An urban road extreme weather real-time prediction and risk early warning method and system based on artificial intelligence and digital twinning

Abstract

The application belongs to the technical field of meteorological monitoring, and provides a city road extreme weather real-time forecasting and risk early warning method and system based on artificial intelligence and digital twinning. The system comprises a data acquisition layer, a data processing and calculation layer, a business application layer and a user interaction layer. The application fuses radar, meteorological, geographical, municipal and other multi-source data, uses artificial intelligence technology to accurately forecast short-term precipitation, and drives a city hydrology and water power model based on digital twinning technology to simulate quickly, thereby realizing high-precision, dynamic and visual forecasting and early warning of urban waterlogging risk. The application effectively solves the problems of poor accuracy, slow timeliness and weak decision support of traditional early warning methods, can provide technical support for changing from passive response to active prevention and control for city safety management, and significantly improves the ability of cities to cope with extreme weather events.

Description

Technical Field

[0001] This invention belongs to the field of meteorological monitoring technology and relates to a method and system for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins. Background Technology

[0002] With the intensification of global climate change and the rapid advancement of urbanization, urban flooding disasters caused by extreme precipitation are occurring frequently, posing a serious threat to people's lives and property, urban operational safety, and socio-economic stability. Existing flood warning methods typically rely on regional precipitation forecast data provided by meteorological departments and emergency response mechanisms built upon historical experience.

[0003] However, traditional numerical weather prediction models have limited spatial resolution, typically greater than 1 kilometer, making it difficult to accurately capture the key impacts of urban micro-scale topography, building layout, and underground drainage networks on water accumulation formation and distribution. Furthermore, inputting this forecast data into computationally inefficient hydrological models for urban flooding simulations leads to significant prediction biases and delayed early warning updates, failing to provide timely and accurate decision support for urban disaster prevention and mitigation. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a real-time forecast and risk warning system for extreme weather on urban roads based on artificial intelligence and digital twins, so as to solve the problems of insufficient forecast accuracy, delayed warning, information silos and lack of dynamic simulation capabilities in traditional warning methods.

[0005] The technical solution of this invention:

[0006] A method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins includes:

[0007] Acquire multi-source heterogeneous data, including meteorological monitoring data, high-precision geographic information data, urban infrastructure data, and real-time feedback data;

[0008] We utilize an artificial intelligence short-term forecasting model to process multi-source heterogeneous data and generate high spatiotemporal resolution short-term precipitation forecasts. The artificial intelligence short-term forecasting model is constructed based on an attention mechanism and a long short-term memory network.

[0009] The short-term precipitation forecast results drive the urban hydrological and hydraulic coupling model to simulate, and the simulation process is optimized in real time by combining the AI-driven model optimization module to obtain the prediction results of urban waterlogging.

[0010] A high-fidelity digital twin of the city is constructed based on digital twin technology, and the prediction results of urban waterlogging are dynamically simulated and visualized in the digital twin.

[0011] Based on the dynamic simulation results, a dynamic assessment of urban flooding risk is conducted, and tiered early warning information is generated.

[0012] Emergency response plans are developed based on tiered early warning information and then pushed to user terminals.

[0013] Furthermore, the acquisition of multi-source heterogeneous data includes: meteorological monitoring data, obtained from meteorological departments using radar, satellite, and ground station meteorological data; high-precision geographic information data, obtained from natural resources and housing and construction departments using digital elevation models, land use types, and building outlines; urban infrastructure data, obtained from water resources departments using drainage network data; real-time feedback data, obtained from traffic management departments using real-time traffic monitoring video streams and road condition information; and receiving and processing information on waterlogged areas reported by the public through a public crowdsourcing platform.

[0014] Furthermore, the process of using an artificial intelligence short-term forecast model to process multi-source heterogeneous data and generate short-term precipitation forecast results with high spatiotemporal resolution includes: using an attention-based spatiotemporal fusion network to extract and fuse features from radar base data, satellite cloud images, and ground station data; and using a long short-term memory network to learn the spatiotemporal evolution of precipitation to generate quantitative precipitation forecast results with a spatial resolution higher than 1 kilometer for the next 0-2 hours.

[0015] Furthermore, the AI-driven model optimization module optimizes the simulation process in real time, including: using a deep reinforcement learning algorithm to dynamically calibrate the Manning roughness coefficient of the urban hydrological-hydraulic coupling model based on real-time feedback of water accumulation point information; and using a physical information neural network to construct a lightweight proxy model of the urban hydrological-hydraulic coupling model to accelerate the generation of urban waterlogging prediction results.

