Damage assessment system for deep-sea polymetallic nodule mining disturbance to benthic ecosystems

Abstract

The present invention relates to the technical field of deep-sea resource development, and specifically to a damage assessment system for deep-sea polymetallic nodule test mining disturbance to benthic ecosystems, comprising a data acquisition module, an ecological baseline model construction module, a disturbance simulation module, an ecological impact assessment module, a decision support module, a feedback learning module and a visualization module, wherein the data acquisition module monitors the ecological environment data of the test mining area in real time, the ecological baseline model construction module constructs an ecological baseline model of the test mining area to ensure the scientific nature of the assessment, the disturbance simulation module predicts the impact of different test mining schemes on water flow patterns, sediments and biological habitats, the ecological impact assessment module analyzes the impact of mining activities on benthic organisms through an assessment model, the decision support module provides an optimized management strategy according to the assessment results, the feedback learning module is used to iteratively update the assessment model, and the visualization module displays the assessment results in an intuitive form. The present invention provides a more accurate ecological impact assessment for mining activities.

Description

Technical Field

[0001] The present invention relates to the technical field of deep-sea resource development, and in particular to a system for assessing damage to benthic ecosystems caused by disturbances in deep-sea polymetallic nodule test mining. Background Art

[0002] As an important marine mineral resource, deep-sea polymetallic nodules have attracted global attention in recent years. With the advancement of science and technology and the increasing demand for marine resource development, the mining of deep-sea nodules has gradually become a feasible way to develop mineral resources. However, the trial mining of deep-sea nodules may have potential damage to the marine benthic ecosystem. As an important part of the deep-sea ecosystem, the growth environment of benthic organisms is affected by many factors such as water flow, sediment, temperature, and salinity. As mining activities proceed, the trial mining area may experience changes in water flow patterns, sediment disturbance, and changes in biological habitats. These changes may lead to a reduction in species abundance, an imbalance in community structure, and a loss of ecological functions.

[0003] At present, ecological impact assessments for deep-sea mineral resource mining mainly rely on traditional monitoring and assessment methods, which are usually based on qualitative analysis of empirical or simplified ecological models, lacking accurate prediction and dynamic assessment of test mining disturbances. Most assessment methods are difficult to provide real-time and comprehensive ecological monitoring data, resulting in the inability to timely discover and respond to ecological risks that may arise in test mining activities. Existing disturbance simulation methods mostly focus on a single ecological factor, ignoring the interaction of multiple factors such as water flow, sediment resuspension and habitat changes. Therefore, in the ecological damage assessment of deep-sea polymetallic nodule test mining activities, existing technologies cannot achieve comprehensive, dynamic and high-precision impact assessments of mining activities, and it is difficult to provide decision makers with reliable management basis and response strategies. Summary of the invention

[0004] The present invention provides a system for assessing damage to benthic ecosystems caused by disturbance caused by deep-sea polymetallic nodule trial mining.

[0005] The damage assessment system for the disturbance of deep-sea polymetallic nodule test mining to benthic ecosystems includes a data acquisition module, an ecological baseline model construction module, a disturbance simulation module, an ecological impact assessment module, a decision support module, a feedback learning module and a visualization module, among which;

[0006] The data acquisition module monitors the ecological data of the test area in real time through sensor networks and remote sensing technology, including temperature, salinity, sediment characteristics, biological community structure and biodiversity;

[0007] The ecological baseline model building module uses historical ecological data and existing biodiversity information to build an ecological baseline model for the test mining area, which is used to compare and evaluate ecological changes before and after mining disturbance;

[0008] The disturbance simulation module uses numerical simulation methods to predict the disturbance of different trial mining schemes, including the impact on changes in water flow patterns, sediment resuspension and biological habitats, so as to evaluate the potential impact of disturbances of different trial mining schemes on ecological functions;

[0009] The ecological impact assessment module constructs an assessment model based on the ecological data collected by the data acquisition module and the output of the disturbance simulation module to assess the impact of mining activities on benthic organisms, including species abundance, changes in community structure, and loss of ecological functions;

[0010] The decision support module provides suggestions and management strategies based on the assessment results of the ecological impact assessment module to reduce the damage of mining activities to the ecosystem. The suggestions and management strategies include adjusting the mining intensity and time window and formulating ecological restoration measures.

[0011] The feedback learning module collects ecological data after the test mining, and iteratively updates the evaluation model through the gradient boosting algorithm to improve the evaluation accuracy and adaptability;

[0012] The visualization module is used to present the real-time monitored ecological data and evaluation results in a visualized form.

