A coastal tide level automatic early warning and regulation system
By integrating real-time data with multi-source heterogeneous data, and automatically identifying and switching tide level models, the coastal tide level early warning system has achieved high efficiency, accuracy, and self-optimization, solving the problems of insufficient forecasting and slow response of traditional systems, and improving emergency response capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 自然资源部天津海洋中心(自然资源部天津海洋预报台)
- Filing Date
- 2026-01-29
- Publication Date
- 2026-06-09
AI Technical Summary
Traditional coastal tide level warning systems rely on single hydrological and meteorological data, which cannot distinguish between regular astronomical tides and sudden disasters. They suffer from insufficient forecast accuracy, slow response, and lack of multi-source data fusion and model optimization, making it difficult to meet the modern early warning requirements of high timeliness and high accuracy.
Design an automatic early warning and control system for coastal tide levels. Obtain a regular dataset by fusing real-time data and background data, identify special disasters using multi-source heterogeneous monitoring data, automatically switch models for simulation, generate early warning information, and continuously improve model accuracy through an iterative optimization module.
It enables precise simulation of tidal processes with different physical mechanisms, improves emergency response speed and early warning accuracy, has self-optimization capabilities, and significantly enhances the long-term reliability and forecasting ability of the system.
Smart Images
Figure CN122176861A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of data processing, and in particular relates to an automatic early warning and control system for coastal tide levels. Background Technology
[0002] Traditional coastal tide level early warning systems rely heavily on single hydrological and meteorological data and manual experience for judgment, which has significant limitations. First, these systems typically use generic tide level models, which cannot effectively distinguish between the different physical mechanisms of regular astronomical tides and sudden disasters such as storm surges, earthquakes, tsunamis, landslides, and wave surges, leading to insufficient forecast accuracy or missed warnings for the latter. Second, disaster assessment depends on manual monitoring and intervention, resulting in slow response times and a lack of fully automated, standardized fusion and triggering processes for integrating multi-source heterogeneous data (such as earthquakes and seafloor pressure) into early warnings. Third, model parameters and warning thresholds are statically fixed, making it difficult to rapidly assimilate and dynamically optimize them using real-time observation data, hindering continuous iterative improvement of forecasting capabilities.
[0003] In summary, existing coastal tide level early warning technologies are insufficient to meet the demands of modern comprehensive disaster early warning systems that require high timeliness and precision. Summary of the Invention
[0004] Therefore, it is necessary to provide an automatic early warning and control system for coastal tide levels to address the above-mentioned problems.
[0005] The present invention is implemented as follows: an automatic coastal tide level early warning and control system includes:
[0006] The dataset acquisition module is used to obtain a regular dataset containing precise initial state and boundary driving conditions by fusing real-time tide data with background data; at the same time, by processing multi-source heterogeneous monitoring data that characterizes special disaster mechanisms, a parallel special driving factor dataset is obtained. When the parameters of the special driving factor dataset reach the first threshold, a special disaster event is determined to have occurred, and a disaster event identification signal is generated. The special driving factor dataset is then fused with the current background data to generate a disaster dataset.
[0007] The risk level type output module is used to input a regular dataset into a regular tide level model for simulation, and output a regular risk level by comparing it with a second threshold; if a disaster event identification signal is received, it switches to the corresponding disaster tide level model, uses a disaster dataset for simulation, and outputs a special risk level by comparing it with a third threshold.
[0008] The risk warning module is used to generate warning information (level, time, scope, and recommendations) by calling the corresponding structured warning plan library based on the risk level and type (e.g., risk level 3 - special tsunami, risk level 2 - normal).
[0009] The iterative optimization module is used to continuously import updated regular or disaster datasets after the early warning is issued, continuously correct the regular or disaster tide level model, and achieve continuous optimization of the regular or disaster tide level model and iterative improvement of its forecasting capability.
[0010] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, wherein the data set acquisition module includes:
[0011] The conventional dataset acquisition unit is used to perform quality control and assimilation processing on the collected real-time tide data to obtain standardized tide data. The standardized tide data is then fused with background data (such as astronomical tide background field, meteorological background field, etc.) to generate a conventional dataset containing precise initial state and boundary driving conditions.
[0012] The heterogeneous data processing unit is used to acquire multi-source heterogeneous data streams (including submarine earthquake monitoring network, volcanic activity observation, submarine pressure sensor array and satellite rapid scan data) in parallel to characterize special disaster mechanisms. It performs independent quality control and assimilation processing on the multi-source heterogeneous data streams to generate a parallel special driving factor dataset.
