0027] The matching degree between current rescue resources and demand is obtained, where R available Represents the available resource index, R required Represents the demand resource index.

[0028] The present invention is improved in that the steps of obtaining the optimal configuration of the rescue deployment are specifically as follows:

[0029] According to traffic conditions and route obstacles, calculate the distance from the current location of each rescue team and equipment to the fire point to obtain route distance information;

[0030] Based on the route distance information, the resource status and fire situation are updated in real time, and the data of on-site rescue communication equipment and fire monitoring are received and updated to obtain real-time update results;

[0031] Based on the real-time update results, resource allocation is adjusted using the formula:

[0032]

[0033] The optimal configuration of rescue deployment is obtained, where CZ represents the configuration efficiency and DZ i is the distance from the ith resource to the fire scene, TZ i is the estimated time of arrival, RZ i is the weight of the resource type, n z is the total number of rescue resources.

[0034] The present invention is improved in that the step of performing real-time analysis of road conditions is specifically as follows:

[0035] Based on the optimized configuration of the rescue deployment, GIS technology is used to collect real-time traffic data, including traffic flow and accident information, and generate traffic condition information;

[0036] Based on the traffic condition information, identify traffic congestion areas and accident-prone areas, extract key road section information, and obtain key road section analysis results;

[0037] Based on the analysis results of the key sections, the traffic conditions of the different sections are evaluated using the formula:

[0038]

[0039] Calculate the estimated rescue arrival time TB and obtain the road condition assessment result, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n b is the number of key sections.

[0040] The present invention is improved in that the step of obtaining the rescue path update information is specifically as follows:

[0041] Combining the road conditions and GIS data, the shortest path algorithm is used to calculate the initial optimal path from the rescue vehicle to the fire scene and generate a preliminary rescue path;

[0042] Based on the preliminary rescue path, monitor and update real-time traffic, including new accidents and traffic flow changes, to obtain updated traffic conditions;

[0043] Based on the updated traffic conditions, the rescue path is recalculated using the formula:

[0044]

[0045] Determine the optimal rescue path PH and obtain the rescue path update information, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n Q is the total number of road segments.

[0046] The present invention is improved in that the steps of obtaining the fire response judgment result are specifically as follows:

[0047] Based on the rescue path update information, fire condition data of different areas are collected, including temperature, smoke density and flame size, to obtain a fire condition feature data set;

[0048] Based on the fire characteristic data set, compare the current fire data with the known fire pattern, extract the fire source image features, and generate a pattern matching result;

[0049] Based on the pattern matching results, a fire model is constructed and continuously trained using the formula:

[0050]

[0051] Assess the urgency of the fire UR and obtain the fire response judgment result, where xu i represents the fire characteristic value, wu i is the corresponding feature weight, max(xu) represents the maximum value of the fire characteristic value, n u is the total number of fire characteristics.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, through the application of real-time monitoring and data analysis, the response speed and accuracy of wildfire warnings are greatly improved. The real-time measurement and analysis of meteorological variables make the fire risk warning no longer rely solely on the traditional probability model, but can dynamically adjust the warning threshold based on real-time data, making the warning more timely and targeted, overcoming the problem of data update delay, providing accurate risk assessment, ensuring the immediate release of fire risk alerts, real-time optimization of rescue paths, ensuring that rescue resources can respond quickly through the shortest path, directly affecting the success rate and efficiency of rescue operations, and the fire prediction model uses continuous data training to further enhance the adaptability and prediction capabilities to changes in fire conditions, and support more effective response decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a system flow chart of the present invention;

[0055] Figure 2 It is a flow chart for calculating the historical data change rate and the current data abnormal value in the present invention;

[0056] Figure 3 This is a flow chart for obtaining the climate change early warning index in the present invention;

[0057] Figure 4 It is a flow chart for evaluating the matching degree between currently available rescue resources and needs in the present invention;

[0058] Figure 5 A flowchart for obtaining the optimal configuration of the rescue deployment in the present invention;

[0059] Figure 6 A flow chart of real-time analysis of road conditions in the present invention;

[0060] Figure 7 A flowchart for obtaining rescue path update information in the present invention;

[0061] Figure 8 The figure is a flow chart for obtaining the fire response judgment result in the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0064] Example

[0065] See also Figure 1 The present invention provides a technical solution: a meteorologically assisted high-efficiency early warning and dispatching system for mountain fires, comprising:

[0066] The meteorological data analysis module collects key climate variables based on regional meteorological information, measures temperature, humidity, wind speed and rainfall, calculates the change rate of historical data and the abnormal value of current data, identifies abnormal data points, and adjusts the fire risk warning threshold according to the identification results to obtain the climate variation warning index;

[0067] The rescue resource scheduling module evaluates the matching degree between the currently available rescue resources and the demand based on the climate variability early warning index, calculates the distance between the location of the rescue team and equipment and the fire point, and updates the resource status and fire situation in real time, adjusts the resource allocation, and obtains the optimal configuration of the rescue deployment;

[0068] The real-time path planning module is based on the rescue deployment optimization configuration, collects real-time traffic and fire dynamics, uses GIS technology to analyze road conditions in real time, calculates the optimal path from the rescue vehicle to the fire scene, and adjusts the rescue path in real time according to changes in road conditions, and obtains rescue path update information;

[0069] The fire pattern prediction module updates information based on the rescue path, collects fire data in different areas, extracts fire source image features by comparing the fire pattern with the current data, builds a fire model, and continuously trains the model with the newly added data to obtain the fire response judgment results.

[0070] The climate variation warning index includes risk level, variation frequency, and abnormal pattern. The rescue deployment optimization configuration includes deployment efficiency, coverage, and resource optimization index. The rescue path update information specifically refers to path priority, navigation accuracy, and update frequency. The fire response judgment results include warning level, fire source intensity, and fire source location.

[0071] See also Figure 2 , the calculation steps of historical data change rate and current data abnormal value are as follows:

[0072] Based on regional meteorological information, historical temperature, humidity, wind speed and rainfall data in the region are collected, and the annual average values ​​are calculated to obtain the historical annual average data set;

[0073] In the process of collecting data from the meteorological database, the source and type of data, including temperature, humidity, wind speed and rainfall, are determined to ensure the comprehensiveness and accuracy of the data. Then, the data for each year is averaged, including adding up the daily values ​​and dividing them by the total number of days to obtain the average value for each year, ensuring the consistency and comparability of data processing. The historical annual average data set obtained provides basic data for subsequent analysis.

[0074] Based on the historical annual average data set, the formula is used:

[0075]

[0076] Determine the historical data change rate R, where x i Represents data for a certain year. represents the average value of all years’ data, and n represents the number of years’ data;

[0077] Taking temperature as an example, the average annual temperatures in the past five years are x1=15, x2=15.5, x3=14.8, x4=15.2, x5=15.1. Substituting into the formula:

[0078] (15-15.12) 2 +(15.5-15.12) 2 +(14.8-15.12) 2

[0079]

[0080] This result shows that the rate of change in historical data is small, indicating that the temperature has been relatively stable over the past five years, providing a stable baseline for further analysis of current year data.

[0081] Perform outlier analysis on the real-time data of the current year. Based on the rate of change of historical data, use the Z-score method to calculate the degree of deviation of each meteorological variable from the historical annual average data and identify outliers in the current data.

[0082] When conducting outlier analysis on the current year’s data, the standard deviation of the current data and the historical annual average data set is calculated, and the Z-score method is used to identify outliers. Whether the data is abnormal is determined by comparing the deviation between the current data point and the historical average. If the absolute value of the Z-score is greater than 2, the data point is considered abnormal, making the identification of abnormal data both statistically significant and easy to understand, thereby providing a basis for adjusting the fire risk warning threshold.

[0083] See also Figure 3 , the specific steps for obtaining the climate variability early warning index are:

[0084] Based on the identified results, including current and historical abnormal climate data, readjust the fire danger warning threshold to reflect recent climate change trends and anomalies;

[0085] Readjust the fire risk warning threshold, collect current and historical meteorological data, including temperature, humidity, wind speed and rainfall, based on real-time monitoring data and meteorological analysis models. The data is automatically recorded and uploaded to the database through meteorological collection. After preliminary cleaning and verification, trend analysis and anomaly detection are carried out. The analysis results help determine which meteorological factors are the main cause of the increase in fire risk. Based on the analysis results and the latest meteorological forecasts, the threshold is reset to reflect the recent climate change trends and anomalies, ensuring that all relevant parties can respond in a timely manner to reduce potential fire risks.

