Estuary and gulf digital twin system based on multi-source heterogeneous monitoring data and construction method

Through the Hekou Bay digital twin system of multi-source heterogeneous monitoring data, the problem that a single data source and static monitoring means in the existing technology is difficult to capture the dynamic changes of the ecosystem, realizing dynamic monitoring and risk assessment of the ecosystem, providing accurate The governance suggestions have improved the scientificity and flexibility of ecological management.

CN119047894AInactive Publication Date: 2024-11-29BEIHAI FORECASTING CENT OF STATE OCEANIC ADMINISTRATION ((QINGDAO MARINE FORECASTING STATION OF STATE OCEANIC ADMINISTRATION) (QINGDAO MARINE ENVIRONMENT MONITORING CENT OF STATE OCEANIC ADMINISTRATION))

Patent Information

Application Number
CN202411541371.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-31
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing estuary bay ecosystem monitoring and evaluation methods rely on a single data source or static monitoring method, and cannot fully capture the dynamic changes of the ecosystem. There are technical challenges in the integration and processing of multi-source heterogeneous data, resulting in the accuracy and real-time monitoring results. It is difficult to meet the needs of ecological management, lacks comprehensive analysis of time and space dimensions, and cannot accurately predict the transmission path and impact range of pollutants or ecological events.

Method used

Hekou Bay digital twin system based on multi-source heterogeneous monitoring data, including data acquisition and preprocessing modules, spatiotemporal ecological feature extraction modules, spatiotemporal ecological communication modules, ecological communication risk assessment modules and decision support modules, through multi-source data acquisition, Denoising, format standardization, spatial alignment and time synchronization processing, extracting ecological characteristics, simulate propagation paths and diffusion patterns, dynamically evaluate ecological risks, and generate decision-making suggestions.

Benefits of technology

Realize dynamic monitoring and real-time risk assessment of ecosystems, provide accurate ecological change prediction and governance suggestions, improve the scientificity and flexibility of ecological management, help identify high-risk areas and optimize governance plans, and ensure the sustainability of ecosystems. Development and management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047894A_ABST
    Figure CN119047894A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of ecological environment monitoring, in particular to an estuary and gulf digital twinning system based on multi-source heterogeneous monitoring data and a construction method, and the system comprises a data acquisition and preprocessing module, a space-time ecological feature extraction module, a space-time ecological propagation module, an ecological propagation risk assessment module and a decision support module, the data acquisition and preprocessing module acquires multi-source data; the space-time ecological feature extraction module extracts ecological features; the space-time ecological propagation module simulates a propagation path and a diffusion mode of multi-source data in a T-shaped bay and a peripheral area; the ecological propagation risk assessment module dynamically assesses the potential risk of the ecological event; the decision support module generates decision suggestions. According to the method, the change trend of the ecological system can be comprehensively predicted, accurate ecological change prediction is provided for managers, and identification of high-risk areas of pollution diffusion and vegetation degradation is facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ecological environment monitoring, and in particular to an estuary and bay digital twin system based on multi-source heterogeneous monitoring data and a construction method thereof. Background Art

[0002] The estuary and bay areas are important ecological environments and economic resources. Due to their special geographical location and ecosystem, they have become an important place for marine life to live and reproduce. They are also key areas for water quality regulation and vegetation conservation. However, with the intensification of human activities, including industrial emissions, agricultural pollution and urbanization development, the estuary and bay ecosystems are facing serious risks of pollution and ecological degradation. Problems such as water quality deterioration, vegetation degradation and the spread of pollutants not only affect the living environment of marine life, but also pose a threat to the sustainability of coastal vegetation and water resources. Therefore, how to accurately monitor, evaluate and manage the ecological environment of estuaries and bays has become an important issue that needs to be urgently addressed.

[0003] Existing estuarine and bay ecosystem monitoring and assessment methods usually rely on a single data source or static monitoring methods, which cannot fully capture the dynamic changes of the ecosystem. At the same time, due to the heterogeneity of data sources (such as water quality monitoring, pollutant concentration, vegetation coverage and other data from different types of sensors or equipment), there are technical challenges in data integration and processing, resulting in the accuracy and real-time nature of the monitoring results being difficult to meet the needs of ecological management. In addition, the existing ecological transmission and risk assessment models lack comprehensive analysis of the temporal and spatial dimensions, making it difficult to accurately predict the transmission path and impact range of pollutants or ecological events, and are unable to provide timely and scientific decision-making basis for ecological managers.

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art, ensure the scientificity and flexibility of ecological management, and achieve sustainable protection and restoration of the ecosystem through a digital twin system and construction method for estuaries and bays based on multi-source heterogeneous monitoring data. Summary of the invention

[0005] The present invention provides an estuary and bay digital twin system based on multi-source heterogeneous monitoring data and a construction method thereof.