[0016] Furthermore, the construction of a high-fidelity digital twin of the city based on digital twin technology includes: integrating a real-scene 3D model, a building information model, and an urban drainage network model to construct a comprehensive urban digital twin containing geospatial entities, physical process mechanisms, and behavioral rules; dynamically extrapolating and visualizing the prediction results of urban waterlogging in the digital twin, which involves mapping the prediction results of urban waterlogging into the digital twin, and simulating and visualizing the spatial distribution, depth changes, and spread process of water accumulation in real time.

[0017] Furthermore, the dynamic assessment of urban flooding risk based on the dynamic simulation results and the generation of graded early warning information include: constructing a dynamic risk assessment model based on the simulated water depth, flood range and duration, combined with road network, population density and critical infrastructure distribution information; and classifying risk levels and generating corresponding early warning level information based on the output of the dynamic risk assessment model.

[0018] Furthermore, the emergency response plan based on tiered early warning information includes: automatically matching a pre-set emergency plan library according to the early warning level, predicted location of water accumulation and scope of impact, and generating an emergency response plan that includes traffic control, drainage scheduling and personnel evacuation; and linking the emergency response plan with real-time traffic information to optimize resource allocation and action routes.

[0019] Furthermore, the method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins also includes: constructing a road surface weather forecasting system, which is based on a deep neural network and takes real-time traffic monitoring video streams and road condition information, information on water accumulation points reported by the public, and real-time meteorological data as inputs to predict the road surface conditions of water accumulation, ice accumulation, or snow accumulation on urban roads in the future; and integrating the road surface condition prediction information with the urban waterlogging prediction results to serve as the basis for generating graded early warning information and formulating emergency response plans.

[0020] A real-time forecasting and risk warning system for extreme weather on urban roads based on artificial intelligence and digital twins includes:

[0021] The data acquisition and processing module is used to acquire and fuse multi-source heterogeneous data.

[0022] The AI-powered short-term forecasting module is used to generate high-precision short-term precipitation forecasts based on attention mechanisms and spatiotemporal deep learning networks.

[0023] The urban flooding simulation and optimization module includes an urban hydrological and hydraulic coupling model and an AI-driven model optimization unit, which are used to generate and optimize the prediction results of urban flooding.

[0024] The digital twin construction and simulation module is used to construct a high-fidelity digital twin of the city and to dynamically simulate and visualize the urban flooding process;

[0025] The risk assessment and early warning generation module is used to perform dynamic risk assessments and generate tiered early warning information based on the simulation results.

[0026] The emergency decision-making and information dissemination module is used to formulate emergency response plans and push early warning information and action guidelines to user terminals.

[0027] The beneficial effects of this invention are as follows: This invention provides a method and system for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins. It can achieve high-precision short-term precipitation forecasting by using multi-source heterogeneous data fusion and artificial intelligence technology, and can dynamically extrapolate and visualize the urban flooding process through digital twins. This enables real-time and accurate early warning of urban flooding risks and scientific emergency decision-making. Compared with existing urban flooding early warning methods, this invention solves the problems of insufficient forecast accuracy, delayed early warning, information silos, and lack of dynamic extrapolation capabilities. Detailed Implementation

[0028] The specific embodiments of the present invention will be further described below in conjunction with the technical solution.

[0029] It is worth noting that prior to this invention, with the intensification of global climate change and the acceleration of urbanization, urban flooding caused by extreme precipitation events has become increasingly serious, posing a significant threat to people's lives and property, normal urban operations, and economic and social stability. Existing urban flooding early warning methods typically rely on regional precipitation forecasts from meteorological departments and emergency responses based on historical experience. However, traditional numerical weather prediction models have low spatial resolution (usually greater than 1 kilometer), making it difficult to capture the precise impact of urban micro-scale topography, building clusters, and drainage networks on the formation and distribution of water accumulation. Furthermore, inputting the aforementioned forecast data into computationally inefficient hydrological models for flooding simulation leads to large prediction biases and slow early warning updates, failing to meet the rapid response requirements for short-term disasters (tens of minutes to several hours in advance) and hindering refined and visualized emergency decision-making.

[0030] Based on this, embodiments of the present invention provide a method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins, so as to improve the accuracy of urban flooding forecasts, the timeliness of warnings, and emergency decision-making capabilities.