[0013] Optionally, the data acquisition module includes:

[0014] Arrange the sensor network, select multiple monitoring points in the test mining area, configure water temperature and salinity sensors, and ensure that the distance between sensors does not exceed 50 meters to achieve high-density data collection. Use water temperature and salinity sensors to continuously monitor the temperature and salinity data of the water body;

[0015] Sediment sampling technology is used to randomly select multiple sampling points in the test area. Sediment samples are collected using sediment sampling tubes according to the stratified sampling method. The collected sediment samples are then subjected to laboratory analysis, including particle size distribution, chemical composition (such as heavy metal content, nutrient content) and organic matter content, to obtain sediment characteristic data;

[0016] Conduct biodiversity surveys using standard plot survey methods. In each plot, record all species observed and their number of individuals, and classify species using a species identification manual;

[0017] Through the analysis of biological community structure, the species diversity of each site is evaluated using diversity indices (such as the Shannon index), while the community evenness is calculated to analyze the relative distribution of different species in the ecosystem;

[0018] The collected ecological data (including water temperature, salinity, sediment characteristics, biodiversity and community structure) are transmitted to a preset central processing unit to ensure a uniform data format for subsequent processing. In the central processing unit, a comprehensive data repository is established to integrate ecological data from different sensors and sample sites.

[0019] Optionally, the ecological baseline model construction module specifically includes:

[0020] Collect historical ecological data, including previous biodiversity survey results, species abundance, community structure, sediment characteristics, water temperature, and salinity data in the test mining area;

[0021] Integrate existing biodiversity information and compile data on species distribution and ecological function from regional or global databases, including existing species lists and distribution data on habitat types;

[0022] Using the real-time ecological data provided by the data acquisition module, we conduct a detailed analysis of the ecological environment at different depths and terrain conditions within the pilot mining area, ensuring that depth gradients and terrain features (such as slope and seabed structure) are taken into account in the model;

[0023] Based on historical ecological data and real-time ecological data, the ecological baseline model is constructed using the support vector machine regression algorithm;

[0024] Model validation was conducted to evaluate the accuracy and effectiveness of the model by comparing and analyzing the ecological data around the test mining area or other known areas.

[0025] Optionally, the disturbance simulation module specifically includes:

[0026] Select numerical simulation methods, establish a three-dimensional ocean circulation model, and numerically simulate the water flow pattern in the test mining area;

[0027] In a three-dimensional ocean circulation model, simulate the impact of different trial mining plans (such as mining intensity, mining time, mining area, etc.) on water flow patterns, including seawater flow velocity, flow direction, water temperature and salinity;

[0028] Based on the simulation results, the effects of different trial mining schemes on water flow patterns were analyzed, including changes in flow velocity, generation of vortices, and turbulence of water flow;

[0029] Assess the impact of water flow disturbances on ecosystems by analyzing changes in water flow patterns to assess their impact on aquatic habitats.

[0030] Optionally, the disturbance simulation module further includes:

[0031] Select the numerical simulation method and use the k-ε turbulence model to simulate the sediment resuspension process;

[0032] In the process of simulating the resuspension of sediments using the k-ε turbulence model, different disturbance sources of test mining schemes were set, such as bottom disturbance during test mining, changes in water flow velocity, etc., to simulate the resuspension of sediment particles under different disturbance sources. By simulating different intensities, operating depths and mining methods of mining operations, the resuspension degree of sediment particles under different test mining schemes was predicted.

[0033] The k-ε turbulence model was used to simulate the process of sediment resuspension in water flow, and the impact of different trial mining schemes on the benthic habitat was analyzed.

[0034] Optionally, the ecological impact assessment module includes:

[0035] Collect ecological data collected by the data collection module, including temperature, salinity, sediment properties, biome structure, and biodiversity data;

[0036] Collect output data from the disturbance simulation module, including simulation results of changes in water flow patterns, sediment resuspension processes, and changes in biological habitats;

[0037] Construct an assessment model by combining the ecological data from the data acquisition module with the output of the disturbance simulation module to establish a comprehensive assessment framework;

[0038] According to the assessment model, multiple ecological assessment indicators are set, including changes in species abundance, changes in community structure, and loss of ecological functions;

[0039] Based on the output of the assessment model, a detailed ecological impact report is generated, which includes quantitative assessments of benthic communities, species abundance, and ecological functions.