[0006] A digital twin system for estuaries and bays based on multi-source heterogeneous monitoring data, including a data acquisition and preprocessing module, a spatiotemporal ecological feature extraction module, a spatiotemporal ecological propagation module, an ecological propagation risk assessment module, and a decision support module, wherein; The data acquisition and preprocessing module collects multi-source data from multi-source heterogeneous monitoring equipment, including water quality parameters, pollutant concentrations, vegetation coverage, and tidal data, and preprocesses the collected multi-source data, including denoising, format standardization, spatial alignment, and time synchronization processing; The spatiotemporal ecological feature extraction module extracts ecological features that reflect the dynamic changes of the ecosystem based on spatiotemporal data analysis technology, including pollutant diffusion rate, water quality parameter changes, vegetation cover fluctuations, and tidal change amplitudes; The spatiotemporal ecological propagation module simulates the propagation path and diffusion pattern of multi-source data in the ecosystem in Dingzi Bay and surrounding areas based on the extracted ecological features; The ecological transmission risk assessment module dynamically assesses the potential risks of ecological events to marine life, water quality and coastal vegetation through simulated multi-source data transmission paths and diffusion patterns; The decision support module generates decision suggestions based on the results of risk assessment, including pollution source control, estuary management, and vegetation restoration.

[0007] Optionally, the data acquisition and preprocessing module includes: Data collection: water quality parameters (such as pH value, dissolved oxygen, temperature, etc.) are collected through water quality sensors at fixed monitoring stations, pollutant concentrations (such as heavy metals, chemical pollutants, etc.) are obtained through water quality analysis equipment, drone or satellite image data are collected, optical sensors are used to capture vegetation reflectance spectra, vegetation coverage is calculated through the Normalized Difference Vegetation Index (NDVI), and tidal data (tidal level, tidal velocity) are collected through tidal monitoring equipment; Denoising: Use wavelet transform to denoise the collected multi-source data and remove high-frequency noise in the data; Format standardization: convert the acquisition formats of different devices into a unified format (such as JSON, CSV, etc.); Spatial alignment: Align the spatial coordinate systems of different data sources (such as satellite images and drone images) and use the nearest neighbor interpolation method to spatially transform the images to ensure that data of different spatial scales are aligned in the same coordinate system; Time synchronization processing: The collected multi-source data is synchronized through timestamps. For data sources with different time scales, linear interpolation is used to fill in or adjust time nodes.

[0008] Optionally, the spatiotemporal ecological feature extraction module includes: Pollutant diffusion rate extraction: Based on the pollutant concentration, the pollutant diffusion rate is determined by calculating the concentration changes of pollutants at different time points and spatial locations; Extraction of water quality parameter changes: Use the weighted moving average method to analyze the changing trend of water quality parameters (such as pH value, dissolved oxygen, etc.) over time and smooth the historical water quality data; Vegetation coverage fluctuation extraction: Extract vegetation coverage fluctuation by calculating the fluctuation amplitude (maximum variation range) of vegetation coverage; Tidal variation amplitude extraction: Tidal data recorded by tidal monitoring equipment is used to calculate the difference between the maximum and minimum values ​​of the tidal level during the rise and fall process.

[0009] Optionally, the spatiotemporal ecological communication module includes: Propagation path simulation: Based on the extracted ecological features, the propagation paths of ecological features in Dingzi Bay and surrounding areas were simulated by using a partial differential equation model (PDE); Diffusion pattern simulation: Based on the simulated propagation paths, the Gaussian diffusion model was used to simulate the diffusion patterns of ecological characteristics in Dingzi Bay and surrounding areas.

[0010] Optionally, the propagation path simulation includes: Establish a propagation model of ecological characteristics: Based on the extracted ecological characteristics, a partial differential equation model of the propagation of ecological characteristics in estuaries and bays is constructed, and a two-dimensional diffusion equation is used to describe the propagation path of ecological characteristics; Solving the propagation path: The partial differential equations were solved by the finite difference method to simulate the propagation path of ecological characteristics in Dingzi Bay and its surrounding areas.

[0011] Optionally, the diffusion mode simulation includes: Construct diffusion model: Based on the results of propagation path simulation, the Gaussian diffusion model is used to simulate the diffusion behavior of ecological characteristics in space; Solving the diffusion pattern: Through the Gaussian diffusion model, combined with the initial conditions of the propagation path, the diffusion pattern of ecological characteristics in Dingzi Bay and its surrounding areas is simulated, and the spatial distribution and diffusion trend of the characteristics in the entire area over time are predicted.

[0012] Optionally, the ecological transmission risk assessment module includes: Dynamic risk assessment: Based on the simulated transmission path and diffusion pattern, the weighted risk index method is used to calculate the ecological risk value of ecological events to marine life, water quality and coastal vegetation in real time; Identification of potential risk areas: By analyzing the risk values ​​at each time and location, a spatial risk distribution map reflecting the ecological risk levels of different regions is dynamically generated.