[0031] Step S101: Obtain multi-source heterogeneous data, including meteorological monitoring data, high-precision geographic information data, urban infrastructure data, and real-time feedback data;

[0032] Step S102: The multi-source heterogeneous data is processed using an artificial intelligence short-term forecast model to generate short-term precipitation forecast results with high spatiotemporal resolution; wherein, the artificial intelligence short-term forecast model is constructed based on attention mechanism and long short-term memory network.

[0033] Step S103: The short-term precipitation forecast results drive the urban hydrological and hydraulic coupling model to simulate, and the simulation process is optimized in real time by combining the AI-driven model optimization module to obtain the prediction results of urban waterlogging.

[0034] Step S104: Construct a high-fidelity digital twin of the city based on digital twin technology, and dynamically extrapolate and visualize the prediction results of urban waterlogging in the digital twin.

[0035] Step S105: Based on the dynamic simulation results, conduct a dynamic assessment of urban flooding risk and generate tiered early warning information;

[0036] Step S106: Develop an emergency response plan based on the graded early warning information and push it to the user terminal.

[0037] The embodiment provides a method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins. It can achieve high-precision short-term precipitation forecasting by using multi-source heterogeneous data fusion and artificial intelligence technology, and can dynamically extrapolate and visualize the urban flooding process through digital twins. This enables real-time and accurate early warning of urban flooding risks and scientific emergency decision-making, solving the problems of insufficient forecast accuracy, delayed early warning, information silos and lack of dynamic extrapolation capabilities in traditional methods.

[0038] To facilitate understanding of this embodiment, the following example illustrates the exemplary steps provided in this embodiment of the invention by applying the method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins to an urban emergency management server.

[0039] In step S101, multi-source heterogeneous data is acquired, including meteorological monitoring data, high-precision geographic information data, urban infrastructure data, and real-time feedback data.

[0040] Access the following multi-source heterogeneous data through the government data sharing and exchange platform or dedicated line API interface:

[0041] Meteorological monitoring data: Doppler weather radar base data (once every 6 minutes), Fengyun satellite cloud image data, and real-time observation and forecast data from ground automatic weather stations (data every minute) are obtained from meteorological departments.

[0042] High-precision geographic information data: 1-meter resolution digital elevation model (DEM), 0.5-meter resolution high-definition orthophotos, building outline vector data, and drainage network data generated from LiDAR scanning data obtained from natural resources, housing and construction, and water departments.

[0043] Urban infrastructure data: Obtain BIM models of drainage pipe networks from water authorities, including pipe diameter, pipe material, slope, and manhole location information; obtain real-time operational status data of facilities such as pumping stations and gates.

[0044] Real-time data feedback: Obtain road surveillance video streams from traffic management departments; receive location and photo information of waterlogged areas reported by citizens through a developed crowdsourcing mini-program.

[0045] In step S102, the multi-source heterogeneous data is processed using an artificial intelligence short-term forecast model to generate short-term precipitation forecast results with high spatiotemporal resolution.

[0046] In this step, the artificial intelligence short-term forecast model is constructed based on an attention mechanism and a spatiotemporal deep learning network, such as a spatiotemporal graph convolutional network-long short-term memory (STGCN-LSTM) coupled model.

[0047] The latest radar reflectivity factor, satellite brightness temperature, and ground station temperature, humidity, pressure, and wind data are input into a pre-trained spatiotemporal graph convolutional network-long short-term memory coupled model. This model, trained using historical precipitation data, can capture the evolution characteristics of localized precipitation. The model outputs quantitative precipitation forecasts (QPF) with a spatial resolution of 500m × 500m, occurring every 10 minutes for the next two hours.

[0048] In step S103, the short-term precipitation forecast results are used to drive the urban hydrological and hydraulic coupling model to simulate the process, and the simulation process is optimized in real time by combining the AI-driven model optimization module to obtain the prediction results of urban waterlogging.

[0049] In this step, the urban hydrological and hydraulic coupling model is constructed based on the coupling of the one-dimensional Saint-Venant equation and the two-dimensional shallow water equation. To meet the real-time requirements, a lightweight proxy model of the urban hydrological and hydraulic coupling model is constructed using a Physical Information Neural Network (PINN), which reduces the computation time from several hours to within 3 minutes.

[0050] Simultaneously, a deep reinforcement learning (DRL) algorithm is employed to dynamically adjust key parameters such as the Manning roughness coefficient in the lightweight proxy model based on the actual water depth monitored over the past hour (from camera and crowdsourced data), achieving online self-calibration of the lightweight proxy model. Finally, the predicted water depth and inundation extent for key areas are output for the next two hours.

