An emergency management method and system based on multimodal transport

Abstract

This invention discloses an emergency management method and system based on multimodal transport, relating to the field of emergency management technology. The method includes the following steps: S1, acquiring dynamic geographic information of disaster areas in real time through satellite remote sensing technology; This invention constructs a dynamic cross-modal collaborative scheduling mechanism by fusing satellite remote sensing data, realizing real-time mastery of geographic information of disaster areas, solving the problem of lack of real-time geographic information support for scheduling, and automatically adjusting the connection nodes and transfer processes of different modes of transport based on real-time road conditions through a model, avoiding delays in mode of transport adjustment and excessively long transfer waiting times, improving the timeliness of emergency material transport, and promoting information sharing and collaborative cooperation among various modes of transport by establishing cross-modal collaborative scheduling, forming an efficient transport chain, meeting the urgent needs of emergency management for material transport, realizing dynamic adaptation and efficient scheduling of multimodal transport of emergency materials, and ensuring the timeliness and effectiveness of emergency response.

Description

Technical Field

[0001] This invention relates to the field of emergency management technology, specifically to an emergency management method and system based on multimodal transport. Background Technology

[0002] Multimodal transport refers to a comprehensive transportation method that relies on two or more different modes of transport (such as road, rail, air, and waterway) and constructs a unified transport organization model to transport goods from the origin to the destination. In the process of multimodal transport, various modes of transport cooperate with each other and are organically connected to form a coherent transport chain, realizing the efficient transshipment of goods.

[0003] In emergency management, the timely and accurate transportation of emergency supplies is a crucial aspect of emergency response. Multimodal transport, with its advantages of coordinating multiple modes of transport, plays a vital role in emergency supply transportation. Through multimodal transport, the optimal combination of transport methods can be selected based on factors such as the characteristics of the emergency supplies, transport distance, and road conditions in the disaster area, ensuring the rapid delivery of emergency supplies to the disaster area. Therefore, emergency management methods based on multimodal transport have emerged, aiming to improve the response speed and effectiveness of emergency management through efficient transport organization.

[0004] However, existing emergency management technologies still have certain shortcomings in use. In current emergency management, the scheduling of multimodal transport lacks real-time dynamic geographic information support, making it difficult to quickly grasp the road damage, terrain changes, and other conditions in disaster areas. This leads to a lag in the adjustment of transportation modes. The connection nodes and transfer processes between different transportation modes are mostly pre-set and cannot be automatically adapted to real-time road conditions. When encountering sudden road interruptions, the problem of excessively long transfer waiting times can easily occur, affecting the transportation efficiency of emergency supplies. There is a lack of cross-modal collaborative scheduling mechanisms, poor information sharing among road, rail, and air transportation modes, and poor coordination between various transportation links, making it difficult to form an efficient transportation chain and failing to meet the urgent needs of emergency management for material transportation. Therefore, developing an emergency management method and system based on multimodal transport is of great significance. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an emergency management method and system based on multimodal transport. It can construct a dynamic cross-modal collaborative scheduling mechanism by integrating satellite remote sensing data, obtain real-time changes in geographical information of disaster areas, and automatically adjust the connection nodes and transfer processes of different modes of transportation such as highways, railways, and aviation accordingly. This enables dynamic adaptation and efficient scheduling of multimodal transport of emergency supplies, improving the timeliness of emergency response and the efficiency of material transportation.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an emergency management method based on multimodal transport, the method comprising the following steps:

[0007] S1. Real-time acquisition of dynamic geographic information of the disaster area through satellite remote sensing technology, including road damage and terrain change data;

[0008] S2. Process dynamic geographic information and extract key information related to transportation;

[0009] S3. Integrate key information into the cross-modal collaborative scheduling model. The cross-modal collaborative scheduling model evaluates the current transportation plans of road, rail, and air transport based on key information and monitors the traffic status of transportation routes simultaneously.

[0010] S4. During the monitoring process, when it is detected that the transportation route is interrupted due to disaster and the traffic capacity is reduced, the cross-modal collaborative scheduling model automatically triggers the transportation mode switching plan, re-plans the transportation route, and adjusts the connection nodes and transfer processes of different transportation modes.

[0011] S5. Based on the determined transportation routes, connection nodes, and transfer processes, the scheduling decision results are sent to the execution terminals of each transportation link, while feedback information during the transportation process is collected in real time to optimize the scheduling plan.