[0013] Optionally, the potential risk area identification includes: Risk level classification: Based on the calculated ecological risk value, each spatial location and time point is classified into a risk level. If the ecological risk value is lower than the lower limit of the risk threshold, it is represented as low risk. If the ecological risk value is between the lower limit of the risk threshold and the upper limit of the risk threshold, it is represented as medium risk. If the ecological risk value is higher than the upper limit of the risk threshold, it is represented as high risk. Generate a spatial risk distribution map: Display the ecological risk level of different areas based on the risk level at each location and time.

[0014] Optionally, the decision support module includes: Pollution source control recommendations: Based on the identified high-risk areas and pollution source locations, combined with the pollutant diffusion paths, recommendations on pollution source control are generated, including reducing emissions, setting up pollution source protection barriers, or strengthening monitoring through analysis of pollutant concentrations and diffusion patterns; Estuary management plan: Based on the simulation results of water quality changes and propagation paths, estuary management suggestions are generated according to the pollution diffusion of estuary water bodies, including river channel dredging, ecological slope protection, and wetland restoration; Vegetation restoration recommendations: Based on the analysis of vegetation cover fluctuations and tidal changes, vegetation restoration recommendations are generated for areas with coastal vegetation degradation or high risk, including restoration of ecological balance through artificial vegetation restoration, protection of coastal vegetation or introduction of salt-tolerant plant populations.

[0015] A method for constructing an estuary and bay digital twin system based on multi-source heterogeneous monitoring data is used to construct the above-mentioned estuary and bay digital twin system based on multi-source heterogeneous monitoring data, comprising the following steps: Data collection and preprocessing: Collect multi-source data, including water quality parameters, pollutant concentrations, vegetation coverage and tidal data, through multi-source heterogeneous monitoring equipment, and perform denoising, format standardization, spatial alignment and time synchronization on the multi-source data; Extraction of spatiotemporal ecological characteristics: Based on spatiotemporal data analysis technology, ecological characteristics are extracted from pre-processed multi-source data, including pollutant diffusion rate, changes in water quality parameters, vegetation cover fluctuations, and tidal change amplitudes; Spatiotemporal ecological propagation simulation: Based on the extracted ecological characteristics, the propagation path and diffusion pattern of multi-source data in Dingzi Bay and surrounding areas are simulated to describe the dynamic change process of multi-source data in space and time; Ecological transmission risk assessment: Based on the simulated transmission paths and diffusion patterns, the potential risks of ecological events to marine life, water quality and coastal vegetation are assessed, and an ecosystem risk map is generated; Decision support: Based on the results of risk assessment, decision recommendations are generated including pollution source control, estuary management and vegetation restoration.

[0016] Beneficial effects of the present invention: The present invention collects a variety of ecological data (such as water quality parameters, pollutant concentrations, vegetation coverage and tidal data) from multi-source heterogeneous monitoring equipment, and performs denoising, format standardization, spatial alignment and time synchronization processing, thereby ensuring the accuracy, consistency and comparability of multi-source data, improving the data processing quality, and providing a solid data foundation for the subsequent extraction of spatiotemporal ecological characteristics and the construction of propagation models, which is conducive to real-time monitoring and analysis of dynamic changes in ecosystems.

[0017] The present invention, through the partial differential equation model and the Gaussian diffusion model, can accurately simulate the propagation path and diffusion pattern of ecological characteristics in Dingzi Bay and surrounding areas. By accurately simulating the dynamic propagation process of ecological characteristics such as pollutants, water quality parameters and vegetation coverage, it can comprehensively predict the changing trend of the ecosystem, provide managers with accurate ecological change predictions, and help identify high-risk areas for pollution spread and vegetation degradation, thereby providing a scientific basis for timely and effective ecological protection measures.

