A marine pollution accident emergency disposal scheme generation method, device, equipment and medium

Abstract

This application provides a method, apparatus, equipment, and medium for generating emergency response plans for marine pollution accidents, including: collecting environmental monitoring data, risk source information, and emergency resource information for the target sea area before a pollution accident occurs; conducting dynamic risk assessments of various risk sources based on the above information to generate sea area risk level distribution information; collecting accident monitoring information to form pollution situation information after an accident is triggered; combining the pollution situation, risk source information, and environmental forecast data; and calling a pollutant diffusion prediction model to obtain the spatiotemporal distribution information of pollutants; calculating multi-dimensional damage risk indicators based on the spatiotemporal distribution of pollutants and the distribution of sensitive targets in the environmental monitoring data; and generating early warning level information; and finally, automatically generating multiple emergency response plans through an intelligent decision-making model by comprehensively considering the pollution situation, early warning level, emergency resources, and sea area risk level distribution. Using this method can improve the predictability, accuracy, and scientific rigor of marine pollution accident emergency response.

Description

Technical Field

[0001] This application relates to the field of marine environmental engineering, and more specifically, to a method, apparatus, equipment, and medium for generating emergency response plans for marine pollution accidents. Background Technology

[0002] With the continuous expansion of my country's maritime shipping, oil and gas extraction, coastal chemical and nuclear power industries, the risk of sudden marine pollution accidents such as oil spills, hazardous chemical leaks and radioactive nuclide pollution in nearshore waters has increased significantly. These accidents are characterized by their suddenness, rapid spread, wide impact, and lasting ecological damage. Scientific and efficient emergency response is the core link in reducing marine ecological losses and ensuring the safety of coastal areas, and it is also a key research direction in the field of marine environmental emergency management.

[0003] Currently, the industry generally adopts a special emergency response method for marine oil spills. This method focuses solely on marine oil spill accidents, collects basic accident information manually, displays the distribution of oil spills based on two-dimensional geographic information, uses a single oil spill diffusion model to simulate the drift trajectory of the oil film, and finally, emergency personnel develop an oil spill cleanup and disposal plan based on their experience.

[0004] This oil spill emergency response method has fundamental flaws. It can only be adapted to a single oil spill accident scenario and cannot be compatible with the diffusion characteristics and disposal needs of hazardous chemicals and radioactive nuclides. Furthermore, it relies entirely on human experience and judgment, lacks intelligent decision-making and full-process disposal capabilities, and cannot meet the comprehensive emergency response requirements for various types of marine pollution accidents in nearshore areas. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method, device, equipment and medium for generating emergency response plans for marine pollution accidents, which can improve the predictability, accuracy and scientific nature of emergency response to marine pollution accidents.

[0006] In a first aspect, embodiments of this application provide a method for generating an emergency response plan for a marine pollution incident, the method comprising: Before a pollution incident occurs, environmental monitoring data, risk source information, and emergency resource information for the target sea area are acquired. Based on the risk source information and the environmental monitoring data, dynamic risk assessments are conducted on various risk sources to obtain sea area risk level distribution information. After a pollution incident is triggered, the incident monitoring information is obtained to form pollution situation information. Based on the pollution situation information, the risk source information and environmental forecast data, the pollutant diffusion prediction model is called to predict the spatiotemporal distribution information of pollutants. Based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, a multi-dimensional damage risk index is calculated, and an early warning level information is generated based on the multi-dimensional damage risk index. Based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model.

[0007] Optionally, the step of dynamically assessing various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information includes: The risk source type is determined based on the aforementioned risk source information; When the risk source type is a fixed facility, the maximum credible accidental leakage amount of the fixed facility is determined based on the maximum storage capacity and containment facility capacity of the fixed facility; When the risk source type is a mobile carrier, the leakage probability of the mobile carrier is determined based on the dynamic data and historical accident probability of the mobile carrier. Based on the maximum credible accident leakage amount or the leakage probability, and combined with the hydrological and meteorological conditions in the environmental monitoring data, the potential impact range of the accident is simulated, and the risk level distribution information of the sea area is generated.

[0008] Optionally, the step of using a pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information, and environmental forecast data includes: Based on the pollution situation information, the type of leaked substance, the amount leaked, and the location of the leak are determined; Based on the risk source information, obtain the physicochemical properties of the leaked substance; Based on the aforementioned environmental forecast data, ocean current, wind speed and direction, and tidal data are obtained. The type of leaked substance, the amount of leak, the location of the leak, the physicochemical properties, the ocean current, the wind speed and direction, and the tidal data are input into the pollutant drift and diffusion numerical model to simulate the spatiotemporal distribution information of the pollutants.

[0009] Optionally, the calculation of multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data includes: Based on the spatiotemporal distribution information of the pollutants, extract the pollutant concentration or thickness data within each computational grid; Based on the sensitive target distribution information, the sensitive target types and sensitivity coefficients within each computational grid are determined; Based on the pollutant concentration or thickness data, the sensitive target type and sensitivity coefficient, multiple preset dimensions of sub-item damage risk indicators are calculated respectively; The multi-dimensional damage risk index is obtained by weighting and synthesizing the various sub-items of damage risk index.

[0010] Optionally, generating early warning level information based on the multi-dimensional damage risk indicators includes: The multi-dimensional damage risk indicators are compared with preset classification thresholds to determine the warning level; Identify affected sensitive targets based on the spatiotemporal distribution information of the pollutants; The warning level information is generated based on the warning level and the affected sensitive targets.

[0011] Optionally, based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model, including: Based on the pollution situation information, the early warning level information, and the marine risk level distribution information, the priority of response in each region is determined; With the optimization objectives of minimizing ecological loss, minimizing disposal time, and minimizing economic cost, and with the resource reserves and disposal capacity in the emergency resource information as constraints, a multi-objective optimization algorithm is used to solve the problem based on the disposal priority, generating multiple emergency disposal plans. Each emergency disposal plan includes an emergency resource scheduling plan, a ship navigation path planning plan, and a disposal strategy.

[0012] Optionally, the method further includes: Based on real-time updated accident monitoring information, the steps of generating pollution situation information, predicting the spatiotemporal distribution information of pollutants, calculating multi-dimensional damage risk indicators, generating early warning level information, and generating multiple emergency response plans are re-executed to achieve dynamic updating and closed-loop optimization of emergency response plans. Based on the real-time updated accident monitoring information, it is determined whether the pollution has been effectively controlled. Once it is determined that the pollution has been effectively controlled, post-accident environmental monitoring data is obtained. Based on the environmental monitoring data after the accident, the ecological damage caused by the accident was quantitatively assessed from multiple dimensions, including seawater quality, sediment quality, and biological resources, and the ecological damage assessment results were obtained. Based on the ecological damage assessment results, ecological restoration plan recommendations are generated.

[0013] Secondly, embodiments of this application provide a device for generating emergency response plans for marine pollution incidents, the device comprising: The marine risk level distribution information determination module is used to acquire environmental monitoring data, risk source information and emergency resource information of the target marine area when no pollution accident occurs, and to conduct dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information. The spatiotemporal distribution information acquisition module is used to acquire accident monitoring information to form pollution situation information after a pollution accident is triggered, and to call the pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information and environmental forecast data. The early warning level information acquisition module is used to calculate multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, and to generate early warning level information based on the multi-dimensional damage risk indicators; The emergency response plan generation module is used to generate multiple emergency response plans based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, through an intelligent decision-making model.