[0051] In step S104, a high-fidelity digital twin of the city is constructed based on digital twin technology, and the prediction results of urban waterlogging are dynamically simulated and visualized in the digital twin.

[0052] In this step, based on the multi-source heterogeneous data acquired in S101, a high-fidelity digital twin of the city is constructed in the Unity3D engine, integrating an integrated real-scene 3D model, a building information model, and an urban drainage network model. The urban flooding prediction results obtained in S103 are mapped in real time onto this high-fidelity digital twin, dynamically and visually presenting the spread of floodwater with different colors and heights. Decision-makers can use computers or VR devices to view the potential flooding situation in key areas at different times in the future from any angle.

[0053] In step S105, a dynamic assessment of urban flooding risk is conducted based on the dynamic simulation results, and graded early warning information is generated.

[0054] In this step, the system's built-in dynamic risk assessment algorithm automatically generates a dynamic risk level distribution map based on the predicted water depth (e.g., >15cm for mild risk, >25cm for moderate risk, and >40cm for high risk), combined with real-time population heat maps of the area (from mobile signaling data) and location information of key facilities (e.g., subway entrances, substations, hospitals). When the system predicts that the risk level at a certain location is about to exceed the threshold, it automatically generates a graded warning (e.g., orange warning).

[0055] In step S106, an emergency response plan is formulated based on the graded early warning information and pushed to the user terminal.

[0056] In this step, after the early warning information is triggered, the emergency decision support module automatically matches the corresponding emergency response plan from the contingency plan database and generates a specific action plan based on real-time traffic flow data: "Close the entrances to the relevant road sections and guide vehicles to detour; dispatch drainage equipment to the scene within a specified time." This emergency response plan and early warning information are distributed to relevant department terminals through the municipal emergency management command platform, and at the same time, early warning notices and detour instructions are pushed to citizens in the affected areas through government affairs APP and public mini-programs.

[0057] Based on the same inventive concept, this invention also provides a system corresponding to the method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins. Since the principle of the device in this invention is similar to the method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0058] The following is a real-time forecast and risk warning system for extreme weather on urban roads based on artificial intelligence and digital twins, including:

[0059] The data acquisition module is used to acquire and fuse multi-source heterogeneous data.

[0060] The AI-powered short-term forecasting module is used to generate high-precision short-term precipitation forecasts based on attention mechanisms and spatiotemporal deep learning networks.

[0061] The urban flooding simulation and optimization module includes an urban hydrological and hydraulic coupling model and an AI-driven model optimization unit, which are used to generate and optimize the prediction results of urban flooding.

[0062] The digital twin construction and simulation module is used to construct a high-fidelity digital twin of the city and to dynamically simulate and visualize the urban flooding process;

[0063] The risk assessment and early warning generation module is used to perform dynamic risk assessments and generate tiered early warning information based on the simulation results.

[0064] The emergency decision-making and information dissemination module is used to formulate emergency response plans and push early warning information and action guidelines to user terminals.

[0065] The following embodiment of the present invention provides a structure of an electronic device. The electronic device includes a processor, a memory, and a bus.

[0066] The memory stores machine-readable instructions that can be executed by the processor. When the electronic device is running, the processor and the memory communicate via a bus. When the machine-readable instructions are executed by the processor, the steps of the method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins in the above method embodiment can be performed. For specific implementation methods, please refer to the method embodiment, which will not be repeated here.

[0067] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the method embodiment described above for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0068] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0069] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0070] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0072] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins, characterized in that, include: Acquire multi-source heterogeneous data, including meteorological monitoring data, high-precision geographic information data, urban infrastructure data, and real-time feedback data; We utilize an artificial intelligence short-term forecasting model to process multi-source heterogeneous data and generate high spatiotemporal resolution short-term precipitation forecasts. The artificial intelligence short-term forecasting model is constructed based on an attention mechanism and a long short-term memory network. The simulation is driven by short-term precipitation forecast results, and the simulation process is optimized in real time by an AI-driven model optimization module to obtain urban flooding prediction results. The real-time optimization of the simulation process by the AI-driven model optimization module includes: using a deep reinforcement learning algorithm to dynamically calibrate the Manning roughness coefficient of the urban hydrological and hydraulic coupling model based on real-time feedback of water accumulation point information; and using a physical information neural network to construct a lightweight surrogate model of the urban hydrological and hydraulic coupling model to accelerate the generation of urban flooding prediction results. A high-fidelity digital twin of the city is constructed based on digital twin technology, and the prediction results of urban waterlogging are dynamically simulated and visualized in the digital twin. Based on the dynamic simulation results, a dynamic assessment of urban flooding risk is conducted, and tiered early warning information is generated. Emergency response plans are developed based on tiered early warning information and then pushed to user terminals.

2. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins according to claim 1, characterized in that, The acquisition of multi-source heterogeneous data includes: meteorological monitoring data, obtained from meteorological departments using radar, satellite, and ground station data; high-precision geographic information data, obtained from natural resources and housing and construction departments using digital elevation models, land use types, and building outlines; urban infrastructure data, obtained from water resources departments using drainage network data; real-time feedback data, obtained from traffic management departments using real-time traffic monitoring video streams and road condition information; and receiving and processing information on waterlogged areas reported by the public through a public crowdsourcing platform.

3. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins according to claim 2, characterized in that, The AI-driven model optimization module optimizes the simulation process in real time, including: using a deep reinforcement learning algorithm to dynamically calibrate the Manning roughness coefficient of the urban hydrological-hydraulic coupling model based on real-time feedback of water accumulation point information; and using a physical information neural network to construct a lightweight proxy model of the urban hydrological-hydraulic coupling model to accelerate the generation of urban flooding prediction results.

4. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins as described in claim 3, is characterized in that... The construction of a high-fidelity digital twin of the city based on digital twin technology includes: integrating a real-scene 3D model, a building information model, and an urban drainage network model to construct a comprehensive urban digital twin containing geospatial entities, physical process mechanisms, and behavioral rules; and dynamically extrapolating and visualizing the prediction results of urban flooding in the digital twin, which involves mapping the prediction results of urban flooding into the digital twin to simulate and visualize the spatial distribution, depth changes, and spread process of floodwater in real time.

5. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins according to claim 4, characterized in that, The process of dynamically assessing urban flooding risk based on dynamic simulation results and generating tiered early warning information includes: constructing a dynamic risk assessment model based on the simulated water depth, inundation range, and duration, combined with information on road network, population density, and distribution of critical infrastructure; and classifying risk levels and generating corresponding early warning level information based on the output of the dynamic risk assessment model.

6. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins as described in claim 5, is characterized in that... The emergency response plan based on tiered early warning information includes: automatically matching a pre-set emergency plan library according to the early warning level, predicted location of water accumulation and scope of impact, and generating an emergency response plan that includes traffic control, drainage scheduling and personnel evacuation; and linking the emergency response plan with real-time traffic information to optimize resource allocation and action routes.

7. The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins as described in claim 6, is characterized in that... The method for real-time forecasting and risk warning of extreme weather on urban roads based on artificial intelligence and digital twins also includes: constructing a road surface weather forecasting system. The road surface weather forecasting system is based on a deep neural network and takes real-time traffic monitoring video streams and road condition information, information on water accumulation points reported by the public, and real-time meteorological data as inputs to predict the road surface conditions of water accumulation, ice accumulation, or snow accumulation on urban roads in the future. The road surface condition prediction information is integrated with the urban waterlogging prediction results and used together as the basis for generating graded early warning information and formulating emergency response plans.

8. A real-time forecasting and risk warning system for extreme weather on urban roads based on artificial intelligence and digital twins, used to implement the real-time forecasting and risk warning method for extreme weather on urban roads based on artificial intelligence and digital twins as described in any one of claims 1-7, characterized in that, The real-time forecasting and risk warning system for extreme weather on urban roads based on artificial intelligence and digital twins includes: The data acquisition and processing module is used to acquire and fuse multi-source heterogeneous data. The AI-powered short-term forecasting module is used to generate high-precision short-term precipitation forecasts based on attention mechanisms and spatiotemporal deep learning networks. The urban flooding simulation and optimization module includes an urban hydrological and hydraulic coupling model and an AI-driven model optimization unit, which are used to generate and optimize the prediction results of urban flooding. The digital twin construction and simulation module is used to construct a high-fidelity digital twin of the city and to dynamically simulate and visualize the urban flooding process; The risk assessment and early warning generation module is used to perform dynamic risk assessments and generate tiered early warning information based on the simulation results. The emergency decision-making and information dissemination module is used to formulate emergency response plans and push early warning information and action guidelines to user terminals.