[0018] The present invention generates a dynamic spatial risk distribution map through risk assessment, and provides comprehensive risk assessment and governance recommendations in combination with historical data and simulation results of propagation paths. The decision support module can generate specific recommendations for pollution source control, estuary management, and vegetation restoration based on real-time monitoring data, helping ecological managers to respond quickly to potential ecological threats, optimize governance plans, and enhance the self-repair ability of the ecosystem, thereby ensuring the sustainable development of the ecosystem and the high efficiency of management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention; Figure 2 The figure is a schematic diagram of the construction method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0022] like Figure 1 As shown, a digital twin system of estuaries and bays based on multi-source heterogeneous monitoring data includes a data acquisition and preprocessing module, a spatiotemporal ecological feature extraction module, a spatiotemporal ecological propagation module, an ecological propagation risk assessment module, and a decision support module, wherein; The data acquisition and preprocessing module collects multi-source data from multi-source heterogeneous monitoring equipment, including water quality parameters, pollutant concentrations, vegetation coverage, and tidal data, and preprocesses the collected multi-source data, including denoising, format standardization, spatial alignment, and time synchronization processing; The spatiotemporal ecological feature extraction module extracts ecological features that reflect the dynamic changes of the ecosystem based on spatiotemporal data analysis technology, including pollutant diffusion rate, changes in water quality parameters, vegetation cover fluctuations, and tidal changes. The spatiotemporal ecological propagation module simulates the propagation path and diffusion pattern of multi-source data in the ecosystem in Dingzi Bay and surrounding areas based on the extracted ecological features; The ecological transmission risk assessment module dynamically evaluates the potential risks of ecological events to marine life, water quality, and coastal vegetation through the transmission paths and diffusion patterns of multi-source data based on simulation; The decision support module generates decision recommendations based on the results of risk assessment, including pollution source control, estuary management, and vegetation restoration; Through the above content, it is possible to dynamically and accurately monitor the changes in estuary and bay ecosystems, and evaluate their potential risks to marine life, water quality and vegetation in real time. It can not only provide efficient decision-making support, but also have an adaptive feedback mechanism, which can continuously optimize governance strategies according to actual ecological conditions, improve the scientific nature and flexibility of ecological management, and help to provide timely warnings and take effective ecological protection and restoration measures.

[0023] The data acquisition and preprocessing modules include: Data collection: Water quality parameters (such as pH value, dissolved oxygen, temperature, etc.) are collected through water quality sensors at fixed monitoring sites, pollutant concentrations (such as heavy metals, chemical pollutants, etc.) are obtained through water quality analysis equipment, and drone or satellite image data are collected. Optical sensors are used to capture vegetation reflectance spectra, and vegetation coverage is calculated through the Normalized Difference Vegetation Index (NDVI). Tidal data (tidal level, tidal velocity) are collected through tidal monitoring equipment. The calculation formula for vegetation coverage is: ; Among them, NIR represents the reflectance value of the near-infrared band, RED represents the reflectance value of the red light band, and the value of NDVI is between -1 and 1. The closer the value is to 1, the denser the vegetation coverage. Denoising: Use wavelet transform to denoise the collected multi-source data and remove high-frequency noise in the data, which can be expressed as: ; in, For signal The wavelet transform of is the mother wavelet function, and s are displacement and translation parameters; Format standardization: convert the acquisition formats of different devices into a unified format (such as JSON, CSV, etc.); Spatial alignment: Align the spatial coordinate systems of different data sources (such as satellite images and drone images) and use the nearest neighbor interpolation method to perform spatial transformation on the images to ensure that data of different spatial scales are aligned in the same coordinate system, expressed as: ; in, is the interpolated pixel value in the target image, is the pixel value in the source image, and is the coordinate after geometric transformation Rounded to the nearest integer coordinate of the source image ; Time synchronization processing: The collected multi-source data is synchronized through timestamps. For data sources with different time scales, linear interpolation is used to fill in or adjust the time nodes, which is expressed as: ; in, and are known time points, and is the corresponding sampling value, is the interpolated value; Through the above content, the accuracy, consistency and comparability between different data sources are ensured, the quality of data processing is improved, the precision and reliability of subsequent analysis are ensured, and at the same time, heterogeneous data from different monitoring devices can be analyzed under a unified framework, providing a solid data foundation for dynamic monitoring and propagation modeling of ecosystems.

[0024] The spatiotemporal ecological feature extraction module includes: Pollutant diffusion rate extraction: Based on the pollutant concentration, the pollutant diffusion rate is determined by calculating the concentration changes of pollutants at different time points and spatial locations, which is expressed as: ; in, is the pollutant diffusion rate, is the change in pollutant concentration at different time points, is the time interval; Extraction of water quality parameter changes: Use the weighted moving average method to analyze the changing trend of water quality parameters (such as pH value, dissolved oxygen, etc.) over time, and smooth the historical water quality data, which can be expressed as: ; in, is the weighted average at time point t, is a water quality parameter, is the corresponding weight; Extraction of vegetation cover fluctuation: Extract vegetation cover fluctuation by calculating the fluctuation amplitude of vegetation cover (maximum variation range), expressed as: ; in, is the maximum value in the time period, is the minimum value in the time period; Tidal change amplitude extraction: The tidal data recorded by the tidal monitoring equipment is used to calculate the difference between the maximum and minimum values ​​of the tidal level during the rise and fall process, expressed as: ; Where A represents the tidal variation amplitude, and are the maximum and minimum values ​​of the tide level respectively; Through the above content, it is possible to accurately extract key features that reflect the dynamic changes of ecosystems, such as pollutant diffusion rate, changes in water quality parameters, fluctuations in vegetation cover and tidal changes, through spatiotemporal data analysis technology. It can not only capture changes in ecosystems in real time, but also provide deeper insights into ecological changes through comprehensive analysis of spatiotemporal dimensions, ensure the comprehensiveness and scientific nature of monitoring results, and help ecological managers to promptly identify potential problems and take effective measures.