[0014] Optionally, the step of dynamically assessing various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information includes: The risk source type is determined based on the aforementioned risk source information; When the risk source type is a fixed facility, the maximum credible accidental leakage amount of the fixed facility is determined based on the maximum storage capacity and containment facility capacity of the fixed facility; When the risk source type is a mobile carrier, the leakage probability of the mobile carrier is determined based on the dynamic data and historical accident probability of the mobile carrier. Based on the maximum credible accident leakage amount or the leakage probability, and combined with the hydrological and meteorological conditions in the environmental monitoring data, the potential impact range of the accident is simulated, and the risk level distribution information of the sea area is generated.

[0015] Optionally, the step of using a pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information, and environmental forecast data includes: Based on the pollution situation information, the type of leaked substance, the amount leaked, and the location of the leak are determined; Based on the risk source information, obtain the physicochemical properties of the leaked substance; Based on the aforementioned environmental forecast data, ocean current, wind speed and direction, and tidal data are obtained. The type of leaked substance, the amount of leak, the location of the leak, the physicochemical properties, the ocean current, the wind speed and direction, and the tidal data are input into the pollutant drift and diffusion numerical model to simulate the spatiotemporal distribution information of the pollutants.

[0016] Optionally, the calculation of multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data includes: Based on the spatiotemporal distribution information of the pollutants, extract the pollutant concentration or thickness data within each computational grid; Based on the sensitive target distribution information, the sensitive target types and sensitivity coefficients within each computational grid are determined; Based on the pollutant concentration or thickness data, the sensitive target type and sensitivity coefficient, multiple preset dimensions of sub-item damage risk indicators are calculated respectively; The multi-dimensional damage risk index is obtained by weighting and synthesizing the various sub-items of damage risk index.

[0017] Optionally, generating early warning level information based on the multi-dimensional damage risk indicators includes: The multi-dimensional damage risk indicators are compared with preset classification thresholds to determine the warning level; Identify affected sensitive targets based on the spatiotemporal distribution information of the pollutants; The warning level information is generated based on the warning level and the affected sensitive targets.

[0018] Optionally, based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model, including: Based on the pollution situation information, the early warning level information, and the marine risk level distribution information, the priority of response in each region is determined; With the optimization objectives of minimizing ecological loss, minimizing disposal time, and minimizing economic cost, and with the resource reserves and disposal capacity in the emergency resource information as constraints, a multi-objective optimization algorithm is used to solve the problem based on the disposal priority, generating multiple emergency disposal plans. Each emergency disposal plan includes an emergency resource scheduling plan, a ship navigation path planning plan, and a disposal strategy.

[0019] Optionally, the device further includes an ecological restoration scheme suggestion generation module, used for: Based on real-time updated accident monitoring information, the steps of generating pollution situation information, predicting the spatiotemporal distribution information of pollutants, calculating multi-dimensional damage risk indicators, generating early warning level information, and generating multiple emergency response plans are re-executed to achieve dynamic updating and closed-loop optimization of emergency response plans. Based on the real-time updated accident monitoring information, it is determined whether the pollution has been effectively controlled. Once it is determined that the pollution has been effectively controlled, post-accident environmental monitoring data is obtained. Based on the environmental monitoring data after the accident, the ecological damage caused by the accident was quantitatively assessed from multiple dimensions, including seawater quality, sediment quality, and biological resources, and the ecological damage assessment results were obtained. Based on the ecological damage assessment results, ecological restoration plan recommendations are generated.

[0020] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the marine pollution accident emergency response plan generation method described in any of the optional embodiments of the first aspect above are performed.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the marine pollution accident emergency response plan generation method described in any of the optional embodiments of the first aspect.

[0022] The technical solution provided in this application includes, but is not limited to, the following beneficial effects: Before a pollution incident occurs, environmental monitoring data, risk source information, and emergency resource information for the target sea area can be obtained. Based on the risk source information and the environmental monitoring data, dynamic risk assessments of various risk sources can be conducted to obtain information on the distribution of sea area risk levels. This allows for the quantitative assessment of sea area pollution risks in advance, accurately identifying high-risk areas and risk sources, providing direct data support for pre-emptive risk prevention and emergency resource pre-positioning, and improving the pertinence and effectiveness of pre-incident prevention and control.

[0023] After a pollution incident is triggered, the pollution situation information is obtained by acquiring the incident monitoring information. Based on the pollution situation information, the risk source information and environmental forecast data, the pollutant diffusion prediction model is called to predict the spatiotemporal distribution information of pollutants. This allows for a rapid understanding of the real-time pollution status and future diffusion patterns of the incident, enabling accurate prediction of pollution development trends. This provides real-time and accurate situational information for emergency response and avoids decision-making lagging behind the pollution diffusion process.

[0024] Based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, multi-dimensional damage risk indicators are calculated. Based on the multi-dimensional damage risk indicators, early warning level information is generated, which can objectively quantify the degree of multi-dimensional damage caused by pollution, realize graded and accurate risk early warning, provide scientific standards for emergency response level determination, and improve the practicality and guidance of early warning information.

[0025] Based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model. This enables the intelligent and diversified generation of response plans, ensuring that the plans are tailored to the actual conditions and needs of the accident, providing multiple options for emergency command, and improving the scientific and rational nature of response decisions.

[0026] This invention constructs a highly efficient emergency response plan generation mechanism by implementing risk assessment, situation prediction, damage warning, and plan generation in stages. It relies on data-driven approaches to achieve scientific response throughout the process, significantly improving the predictability, accuracy, and scientific rigor of marine pollution accident emergency response, and effectively meeting the core needs of marine pollution accident emergency response.

[0027] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart of a method for generating an emergency response plan for a marine pollution accident, as provided in Embodiment 1 of this application, is shown. Figure 2 A flowchart of a method for determining the distribution information of marine risk levels provided in Embodiment 1 of this application is shown; Figure 3 A flowchart of a spatiotemporal distribution information prediction method provided in Embodiment 1 of this application is shown; Figure 4 A flowchart of a multi-dimensional damage risk index calculation method provided in Embodiment 1 of this application is shown; Figure 5 A flowchart of a method for generating early warning level information provided in Embodiment 1 of this application is shown; Figure 6 A flowchart of an emergency response plan generation method provided in Embodiment 1 of this application is shown; Figure 7 The flowchart of the emergency response closed-loop optimization and ecological restoration method provided in Embodiment 1 of this application is shown; Figure 8 This paper shows a schematic diagram of the structure of a marine pollution accident emergency response device provided in Embodiment 2 of this application; Figure 9 A schematic diagram of the structure of a computer device provided in Embodiment 3 of this application is shown. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0031] Example 1 This method relies on a five-layer architecture—data resource layer, microservice support platform, business support layer, visualization layer, and application layer—to implement a comprehensive prevention and intelligent decision-making platform for marine emergency pollution incidents. The platform's underlying architecture is built using Spring Cloud (a microservice development framework). Services are connected and managed through an API gateway, which also handles core functions such as load balancing, authentication, and permission verification. The platform is equipped with a dedicated security system and standardized specifications to resist security risks such as data tampering and unauthorized access, while adhering to national industry standards for marine environmental monitoring and emergency response to ensure compliance. The platform hardware employs a combination of server clusters and distributed computing nodes. The master node handles business logic and data scheduling, while the computing nodes handle numerical model solving and 3D simulation rendering, supporting parallel computing needs across multiple sea areas and incidents.