[0012] Furthermore, in step S1, acquiring dynamic geographic information of the disaster area in real time using satellite remote sensing technology includes: simultaneously monitoring the disaster area using at least two satellites in different orbits to obtain multiple sets of remote sensing data; performing spatiotemporal registration processing on the multiple sets of remote sensing data to eliminate data bias and obtain high-precision dynamic geographic information; the spatiotemporal registration processing uses data fusion weight calculation, the formula of which is: ,in, For the first The fusion weights of remote sensing data sets For the first Time deviation of the data set For the first Spatial deviation of the set of data, This is a group index for remote sensing data, used to traverse all remote sensing data groups. , For the first Time deviation of the data set For the first Spatial deviation of the set of data, , This is the deviation influence coefficient. Based on road design standards, functional levels, and emergency transport adaptability, the following criteria were determined: The impact of road damage type (such as cracks, collapses, and water accumulation) on traffic capacity is determined based on the degree of impact. This represents the total number of remote sensing data sets.

[0013] Furthermore, in step S2, the dynamic geographic information is processed to extract key information related to transportation, including: identifying road areas in the dynamic geographic information using an image segmentation algorithm; analyzing the traffic capacity of the identified road areas using a road condition assessment model; determining the location, degree of damage, and traffic status of alternative routes for damaged roads; and using the road traffic capacity assessment formula as follows: ,in, For real-time passage capability, Design the road to accommodate traffic flow. For the number of damage types, For the first Impact coefficient of damage type For the first The percentage of area damaged in this category The topographic slope is an influencing factor. This represents the average slope of the road.

[0014] Furthermore, in step S3, the cross-modal collaborative scheduling model evaluates the current transportation plan based on preset scheduling rules and algorithms. The scheduling rules include the priority of emergency supplies, transportation distance, capacity of each transportation mode, and historical scheduling efficiency.

[0015] Furthermore, in step S4, the automatic triggering of the transportation mode switching scheme includes: when the road transportation route is interrupted, prioritizing the matching of the nearest railway station or airport as the transfer node, and selecting railway or air transportation mode for connection according to the weight, volume and timeliness requirements of the emergency supplies.

[0016] Furthermore, in step S4, adjusting the connection nodes and transfer processes of different transportation modes includes: recalculating the transportation time and transfer costs between each connection node; optimizing the loading and unloading sequence of materials and the allocation plan of transfer vehicles based on the calculation results; reducing time loss in the transfer process; and calculating the overall adaptability of the transfer nodes as follows: ,in, To improve the overall adaptability of the transfer nodes, For the transit time between nodes, For transportation costs, The node coordination efficiency score is a comprehensive indicator used to quantitatively evaluate the smoothness of coordination among various links in emergency transportation scenarios at nodes connecting different modes of transportation (such as road-rail transfer stations, rail-air intermodal hubs, etc.). The value range is usually [0,1], with higher scores indicating higher coordination efficiency. Its core function is to supplement the consideration of the actual operational coordination of nodes in the selection of transfer nodes and process optimization, rather than relying solely on single factors such as transportation time or cost. , , The weighting coefficients are satisfied. The weight allocation for multi-source satellite data fusion is determined based on the accuracy, timeliness, and disaster area coverage of satellite remote sensing data.

[0017] Furthermore, in step S5, real-time collection of feedback information during transportation includes: obtaining real-time location information of materials through the positioning module of the execution terminal, receiving road condition updates and material status data uploaded by transportation personnel, and the material status data including the integrity of the materials and the remaining transportation distance.

[0018] An emergency management system based on multimodal transport, applicable to any of the above-mentioned emergency management methods based on multimodal transport, the system comprising:

[0019] The satellite remote sensing data receiving module is used to receive dynamic geographic information data of disaster areas transmitted by satellite remote sensing equipment;

[0020] The data processing module is used to parse, filter, and extract the received dynamic geographic information data to obtain key information related to transportation.

[0021] The cross-modal collaborative scheduling module has a built-in scheduling model, which is used to evaluate the current transportation plan based on key information and automatically trigger a transportation mode switching plan when an anomaly in the transportation route is detected, and adjust the connection nodes and transfer process.