[0025] The spatiotemporal ecological communication module includes: Propagation path simulation: Based on the extracted ecological features, the propagation paths of ecological features in Dingzi Bay and surrounding areas were simulated by using a partial differential equation model (PDE); Diffusion pattern simulation: Based on the simulated propagation path, the Gaussian diffusion model was used to simulate the diffusion pattern of ecological characteristics in Dingzi Bay and surrounding areas; Through the above content, we can more comprehensively analyze and predict the dynamic changes of ecological characteristics in Dingzi Bay and surrounding areas, accurately capture the directional propagation of ecological characteristics, consider the dynamic changes in space and time, and use the Gaussian diffusion model to effectively predict the spatial distribution and diffusion trend of ecological characteristics. It can provide more accurate predictions of ecological changes and help managers better understand the propagation and diffusion processes of pollutants, water quality and vegetation, thereby providing a scientific basis for ecological protection and management.

[0026] Propagation path simulation includes: Establish a propagation model of ecological characteristics: Based on the extracted ecological characteristics, a partial differential equation model of the propagation of ecological characteristics in estuaries and bay areas is constructed. A two-dimensional diffusion equation is used to describe the propagation path of ecological characteristics, which is expressed as: ; Where C is the concentration or value of the ecological characteristic (such as pollutant concentration, water quality parameter value, etc.), D is the diffusion coefficient, x and y are spatial coordinates, and t is time; Solving the propagation path: The finite difference method is used to solve the partial differential equations to simulate the propagation path of ecological characteristics in Dingzi Bay and its surrounding areas, including: Discretize partial differential equations: Discretize time t and space coordinates x, y, and define them as , and The corresponding discrete points have a time step of , the spatial step length is and , the discretized two-dimensional diffusion equation is expressed as: ; in, For time and location , The concentration of ecological characteristics at is the time step, and are the spatial step length, For the next time step In Location The concentration of ecological characteristics at , are spatially adjacent points and In time The ecological characteristic concentration at , represents the concentration of adjacent points in the x direction, , are spatially adjacent points and In time The ecological characteristic concentration at , represents the concentration of adjacent points in the y direction, and D is the diffusion coefficient, which represents the diffusion rate; Update equations: Reorganize the equations and solve them , that is, the concentration value of the next time step, expressed as: ; Boundary conditions and initial conditions: The initial conditions are to set the initial time When , boundary conditions are set according to the actual ecosystem (such as whether pollutants have reflection, absorption or fixed concentration at the boundary), including Dirichlet boundary conditions (fixed concentration boundary) or Neumann boundary conditions (the concentration derivative at the boundary is zero, indicating no net flow); Results of numerical simulation: Through the iteration of the finite difference method, the propagation path of ecological characteristics that varies with time and space is obtained, showing how pollutants or water quality parameters diffuse from the initial point to the surrounding area; Through the above content, the propagation behavior of ecological characteristics in Dingzi Bay and surrounding areas can be accurately captured, especially the dynamically changing paths in spatial and temporal dimensions. It can simulate how ecological characteristics such as pollutants and water quality parameters are affected by external factors such as topography and tides and propagate along specific paths. It can provide clear propagation path predictions, help ecological managers identify potential pollution risk areas and diffusion directions, and then formulate targeted governance measures.

[0027] Diffusion mode simulation includes: Constructing diffusion model: Based on the results of propagation path simulation, the Gaussian diffusion model is used to simulate the diffusion behavior of ecological characteristics in space. Assuming that the diffusion process conforms to the Gaussian distribution, the diffusion pattern is expressed as: ;in, is the position at time t and space The concentration of ecological characteristics at the location, Q is the intensity of the pollution source or the amount of release from the source, D is the diffusion coefficient, which indicates the diffusion rate of ecological characteristics in space, x, y are spatial coordinates, indicating the position of diffusion on the two-dimensional plane, and t is time; Solving the diffusion pattern: Through the Gaussian diffusion model, combined with the initial conditions of the propagation path, the diffusion pattern of ecological characteristics in Dingzi Bay and its surrounding areas is simulated, and the spatial distribution and diffusion trend of the characteristics in the entire area over time are predicted, including: Initial conditions: Assume that ecological characteristics start from the source Start spreading, initial moment When the concentration at the source is ; Calculate the diffusion at each time step: Use the Gaussian diffusion model to calculate the spatial distribution of ecological characteristics at each time step t; Spatial grid calculation: The simulation area is divided into a spatial grid (x and y grid points in a two-dimensional coordinate system) and the concentration is calculated using a Gaussian diffusion model at each grid point , thus obtaining a concentration distribution map in the entire area, and by calculating point by point, obtaining a complete picture of how the concentration spreads in space over time; Through the above content, combined with the initial conditions of the propagation path, a grid-based approach is used to gradually iterate the calculation, providing a complete diffusion map of ecological characteristics in time and space dimensions. It can intuitively and accurately display the dynamic process of pollutant concentration diffusion over time, which helps ecological managers identify potential high-risk areas, respond in a timely manner and formulate more scientific governance and protection measures.