[0032] To facilitate understanding of this application, the following is combined with... Figure 1 The flowchart illustrating the method for generating an emergency response plan for a marine pollution accident provided in Embodiment 1 of this application will be described in detail for Embodiment 1 of this application.

[0033] See Figure 1 As shown, Figure 1 A flowchart of a method for generating an emergency response plan for a marine pollution accident, as provided in Embodiment 1 of this application, is shown, wherein the method includes steps S101 to S104: S101: When no pollution incident occurs, acquire environmental monitoring data, risk source information and emergency resource information of the target sea area, and conduct dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data to obtain the sea area risk level distribution information.

[0034] Specifically, environmental monitoring data is acquired by the platform's data resource layer through multi-channel parallel acquisition technology, covering four main data sources: shore-based monitoring stations, shipborne buoy sensors, satellite remote sensing equipment, and maritime department data interfaces.

[0035] Each type of data source is equipped with an independent data transmission link. The transmission process uses an encryption protocol to ensure data security. The data transmission frequency of different data sources can be flexibly configured according to business needs. Regular monitoring data is updated every 15 minutes.

[0036] After the raw data is collected, it will enter a standardized preprocessing process. The preprocessing module will perform four operations in sequence: missing value filling, outlier removal, format normalization, and spatiotemporal coordinate matching, so that multi-source heterogeneous data can have a unified standard for use.

[0037] The preprocessed data will be stored in a three-tier storage system according to data type: static data will be stored in a relational database to ensure query stability, real-time data will be stored in a cache database to improve read speed, and unstructured data will be stored in object storage to save storage space.

[0038] Risk source information is digitally entered using spatial vector modeling technology. Fixed risk sources generate area vector data to mark the coverage area, while mobile risk sources generate point vector data to record the real-time location. The data fields fully contain the full-dimensional attribute information of the risk sources.

[0039] Emergency resource information will establish a full lifecycle management ledger, recording the entire process from resource entry, maintenance, scheduling to disposal. The location information of all resources will be mapped onto a GIS map, facilitating rapid location and retrieval during emergency command.

[0040] For stationary storage tanks, the platform uses the formula for the maximum credible accidental leakage of storage tanks to calculate the risk scale. The formula is as follows:

[0041] in: The maximum credible accidental leakage of the storage tank is expressed in cubic meters (m³). For the first in the sea area The maximum storage capacity of each tank, in cubic meters (m³). For the first in the sea area Available capacity of each protective facility, accident pool, and ditch, in cubic meters (m³). The total number of storage tanks within the target sea area; The total number of protective facilities within the target sea area.

[0042] For fixed risk sources such as nuclear facilities, the platform uses a formula for calculating the scale of radioactive leakage from a radionuclide accident release. The formula is as follows:

[0043] in: For the first type The scale of radionuclides released into the environment, measured in becquerels (Bq). For the first The amount of a radionuclide in the reactor core, expressed in becquerels (Bq). For the first The percentage of radionuclides released into the containment vessel, expressed as a percentage (%). For the first The radioactive nuclide underwent the first The degree of weakening of the containment-like weakening mechanism, expressed as a percentage (%). For the first The percentage of radionuclides leaked into the environment, expressed as a percentage (%). The total number of containment weakening mechanisms.

[0044] For mobile risk sources such as ships, the platform combines AIS dynamic data, historical accident probabilities, and meteorological and hydrological data to complete dynamic leakage probability calculations.

[0045] The system overlays the risk calculation results with hydrological and meteorological data to generate a risk level distribution map through 100-meter precision grid rendering. Different colors correspond to different risk levels, intuitively displaying the risk distribution status of the entire sea area.

[0046] S102: After a pollution accident is triggered, accident monitoring information is obtained to form pollution situation information. Based on the pollution situation information, the risk source information and environmental forecast data, a pollutant diffusion prediction model is called to predict the spatiotemporal distribution information of pollutants.

[0047] Specifically, accident triggering includes two modes: manual active triggering and automatic system triggering. Manual triggering is suitable for scenarios where accidents have been manually confirmed, while automatic triggering is achieved by identifying data exceeding the standard, enabling immediate response to sudden accidents.

[0048] Accident monitoring information is uniformly accessed by a multi-source data fusion module. Five types of data, including satellite remote sensing, airborne SAR, shipborne radar, shore-based video, and on-site sampling, will first complete time synchronization to ensure that the timestamps of all data are completely consistent.

[0049] The synchronized data will undergo spatial registration to convert data from different coordinate systems and resolutions into the WGS84 geographic coordinate system, eliminating spatial location bias and ensuring accurate matching of pollution monitoring results from multiple sources.

[0050] The pollution status information is dynamically generated by a real-time statistical analysis engine. The engine continuously calculates the core indicators of pollutants, and the indicator data is refreshed every 30 seconds to reflect the development and changes of pollution in real time.

[0051] Environmental forecast data is obtained from meteorological and marine departments via dedicated line interfaces. The data is processed by the Kriging interpolation algorithm to transform discrete station data into continuous areal data covering the entire region, providing complete driving parameters for the diffusion model.

[0052] The pollutant diffusion model adopts a hybrid numerical solution method, combining the advantages of the finite difference method and the particle tracking method. This method can ensure both computational accuracy and improve computational speed. The model parameters can be flexibly configured through the front-end interface to adapt to different accident scenarios.

[0053] After inputting the type of leaked substance, the amount of leak, the location of the leak, the physicochemical parameters, and the hydrological and meteorological data, the model can output the spatiotemporal distribution data of pollutants for the next 1 hour, 24 hours, 48 ​​hours, and 72 hours. The data includes all dimensions of information such as drift trajectory, concentration distribution, and diffusion range.

[0054] The model calculation results are simultaneously pushed to the 2D WebGIS and 3D UE5 digital twin scene, and the pollution diffusion process is dynamically displayed through timeline animation, supporting the comparison and display of simulation results in multiple scenarios.

[0055] S103: Calculate multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, and generate early warning level information based on the multi-dimensional damage risk indicators.

[0056] Specifically, the distribution information of sensitive targets is retrieved from the platform's ecologically sensitive area vector database, which contains data on all types of sensitive targets, including aquaculture areas, ecological protection areas, bathing beaches, beaches, and protected species habitats.

[0057] The system uses spatial topology overlay analysis technology to match the vector data of sensitive targets with the pollution calculation grid one by one, accurately identify the type of sensitive targets in each grid, and automatically assign the corresponding sensitivity coefficient.

[0058] The multi-dimensional damage risk index calculation adopts a gridded independent accounting mode, dividing the target sea area into a uniform grid of 100m×100m, and calculating the risk index for each grid separately to ensure the precision of risk assessment.

[0059] The system first calculates the comprehensive pollution damage risk index, the core formula of which is:

[0060] in: A multidimensional comprehensive pollution damage risk index; For the first Weighting coefficients for marine ecological environment elements; For the first Pollution risk index of marine ecological environment elements; =1 to 5 correspond to the five elements of shoreline, sea surface, water body, bottom sediment, organisms and ecology, respectively.

[0061] Fixed weighting coefficients assigned to beach elements =0.35, biological and ecological elements =0.25, water body elements =0.15, sea surface elements =0.15, substrate elements =0.10.