[0022] The execution terminal module is used to receive scheduling decision results and execute transportation and transfer operations, while also providing feedback on information during the execution process;

[0023] The database module is used to store satellite remote sensing data, transportation planning data, and scheduling decision data.

[0024] Furthermore, the cross-modal collaborative scheduling module also includes an algorithm update unit, which is used to iteratively optimize the algorithm in the scheduling model based on historical scheduling data and feedback information to improve the accuracy and response speed of scheduling decisions. The execution terminal module includes an information interaction unit, which supports real-time information interaction between transportation personnel and the scheduling center.

[0025] Compared with existing technologies, this multimodal transport-based emergency management method and system has the following advantages:

[0026] This invention constructs a dynamic cross-modal collaborative scheduling mechanism by integrating satellite remote sensing data, enabling real-time monitoring of geographic information in disaster areas and addressing the problem of insufficient real-time geographic information support for scheduling. The model automatically adjusts the connection nodes and transfer processes of different transportation modes based on real-time road conditions, avoiding delays in mode adjustments and excessively long transfer waiting times, thus improving the timeliness of emergency material transportation. By establishing cross-modal collaborative scheduling, it promotes information sharing and coordination among various transportation modes, forming an efficient transportation chain that meets the urgent needs of emergency management for material transportation. Ultimately, it achieves dynamic adaptation and efficient scheduling of multimodal transport of emergency materials, ensuring the timeliness and effectiveness of emergency response.

[0027] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0029] Figure 1 A flowchart for an emergency management method based on multimodal transport;

[0030] Figure 2 This is a flowchart illustrating an emergency management method based on multimodal transport.

[0031] Figure 3 This is a schematic diagram of the structure of an emergency management system based on multimodal transport. Detailed Implementation

[0032] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0033] See Figure 1 and Figure 2 The present invention discloses an emergency management method based on multimodal transport, the specific steps of which are as follows:

[0034] S1. Obtain dynamic geographic information of the disaster area.

[0035] Real-time dynamic geographic information of disaster areas is obtained through satellite remote sensing technology. This information mainly includes road damage and terrain change data. To improve data accuracy, at least two satellites in different orbits are used to conduct synchronous remote sensing monitoring of the disaster area, thereby obtaining multiple sets of remote sensing data. Then, the multiple sets of remote sensing data are spatiotemporally registered to eliminate data bias and finally obtain high-precision dynamic geographic information.

[0036] S2. Process dynamic geographic information and extract key information.

[0037] The acquired dynamic geographic information is processed to extract key information related to transportation. Specifically, image segmentation algorithms are used to identify road areas in the dynamic geographic information, and then a road condition assessment model is used to analyze the traffic capacity of the identified road areas in order to determine the location, degree of damage, and traffic status of alternative routes of the damaged roads.

[0038] S3, Accessing cross-modal collaborative scheduling model to evaluate transportation plans

[0039] The extracted key information is integrated into a cross-modal collaborative scheduling model. Based on this key information, the model evaluates the current transportation plans for road, rail, and air transport. The evaluation process follows preset scheduling rules and algorithms, which include the priority of emergency supplies, transportation distance, capacity of each mode of transport, and historical scheduling efficiency.

[0040] S4. Trigger the transportation mode switching plan and adjust related processes.

[0041] When a transportation route is detected to be interrupted or its capacity reduced due to a disaster, the cross-modal collaborative scheduling model will automatically trigger a transportation mode switching plan. If a road transportation route is interrupted, the nearest railway station or airport will be prioritized as a transfer node. Based on the weight, volume, and timeliness requirements of emergency supplies, railway or air transportation will be selected for connection. At the same time, the transportation route will be replanned, and the connection nodes and transfer processes of different transportation modes will be adjusted. This includes recalculating the transportation time and transfer costs between each connection node, and optimizing the loading and unloading sequence of supplies and the allocation plan of transfer vehicles based on the calculation results to reduce time loss in the transfer process.

[0042] S5. Send scheduling results and collect feedback information.

[0043] The scheduling decision results are sent to the execution terminals of each transportation link, enabling each link to carry out transportation and transfer operations according to the decision. At the same time, feedback information during the transportation process is collected in real time. Specifically, the real-time location information of the materials is obtained through the positioning module of the execution terminal, and the road condition update information and material status data (including the integrity of the materials and the remaining transportation distance) uploaded by the transportation personnel are received. The scheduling plan is further optimized using this feedback information.