[0013] The disaster dataset acquisition unit is used to set a trigger threshold. When the parameters of the special driving factor dataset (such as earthquake moment magnitude and seafloor pressure mutation rate) reach the first threshold, a disaster event is determined to exist, and a disaster event identification signal is generated. Different disaster events have different identification signals. The special driving factor dataset is fused with the current background data to construct a disaster dataset specific to the disaster event.
[0014] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, wherein the disaster data set acquisition unit includes:
[0015] The rule base setting sub-unit is used to pre-set the disaster triggering rule base. Each rule clearly defines the combination of parameters that need to be monitored to determine a specific disaster event, as well as the first threshold corresponding to each parameter.
[0016] The disaster type determination subunit is used to compare the parameters of the special driving factor dataset with all the rules of the disaster triggering rule base one by one. If the parameters of the special driving factor dataset meet all the preset first threshold conditions in any rule, the corresponding disaster event is determined to have occurred, and a unique disaster event identification signal is generated and output.
[0017] The data fusion subunit is used to associate and call predefined data fusion templates corresponding to the disaster type based on the disaster event identification signal. It fuses the characteristic parameters that triggered the event (such as the earthquake source mechanism), the associated multi-source observation data (such as pressure sensor anomaly records), and the current background data (such as real-time astronomical tides and high-precision topography) to generate a disaster dataset customized for the disaster event.
[0018] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, wherein the risk level type output module includes:
[0019] The conventional risk assessment unit is used to input conventional datasets into conventional tide level models (such as ROMS, FVCOM, SCHISM, etc.) if no disaster event identification signal is received. The conventional tide level model simulates the spatiotemporal changes of tide level, waves and storm surge within a future set time period (such as 72 hours) by solving a set of fluid dynamic equations, obtains simulation results, compares the simulation results with preset second thresholds for each level of early warning, and thus determines and outputs the conventional risk level.
[0020] The disaster risk assessment unit is used to switch the conventional tide level model to a disaster tide level model (such as a tsunami propagation model or a landslide surge model) that matches the physical mechanism of the disaster based on the disaster event type when a disaster event identification signal is received. Based on the disaster event type, the unit drives the disaster tide level model to simulate the spatiotemporal evolution of the disaster, obtain simulation results, compare the simulation results with the preset third threshold for disaster emergency response, and determine and output the corresponding special risk level.
[0021] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, wherein the risk early warning module includes:
[0022] The template matching unit is used to receive the conventional risk level or special risk level and disaster event identification signal. Based on the pre-set template for matching, it fills the template with the current time, the simulation results obtained from the conventional tide level model or the disaster tide level model (such as the peak tide time and tide height predicted by the conventional tide level model, or the arrival time and impact range of the initial wave of the tsunami predicted by the disaster tide level model), and generates structured early warning information containing a definite level, precise time, specific range and clear recommendations.
[0023] The early warning push unit is used to synchronously and in real time push the generated early warning information to all preset receiving terminals through the communication interface. The receiving terminals include the emergency command platform, public release channels (such as government microblogs, emergency broadcasts, and mobile SMS broadcasts across the network), and designated responsible person terminals.
[0024] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, wherein the iterative optimization module includes:
[0025] The data update unit is used to import updated regular datasets or disaster datasets (such as more data triggered by seabed sensors, and subsequent earthquake source revision information) after the early warning is issued.
[0026] The model assimilation unit selects an assimilation strategy based on whether the currently used model is a conventional tidal level model or a catastrophic tidal level model. For a conventional tidal level model, it uses an updated conventional dataset and employs data assimilation techniques (such as ensemble Kalman filtering) to correct the initial field (i.e., the three-dimensional sea state of the entire computational domain at the start of the simulation, including the spatial distribution of water level, current velocity, temperature, and salinity) and internal state (referring to internal variables and parameters affecting the evolution of the model during integration, excluding the initial field, such as bottom friction coefficient, turbulent mixing intensity, and boundary layer structure). For a catastrophic tidal level model, it uses an updated catastrophic dataset, assimilates real-time observation data to invert and correct catastrophic source parameters (such as the spatial morphology and initial displacement of the tsunami source), and optimizes the internal state of the catastrophic tidal level model (ensuring its dynamic processes accurately respond to the updated catastrophic source drive).
[0027] The feedback adjustment unit is used to compare the model simulation results with the final actual observation data after each forecast period (i.e., the complete process from starting the model simulation to completing the forecast for the next 72 hours), calculate the forecast error, and record the error statistics for: evaluating and reporting the changing trend of the model's forecast capability; and, as feedback information, optimizing and adjusting the second (normal) and third thresholds within a safe range so that the threshold settings better reflect the current actual disaster risk and the forecast bias characteristics of the model.