[0062] The system calculates the beach pollution risk index using two sets of formulas to perform grid value and comprehensive value calculations. The formulas are as follows:

[0063]

[0064] in: For the beach Pollution risk index of each computational grid; The comprehensive pollution risk index for the entire beach area; For the beach Oil film thickness within each grid, in millimeters (mm); For the beach Oil spill viscosity within each grid, in centistokes (cSt). For the beach Sensitivity coefficient of beach type within each grid; For the beach Sensitivity coefficient of marine functional zones within each grid; For the beach Each grid area is expressed in square kilometers (km²). Calculate the total number of grids for the beach.

[0065] The system calculates the sea surface pollution risk index using two sets of formulas to perform grid value and comprehensive value calculations. The formulas are as follows:

[0066]

[0067] in: For the sea surface Pollution risk index of each computational grid; A comprehensive pollution risk index for the entire sea surface area; For the sea surface Oil film thickness within each grid, in millimeters (mm); For the sea surface Oil spill viscosity within each grid, in centistokes (cSt). For the sea surface Sensitivity coefficient of marine functional zones within each grid; For the sea surface Sensitive resource factors within each grid; For the sea surface Each grid area is expressed in square kilometers (km²). Calculate the total number of grids for the sea surface.

[0068] The system calculates the water pollution risk index using two sets of formulas to perform grid value and comprehensive value calculations. The formulas are as follows:

[0069]

[0070] in: For water bodies Pollution risk index of each computational grid; The comprehensive pollution risk index for the entire water body; For water bodies Pollutant concentration within each grid, in milligrams per liter (mg / L). The limit value for seawater quality standards for the corresponding functional zones is expressed in milligrams per liter (mg / L). The importance coefficient of the water body functional zone; For water bodies Each grid area is expressed in square kilometers (km²). Calculate the total number of grids for the water body.

[0071] The system calculates the sediment pollution risk index using two sets of formulas to perform grid value and comprehensive value calculations. The formulas are as follows:

[0072]

[0073] in: For the first substrate Pollution risk index of each computational grid; The overall pollution risk index for the entire sedimentary basin; For the first substrate Pollutant concentration within each grid, unit 10 -6 (dry weight); The unit is 10, which represents the sediment quality standard limit for the corresponding functional area. -6 ; For the first substrate Individual grid sediment type coefficients; For the first substrate Organic matter content correction factor for each grid; For the first substrate Sensitivity coefficient of benthic organisms in each grid; For the first substrate Each grid area is expressed in square kilometers (km²). The total number of grids is calculated for the substrate.

[0074] The system calculates the biological and ecological pollution risk index using four sets of formulas to complete the full-dimensional accounting. The formulas are as follows:

[0075]

[0076]

[0077]

[0078] in: For the first biological Within the first grid Pollution risk value for species; It is a comprehensive pollution risk index covering the entire biological and ecological domain; For the actual exposure time of the biological number Pollutant concentration within each grid, in milligrams per liter (mg / L). For the first 96h-LC50 damage threshold of the species, in milligrams per liter (mg / L). This is a function of the cumulative effect of biological exposure over time. This refers to the actual exposure time of the organism. For reference exposure time (fixed at 96 hours); The maximum effective exposure time (fixed at 720 hours); For the first Species resource density coefficient; For the first Species sensitivity coefficient; For the first biological Each grid area is expressed in square kilometers (km²). This represents the total number of biological computing grids. To protect the total number of species; This is the original sum of biological risk values; This is a biological risk half-saturation parameter.

[0079] The system compares the comprehensive pollution damage risk index with four fixed thresholds to automatically determine the four warning levels: blue, yellow, orange, and red. The threshold ranges are unique, fixed, and non-overlapping.

[0080] The system identifies sensitive targets affected by pollution through spatial analysis, calculates the arrival time of pollutants by combining diffusion rates, and finally generates complete early warning information including warning level, scope of impact, and protection recommendations.

[0081] S104: Based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model.

[0082] The intelligent decision-making model adopts the NSGA-Ⅲ multi-objective non-dominated genetic algorithm. The algorithm is deployed on distributed computing nodes and improves the solution speed through parallel computing, which can generate multiple optimization schemes in a short time.

[0083] The model has three optimization objectives: minimizing ecological loss, shortening disposal time, and minimizing economic cost. Each objective has an independent quantitative function, and the digital evaluation of the objective is achieved through function calculation.

[0084] The objective function for minimizing ecological loss is:

[0085] in: The total value of ecological losses; For use as an emergency response area; For disposal area The ecological loss value at the time of disposal; This represents the total duration of the emergency response.

[0086] The objective function for minimizing processing time is:

[0087] in: This represents the maximum processing time for a single region. For disposal area Emergency response time; This is a designated area for emergency response.

[0088] The objective function for minimizing economic costs is:

[0089] in: The total economic cost of emergency response; For emergency vessel operating costs; Costs of emergency vessel navigation; Costs associated with pollutant recovery; Cost of emergency supplies; Labor costs for emergency personnel; Costs related to the wear and tear of emergency equipment.

[0090] The comprehensive weighted objective function is:

[0091] in: Optimize target values ​​for emergency response; This is the ecological loss weighting coefficient; This is a weighting coefficient for processing time; This is the economic cost weighting coefficient.

[0092] The core formula and constraints for ship dynamic path planning are as follows:

[0093]

[0094] in: For emergency vessels to reach the The moment of a contaminated mass; For the first The length of the contamination zone is controlled by one pollution cluster. To improve the efficiency of oil boom deployment; For the first Critical response time of each contamination cluster; This represents the total number of contaminated clumps.

[0095] The model will set multiple constraints, including upper limits for emergency resource reserves, equipment performance parameters, restricted navigation areas for ships, and operation time windows. All constraints are derived from the normative requirements of actual emergency response.

[0096] The model will eventually generate three differentiated solutions: ecological priority, efficiency priority, and comprehensive optimal solution. Each solution includes complete resource scheduling, path planning, and disposal strategies to meet different emergency command needs.

[0097] Once the solution is generated, it will be pushed to the UE5 digital twin scenario for full-process simulation. The simulation process can intuitively display the handling effect, and supports manual adjustment of parameters and recalculation to ensure the feasibility and optimality of the solution.

[0098] This implementation plan relies on a five-layer microservice architecture and distributed computing to build a full-process emergency response system covering pre-event, during-event, and post-event stages. Through four core technologies—multi-source data fusion, gridded spatial computing, NSGA-Ⅲ multi-objective optimization, and digital twin simulation—it achieves unified treatment of three types of pollutants, solving the problems of traditional emergency functions being singular, decision-making being experience-based, and lacking visualization, and significantly improving the scientific nature, timeliness, and operability of emergency response.

[0099] In an optional implementation, see Figure 2 As shown, Figure 2 The flowchart illustrates a method for determining marine risk level distribution information according to Embodiment 1 of this application. The method involves dynamically assessing various risk sources based on the risk source information and environmental monitoring data to obtain marine risk level distribution information, and includes steps S201-S204: S201: Determine the risk source type based on the risk source information.

[0100] Specifically, after the system loads the risk source data, it will automatically read the facility type field in the data attributes, complete the accurate classification of the risk source through the field identifier, and store the classification result in a temporary calculation variable.

[0101] Fixed infrastructure risk sources include three categories: coastal storage tanks, oil and gas platforms, and nuclear power facilities. Mobile carrier risk sources are mainly maritime transport vessels. The classification rules are fully consistent with the actual classification standards for marine risk sources.

[0102] Accurate risk source classification is the foundation for subsequent differentiated assessment, which can avoid calculation errors caused by using the same assessment model for different types of risk sources and improve the accuracy of risk assessment.