[0044] Example 1

[0045] This embodiment is applied to an emergency supplies transportation scenario following an earthquake disaster. When an earthquake causes extensive damage to roads in a mountainous county and surrounding areas, with some sections completely cut off, there is an urgent need to transport emergency supplies such as tents, food, and medical equipment to the disaster area. Due to the complex terrain of the disaster area, a single mode of transportation is insufficient to meet the demand for rapid delivery of supplies. Therefore, the multimodal transport-based emergency management method described in this invention is adopted. See [link to relevant documentation]. Figure 1 and Figure 2 By monitoring road conditions in real time through satellite remote sensing and dynamically adjusting transportation plans in conjunction with a cross-modal collaborative scheduling model, efficient connections between highway, railway, and air transportation can be achieved.

[0046] After an earthquake, an emergency response mechanism is activated. Two remote sensing satellites in different orbits (such as a low-orbit optical satellite and a high-orbit synthetic aperture radar satellite) are mobilized through a satellite remote sensing data receiving module to monitor the disaster area simultaneously. The low-orbit satellite provides high-resolution optical images, which can clearly identify visible damage such as road cracks and collapses. The high-orbit radar satellite is not affected by weather and can penetrate clouds to obtain terrain change data, which is especially suitable for monitoring landslide areas caused by earthquakes.

[0047] Spatiotemporal registration was performed on multiple sets of remote sensing data (optical data and radar data) transmitted from two satellites. First, the time deviation value of each set of data was calculated. (Difference from standard time) and spatial deviation value (Offset from baseline geographic coordinates), where optical data is affected by imaging time differences. Slightly larger than radar data, while radar data is affected by terrain obstruction. Relatively high.

[0048] The data fusion weight calculation formula is as follows: In the formula, According to the design standards of roads in the disaster area (such as main transportation routes) The higher value is used to determine the outcome. Based on the type of road damage (the type of damage that has a greater impact on traffic) (Using a higher value) The formula is used to calculate the fusion weight of each group of data. Data with higher weights (such as radar data with small spatial deviations) account for a larger proportion in the fusion process, ultimately generating high-precision dynamic geographic information, including multiple collapses on major provincial highways, landslides covering some county roads, and terrain data of temporary helicopter landing points in surrounding towns.

[0049] The data processing module analyzes the received fused geographic information. First, it uses the U-Net image segmentation algorithm to perform pixel-level identification of road areas in the remote sensing image, distinguishing transportation facilities such as highways, railway tracks, and airport runways. For the identified major provincial highways, it analyzes their traffic capacity using a road condition assessment model.

[0050] The formula for assessing road capacity is: ,in, The design capacity of the provincial highway; The number of damage types (e.g., collapse and crack). Impact coefficients for various types of damage (damage types with the greatest impact on traffic). (The higher the value) The percentage of area affected by each type of damage; This is the slope influence factor (set according to the characteristics of mountain roads). This represents the average slope of the road.

[0051] Calculations showed that the real-time traffic capacity of the road section had dropped significantly, only allowing one-way passage for small vehicles. At the same time, some county roads were identified as having zero real-time traffic capacity due to severe damage, and were judged as completely interrupted. Although the alternative rural roads had a steep slope, they were not severely damaged, and their real-time traffic capacity could meet basic transportation needs, so they could be used as emergency channels. The key information extracted included: the traffic status of the main roads, the distribution of available railway stations, and the terrain adaptability data of temporary helicopter landing points.

[0052] Inputting the above key information into the cross-modal collaborative scheduling model, the model first calls the pre-stored transportation plan in the database: the original plan was to transport tents (medium priority), food (high priority), and medical equipment (highest priority) by road, starting from the material reserve and going directly to the county town via the main provincial highway.

[0053] The cross-modal collaborative scheduling model assesses the feasibility of the plan based on scheduling rules: medical equipment has the highest timeliness requirements, but the real-time traffic capacity of the main provincial highways can only support small vehicles, and the estimated travel time cannot meet the demand; food and tents can be transported via rural roads, but the transportation time is long and cannot meet the priority demand. At the same time, the railway transportation is assessed: some railway stations have freight trains available with sufficient capacity, but the route from the storage warehouse to the station needs to be detoured, and after arriving at the station, it is necessary to transfer to the road; in terms of air transportation, temporary take-off and landing points can accommodate helicopter take-off and landing, and medical equipment can be transported in one trip, but the capacity is limited.