[0086] Based on the fire risk warning threshold, the formula is used:

[0087]

[0088] Calculate the climate variability early warning index IG, where xs i represents the adjusted threshold of the ith meteorological variable, ws i represents the weight of the i-th meteorological variable, ns is the total number of meteorological variables, and ws i It can be the weight of temperature or humidity. If the temperature change has a greater impact on fire risk, the temperature weight will be higher than the humidity weight, ensuring that the warning index can reflect the real impact of various meteorological factors on the current fire risk situation;

[0089] Currently, three main meteorological factors are considered: temperature, humidity, and wind speed. The corresponding adjusted thresholds are xs1 = 30 ° C, xs2 = 75%, and xs3 = 20 km / h. The corresponding weights are set to ws1 = 0.5, ws2 = 0.3, and ws3 = 0.2. The weights are determined based on the analysis of past event data to ensure that the impact of each variable is properly considered. The calculation formula is:

[0090] IG=0.5·30+0.3·75+0.2·20=15+22.5+4=41.5

[0091] The results show that based on the currently set thresholds and weights, the climate variability early warning index is 41.5. This index can help decision makers understand the fire risk level under current meteorological conditions and take appropriate preventive measures.

[0092] See also Figure 4 ,The specific steps for evaluating the matching degree between the currently available rescue resources and the needs are as follows:

[0093] Collect and organize the data of currently available rescue resources, including lists of personnel, equipment and supplies, to obtain a list of rescue resources;

[0094] First, obtain personnel lists, rescue equipment and material inventory lists from local rescue departments through real-time data interfaces. Each rescue unit must report its available resources, including the number of rescue personnel, detailed information on special equipment such as fire trucks and ambulances, and their operating status to ensure real-time updating and accuracy of information. In addition, resources need to be pre-allocated based on recent events and potential needs to ensure a rapid response when a fire or other emergency occurs.

[0095] Based on the climate variability early warning index, analyze the needs of the current fire risk areas, including the number of rescue teams and types of rescue equipment required, and obtain demand assessment records;

[0096] Based on the current climate variability warning index, analyze the fire risk in specific areas and determine the specific resources required for rescue operations, including detailed climate data and historical fire statistics obtained from meteorological stations to assess the scale and type of fires. The rescue team will use geographic information system (GIS) technology to determine the specific location of the fire and calculate the shortest route from the nearest rescue base to the location, as well as the type of manpower and equipment required. The information will be summarized in the demand assessment record.

[0097] Compare the rescue resource list and demand assessment records, calculate the resource matching degree, and use the formula:

[0098]

[0099] The matching degree between current rescue resources and demand is obtained, where R available Represents the available resource index, R required represents the demand resource index;

[0100] The current available rescue resources include 50 rescuers and 10 rescue vehicles, and the corresponding resource index R available The calculation is 50×1+10×5=100 (assuming that the resource index of each person is 1 and each vehicle is 5. This means that each rescuer is assigned a resource index value (e.g. 1), while each rescue vehicle is assigned a higher resource index value (e.g. 5) due to its higher function and range of action. The resource assessment required for the current fire indicates that 40 people and 8 vehicles are needed, and the corresponding R required 40×1+8×5=80, substitute into the formula:

[0101]

[0102] The results show that currently available resources are 25% more than what is needed, indicating that existing resources are sufficient and support a wider range of rescue operations.

[0103] See also Figure 5 , the specific steps for obtaining the optimized configuration of rescue deployment are:

[0104] According to traffic conditions and route obstacles, calculate the distance from the current location of each rescue team and equipment to the fire point to obtain route distance information;

[0105] In the current task, Geographic Information System (GIS) technology is used to calculate the shortest feasible distance for rescue teams and equipment from their respective starting points to the fire scene based on real-time traffic conditions and route obstruction assessments. This involves obtaining data from the traffic management system, including information on road closures, traffic accidents or construction activities. At the same time, the GIS system will provide alternative route suggestions to ensure that rescue units can arrive at the scene in the shortest time. The calculation results are integrated into a dynamically updated route distance information.

[0106] Based on route distance information, the resource status and fire situation are updated in real time, and data from on-site rescue communication equipment and fire monitoring are received and updated to obtain real-time update results;

[0107] Based on the route distance information, the status of resources and the situation at the fire scene are further updated in real time, which involves receiving real-time data from on-site rescue communication equipment and fire monitoring, including the spread speed of the fire, the scope of impact and the immediate availability of rescue resources. The information is analyzed through data processing to generate real-time update results. The results not only include the latest developments of resources and fire conditions, but also predict the changing trends in the next few hours to ensure that they can adapt to the ever-changing on-site conditions.