[0103] S202: When the risk source type is a fixed facility, determine the maximum credible accidental leakage amount of the fixed facility based on the maximum storage capacity and containment facility capacity of the fixed facility.

[0104] Specifically, basic data of fixed facilities are collected through a combination of IoT terminals and manual input, and the maximum storage capacity of storage tanks is obtained from real-time data of liquid level gauges and design drawings, with data accuracy reaching the cubic meter level.

[0105] The capacity of the retaining facilities includes the available volume of the emergency pool, seepage prevention ditch, and cofferdam. The data are all from the as-built drawings of the facilities and on-site measurement data to ensure the authenticity and reliability of the data.

[0106] The system automatically calls the formula for calculating the maximum credible accidental leakage of the storage tank, substitutes the collected parameters into the formula to complete the calculation, and the calculation process is completed automatically without the need for manual parameter input, thus reducing human error.

[0107] S203: When the risk source type is a mobile carrier, the leakage probability of the mobile carrier is determined based on the dynamic data and historical accident probability of the mobile carrier.

[0108] Specifically, the dynamic data of the mobile carrier is acquired in real time through the AIS parsing engine. The engine continuously extracts core dynamic parameters such as the ship's speed, heading, cargo load, and route deviation, with the parameters being updated every 10 seconds.

[0109] Historical accident probabilities are retrieved from the platform's historical accident case database, which contains leakage accident data of similar ships at home and abroad over the past ten years. Standardized baseline probability values ​​are obtained through statistical analysis.

[0110] The system combines ship dynamic data with historical accident probabilities to calculate the probability of leakage.

[0111] S204: Based on the maximum credible accident leakage amount or leakage probability, and combined with the hydrological and meteorological conditions in the environmental monitoring data, simulate the possible impact range of the accident and generate marine risk level distribution information.

[0112] Specifically, hydrological and meteorological data will first undergo interpolation processing to transform it into continuous driving data covering the entire region, including core parameters that affect pollution diffusion such as ocean currents, wind speed, wind direction, tides, and topography.

[0113] The system simulates the impact range through a risk diffusion numerical model. Fixed risk sources simulate diffusion trajectories based on leakage amount, while mobile risk sources simulate potential impact areas based on leakage probability and flight path, achieving simulation accuracy at the hundred-meter level.

[0114] The simulation results will be rendered into a risk level distribution map using a four-level color mapping technology, with red representing extremely high risk, orange representing high risk, yellow representing medium risk, and blue representing low risk. The visualization effect is intuitive and clear.

[0115] This implementation plan employs classification assessment, quantitative calculation, and spatial visualization technologies to achieve accurate assessment of fixed / mobile risk sources. Formulaic calculations replace empirical judgments, and combined with hydrological and meteorological simulations of risk ranges, it generates high-precision risk distribution maps, identifies high-risk areas in advance, provides data support for pre-emptive prevention and control, and reduces the accident rate.

[0116] In an optional implementation, see Figure 3 As shown, Figure 3 The flowchart of a spatiotemporal distribution information prediction method provided in Embodiment 1 of this application is shown. The step of predicting the spatiotemporal distribution information of pollutants based on pollution status information, risk source information, and environmental forecast data by calling a pollutant diffusion prediction model includes steps S301-S304: S301: Determine the type, amount, and location of the leaked substance based on pollution situation information.

[0117] Specifically, the system extracts core parameters of the pollution situation through the accident information analysis engine. The leaked substances are automatically classified into three categories: oil spill, hazardous chemicals, and radioactive nuclides. The classification results directly determine the type of diffusion model to be called subsequently.

[0118] The leakage amount is determined by verifying the on-site monitoring data with the estimated data. The system will automatically remove abnormal data and use the weighted average as the final leakage amount parameter to ensure the accuracy of the parameter.

[0119] The leak location was precisely pinpointed using GPS coordinate calibration technology, with a coordinate accuracy of 0.01 degrees per second. This allowed for accurate marking of the specific sea area where the accident occurred, providing a precise starting point for diffusion simulation.

[0120] S302: Obtain the physicochemical properties of the leaked substance based on risk source information.

[0121] Specifically, the system retrieves parameters through the standard interface of the pollution feature database, which contains comprehensive physicochemical parameters of common marine pollutants. All parameters are derived from authoritative test reports and national industry standards.

[0122] For oil spill pollutants, parameters such as viscosity, density, and evaporation rate are retrieved; for hazardous chemical pollutants, parameters such as solubility, toxicity, and diffusion coefficient are retrieved; and for radionuclide pollutants, parameters such as half-life and decay coefficient are retrieved.

[0123] The parameter retrieval process is fully automated, eliminating the need for manual querying and input, significantly improving the efficiency of model calculation, and avoiding errors caused by manual parameter input.

[0124] S303: Obtain ocean current, wind speed and direction, and tidal data based on environmental forecast data.

[0125] Specifically, the system establishes a stable data transmission channel with the National Meteorological Center and the National Marine Environmental Forecasting Center through dedicated line data docking technology, with a data transmission delay of no more than 1 minute, ensuring the real-time nature of the forecast data.

[0126] The acquired raw data will undergo outlier filtering. The system automatically identifies and removes obviously erroneous data to ensure that the parameters of the input model are stable and reliable.

[0127] After data processing, it will be converted into a format that the model can recognize, organized by time series, and provide the model with high-precision driving parameters hourly.

[0128] S304: Input the type of leaked substance, leakage amount, leakage location, physicochemical properties, ocean current, wind speed and direction, and tidal data into the pollutant drift and diffusion numerical model to simulate the spatiotemporal distribution information of the pollutants.

[0129] Specifically, after loading all parameters, the model adopts a multi-core CPU parallel computing mode, with a default configuration of 100,000 particles for tracking calculation. The number of particles can be flexibly adjusted according to the calculation accuracy requirements.

[0130] The model outputs spatiotemporal sequence data, including pollutant drift paths, concentration / activity distribution, diffusion boundary coordinates, arrival time of sensitive targets, and other full-dimensional results, covering the pollution development trend for the next 72 hours.

[0131] The calculation results will be simultaneously pushed to the 2D WebGIS and 3D UE5 digital twin scene, supporting timeline drag-and-drop playback, layer hiding and display, multi-scenario comparison and analysis, and the visualization effect meets the needs of emergency command.

[0132] This implementation plan is based on a multi-source high-precision data-driven diffusion model. It adopts a hybrid numerical solution method to improve accuracy and parallel computing to shorten the time consumption, thereby achieving accurate simulation of the spatiotemporal distribution of pollutants. It provides intuitive prediction for emergency command and solves the problems of poor adaptability, low accuracy and insufficient timeliness of traditional simulations.

[0133] In an optional implementation, see Figure 4 As shown, Figure 4 The flowchart of a multi-dimensional damage risk index calculation method provided in Embodiment 1 of this application is shown. The calculation of the multi-dimensional damage risk index based on the spatiotemporal distribution information of pollutants and the distribution information of sensitive targets in environmental monitoring data includes steps S401-S404: S401: Based on the spatiotemporal distribution information of pollutants, extract pollutant concentration or thickness data within each computational grid.

[0134] Specifically, the platform divides the target sea area into uniform calculation grids with a precision of 100m×100m, and assigns a unique ID number to each grid to facilitate data statistics and management.