[0054] The cross-modal collaborative scheduling model detects that the original highway transportation plan cannot be executed due to insufficient capacity and automatically triggers a switching scheme:

[0055] Medical equipment transportation: highest priority, air transport will be selected, the airport closest to the storage warehouse will be matched, helicopters will be arranged to transport in batches, take off from the airport to the temporary take-off and landing point, and ground vehicles will be arranged to connect to the county town.

[0056] Food transportation: A combination of road and rail transport is used. Food is transported from the storage warehouse by truck to the nearest railway station, then transferred to a freight train, and finally delivered to the disaster area by small trucks via rural roads.

[0057] Tent transportation: Pure road transportation, the route has been adjusted to storage warehouse → rural road → county town. Although the distance has increased, the traffic capacity remains stable.

[0058] Simultaneously calculate the overall adaptability of each transit node: ,in, , , These are the weighting coefficients (time has the highest weight). For the transit time between nodes, For transportation costs, The node collaboration efficiency is scored, and the railway station with the highest comprehensive suitability is selected as the railway transfer node through calculation. This node is determined because of its short transportation time, reasonable transfer cost, and high collaboration efficiency.

[0059] Based on the calculation results, the transfer process was optimized: loading and unloading equipment and personnel were pre-allocated at transfer nodes to ensure rapid loading and unloading of materials upon arrival; personnel were arranged at temporary take-off and landing points to receive medical equipment and shorten ground transfer time.

[0060] The cross-modal collaborative scheduling module sends the above decision results to each execution terminal. For the specific structure of this system, please refer to [link / reference needed]. Figure 3 Helicopter crews receive flight routes and takeoff and landing coordinates; truck drivers obtain navigation routes (including real-time traffic updates); and train stations receive loading and unloading schedules.

[0061] During transportation, the terminal provides real-time feedback: the positioning module displays the time the helicopter arrives at the take-off and landing point; truck drivers upload information about minor obstacles on rural roads and changes in traffic speed, which is fed back to the model; the railway station reports the completion time of food loading and unloading, confirming that the train can depart as planned or ahead of schedule. Based on the feedback, the model optimizes subsequent scheduling: adjusting the departure time of the tent transport convoy to avoid the time spent dealing with obstacles; and instructing freight trains to adjust their departure times according to the actual situation, further shortening the overall transportation time.

[0062] In summary, this embodiment achieves high-precision real-time acquisition of geographic information in disaster areas through satellite remote sensing data fusion technology, solving the problem of lagging road condition information in traditional scheduling. Through a cross-modal collaborative scheduling model, transportation mode switching and route replanning are completed in a short time, significantly improving the transportation efficiency of medical equipment, food, and tents. During transportation, by dynamically adjusting connection nodes and transfer processes, transfer waiting time is greatly shortened, and the collaborative efficiency of helicopter and ground docking is significantly improved. At the same time, the real-time feedback mechanism enables the scheduling plan to be continuously optimized according to sudden road conditions, ensuring the efficient operation of the entire transportation chain.

[0063] Example 2

[0064] This embodiment is applied to an emergency supplies transportation scenario for floods caused by continuous heavy rainfall. In a plain area, multiple rivers breached their banks due to torrential rain, flooding large areas and damaging transportation infrastructure such as highways and railways to varying degrees. Some road sections were completely cut off due to flooding. There was an urgent need to transport emergency supplies such as drinking water, life-saving equipment, medicines, and temporary housing to the disaster area. Due to the wide area of ​​flooding and continuously fluctuating water levels, traditional single-mode transportation was insufficient to meet the need for precise delivery of supplies. Therefore, the multimodal transport-based emergency management method described in this invention was adopted. (See also...) Figure 1 and Figure 2 By dynamically monitoring changes in waterways and the status of transportation facilities through satellite remote sensing, and combining this with a cross-modal collaborative scheduling model, we can achieve flexible combination and efficient connection of waterway, highway and air transportation.