[0028] The ecological transmission risk assessment module includes: Dynamic risk assessment: Based on the simulated propagation path and diffusion pattern, the weighted risk index method is used to calculate the ecological risk value of ecological events to marine life, water quality and coastal vegetation in real time, expressed as: ; in, For the spatial position and the ecological risk value at time t, is the weight coefficient of different ecological characteristics, indicating the impact of each ecological characteristic on the overall risk. For the location and the concentration or value of the ith ecological characteristic at time t, n is the total number of ecological characteristics involved in the assessment; Identification of potential risk areas: By analyzing the risk values ​​at each time and location, a spatial risk distribution map reflecting the ecological risk level of different areas is dynamically generated; Through the above content, it is possible to accurately calculate the risk distribution of different ecological characteristics in time and space, combine the simulation results of transmission paths and diffusion patterns, generate risk maps of ecosystems in real time, help identify high-risk areas, provide timely early warnings and data support, and continuously monitor changes in ecosystems, providing managers with scientific decision-making basis, helping to quickly formulate protection measures and reduce the potential threats of ecological disasters.

[0029] Identification of potential risk areas includes: Risk level classification: Based on the calculated ecological risk value, each spatial location and time point is classified into a risk level. If the ecological risk value is lower than the lower limit of the risk threshold, it is represented as low risk. If the ecological risk value is between the lower limit of the risk threshold and the upper limit of the risk threshold, it is represented as medium risk. If the ecological risk value is higher than the upper limit of the risk threshold, it is represented as high risk. Generate spatial risk distribution maps: Display ecological risk levels in different regions based on risk levels at different locations and times, which can be updated at different time points to show the impact of pollutants, water quality, vegetation and other ecological characteristics on different areas of the ecosystem; The lower and upper risk thresholds are set based on the distribution of ecological characteristics, including: Data collection: Collect historical data on ecological characteristics (such as pollutant concentrations, water quality changes, vegetation cover, etc.), conduct long-term monitoring in Dingzi Bay and its surrounding areas, and obtain sample data on changes in ecological characteristics over time and space; Calculate the distribution percentile of the feature: the 25th percentile is used as the lower limit of the risk threshold ( ), represents the lower limit of ecological characteristic concentration or change value, below which areas are considered to be at low risk, and the 75th percentile is the upper limit of the risk threshold ( ), represents the boundary of the high-risk area, and the area above this value is high-risk; Through the above content, it is possible to accurately divide low-, medium- and high-risk areas in the ecosystem, and use actual monitoring data and flexible percentile methods to set thresholds, making risk assessment more objective and data-driven, avoiding errors in subjective settings. Combined with the dynamic changes of ecological characteristics, the system can generate spatial risk distribution maps in real time, helping ecological managers to quickly identify high-risk areas and respond to potential ecological threats in a timely manner, thereby improving the scientific nature of decision-making and the effectiveness of responses.

[0030] The decision support modules include: Pollution source control recommendations: Based on the identified high-risk areas and pollution source locations, combined with the pollutant diffusion path, recommendations on pollution source control are generated, including analysis of pollutant concentrations and diffusion patterns, and recommendations on reducing emissions, setting up pollution source protection barriers, or strengthening monitoring to reduce further impacts on marine life and water quality; Estuary management plan: Based on the simulation results of water quality changes and propagation paths, estuary management suggestions are generated according to the pollution diffusion of estuary water bodies, including river channel dredging, ecological slope protection, and wetland restoration, aiming to reduce the spread of water pollution, improve water quality, and strengthen the protection of the surrounding ecological environment; Vegetation restoration recommendations: Based on the analysis of vegetation cover fluctuations and tidal changes, vegetation restoration recommendations are generated for coastal vegetation degradation or high-risk areas, including restoration of ecological balance through artificial vegetation restoration, protection of coastal vegetation or introduction of salt-tolerant plant populations, thereby enhancing the self-repair capacity of the ecosystem; Through the above content, specific decision-making recommendations can be generated for pollution source control, estuary management and vegetation restoration. Combined with data such as the transmission path of ecological characteristics, water quality changes and vegetation coverage fluctuations, scientific and precise management plans can be provided to help managers respond quickly to different ecological risks and take effective measures, such as reducing pollutant emissions, improving estuary water quality, and restoring coastal vegetation, thereby enhancing the self-repair ability of the ecosystem and ensuring the efficiency and sustainability of ecological management.