[0028] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, further comprising:
[0029] The multi-model result processing module is used to receive the independent simulation results of each model when multiple available models (such as different tsunami propagation models) are configured for the same scenario (especially disaster scenario), and to apply a preset fusion strategy (such as weighted average based on historical performance, taking the most conservative result, etc.) to integrate them and generate a unified simulation result, thereby determining and outputting the conventional risk level or disaster risk level.
[0030] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, further comprising:
[0031] The contingency plan simulation module provides a simulation environment independent of real-time business operations. It allows operators to input parameter adjustment instructions (such as modifying typhoon paths or setting different magnitudes) based on (current or historical) conventional or disaster datasets, driving conventional or disaster tide level models to perform scenario simulations and generate complete simulation results (such as inundation range and spatiotemporal distribution of wave height) and corresponding risk levels. If operators further input or select preset emergency response plans, the module compares the matching degree between the simulation results and the plans (such as whether the evacuation range defined in the plan covers the simulated disaster area) and presents a comparative analysis report in a visual manner.
[0032] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, further comprising:
[0033] The training delivery module extracts typical cases with teaching value (including cases of efficient handling and cases with deviations) from the historical operation records of the contingency plan simulation module and the operation logs of actual emergency response events. Using natural language processing technology, these cases are automatically generated into structured analysis reports, and then tagged, classified, and archived (based on dimensions such as event type, handling complexity, and key decision-making nodes). The module regularly pushes case analysis reports and corresponding simulation exercises related to the responsibilities of designated personnel, serving as continuous job competency training materials.
[0034] In one embodiment, the present invention provides an automatic coastal tide level early warning and control system, further comprising:
[0035] The materials inspection module is used to build a dynamically updated materials database. This database records the real-time reserves, sustainable supply capacity, and maximum transport time of various emergency materials (such as sandbags, water pumps, generators, and special rescue equipment) in different regions (e.g., region A and region B). After the contingency plan simulation module generates the matching degree between the simulation results and the contingency plan, it automatically analyzes the resource consumption requirements in the corresponding contingency plan based on the specific target areas affected by the disaster simulation, and compares and quantifies them one by one with the actual support capacity in the materials database of the target areas. It then generates a materials support feasibility assessment report, clearly listing the key materials items with shortages and the estimated support delay time.
[0036] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention innovatively designs an architecture that separates the acquisition of conventional and disaster datasets and automatically switches models according to event identifiers, realizing accurate and specialized simulation of tidal processes driven by different physical mechanisms; by establishing automatic disaster identification and data fusion based on multi-threshold rules, it achieves full-process automation from multi-source information to disaster identification and then to the generation of customized datasets, greatly improving the speed of emergency response; relying on the closed-loop iterative optimization module, the system can continuously assimilate new data and correct models and thresholds, enabling the forecasting and early warning capabilities to have the adaptive characteristics of continuous self-improvement, significantly improving the long-term reliability and early warning accuracy of the system. Attached Figure Description
[0037] Figure 1 This is a schematic diagram of the first part of an automatic coastal tide level early warning and control system provided in an embodiment of the present invention.
[0038] Figure 2 This is a schematic diagram of the dataset acquisition module provided in an embodiment of the present invention.
[0039] Figure 3 This is a schematic diagram of a disaster dataset acquisition unit provided in an embodiment of the present invention.
[0040] Figure 4 This is a schematic diagram of a risk level type output module provided in an embodiment of the present invention.
[0041] Figure 5 This is a schematic diagram of a risk warning module provided in an embodiment of the present invention.
[0042] Figure 6 This is a schematic diagram of the iterative optimization module provided in an embodiment of the present invention.
[0043] Figure 7 This is a schematic diagram of the second part of an automatic coastal tide level early warning and control system provided in an embodiment of the present invention.
[0044] Figure 8 This is a schematic diagram of the third part of an automatic coastal tide level early warning and control system provided in an embodiment of the present invention.
[0045] Figure 9 This is a schematic diagram of the fourth part of an automatic coastal tide level early warning and control system provided in an embodiment of the present invention.
[0046] Figure 10 This is a schematic diagram of the fifth part of an automatic coastal tide level early warning and control system provided in an embodiment of the present invention. Detailed Implementation
[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.
[0048] It is understood that the terms "first," "second," etc., used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script.