[0065] After the floods occurred, an emergency response mechanism was activated. The satellite remote sensing data receiving module coordinated two remote sensing satellites in different orbits (a high-resolution optical satellite and a microwave remote sensing satellite) to conduct all-weather monitoring of the disaster area. The optical satellite can clearly identify the distribution of roads, bridges and settlements that have not been submerged; the microwave remote sensing satellite is not affected by clouds and rain and fog, and can penetrate water to obtain underwater topographic data and road submersion depth, accurately judging the damage status of transportation facilities.

[0066] Spatiotemporal registration was performed on multiple sets of remote sensing data transmitted from two satellites. First, the time deviation value of each set of data was calculated. (Difference between data acquisition time and standard time) and spatial deviation value (Offset between geographic coordinates and reference coordinates of data). Among them, optical satellites may have a longer data acquisition interval due to weather conditions, resulting in a relatively large time deviation. Although microwave remote sensing satellites have good temporal continuity, they are affected by water reflection, resulting in a slightly higher spatial deviation in some areas.

[0067] The data fusion weight calculation formula is as follows: ,in, Determined based on the emergency priority of transportation facilities (such as main disaster relief routes). (Higher value) Adaptability settings for water body monitoring based on data type (microwave remote sensing data for water body monitoring) (The value is higher than that of optical data), and the fusion weight of each group of data is calculated using this formula. Data with higher weights account for a larger proportion in the fusion process, ultimately generating high-precision dynamic geographic information that includes the flood inundation range, road water depth, bridge damage, distribution of navigable waters, and terrain conditions of temporary helicopter landing sites.

[0068] The data processing module analyzes the fused dynamic geographic information, using the Mask R-CNN image segmentation algorithm to identify key areas such as roads, railways, rivers, and buildings in the remote sensing imagery. It focuses on extracting transportation-related information and analyzes the traffic capacity of roads not submerged using a road condition assessment model. The calculation formula is as follows: ,in, Design the road to accommodate traffic flow; This refers to the number of types of damage caused by flooding (such as water accumulation, road collapse, slope landslides, etc.). The impact coefficients for various types of damage (the impact coefficient of water accumulation on traffic capacity is higher than that of ordinary cracks). The percentage of length for each type of damage; The topographic flatness factor has a lower value (for plains areas). This represents the local slope value of the road.

[0069] Calculations show that the real-time traffic capacity of some road sections is affected by water depth exceeding the vehicle's passage limit. A score of 0 indicates a complete disruption; while some sections of the road have no water accumulation, there is a risk of slope collapse, significantly reducing traffic capacity and allowing only small vehicles to pass slowly. At the same time, the locations and carrying capacities of two navigable rivers and three temporary docks along the banks were identified, and three high-lying and flat areas were determined as temporary helicopter landing points. The key information extracted includes: available road sections / waterways for each mode of transportation, locations of damaged nodes, traffic status of alternative routes, and basic conditions of transfer nodes.

[0070] The extracted key information is input into the cross-modal collaborative scheduling model, which calls the initial transportation plan pre-stored in the database: transport drinking water and medicine (highest priority), life-saving equipment (high priority), and temporary housing (medium priority) from the material reserve center to the disaster area via highway.

[0071] The model assesses the feasibility of the plan based on scheduling rules: drinking water and medicine need to be delivered in the shortest possible time, but the main roads leading to the disaster-stricken areas are completely blocked by flooding, and detour routes have low traffic capacity and take too long; life-saving equipment needs to be deployed to multiple besieged villages, and road transport alone cannot cover the water-isolated areas; temporary housing is large and heavy, and air transport capacity is insufficient, so waterway and road transport need to be combined, while assessing the suitability of each mode of transport: waterway transport is suitable for long-distance transport of large quantities of supplies, but is limited by river levels and bridge clearance; air transport is suitable for point-to-point delivery of emergency supplies, but is limited by weather and take-off and landing conditions; road transport is suitable for short-distance connections, but is limited by the extent of flooding.

[0072] The model detected that the original road transport plan could not be executed and automatically triggered a multimodal transport switching scheme:

[0073] Drinking water and medicine transportation: "Road + air" combined transport is adopted. The supplies are transported from the storage center to the nearest helicopter landing point by small trucks (the section of road was not affected by the flood), and then dropped in batches by helicopter to temporary resettlement sites in various disaster areas, giving priority to severely affected areas.

[0074] Lifesaving equipment transportation: A combination of waterway and road transport is adopted. Using navigable rivers, cargo ships transport lifesaving equipment to temporary docks along the river, and then off-road vehicles transfer it to the besieged villages. For areas with shallow water, inflatable boats are deployed for the last mile of transportation.