[0031] like Figure 2 As shown, a method for constructing an estuary and bay digital twin system based on multi-source heterogeneous monitoring data is used to construct the above-mentioned estuary and bay digital twin system based on multi-source heterogeneous monitoring data, comprising the following steps: Data collection and preprocessing: Collect multi-source data, including water quality parameters, pollutant concentrations, vegetation coverage and tidal data, through multi-source heterogeneous monitoring equipment, and perform denoising, format standardization, spatial alignment and time synchronization on the multi-source data; Extraction of spatiotemporal ecological characteristics: Based on spatiotemporal data analysis technology, ecological characteristics are extracted from pre-processed multi-source data, including pollutant diffusion rate, changes in water quality parameters, vegetation cover fluctuations, and tidal change amplitudes; Spatiotemporal ecological propagation simulation: Based on the extracted ecological characteristics, the propagation path and diffusion pattern of multi-source data in Dingzi Bay and surrounding areas are simulated to describe the dynamic change process of multi-source data in space and time; Ecological transmission risk assessment: Based on the simulated transmission paths and diffusion patterns, the potential risks of ecological events to marine life, water quality and coastal vegetation are assessed, and an ecosystem risk map is generated; Decision support: Based on the results of risk assessment, decision recommendations are generated including pollution source control, estuary management and vegetation restoration.

[0032] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0033] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A digital twin system for estuaries and bays based on multi-source heterogeneous monitoring data, characterized in that: It includes data collection and preprocessing module, spatiotemporal ecological feature extraction module, spatiotemporal ecological communication module, ecological communication risk assessment module and decision support module, among which; The data acquisition and preprocessing module collects multi-source data from multi-source heterogeneous monitoring equipment, including water quality parameters, pollutant concentrations, vegetation coverage, and tidal data, and preprocesses the collected multi-source data, including denoising, format standardization, spatial alignment, and time synchronization processing; The spatiotemporal ecological feature extraction module extracts ecological features that reflect the dynamic changes of the ecosystem based on spatiotemporal data analysis technology, including pollutant diffusion rate, water quality parameter changes, vegetation cover fluctuations, and tidal change amplitudes; The spatiotemporal ecological propagation module simulates the propagation path and diffusion pattern of multi-source data in the ecosystem in Dingzi Bay and surrounding areas based on the extracted ecological features; The ecological transmission risk assessment module dynamically assesses the potential risks of ecological events to marine life, water quality and coastal vegetation through simulated multi-source data transmission paths and diffusion patterns; The decision support module generates decision suggestions based on the results of risk assessment, including pollution source control, estuary management, and vegetation restoration.

2. According to claim 1, a digital twin system for estuaries and bays based on multi-source heterogeneous monitoring data is characterized in that: The data acquisition and preprocessing module includes: Data collection: water quality parameters are collected through water quality sensors at fixed monitoring sites, pollutant concentrations are obtained through water quality analysis equipment, drone or satellite image data are collected, vegetation reflectance spectra are captured using optical sensors, vegetation coverage is calculated using the normalized vegetation index, and tidal data are collected through tidal monitoring equipment; Denoising: Use wavelet transform to denoise the collected multi-source data and remove high-frequency noise in the data; Format standardization: convert the acquisition formats of different devices into a unified format; Spatial alignment: Align the spatial coordinate systems of different data sources and use the nearest neighbor interpolation method to perform spatial transformation on the images to ensure that data of different spatial scales are aligned in the same coordinate system; Time synchronization processing: The collected multi-source data is synchronized through timestamps. For data sources with different time scales, linear interpolation is used to fill in or adjust time nodes.

3. According to claim 1, a digital twin system for estuaries and bays based on multi-source heterogeneous monitoring data is characterized in that: The spatiotemporal ecological feature extraction module includes: Pollutant diffusion rate extraction: Based on the pollutant concentration, the pollutant diffusion rate is determined by calculating the concentration changes of pollutants at different time points and spatial locations; Extraction of water quality parameter changes: Use the weighted moving average method to analyze the changing trend of water quality parameters over time and smooth the historical water quality data; Vegetation cover fluctuation extraction: Extract vegetation cover fluctuation by calculating the fluctuation amplitude of vegetation cover; Tidal variation amplitude extraction: Tidal data recorded by tidal monitoring equipment is used to calculate the difference between the maximum and minimum values ​​of the tidal level during the rise and fall process.

4. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 1 is characterized in that: The spatiotemporal ecological communication module includes: Propagation path simulation: Based on the extracted ecological features, the propagation paths of ecological features in Dingzi Bay and surrounding areas were simulated by using a partial differential equation model; Diffusion pattern simulation: Based on the simulated propagation paths, the Gaussian diffusion model was used to simulate the diffusion patterns of ecological characteristics in Dingzi Bay and surrounding areas.

5. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 4 is characterized in that: The propagation path simulation includes: Establish a propagation model of ecological characteristics: Based on the extracted ecological characteristics, a partial differential equation model of the propagation of ecological characteristics in estuaries and bays is constructed, and a two-dimensional diffusion equation is used to describe the propagation path of ecological characteristics; Solving the propagation path: The partial differential equations were solved by the finite difference method to simulate the propagation path of ecological characteristics in Dingzi Bay and its surrounding areas.

6. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 5 is characterized in that: The diffusion mode simulation includes: Construct diffusion model: Based on the results of propagation path simulation, the Gaussian diffusion model is used to simulate the diffusion behavior of ecological characteristics in space; Solving the diffusion pattern: Through the Gaussian diffusion model, combined with the initial conditions of the propagation path, the diffusion pattern of ecological characteristics in Dingzi Bay and its surrounding areas is simulated, and the spatial distribution and diffusion trend of the characteristics in the entire area over time are predicted.

7. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 1 is characterized in that: The ecological transmission risk assessment module includes: Dynamic risk assessment: Based on the simulated transmission path and diffusion pattern, the weighted risk index method is used to calculate the ecological risk value of ecological events to marine life, water quality and coastal vegetation in real time; Identification of potential risk areas: By analyzing the risk values ​​at each time and location, a spatial risk distribution map reflecting the ecological risk levels of different regions is dynamically generated.

8. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 7 is characterized in that: The identification of potential risk areas includes: Risk level classification: Based on the calculated ecological risk value, each spatial location and time point is classified into a risk level. If the ecological risk value is lower than the lower limit of the risk threshold, it is represented as low risk. If the ecological risk value is between the lower limit of the risk threshold and the upper limit of the risk threshold, it is represented as medium risk. If the ecological risk value is higher than the upper limit of the risk threshold, it is represented as high risk. Generate a spatial risk distribution map: Display the ecological risk level of different areas based on the risk level at each location and time.

9. The estuary and bay digital twin system based on multi-source heterogeneous monitoring data according to claim 8 is characterized in that: The decision support module includes: Pollution source control recommendations: Based on the identified high-risk areas and pollution source locations, combined with the pollutant diffusion paths, recommendations on pollution source control are generated, including reducing emissions, setting up pollution source protection barriers, or strengthening monitoring through analysis of pollutant concentrations and diffusion patterns; Estuary management plan: Based on the simulation results of water quality changes and propagation paths, estuary management suggestions are generated according to the pollution diffusion of estuary water bodies, including river channel dredging, ecological slope protection, and wetland restoration; Vegetation restoration recommendations: Based on the analysis of vegetation cover fluctuations and tidal changes, vegetation restoration recommendations are generated for areas with coastal vegetation degradation or high risk, including restoration of ecological balance through artificial vegetation restoration, protection of coastal vegetation or introduction of salt-tolerant plant populations.

10. A method for constructing a digital twin system of an estuary and bay based on multi-source heterogeneous monitoring data, used to construct a digital twin system of an estuary and bay based on multi-source heterogeneous monitoring data as described in any one of claims 1 to 9, characterized in that: The following steps are involved: Data collection and preprocessing: Collect multi-source data, including water quality parameters, pollutant concentrations, vegetation coverage and tidal data, through multi-source heterogeneous monitoring equipment, and perform denoising, format standardization, spatial alignment and time synchronization on the multi-source data; Extraction of spatiotemporal ecological characteristics: Based on spatiotemporal data analysis technology, ecological characteristics are extracted from pre-processed multi-source data, including pollutant diffusion rate, changes in water quality parameters, vegetation cover fluctuations, and tidal change amplitudes; Spatiotemporal ecological propagation simulation: Based on the extracted ecological characteristics, the propagation path and diffusion pattern of multi-source data in Dingzi Bay and surrounding areas are simulated to describe the dynamic change process of multi-source data in space and time; Ecological transmission risk assessment: Based on the simulated transmission paths and diffusion patterns, the potential risks of ecological events to marine life, water quality and coastal vegetation are assessed, and an ecosystem risk map is generated; Decision support: Based on the results of risk assessment, decision recommendations are generated including pollution source control, estuary management and vegetation restoration.

Citation Information

Patent Citations

  • Gas-soil-water coupling simulation forecasting method for urban ecological environment

    CN114491927A

  • River water quality real-time monitoring platform

    CN118052450A

  • Marine ecological environment prediction and evaluation system based on artificial intelligence

    CN118095972A

  • Lake desilting project sediment environment assessment method

    CN118330173A

  • Estuary bay early warning management method and system based on digital twinning

    CN118657497A

Cited By

  • River model multi-data processing analysis method and system

    CN119476131A

  • A multi-data processing and analysis method and system for river engineering models

    CN119476131B

  • Drinking water detection result calibration method based on multi-source data

    CN119513504A

  • Intelligent runoff pollution monitoring and responding method and system

    CN119642902A

  • Dangerous chemical leakage and diffusion prediction method and system based on unmanned ship, and storage medium

    CN119720867A