[0049] In one embodiment, such as Figure 1 As shown, an automatic coastal tide level early warning and control system includes:
[0050] The dataset acquisition module 1 is used to obtain a regular dataset containing precise initial state and boundary driving conditions by fusing real-time tide data with background data; at the same time, by processing multi-source heterogeneous monitoring data that characterizes special disaster mechanisms, a parallel special driving factor dataset is obtained. When the parameters of the special driving factor dataset reach the first threshold, a special disaster event is determined to have occurred, and a disaster event identification signal is generated. The special driving factor dataset is then fused with the current background data to generate a disaster dataset.
[0051] Risk level type output module 2 is used to input the regular dataset into the regular tide level model for simulation, and output the regular risk level by comparing it with the second threshold; if a disaster event identification signal is received, it switches to the corresponding disaster tide level model, uses the disaster dataset for simulation, and outputs the special risk level by comparing it with the third threshold.
[0052] Risk warning module 3 is used to call the corresponding structured warning plan library to generate warning information (level, time, scope, and recommendations) based on the risk level and type (e.g., risk level 3 - special tsunami, risk level 2 - normal).
[0053] The iterative optimization module 4 is used to continuously import updated regular or disaster datasets after the early warning is issued, continuously correct the regular or disaster tide level model, and achieve continuous optimization of the regular or disaster tide level model and iterative improvement of its forecasting capability.
[0054] Traditional tide level warning systems rely on human experience to distinguish between regular tides and sudden disasters, resulting in slow response and an inability to continuously evolve. This design achieves automated parallel processing and intelligent identification of regular and disaster data through a dataset acquisition module 1; a risk level type output module 2 automatically switches to a dedicated model based on event type for accurate simulation and risk assessment; a risk warning module 3 automatically converts risk conclusions into structured, executable warning instructions; and an iterative optimization module 4 ensures that the system can continuously revise the model and thresholds using subsequent observation data, achieving self-iterative optimization of forecasting capabilities. These four modules work together to fundamentally upgrade the warning service from a passive, static, manual processing mode to a proactive, precise, and learning-capable automated intelligent system.
[0055] In one embodiment, such as Figure 2 As shown, an automatic coastal tide level early warning and control system includes a dataset acquisition module 1 comprising:
[0056] The conventional dataset acquisition unit 11 is used to perform quality control and assimilation processing on the collected real-time tide data to obtain standardized tide data. The standardized tide data is then fused with background data (such as astronomical tide background field, meteorological background field, etc.) to generate a conventional dataset containing precise initial state and boundary driving conditions.
[0057] The heterogeneous data processing unit 12 is used to acquire multi-source heterogeneous data streams (including submarine earthquake monitoring network, volcanic activity observation, submarine pressure sensor array and satellite rapid scan data) in parallel to characterize special disaster mechanisms. It performs independent quality control and assimilation processing on the multi-source heterogeneous data streams to generate a parallel special driving factor dataset.
[0058] The disaster dataset acquisition unit 13 is used to set a trigger first threshold. When the parameters of the special driving factor dataset (such as earthquake moment magnitude and seafloor pressure mutation rate) reach the first threshold, it is determined that a disaster event exists and a disaster event identification signal is generated. Different disaster events have different identification signals. The special driving factor dataset is fused with the current background data to construct a disaster dataset specific to the disaster event.
[0059] For conventional tidal data, quality control is achieved through automatic verification, threshold identification, and spatiotemporal consistency analysis to remove outliers and fill reasonable gaps. Assimilation processing employs algorithms such as ensemble Kalman filtering to integrate the quality-controlled data into a short-term forecast field, outputting standardized tidal data. Independent quality control is implemented for multi-source heterogeneous data streams (such as seismic waveforms, seafloor pressure, and satellite imagery), using differentiated quality control algorithms based on the characteristics of different data sources: integrity verification and signal-to-noise ratio analysis are performed on seismic waveforms; drift correction and peak removal are applied to pressure sensor data; and cloud masking and atmospheric correction are performed on satellite data. After quality control, the system assimilates the effective data from each source through inversion based on physical mechanisms or statistical relationships, extracting and fusing unified quantitative parameters characterizing disaster mechanisms, such as "moment magnitude" and "pressure mutation rate," ultimately generating a special driving factor dataset.
[0060] In one embodiment, such as Figure 3 As shown, a coastal automatic tide level early warning and control system includes a disaster data acquisition unit 13 comprising:
[0061] The rule base setting subunit 131 is used to pre-set the disaster triggering rule base. Each rule clearly defines the combination of parameters that need to be monitored to determine a specific disaster event, as well as the first threshold corresponding to each parameter.
[0062] The disaster type judgment subunit 132 is used to compare the parameters of the special driving factor dataset with all the rules of the disaster triggering rule base one by one. If the parameters of the special driving factor dataset meet all the preset first threshold conditions in any rule, the corresponding disaster event is determined to have occurred, and a unique disaster event identification signal is generated and output.