[0135] The system extracts data by traversing the grid one by one. The engine accurately extracts the oil film thickness, pollutant concentration, and radionuclide radioactivity data in each grid, ensuring that the data extraction is complete and without any omissions or biases.

[0136] The extracted data will be stored in the grid attribute database and associated with the grid ID and spatial coordinates to provide standardized basic data for subsequent risk index calculation.

[0137] S402: Determine the type and sensitivity coefficient of sensitive targets within each computational grid based on the distribution information of sensitive targets.

[0138] Specifically, the system uses spatial overlay matching technology to precisely align the vector data of sensitive targets with the computational grid, with an alignment error of no more than 10 meters, ensuring the accuracy of sensitive target identification.

[0139] The system automatically identifies the types of sensitive targets within the grid, including rocky reefs, beaches, aquaculture areas, ecological protection areas, and bathing beaches. The identification results are directly associated with the corresponding sensitivity coefficient assignment rules.

[0140] The sensitivity coefficient is uniquely assigned based on the protection level and ecological importance, with a value range of 1-10. The higher the protection level and the greater the ecological value, the higher the sensitivity coefficient is assigned. The assignment rules have been verified by experts and are objective and scientific.

[0141] S403: Based on pollutant concentration or thickness data, sensitive target type and sensitivity coefficient, calculate the number of sub-item damage risk indicators for multiple preset dimensions.

[0142] Specifically, the preset dimensions are five major dimensions: shoreline, sea surface, water body, seabed, and organisms and ecology. Each dimension is equipped with an independent calculation model and formula, and the model parameters are unique and not reused.

[0143] The system solves the problem grid by grid through a multi-dimensional independent computing engine. The calculation process is completed on distributed nodes, with each node responsible for the calculation of a portion of the grid, which greatly improves the computational efficiency.

[0144] After the sub-risk indices are calculated, the results will be stored in a grid and a heatmap of risk distribution for each dimension will be generated to visually display the risk distribution for each dimension.

[0145] S404: Weighted synthesis of various sub-item damage risk indicators to obtain multi-dimensional damage risk indicators.

[0146] Specifically, the system calls the comprehensive pollution damage risk index formula through a weighted summation algorithm, completes the weighted synthesis with fixed weights, and the weight assignment is verified by the analytic hierarchy process to scientifically reflect the risk contribution of each dimension.

[0147] The weighted synthesis process is fully automated and requires no manual intervention. The synthesis result is a comprehensive multi-dimensional damage risk index, which is the core basis for determining the warning level.

[0148] The comprehensive risk index will be linked with grid spatial data to generate a comprehensive risk distribution heat map, providing core data support for subsequent early warning generation and scheme formulation.

[0149] This implementation plan employs a 100-meter-level grid-based fine calculation to achieve independent accounting and weighted synthesis of risks across five dimensions. Formulaic calculations replace subjective judgments, accurately reflecting the degree of ecological damage and providing objective quantitative basis for early warning and decision-making.

[0150] In an optional implementation, see Figure 5 As shown, Figure 5The flowchart of a method for generating early warning level information according to Embodiment 1 of this application is shown, wherein the step of generating early warning level information based on multi-dimensional damage risk indicators includes steps S501 to S503: S501: Compare multi-dimensional damage risk indicators with preset classification thresholds to determine the warning level.

[0151] Specifically, the system uses an automatic threshold matching engine to perform the comparison. The preset thresholds are fixed standards of the platform: 0~30 is Level IV (blue), 30~60 is Level III (yellow), 60~90 is Level II (orange), and ≥90 is Level I (red).

[0152] The matching process requires no manual operation. The system executes the process immediately after the comprehensive risk index is calculated, and the warning level determination time is no more than 1 second, ensuring the timeliness of the warning.

[0153] The warning level determination results will be synchronized to the front-end interface, and risk areas will be marked with different colors to intuitively display the spatial distribution of the warning level.

[0154] S502: Identify affected sensitive targets based on the spatiotemporal distribution information of pollutants.

[0155] Specifically, the system uses spatial topology analysis technology to overlay pollution diffusion range and sensitive target data, automatically identifying sensitive targets that pollutants are about to affect. The identification results include the target name, location, and type.

[0156] The system combines pollutant diffusion rate and distance to calculate the precise time it takes for pollutants to reach sensitive targets, with a time accuracy down to the minute level, providing a precise time reference for protective measures.

[0157] Affected sensitive targets will be highlighted on the map, and a list of sensitive targets will be generated to identify the target objects that need to be protected.

[0158] S503: Generate warning level information based on the warning level and the affected sensitive targets.

[0159] Specifically, the system generates early warning information through a standardized template engine. The template includes five core components: early warning level, affected area, threat target, protection recommendations, and emergency response level recommendations.

[0160] The warning information supports multiple export formats, including Word, PDF, and Excel, and also supports multiple push methods such as in-site notifications, SMS, and email to adapt to different emergency notification needs.

[0161] Once generated, the early warning information can be reviewed and confirmed by emergency command personnel. After the review is approved, it will be officially released to ensure the rigor and authority of the early warning information.

[0162] This implementation plan achieves a four-level standardized early warning system based on quantitative indices, automatically identifies sensitive targets and generates targeted information, and solves the shortcomings of traditional early warning systems that only consider leakage volume and ignore ecological sensitivity, thereby improving the scientific nature and practicality of early warning.

[0163] In an optional implementation, see Figure 6 As shown, Figure 6 The flowchart illustrates an emergency response plan generation method provided in Embodiment 1 of this application. The method involves generating multiple emergency response plans using an intelligent decision-making model based on pollution situation information, early warning level information, emergency resource information, and marine risk level distribution information. The steps include S601-S602. S601: Determine the priority of response in each region based on pollution status information, early warning level information, and marine risk level distribution information.

[0164] Specifically, the system sorts the responses using a priority ranking algorithm. The ranking rule is that the higher the warning level, the higher the risk level, and the more important the sensitive target, the higher the response priority. This rule aligns with the actual needs of emergency response.

[0165] The algorithm will traverse all treatment areas across the entire sea area, calculate the priority score for each one, sort them from high to low score, and generate a standardized treatment priority list.

[0166] The priority list will be synchronized to the front-end interface, using numbers to mark the order of handling in each area, guiding emergency resources to be allocated to high-priority areas first.

[0167] S602: With the optimization objectives of minimizing ecological loss, minimizing disposal time, and minimizing economic cost, and with the resource reserves and disposal capacity in the emergency resource information as constraints, a multi-objective optimization algorithm is used to solve the problem based on disposal priority, generating multiple emergency disposal plans. Each emergency disposal plan includes an emergency resource scheduling plan, a ship navigation path planning plan, and a disposal strategy.

[0168] Specifically, the multi-objective optimization algorithm adopts the NSGA-Ⅲ non-dominated genetic algorithm, which has excellent multi-objective solution capabilities and can find the Pareto optimal solution that balances the three objectives.

[0169] The algorithm verifies all constraints, including emergency resource reserves, equipment performance, navigation restrictions, and operation time limits, to ensure that the generated plan meets the actual disposal conditions and is feasible.

[0170] Once the solution is generated, it will be pushed to the UE5 digital twin scenario for full-process simulation and deduction. The simulation process can be played repeatedly, and the parameters can be manually adjusted and recalculated to verify the feasibility of the solution.

[0171] This implementation plan generates three differentiated schemes based on multi-objective optimization, achieves optimal resource scheduling by combining priorities, verifies feasibility through twin simulation, balances ecological, time, and cost objectives, solves the problems of traditional decision-making being based on experience, having a single scheme, and having unreasonable scheduling, and improves the efficiency of handling.