[0075] Transportation of temporary resettlement housing: The "road + waterway" combined transport is adopted. The resettlement housing components are transported from the reserve center to the upstream port via undamaged roads, then transferred to large cargo ships and transported downstream to the dock closest to the disaster area. After unloading, they are transported by heavy trucks via the repaired temporary access road to the resettlement site.

[0076] Simultaneously calculate the overall adaptability of each transit node: ,in, (Time weighting) (Cost weighting) (Collaboration efficiency weight) is set according to emergency priority (emergency material transportation). (Higher value) For the transit time between nodes, This includes transportation costs (including equipment rental and labor costs). The matching degree of loading and unloading equipment at each node is scored. Through calculation, the wharf with the highest comprehensive suitability is selected as the waterway transshipment node. This node is identified as the core transshipment hub because it is close to the main resettlement point, has complete loading and unloading equipment, and has suitable river depth.

[0077] Based on the calculation results, the transfer process was optimized: cranes and waterproof tarpaulins were deployed in advance at the temporary dock to ensure that the life-saving equipment was not damaged again after unloading; medical personnel were arranged at the helicopter landing point to receive medicines and immediately carry out distribution work; during the transfer of resettlement housing components, villages along the way were coordinated in advance to clear obstacles on temporary access roads and shorten the land transportation time.

[0078] The cross-modal collaborative scheduling module sends the scheduling decision results to each execution terminal. The system's structure is described in [reference needed]. Figure 3 Helicopter crews receive flight routes, drop point coordinates, and a list of supplies; cargo ship captains receive route plans, docking schedules, and loading / unloading schedules; truck drivers receive real-time navigation routes (including warnings of flooded road sections).

[0079] During transportation, the terminal provides real-time feedback: the positioning module displays the real-time location of the helicopter group and the progress of material delivery; one helicopter temporarily returned to base due to localized heavy rain, and this was promptly reported to the dispatch center; cargo ship crew members uploaded data on river water level changes, discovering that a certain section of the river was impassable due to insufficient clearance on the bridge caused by rising water levels; truck drivers reported that a temporary access road had partially collapsed, reducing traffic speed and requiring a temporary route adjustment.

[0080] The model dynamically optimizes the solution based on feedback information: coordinates backup helicopters to take over the transportation tasks of the returning crew; replans the route for cargo ships, detouring through another navigable tributary; and plans new connecting routes for truck drivers, utilizing nearby unflooded rural roads to complete the transportation.

[0081] In summary, this embodiment achieved accurate acquisition of dynamic geographic information of flood-affected areas through satellite remote sensing data fusion technology. In particular, the combination of microwave remote sensing and optical remote sensing solved the problem of monitoring transportation facilities during rainstorms. Through a cross-modal collaborative scheduling model, dynamic switching of transportation modes and the formulation of multimodal transport solutions were completed in a short period of time. The delivery time of drinking water and medicines was shortened by nearly half compared to the original plan. During the transportation process, by adjusting transfer nodes and processes in real time, the waiting time between waterways and highways was reduced, the accuracy of air transport in delivering goods was improved, and the collaborative efficiency of various transportation modes was significantly enhanced.

[0082] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An emergency management method based on multimodal transport, characterized in that, The method includes the following steps: S1. Real-time acquisition of dynamic geographic information of the disaster area through satellite remote sensing technology, including road damage and terrain change data; S2. Process dynamic geographic information and extract key information related to transportation; S3. Integrate key information into the cross-modal collaborative scheduling model. The cross-modal collaborative scheduling model evaluates the current transportation plans of road, rail, and air transport based on key information and monitors the traffic status of transportation routes simultaneously. S4. During the monitoring process, when it is detected that the transportation route is interrupted due to disaster and the traffic capacity is reduced, the cross-modal collaborative scheduling model automatically triggers the transportation mode switching plan, re-plans the transportation route, and adjusts the connection nodes and transfer processes of different transportation modes. S5. Based on the determined transportation routes, connection nodes and transfer processes, the scheduling decision results are sent to the execution terminals of each transportation link, and feedback information during the transportation process is collected in real time to optimize the scheduling plan. In step S2, the dynamic geographic information is processed to extract key information related to transportation, including: identifying road areas in the dynamic geographic information using an image segmentation algorithm; analyzing the traffic capacity of the identified road areas using a road condition assessment model; determining the location, degree of damage, and traffic status of alternative routes for damaged roads; and using the road traffic capacity assessment formula as follows: Where C represents real-time traffic capacity, C0 represents road design traffic capacity, m represents the number of damage types, and γ k Let s be the impact coefficient of the k-th type of damage. k Let λ represent the area percentage of damage of type k, λ be the topographic slope influencing factor, and h be the average road slope value.