[0063] The data fusion subunit 133 is used to associate and call a predefined data fusion template corresponding to the disaster type based on the disaster event identification signal, and to fuse the characteristic parameters that triggered the event (such as the earthquake source mechanism), the associated multi-source observation data (such as pressure sensor anomaly records), and the current background data (such as real-time astronomical tides and high-precision topography) to generate a disaster dataset customized for the disaster event.
[0064] For example, the parameter combination is the earthquake moment magnitude Mw and the focal depth H; the corresponding first threshold is Mw≥6.5 and H≤70km, and if the conditions are met, it is determined to be a near-field tsunami event.
[0065] The parameter combination is the seafloor pressure mutation rate dP / dt in a specific area, the seismic signal missing identifier, and the historical topographic slope S; the corresponding first threshold is dP / dt≥10kPa / min and the seismic signal identifier is 1 (indicating signal missing) and S≥15°. If the conditions are met, it is judged as a suspected seafloor landslide event.
[0066] The parameter combination is the typhoon center pressure Pc and the astronomical tide forecast tide level Tide; the corresponding first threshold is Pc≤920hPa and Tide≥local warning tide level. If the conditions are met, it is judged as an extremely large complex storm surge event.
[0067] In one embodiment, such as Figure 4 As shown, a coastal tide level automatic early warning and control system includes a risk level type output module 2 comprising:
[0068] The conventional risk assessment unit 21 is used to input conventional datasets into conventional tide level models (such as ROMS, FVCOM, SCHISM, etc.) if no disaster event identification signal is received. The conventional tide level model simulates the spatiotemporal changes of tide level, waves and storm surge within a future set time period (such as 72 hours) by solving a set of fluid dynamic equations, obtains simulation results, compares the simulation results with preset second thresholds for each level of early warning, and thus determines and outputs the conventional risk level.
[0069] The disaster risk determination unit 22 is used to, upon receiving a disaster event identification signal, switch the conventional tide level model to a disaster tide level model (such as a tsunami propagation model or a landslide surge model) that matches the physical mechanism of the disaster based on the disaster event type, drive the disaster tide level model to simulate the spatiotemporal evolution of the disaster based on the disaster dataset, obtain simulation results, compare the simulation results with the preset third threshold for disaster emergency response, determine and output the corresponding special risk level.
[0070] A disaster chain knowledge graph can be set up, which will be automatically activated after a major disaster (such as a tsunami) is identified in the disaster risk assessment unit 22. Based on the preset disaster chain knowledge graph (such as tsunami → coastal erosion / dike failure → secondary flood), and based on the simulation results of the major disaster (such as inundation range and impact force), potential secondary disasters can be simulated and risk assessed.
[0071] In one embodiment, such as Figure 5 As shown, an automatic coastal tide level early warning and control system includes a risk early warning module 3 comprising:
[0072] Template matching unit 31 is used to receive conventional risk level or special risk level and disaster event identification signal, and based on the matching preset template, fill the template with the current time, simulation results obtained by conventional tide level model or disaster tide level model (such as the peak tide time and tide height predicted by conventional tide level model, or the arrival time and impact range of the initial wave of tsunami predicted by disaster tide level model), and generate structured early warning information containing a definite level, precise time, specific range and clear recommendations;
[0073] The early warning push unit 32 is used to synchronously and in real time push the generated early warning information to all preset receiving terminals through the communication interface. The receiving terminals include the emergency command platform, public release channels (such as government microblogs, emergency broadcasts, and mobile SMS broadcasts across the network), and designated responsible person terminals.
[0074] Building upon the early warning push unit 32, a unique tracking code can be attached to each early warning message, and the "read / confirm / execute" status feedback of each receiving terminal (especially key personnel and emergency platforms) can be monitored. For key terminals that fail to confirm within a preset time, the system automatically escalates the notification method (such as telephone call) and issues an alarm. This achieves traceable and closed-loop management of early warning issuance, ensuring accountability.
[0075] In one embodiment, such as Figure 6 As shown, an automatic coastal tide level early warning and control system includes an iterative optimization module 4 comprising:
[0076] Data update unit 41 is used to import updated regular datasets or disaster datasets (such as more data triggered by seabed sensors, and subsequent earthquake source revision information) after the early warning is issued.