[0108] Based on the real-time update results, resource allocation is adjusted using the formula:

[0109]

[0110] The optimal configuration of rescue deployment is obtained, where CZ represents the configuration efficiency and DZ i is the distance from the ith resource to the fire scene, TZ i is the estimated time of arrival, RZ i is the weight of resource type, including rescue team, fire truck, ambulance, etc., n z is the total amount of rescue resources;

[0111] There are three types of resources, rescue team (1 unit), fire truck (2 units), ambulance (1 unit), the distance to the fire scene is 5 km, 8 km and 10 km respectively, and the estimated arrival time is 15 minutes, 20 minutes and 25 minutes respectively. According to the importance of resources, the weights of the units are 2, 1.5 and 2 respectively. The calculation process is as follows:

[0112]

[0113] The results show that based on the current resource allocation and distance-time weight calculation, the configuration efficiency is 2.07. The numerical value helps decision makers understand the effectiveness of the current resource allocation and make necessary adjustments accordingly to ensure that rescue resources can reach the fire scene as quickly as possible.

[0114] See also Figure 6 ,The specific steps for real-time analysis of road conditions are:

[0115] Based on the optimized configuration of rescue deployment, GIS technology is used to collect real-time traffic data, including traffic flow and accident information, and generate traffic status information;

[0116] Traffic flow and accident information are monitored in real time through GIS technology, and data from multiple sensors and surveillance cameras are integrated. The data covers vehicle speed, density and accidents occurring at any time. Traffic status reports are generated by analyzing the data. The reports include real-time traffic conditions and traffic congestion information on major roads. In addition, the time, location and type of accidents are recorded to provide data for subsequent analysis of traffic hotspots.

[0117] Based on traffic condition information, identify traffic congestion areas and accident-prone areas, extract key road section information, and obtain key road section analysis results;

[0118] Based on the traffic status report, spatial data analysis is applied to identify hot spots in current traffic. These areas include high congestion areas caused by accidents or road conditions. The traffic hot spot analysis results highlight the key sections that need special attention, providing a reference for rescue vehicles to avoid high-risk areas. The information of key sections includes the section location, length and current traffic conditions.

[0119] Based on the analysis results of key sections, the traffic conditions of different sections are evaluated using the formula:

[0120]

[0121] Calculate the estimated rescue arrival time TB and obtain the road condition assessment result, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n b is the number of critical sections;

[0122] There are three key sections, with lengths of 2 km, 3 km and 2.5 km respectively. The corresponding average vehicle speeds are 40 km / h, 30 km / h and 35 km / h respectively, and the congestion coefficients are 0.2, 0.5 and 0.3 respectively. Substituting the values ​​into the formula:

[0123]

[0124] TB=0.05×1.2+0.1×1.5+0.0714×1.3=0.30282

[0125] This result shows that the estimated time for rescue to arrive is 0.30282 hours, or approximately 18.17 minutes, reflecting the time savings that can be achieved by optimizing the route.

[0126] See also Figure 7 , the specific steps for obtaining rescue path update information are:

[0127] Combining road conditions and GIS data, the shortest path algorithm is used to calculate the initial optimal path from the rescue vehicle to the fire scene and generate a preliminary rescue path;

[0128] When applying the shortest path algorithm to calculate the initial rescue path, GIS data and existing road conditions, including road length, traffic signs and historical traffic flow data, are integrated. Through the data, the potential fastest route from the rescue starting point to the fire scene can be identified. Then, the real-time data stream provided by GIS is used to adjust the path to avoid sudden traffic delays or roadblocks. The generated preliminary rescue path ensures the accuracy and real-time nature of the path selection.

[0129] Based on the preliminary rescue route, monitor and update real-time traffic, including new accidents and traffic flow changes, to obtain updated traffic conditions;

[0130] Based on the preliminary rescue route, continue to monitor new changes in traffic conditions, including updated information on new traffic accidents, road closures or temporary traffic control measures, and use the latest information to adjust the planned route to cope with dynamically changing road conditions, including calculating detours around accident-affected areas, or avoiding main roads during peak traffic hours. The updated traffic conditions reflect real-time road usage, so that the rescue route can be adjusted in time before departure to ensure that rescue vehicles can arrive at the scene in the shortest time possible.