[0172] In an optional implementation, see Figure 7 As shown, Figure 7 A flowchart of the emergency response closed-loop optimization and ecological restoration method provided in Embodiment 1 of this application is shown, wherein the method further includes steps S701 to S704: S701: Based on the real-time updated accident monitoring information, re-execute the steps of generating pollution situation information, predicting the spatiotemporal distribution information of pollutants, calculating multi-dimensional damage risk indicators, generating early warning level information, and generating multiple emergency response plans to achieve dynamic updating and closed-loop optimization of emergency response plans.

[0173] Specifically, the system is set to refresh every hour to automatically acquire the latest on-site monitoring data. Once the data is updated, the entire process calculation is restarted immediately to ensure that decisions are synchronized with the on-site situation in real time.

[0174] Each iteration of the calculation retains historical results, allowing for comparison of pollution status, warning levels, and response plans at different time points, and providing an intuitive display of the response effects and pollution changes.

[0175] The closed-loop optimization mechanism can adjust the plan in real time according to the progress of the response, avoiding the disconnect between the plan and the actual situation, and greatly improving the flexibility and effectiveness of emergency response.

[0176] S702: Based on the real-time updated accident monitoring information, determine whether the pollution has been effectively controlled. When it is determined that the pollution has been effectively controlled, obtain post-accident environmental monitoring data.

[0177] Specifically, the criteria for effective pollution control are that pollutant concentration / activity meets the standards and the diffusion range stops expanding. The standards strictly follow the national marine environmental quality standards, and the judgment results are objective and fair.

[0178] Once the standard is met, the system automatically initiates the post-event environmental monitoring data collection process, continuously collecting monitoring data on seawater, sediments, and organisms, with the data collection cycle covering both short-term monitoring and long-term tracking.

[0179] The collected data will undergo standardized preprocessing and be stored in a dedicated database for ecological damage assessment, providing a complete data foundation for subsequent quantitative damage assessment.

[0180] S703: Based on the environmental monitoring data after the accident, the ecological and environmental damage caused by the accident is quantitatively assessed from multiple dimensions, including seawater quality, sediment quality, and biological resources, to obtain the ecological damage assessment results.

[0181] Specifically, the system completes quantitative calculations through an ecological damage assessment model, with assessment dimensions including five major dimensions: seawater quality, sediment quality, biological resources, ecosystem service functions, and environmental capacity.

[0182] The model calculates core indicators such as the scope of damage, the degree of damage, and ecological and economic losses. The calculation of these indicators adopts authoritative national accounting methods, and the results have legal validity and reference value.

[0183] Once the assessment is completed, a standardized ecological damage assessment report is automatically generated. The report includes text descriptions, data charts, and spatial distribution maps to meet the needs of supervision and review.

[0184] S704: Based on the ecological damage assessment results, generate ecological restoration plan recommendations.

[0185] Specifically, the system generates solutions through an ecological restoration matching model. The model combines the ecological characteristics, degree of damage, and restoration conditions of the damaged sea area to automatically match the optimal restoration technology.

[0186] The restoration plan includes the entire process of beach cleanup, sediment restoration, biological propagation and release, and ecological monitoring, and clarifies the technology selection, implementation process, and effect evaluation requirements.

[0187] The platform will continuously track the restoration process, regularly collect restoration monitoring data, and dynamically evaluate the restoration effect until the ecological environment is restored to the pre-accident level.

[0188] This implementation plan enables closed-loop dynamic optimization of the entire emergency response process, ensuring that decision-making is synchronized with the on-site situation, completing quantitative damage assessment and targeted repair, forming a closed loop of "response-optimization-assessment-repair", minimizing ecological losses, and improving the whole-chain prevention and control system.

[0189] Example 2 See Figure 8 As shown, Figure 8 The diagram shows a structural schematic of a marine pollution accident emergency response device provided in Embodiment 2 of this application, wherein the device includes: The marine risk level distribution information determination module 801 is used to obtain environmental monitoring data, risk source information and emergency resource information of the target marine area when no pollution accident occurs, and to conduct dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information. The spatiotemporal distribution information acquisition module 802 is used to acquire accident monitoring information to form pollution situation information after a pollution accident is triggered, and to call a pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information and environmental forecast data. The early warning level information acquisition module 803 is used to calculate a multi-dimensional damage risk index based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, and to generate early warning level information based on the multi-dimensional damage risk index. The emergency response plan generation module 804 is used to generate multiple emergency response plans based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information through an intelligent decision-making model.

[0190] In an optional implementation, the dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information includes: The risk source type is determined based on the aforementioned risk source information; When the risk source type is a fixed facility, the maximum credible accidental leakage amount of the fixed facility is determined based on the maximum storage capacity and containment facility capacity of the fixed facility; When the risk source type is a mobile carrier, the leakage probability of the mobile carrier is determined based on the dynamic data and historical accident probability of the mobile carrier. Based on the maximum credible accident leakage amount or the leakage probability, and combined with the hydrological and meteorological conditions in the environmental monitoring data, the potential impact range of the accident is simulated, and the risk level distribution information of the sea area is generated.

[0191] In an optional implementation, the step of using a pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information, and environmental forecast data includes: Based on the pollution situation information, the type of leaked substance, the amount leaked, and the location of the leak are determined; Based on the risk source information, obtain the physicochemical properties of the leaked substance; Based on the aforementioned environmental forecast data, ocean current, wind speed and direction, and tidal data are obtained. The type of leaked substance, the amount of leak, the location of the leak, the physicochemical properties, the ocean current, the wind speed and direction, and the tidal data are input into the pollutant drift and diffusion numerical model to simulate the spatiotemporal distribution information of the pollutants.

[0192] In an optional implementation, the calculation of multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data includes: Based on the spatiotemporal distribution information of the pollutants, extract the pollutant concentration or thickness data within each computational grid; Based on the sensitive target distribution information, the sensitive target types and sensitivity coefficients within each computational grid are determined; Based on the pollutant concentration or thickness data, the sensitive target type and sensitivity coefficient, multiple preset dimensions of sub-item damage risk indicators are calculated respectively; The multi-dimensional damage risk index is obtained by weighting and synthesizing the various sub-items of damage risk index.

[0193] In an optional implementation, generating early warning level information based on the multi-dimensional damage risk indicators includes: The multi-dimensional damage risk indicators are compared with preset classification thresholds to determine the warning level; Identify affected sensitive targets based on the spatiotemporal distribution information of the pollutants; The warning level information is generated based on the warning level and the affected sensitive targets.

[0194] In an optional implementation, based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model, including: Based on the pollution situation information, the early warning level information, and the marine risk level distribution information, the priority of response in each region is determined; With the optimization objectives of minimizing ecological loss, minimizing disposal time, and minimizing economic cost, and with the resource reserves and disposal capacity in the emergency resource information as constraints, a multi-objective optimization algorithm is used to solve the problem based on the disposal priority, generating multiple emergency disposal plans. Each emergency disposal plan includes an emergency resource scheduling plan, a ship navigation path planning plan, and a disposal strategy.