[0077] Model assimilation unit 42 is used to select an assimilation strategy based on whether the currently used model is a conventional tide level model or a catastrophic tide level model. If it is a conventional tide level model, the updated conventional dataset is used to correct the initial field (i.e., the three-dimensional state of the sea state in the entire computational domain at the start of the simulation, including the spatial distribution of water level, current velocity, temperature, and salinity) and internal state (referring to the internal variables and parameters that affect the evolution of the model during the integration process, excluding the initial field, such as bottom friction coefficient, turbulence mixing intensity, boundary layer structure, etc.) of the conventional tide level model using updated catastrophic datasets, assimilating real-time observation data to invert and correct catastrophic source parameters (such as the spatial morphology and initial displacement of the tsunami source), and optimizing the internal state of the catastrophic tide level model (ensuring that its dynamic process can accurately respond to the updated catastrophic source drive).
[0078] The feedback adjustment unit 43 is used to compare the model simulation results with the final actual observation data after each forecast period ends (i.e., the complete process from starting the model simulation to completing the forecast for the next 72 hours), calculate the forecast error, and record the error statistics and use them to: evaluate and report the changing trend of the model's forecast capability; and, as feedback information, optimize and adjust the second threshold (normal) and the third threshold within a safe range so that the threshold settings can better reflect the current actual disaster risk and the forecast bias characteristics of the model.
[0079] In model assimilation unit 42, the specific implementation example of data assimilation is as follows: For conventional tide level models, the system uses an ensemble Kalman filter algorithm to compare a short-term forecast set (containing slightly different initial fields and physical parameters) with the current real-time tide level observation data. By calculating the likelihood of each set member with the observation, an optimal weighted average analysis field is generated, thereby simultaneously correcting the initial water level, velocity field, and internal turbulence parameters of the conventional tide level model. For disaster tide level models (such as tsunami disaster models), the system assimilates real-time water level anomaly data from nearshore buoys or coastal stations, and uses Green's function or inversion algorithm to dynamically correct the initially set spatial morphology and dislocation amount of the tsunami wave source, optimizing the driving source of disaster simulation.
[0080] In one embodiment, such as Figure 7 As shown, an automatic coastal tide level early warning and control system also includes:
[0081] The multi-model result processing module 5 is used to receive the independent simulation results of each model when multiple available models (such as different tsunami propagation models) are configured for the same scenario (especially disaster scenario), and to apply a preset fusion strategy (such as weighted average based on historical performance, taking the most conservative result, etc.) to integrate them and generate a unified simulation result, thereby determining and outputting the conventional risk level or disaster risk level.
[0082] In critical scenarios such as disaster emergency response, especially tsunami warnings, the forecast results of a single model may contain random errors or limitations, introducing uncertainty into decision-making. This module is designed to integrate the simulation results of multiple independent models and use a fusion strategy based on historical performance (such as weighted averaging or conservative principles) for comprehensive arbitration, thereby smoothing out the biases of a single model and providing a more stable and reliable unified forecast conclusion, significantly improving the scientific rigor and robustness of emergency decision-making.
[0083] In one embodiment, such as Figure 8 As shown, an automatic coastal tide level early warning and control system also includes:
[0084] The contingency plan simulation module 6 provides a simulation environment independent of real-time business operations. It allows operators to input parameter adjustment instructions (such as modifying typhoon paths or setting different magnitudes) based on (current or historical) conventional or disaster datasets, driving conventional or disaster tide level models to perform scenario simulations and generate complete simulation results (such as inundation range and spatiotemporal distribution of wave height) and corresponding risk levels. If operators further input or select preset emergency response plans, the module compares the matching degree between the simulation results and the plans (such as whether the evacuation range defined in the plan covers the simulated disaster area) and presents a comparative analysis report in a visual manner.
[0085] In actual emergency command, decision-makers need to examine the effectiveness of contingency plans. This module provides a simulation sandbox isolated from real-time operations, allowing commanders to simulate various hypothetical scenarios by adjusting disaster parameters (such as typhoon path and magnitude), and to visually verify the matching degree between established plans (such as evacuation areas) and simulated disaster situations. This solves the problems of high cost and difficulty in covering complex scenarios in traditional contingency plan drills, transforming post-event evaluation into pre-event simulation, greatly improving the foresight of command decisions and the practicality of contingency plans.
[0086] In one embodiment, such as Figure 9 As shown, an automatic coastal tide level early warning and control system also includes:
[0087] The training delivery module 7 is used to extract typical cases with teaching value (including cases of efficient handling and cases with deviations) from the historical operation records of the contingency plan simulation module and the operation logs of actual emergency response events. Using natural language processing technology, these cases are automatically generated into structured analysis reports, and tagged, classified and archived (based on event type, handling complexity, key decision nodes, etc.). Case analysis reports and corresponding simulation exercises related to their responsibilities are regularly pushed to designated personnel to serve as continuous job competency training materials.