[0131] Based on the updated traffic conditions, the rescue path is recalculated using the formula:

[0132]

[0133] Determine the optimal rescue path PH and obtain the rescue path update information, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n Q is the total number of road sections;

[0134] There are three sections to choose from, with the following parameters:

[0135] Section 1:

[0136] LB1=2 km, VB1=50 km / h, CB1=0.1 (10% congestion)

[0137] Section 2:

[0138] LB2 = 3 km, VB2 = 40 km / h, CB2 = 0.2 (20% congestion)

[0139] Section 3:

[0140] LB3 = 1.5 km, VB3 = 60 km / h, CB3 = 0.05 (5% congestion)

[0141] Substituting in the arguments, evaluate each expression:

[0142] For segment 1:

[0143]

[0144] For segment 2:

[0145]

[0146] For segment 3:

[0147]

[0148] The shortest time (minimum value) is:

[0149] PH = min (0.0444, 0.09375, 0.0263) = 0.0263 hours

[0150] This means that the fastest route is segment 3, with an estimated arrival time of 0.0263 hours, or about 1.578 minutes.

[0151] See also Figure 8 , the specific steps for obtaining the fire response judgment result are:

[0152] Based on the updated rescue path information, the fire data of different areas are collected, including temperature, smoke density and flame size, to obtain the fire characteristic data set;

[0153] Based on the latest rescue path updates, fire data in the target area is collected, including real-time temperature readings, smoke density monitoring and flame size assessment. Sensors are used to obtain data from various monitoring stations. After preliminary screening and classification, the data is formed into a data set including key fire indicators. This data set not only provides real-time data for fire analysis, but also includes the time and location information of various fires to ensure the integrity of the data and the accuracy of its application.

[0154] Based on the fire feature data set, the current fire data is compared with the known fire pattern, the fire source image features are extracted, and the pattern matching results are generated;

[0155] By conducting in-depth analysis of the collected fire characteristic data sets, comparing the data in the known fire patterns with the currently collected fire data, and using image recognition and pattern matching technology, key features such as flame shape and diffusion speed are extracted from the fire source images, and pattern matching results are generated to help determine the type of fire source and diffusion path, providing a basis for subsequent rescue decisions.

[0156] Based on the pattern matching results, a fire model is constructed and continuously trained using the formula:

[0157]

[0158] Assess the urgency of the fire UR and obtain the fire response judgment result, where xu i Represents fire characteristic values, such as temperature, smoke density, etc. i is the corresponding feature weight, reflecting the influence of different features on the judgment of fire urgency, max(xu represents the maximum value of the fire feature value, n uis the total number of fire characteristics;

[0159] There are three fire characteristics: temperature (50℃), smoke density (0.7), and flame size (2 meters). The corresponding weights are 0.5, 0.3, and 0.2 respectively. The maximum eigenvalue is 50 (temperature). The calculation process is as follows:

[0160]

[0161] UR=0.5+0.0042+0.008=0.5122

[0162] The results show that based on the current fire characteristics and weight configuration, the fire urgency score is 0.5122, indicating that the current fire situation is of medium urgency and rescue resources need to be dispatched in a timely manner.

[0163] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A meteorologically assisted high-efficiency early warning and dispatching system for wildfires, characterized in that: The system comprises: The meteorological data analysis module collects key climate variables based on regional meteorological information, measures temperature, humidity, wind speed and rainfall, calculates the change rate of historical data and the abnormal value of current data, identifies abnormal data points, and adjusts the fire risk warning threshold according to the identification results to obtain the climate variation warning index; The rescue resource scheduling module evaluates the matching degree between the currently available rescue resources and the demand based on the climate variability early warning index, calculates the distance between the location of the rescue team and equipment and the fire point, and updates the resource status and fire situation in real time, adjusts the resource allocation, and obtains the optimal configuration of the rescue deployment; The real-time path planning module collects real-time traffic and fire dynamics based on the rescue deployment optimization configuration, uses GIS technology to analyze road conditions in real time, calculates the optimal path from the rescue vehicle to the fire scene, and adjusts the rescue path in real time according to changes in road conditions, and obtains rescue path update information; The fire pattern prediction module collects fire data in different areas based on the rescue path update information, extracts fire source image features by comparing the fire pattern with the current data, builds a fire model, and continuously trains the model with the newly added data to obtain the fire response judgment result.