[0195] In an optional implementation, the device further includes an ecological restoration scheme recommendation generation module, used for: Based on real-time updated accident monitoring information, the steps of generating pollution situation information, predicting the spatiotemporal distribution information of pollutants, calculating multi-dimensional damage risk indicators, generating early warning level information, and generating multiple emergency response plans are re-executed to achieve dynamic updating and closed-loop optimization of emergency response plans. Based on the real-time updated accident monitoring information, it is determined whether the pollution has been effectively controlled. Once it is determined that the pollution has been effectively controlled, post-accident environmental monitoring data is obtained. Based on the environmental monitoring data after the accident, the ecological damage caused by the accident was quantitatively assessed from multiple dimensions, including seawater quality, sediment quality, and biological resources, and the ecological damage assessment results were obtained. Based on the ecological damage assessment results, ecological restoration plan recommendations are generated.

[0196] Example 3 Based on the same application concept, see [link / reference] Figure 9 As shown, Figure 9 This illustration shows a structural schematic diagram of a computer device provided in Embodiment 3 of this application, wherein, as shown... Figure 9 As shown, the computer device 900 provided in Embodiment 3 of this application includes: The computer device 900 includes a processor 901, a memory 902, and a bus 903. The memory 902 stores machine-readable instructions that can be executed by the processor 901. When the computer device 900 is running, the processor 901 communicates with the memory 902 through the bus 903. When the machine-readable instructions are executed by the processor 901, the steps of the marine pollution accident emergency response plan generation method shown in Embodiment 1 are executed.

[0197] Example 4 Based on the same concept, this application also provides a computer-readable storage medium storing a computer program, which, when run by a processor, executes the steps of the marine pollution accident emergency response plan generation method described in any of the above embodiments.

[0198] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0199] The computer program product for generating emergency response plans for marine pollution accidents provided in this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0200] The marine pollution accident emergency response plan generation device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0201] In the embodiments provided in this application, it should be understood that the disclosed apparatus 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 displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0202] 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.

[0203] In addition, the functional units in the embodiments provided in this application 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.

[0204] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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 application. 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.

[0205] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0206] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for generating an emergency response plan for a marine pollution incident, characterized in that, include: Before a pollution incident occurs, environmental monitoring data, risk source information, and emergency resource information for the target sea area are acquired. Based on the risk source information and the environmental monitoring data, dynamic risk assessments are conducted on various risk sources to obtain sea area risk level distribution information. After a pollution incident is triggered, the incident monitoring information is obtained to form pollution situation information. Based on the pollution situation information, the risk source information and environmental forecast data, the pollutant diffusion prediction model is called to predict the spatiotemporal distribution information of pollutants. Based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, a multi-dimensional damage risk index is calculated, and an early warning level information is generated based on the multi-dimensional damage risk index. Based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model.

2. The method according to claim 1, characterized in that, The dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data, to obtain marine risk level distribution information, includes: The risk source type is determined based on the aforementioned risk source information; When the risk source type is a fixed facility, the maximum credible accidental leakage amount of the fixed facility is determined based on the maximum storage capacity and containment facility capacity of the fixed facility; When the risk source type is a mobile carrier, the leakage probability of the mobile carrier is determined based on the dynamic data and historical accident probability of the mobile carrier. Based on the maximum credible accident leakage amount or the leakage probability, and combined with the hydrological and meteorological conditions in the environmental monitoring data, the potential impact range of the accident is simulated, and the risk level distribution information of the sea area is generated.

3. The method according to claim 1, characterized in that, The step of predicting the spatiotemporal distribution information of pollutants by calling a pollutant diffusion prediction model based on the pollution situation information, the risk source information, and environmental forecast data includes: Based on the pollution situation information, the type of leaked substance, the amount leaked, and the location of the leak are determined; Based on the risk source information, obtain the physicochemical properties of the leaked substance; Based on the aforementioned environmental forecast data, ocean current, wind speed and direction, and tidal data are obtained. The type of leaked substance, the amount of leak, the location of the leak, the physicochemical properties, the ocean current, the wind speed and direction, and the tidal data are input into the pollutant drift and diffusion numerical model to simulate the spatiotemporal distribution information of the pollutants.

4. The method according to claim 1, characterized in that, The calculation of multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data includes: Based on the spatiotemporal distribution information of the pollutants, extract the pollutant concentration or thickness data within each computational grid; Based on the sensitive target distribution information, the sensitive target types and sensitivity coefficients within each computational grid are determined; Based on the pollutant concentration or thickness data, the sensitive target type and sensitivity coefficient, multiple preset dimensions of sub-item damage risk indicators are calculated respectively; The multi-dimensional damage risk index is obtained by weighting and synthesizing the various sub-items of damage risk index.

5. The method according to claim 4, characterized in that, The generation of early warning level information based on the multi-dimensional damage risk indicators includes: The multi-dimensional damage risk indicators are compared with preset classification thresholds to determine the warning level; Identify affected sensitive targets based on the spatiotemporal distribution information of the pollutants; The warning level information is generated based on the warning level and the affected sensitive targets.

6. The method according to claim 1, characterized in that, Based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, multiple emergency response plans are generated through an intelligent decision-making model, including: Based on the pollution situation information, the early warning level information, and the marine risk level distribution information, the priority of response in each region is determined; With the optimization objectives of minimizing ecological loss, minimizing disposal time, and minimizing economic cost, and with the resource reserves and disposal capacity in the emergency resource information as constraints, a multi-objective optimization algorithm is used to solve the problem based on the disposal priority, generating multiple emergency disposal plans. Each emergency disposal plan includes an emergency resource scheduling plan, a ship navigation path planning plan, and a disposal strategy.

7. The method according to claim 1, characterized in that, The method further includes: Based on real-time updated accident monitoring information, the steps of generating pollution situation information, predicting the spatiotemporal distribution information of pollutants, calculating multi-dimensional damage risk indicators, generating early warning level information, and generating multiple emergency response plans are re-executed to achieve dynamic updating and closed-loop optimization of emergency response plans. Based on the real-time updated accident monitoring information, it is determined whether the pollution has been effectively controlled. Once it is determined that the pollution has been effectively controlled, post-accident environmental monitoring data is obtained. Based on the environmental monitoring data after the accident, the ecological damage caused by the accident was quantitatively assessed from multiple dimensions, including seawater quality, sediment quality, and biological resources, and the ecological damage assessment results were obtained. Based on the ecological damage assessment results, ecological restoration plan recommendations are generated.

8. A device for generating emergency response plans for marine pollution accidents, characterized in that, include: The marine risk level distribution information determination module is used to acquire environmental monitoring data, risk source information and emergency resource information of the target marine area when no pollution accident occurs, and to conduct dynamic risk assessment of various risk sources based on the risk source information and the environmental monitoring data to obtain marine risk level distribution information. The spatiotemporal distribution information acquisition module is used to acquire accident monitoring information to form pollution situation information after a pollution accident is triggered, and to call the pollutant diffusion prediction model to predict the spatiotemporal distribution information of pollutants based on the pollution situation information, the risk source information and environmental forecast data. The early warning level information acquisition module is used to calculate multi-dimensional damage risk indicators based on the spatiotemporal distribution information of the pollutants and the distribution information of sensitive targets in the environmental monitoring data, and to generate early warning level information based on the multi-dimensional damage risk indicators; The emergency response plan generation module is used to generate multiple emergency response plans based on the pollution situation information, the early warning level information, the emergency resource information, and the marine risk level distribution information, through an intelligent decision-making model.

9. A computer device, characterized in that, include: The computer device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the marine pollution accident emergency response plan generation method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for generating a marine pollution incident emergency response plan as described in any one of claims 1 to 7.

Images