2. The emergency management method based on multimodal transport according to claim 1, characterized in that, In step S1, dynamic geographic information of the disaster area is acquired in real time using satellite remote sensing technology. This includes: synchronously monitoring the disaster area using at least two satellites in different orbits to obtain multiple sets of remote sensing data; performing spatiotemporal registration processing on the multiple sets of remote sensing data to eliminate data bias and obtain high-precision dynamic geographic information. The spatiotemporal registration processing uses data fusion weight calculation, with the following formula: Among them, w i Let t be the fusion weight of the i-th group of remote sensing data. i Let d be the time deviation value of the i-th data set. i Let t be the spatial deviation value of the i-th data group, and j be the group index of the remote sensing data, used to traverse all remote sensing data groups, j = 1, 2, ..., n. j Let d be the time deviation value of the j-th data group. j Let be the spatial deviation value of the j-th data group, α and β be the deviation influence coefficients, and n be the total number of remote sensing data groups.

3. The emergency management method based on multimodal transport according to claim 1, characterized in that, In step S3, the cross-modal collaborative scheduling model evaluates the current transportation plan based on preset scheduling rules and algorithms. The scheduling rules include the priority of emergency supplies, transportation distance, capacity of each transportation mode, and historical scheduling efficiency.

4. The emergency management method based on multimodal transport according to claim 1, characterized in that, In step S4, the transportation mode switching scheme is automatically triggered, including: when the road transportation route is interrupted, the nearest railway station or airport is prioritized as the transfer node, and the railway or air transportation mode is selected for connection according to the weight, volume and timeliness requirements of the emergency supplies.

5. The emergency management method based on multimodal transport according to claim 1, characterized in that, In step S4, adjusting the connection nodes and transfer processes of different transportation modes includes: recalculating the transportation time and transfer costs between each connection node; optimizing the loading and unloading sequence of materials and the allocation plan of transfer vehicles based on the calculation results; reducing time loss in the transfer process; and calculating the overall adaptability of the transfer nodes as follows: Where F is the overall adaptability of the transfer node, T is the transportation time between nodes, C is the transfer cost, S is the node collaboration efficiency score, and ω1, ω2, and ω3 are weight coefficients that satisfy ω1+ω2+ω3=1.

6. The emergency management method based on multimodal transport according to claim 1, characterized in that, In step S5, feedback information during the transportation process is collected in real time, including: obtaining real-time location information of the materials through the positioning module of the execution terminal, receiving road condition update information and material status data uploaded by the transportation personnel, and the material status data including the integrity of the materials and the remaining transportation distance.

7. An emergency management system based on multimodal transport, applicable to the emergency management method based on multimodal transport as described in any one of claims 1-6, characterized in that, The system includes: The satellite remote sensing data receiving module is used to receive dynamic geographic information data of disaster areas transmitted by satellite remote sensing equipment; The data processing module is used to parse, filter, and extract the received dynamic geographic information data to obtain key information related to transportation. The cross-modal collaborative scheduling module has a built-in scheduling model, which is used to evaluate the current transportation plan based on key information and automatically trigger a transportation mode switching plan when an anomaly in the transportation route is detected, and adjust the connection nodes and transfer process. The execution terminal module is used to receive scheduling decision results and execute transportation and transfer operations, while also providing feedback on information during the execution process; The database module is used to store satellite remote sensing data, transportation planning data, and scheduling decision data.

8. An emergency management system based on multimodal transport according to claim 7, characterized in that, The cross-modal collaborative scheduling module also includes an algorithm update unit, which is used to iteratively optimize the algorithm in the cross-modal collaborative scheduling model based on historical scheduling data and feedback information. The execution terminal module includes an information interaction unit, which supports real-time information interaction between transportation personnel and the scheduling center.

Images