2. The meteorologically assisted high-efficiency mountain fire early warning and dispatching system according to claim 1 is characterized in that: The calculation steps of the historical data change rate and the current data abnormal value are specifically as follows: Based on regional meteorological information, historical temperature, humidity, wind speed and rainfall data in the region are collected, and the annual average values ​​are calculated to obtain the historical annual average data set; Based on the historical annual average data set, the formula is used: Determine the historical data change rate R, where x i Represents data for a certain year. represents the average value of all years’ data, and n represents the number of years’ data; An outlier analysis is performed on the real-time data of the current year. Based on the change rate of the historical data, the Z-score method is used to calculate the degree of deviation of each meteorological variable from the historical annual average data, and identify the outliers of the current data.

3. The meteorologically assisted high-efficiency mountain fire early warning and dispatching system according to claim 1, characterized in that: The steps for obtaining the climate variability early warning index are specifically as follows: Readjusting fire danger warning thresholds based on the identified results, including current and historical abnormal climate data; Based on the fire risk warning threshold, the formula is adopted: Calculate the climate variability early warning index IG, where xs i represents the adjusted threshold of the ith meteorological variable, ws i represents the weight of the ith meteorological variable, and ns is the total number of meteorological variables.

4. The meteorologically assisted high-efficiency forest fire early warning and dispatching system according to claim 1, characterized in that: The steps for evaluating the matching degree between the currently available rescue resources and the needs are specifically as follows: Collect and organize the data of currently available rescue resources, including lists of personnel, equipment and supplies, to obtain a list of rescue resources; Based on the climate variability early warning index, analyze the needs of the current fire risk area, including the number of rescue teams and types of rescue equipment required, and obtain a demand assessment record; Compare the rescue resource list and demand assessment records to calculate resource matching using the formula: The matching degree between current rescue resources and demand is obtained, where R available Represents the available resource index, R required Represents the demand resource index.

5. The meteorologically assisted high-efficiency mountain fire early warning and dispatching system according to claim 1, characterized in that: The steps for obtaining the optimal configuration of the rescue deployment are specifically as follows: According to traffic conditions and route obstacles, calculate the distance from the current location of each rescue team and equipment to the fire point to obtain route distance information; Based on the route distance information, the resource status and fire situation are updated in real time, and the data of on-site rescue communication equipment and fire monitoring are received and updated to obtain real-time update results; Based on the real-time update results, resource allocation is adjusted using the formula: The optimal configuration of rescue deployment is obtained, where CZ represents the configuration efficiency and DZ i is the distance from the ith resource to the fire scene, TZ i is the estimated time of arrival, RZ i is the weight of the resource type, n z is the total number of rescue resources.

6. The meteorologically assisted high-efficiency forest fire early warning and dispatching system according to claim 1, characterized in that: The steps of performing real-time analysis of road conditions are specifically as follows: Based on the optimized configuration of the rescue deployment, GIS technology is used to collect real-time traffic data, including traffic flow and accident information, and generate traffic condition information; Based on the traffic condition information, identify traffic congestion areas and accident-prone areas, extract key road section information, and obtain key road section analysis results; Based on the analysis results of the key sections, the traffic conditions of the different sections are evaluated using the formula: Calculate the estimated rescue arrival time TB and obtain the road condition assessment result, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n b is the number of key sections.

7. The meteorologically assisted high-efficiency early warning and dispatching system for wildfires according to claim 1, characterized in that: The steps for obtaining the rescue path update information are specifically as follows: Combining the road conditions and GIS data, the shortest path algorithm is used to calculate the initial optimal path from the rescue vehicle to the fire scene and generate a preliminary rescue path; Based on the preliminary rescue path, monitor and update real-time traffic, including new accidents and traffic flow changes, to obtain updated traffic conditions; Based on the updated traffic conditions, the rescue path is recalculated using the formula: Determine the optimal rescue path PH and obtain the rescue path update information, where LB i represents the length of the key section i, VB i represents the average speed of the i-th road section, CB i is the congestion coefficient of the ith road section, n Q is the total number of road segments.

8. The meteorologically assisted high-efficiency mountain fire early warning and dispatching system according to claim 1, characterized in that: The steps for obtaining the fire response judgment result are specifically as follows: Based on the rescue path update information, fire condition data of different areas are collected, including temperature, smoke density and flame size, to obtain a fire condition feature data set; Based on the fire characteristic data set, compare the current fire data with the known fire pattern, extract the fire source image features, and generate a pattern matching result; Based on the pattern matching results, a fire model is constructed and continuously trained using the formula: Assess the urgency of the fire UR and obtain the fire response judgment result, where xu i represents the fire characteristic value, wu i is the corresponding feature weight, max(xu) represents the maximum value of the fire characteristic value, n u is the total number of fire characteristics.

Images