[0088] The effectiveness of an early warning system ultimately depends on the professional competence of its operators. However, traditional training is often disconnected from actual business operations, making it difficult to effectively transfer experience. This module is designed to transform real-world operational records and simulation cases generated during system operation into structured teaching resources. By automatically analyzing and tagging these cases, the system can target the most relevant historical lessons or successful experiences to personnel in different positions. This solves the problems of significant differences in personnel capabilities, reliance on individual experts for experience, and difficulty in sustaining training effectiveness, thus systematically improving the overall business level of the team.
[0089] In one embodiment, such as Figure 10 As shown, an automatic coastal tide level early warning and control system also includes:
[0090] The materials inspection module 8 is used to construct a dynamically updated materials database. This database records the real-time reserves, sustainable supply capacity, and maximum transport time of various emergency materials (such as sandbags, water pumps, generators, and special rescue equipment) in different regions (such as region A and region B). After the contingency plan simulation module generates the matching degree between the simulation results and the contingency plan, it automatically analyzes the resource consumption requirements in the corresponding contingency plan based on the specific target areas affected by the disaster simulation, and compares and quantifies them one by one with the actual support capacity in the materials database of the target areas. It then generates a materials support feasibility assessment report, clearly listing the key materials items with shortages and the estimated support delay time.
[0091] In emergency response practice, a theoretically perfect plan may become unenforceable due to localized resource shortages. For example, a plan might require deploying a large number of sandbags to area B, but the area may lack sufficient reserves and face difficulties in transporting them. This module was designed to proactively identify and address such resource bottlenecks. After a plan simulation, it automatically compares the resources required by the plan with the real-time inventory and supply capacity of the target area, generating a feasibility report. This forces the formulation and simulation of plans to consider actual resource constraints, moving the plan from theoretical feasibility to practical operability, significantly improving the precision and reliability of emergency preparedness.
[0092] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.
[0093] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0094] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.
[0095] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
[0096] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.
Claims
1. An automatic coastal tide level early warning and control system, characterized in that, The coastal automatic tide level early warning and control system includes: The dataset acquisition module is used to obtain a regular dataset containing precise initial state and boundary driving conditions by fusing real-time tide data with background data; at the same time, by processing multi-source heterogeneous monitoring data that characterizes special disaster mechanisms, a parallel special driving factor dataset is obtained. When the parameters of the special driving factor dataset reach the first threshold, a special disaster event is determined to have occurred, and a disaster event identification signal is generated. The special driving factor dataset is then fused with the current background data to generate a disaster dataset. The risk level type output module is used to input a regular dataset into a regular tide level model for simulation, and output a regular risk level by comparing it with a second threshold; if a disaster event identification signal is received, it switches to the corresponding disaster tide level model, uses a disaster dataset for simulation, and outputs a special risk level by comparing it with a third threshold. The risk warning module is used to generate warning information by calling the corresponding structured warning plan library according to the risk level and type. The iterative optimization module is used to continuously import updated regular or disaster datasets after the early warning is issued, continuously correct the regular or disaster tide level model, and achieve continuous optimization of the regular or disaster tide level model and iterative improvement of its forecasting capability.
2. The coastal tide level automatic early warning and control system according to claim 1, characterized in that, The dataset acquisition module includes: The conventional dataset acquisition unit is used to perform quality control and assimilation processing on the collected real-time tide data to obtain standardized tide data. The standardized tide data is then fused with the background data to generate a conventional dataset containing precise initial states and boundary-driven conditions. The heterogeneous data processing unit is used to collect multi-source heterogeneous data streams that characterize special disaster mechanisms in parallel, perform independent quality control and assimilation processing on the multi-source heterogeneous data streams, and generate a parallel special driving factor dataset. The disaster dataset acquisition unit is used to set a trigger first threshold. When the parameters of the special driving factor dataset reach the first threshold, it is determined that a disaster event exists and a disaster event identification signal is generated. Different disaster events have different identification signals. The special driving factor dataset is fused with the current background data to construct a disaster dataset specific to the disaster event.
3. The coastal tide level automatic early warning and control system according to claim 2, characterized in that, The disaster dataset acquisition unit includes: The rule base setting sub-unit is used to pre-set the disaster triggering rule base. Each rule clearly defines the combination of parameters that need to be monitored to determine a specific disaster event, as well as the first threshold corresponding to each parameter. The disaster type determination subunit is used to compare the parameters of the special driving factor dataset with all the rules of the disaster triggering rule base one by one. If the parameters of the special driving factor dataset meet all the preset first threshold conditions in any rule, the corresponding disaster event is determined to have occurred, and a unique disaster event identification signal is generated and output. The data fusion subunit is used to associate and call a predefined data fusion template corresponding to the disaster type based on the disaster event identification signal. It then fuses the feature parameters that triggered the event, the associated multi-source observation data, and the current background data to generate a disaster dataset customized for the disaster event.
4. The coastal tide level automatic early warning and control system according to claim 1, characterized in that, The risk level type output module includes: The conventional risk assessment unit is used to input conventional datasets into the conventional tide level model if no disaster event identification signal is received. The conventional tide level model simulates the spatiotemporal changes of tide level, waves and storm surge within a future set time period by solving a set of fluid dynamics equations, obtains simulation results, and compares the simulation results with preset second thresholds for each level of early warning, thereby determining and outputting the conventional risk level. The disaster risk assessment unit is used to switch the conventional tide level model to a disaster tide level model that matches the physical mechanism of the disaster based on the disaster event type when a disaster event identification signal is received. Based on the disaster dataset, the disaster tide level model is driven to simulate the spatiotemporal evolution of the disaster, obtain simulation results, compare the simulation results with the preset third threshold for disaster emergency response, determine and output the corresponding special risk level.
5. The coastal tide level automatic early warning and control system according to claim 1, characterized in that, The risk warning module includes: The template matching unit is used to receive the signals of regular risk level or special risk level and disaster event identification. Based on the preset template for matching, it fills the template with the current time, the simulation results obtained from the regular tide level model or the disaster tide level model, and generates structured early warning information containing the definite level, precise time, specific range and clear recommendations. The early warning push unit is used to synchronously and in real time push the generated early warning information to all preset receiving terminals through the communication interface. The receiving terminals include the emergency command platform, public release channels, and designated responsible person terminals.
6. The coastal tide level automatic early warning and control system according to claim 1, characterized in that, The iterative optimization module includes: The data update unit is used to import updated regular datasets or disaster datasets after an early warning is issued; The model assimilation unit is used to select an assimilation strategy based on whether the currently used model is a conventional tide level model or a disaster tide level model. If it is a conventional tide level model, the updated conventional dataset is used to correct the initial field and internal state of the conventional tide level model through data assimilation techniques. If it is a disaster tide level model, the updated disaster dataset is used to assimilate real-time observation data to invert and correct disaster source parameters and optimize the internal state of the disaster tide level model. The feedback adjustment unit is used to compare the model simulation results with the final actual observation data after each forecast period, calculate the forecast error, and record the error statistics for: evaluating and reporting the changing trend of the model's forecast capability; and, as feedback information, optimizing and adjusting the second and third thresholds within a safe range so that the threshold settings better reflect the current actual disaster risk and the model's forecast bias characteristics.
7. The coastal tide level automatic early warning and control system according to any one of claims 1 to 6, characterized in that, Also includes: The multi-model result processing module is used to receive the independent simulation results of each model when multiple available models are configured for the same scenario, apply a preset fusion strategy to integrate them, generate a unified simulation result, and thus determine and output the conventional risk level or disaster risk level.
8. The coastal tide level automatic early warning and control system according to claim 1, characterized in that, Also includes: The contingency plan simulation module provides a simulation environment independent of real-time business operations, allowing operators to input parameter adjustment instructions based on regular datasets or disaster datasets, drive regular tide level models or disaster tide level models to perform scenario simulations, and generate complete simulation results and corresponding risk levels; If the operator further inputs or selects a preset emergency response plan, the simulation results are compared with the plan, and a comparison analysis report is presented in a visual manner.
9. The coastal tide level automatic early warning and control system according to claim 8, characterized in that, Also includes: The training push module is used to extract typical cases with teaching value from the historical operation records of the contingency plan simulation module and the operation logs of actual emergency response events. Using natural language processing technology, these cases are automatically generated into structured analysis reports, which are then tagged, classified, and archived. Case analysis reports and corresponding simulation exercises related to their responsibilities are pushed to designated personnel on a regular basis, serving as continuous job competency training materials.
10. The coastal tide level automatic early warning and control system according to claim 8 or 9, characterized in that, Also includes: The materials inspection module is used to build a dynamically updated materials database, which records the real-time reserves, sustainable supply capacity, and maximum transport time of various emergency materials in different regions. After the contingency plan simulation module generates the matching degree between the simulation results and the contingency plan, it automatically analyzes the resource consumption requirements in the corresponding contingency plan based on the specific target areas affected by the disaster simulation, and compares and quantifies them one by one with the actual support capacity in the materials database of the target areas. It generates a materials support feasibility assessment report, which clearly lists the key materials items with shortages and the estimated support delay time.