[0040] Optionally, the decision support module specifically includes:

[0041] Receive the results of the ecological impact assessment module, which includes an analysis of the impacts of mining activities on benthic ecosystems, covering changes in species abundance, changes in community structure, sediment disturbance, and loss of ecological functions;

[0042] According to the assessment results, specific decision-making goals are set, such as minimizing the loss of ecological functions, maintaining biodiversity, optimizing benthic habitats, etc. At the same time, constraints are set, including ecological safety requirements, mining intensity, resource consumption, and environmental protection standards during the mining process;

[0043] Provide management strategies for adjusting mining intensity and time windows, analyze the impacts of different mining intensities and time windows on benthic ecosystems based on the results of ecological impact assessment, and propose optimization plans;

[0044] Based on the results of the ecological impact assessment, propose appropriate ecological restoration plans to repair the ecological damage caused by mining activities;

[0045] Provide feedback mechanisms and dynamic adjustment plans to adjust management strategies based on real-time monitoring data and post-evaluation results;

[0046] The decision support module generates a detailed decision recommendation report, which includes mining intensity adjustment plan, time window optimization plan and ecological restoration measures.

[0047] Optionally, the feedback learning module specifically includes:

[0048] After the trial mining, the feedback learning module receives the ecological data monitored in real time from the data collection module;

[0049] Preprocess the collected ecological data after the test mining, including data cleaning, noise removal and missing value filling;

[0050] According to the characteristics of the post-test mining data and the requirements of the ecological impact assessment task, the gradient boosting algorithm was selected to iteratively update the assessment model;

[0051] Feed the iteratively updated assessment model back to the ecological impact assessment module to achieve dynamic updates;

[0052] Adjust management strategies and ecological restoration measures for mining activities based on the updated assessment model.

[0053] Optionally, the visualization module specifically includes:.

[0054] The visualization module receives real-time ecological data from the data acquisition module, including temperature, salinity, sediment properties, biome structure, and biodiversity data;

[0055] The visualization module receives assessment output data from the ecological impact assessment module based on ecological data and disturbance simulation results, including species abundance, community structure changes, and ecological function loss;

[0056] Integrate real-time monitoring ecological data with assessment results to form a comprehensive data view;

[0057] Select visualization methods based on data characteristics and presentation requirements, including heat maps, species distribution maps, community structure maps, bar charts, line charts, and time series charts;

[0058] The visualization module provides an interactive interface to support decision makers and relevant personnel to dynamically view and operate data.

[0059] Beneficial effects of the present invention:

[0060] The present invention realizes real-time ecological monitoring and dynamic evaluation of deep-sea polymetallic nodule test mining areas through close cooperation of data acquisition module, disturbance simulation module and ecological impact assessment module. The data acquisition module uses sensor network and remote sensing technology to monitor ecological environment parameters in real time, such as temperature, salinity, sediment characteristics and biological community structure, and provides accurate and timely data support for disturbance simulation and evaluation. Through the numerical prediction of the disturbance simulation module, combined with the analysis of the ecological impact assessment module, the potential impact of mining activities on benthic ecosystems can be timely evaluated, ensuring that ecological protection decisions are timely and accurate.

[0061] The present invention, relying on the decision support module, can provide scientific management strategies and optimization suggestions based on the results of ecological impact assessment, including adjusting mining intensity, adjusting mining time windows, and formulating corresponding ecological restoration measures. Through the visualization module, decision makers can intuitively understand and analyze ecological impacts, quickly identify potential ecological damage risks, and thus formulate reasonable mining plans and ecological restoration plans to minimize the damage of test mining activities to benthic organisms and the ecological environment.

[0062] In the present invention, the feedback learning module uses a gradient boosting algorithm to learn and iteratively update the ecological data after the test mining in real time. The module optimizes the accuracy and adaptability of the evaluation model by analyzing the new ecological data after the test mining, thereby realizing long-term dynamic monitoring and real-time evaluation. Through this continuous update and adaptive adjustment, the system can adjust the model and evaluation strategy in time according to the changes in the mining process, provide more accurate ecological impact assessment for future mining activities, and ensure the scientificity and effectiveness of ecological protection measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] 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.

[0064] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0065] Figure 2 Schematic diagram of the disturbance simulation module flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] 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.

[0067] like Figure 1-Figure 2 As shown, the damage assessment system for deep-sea polymetallic nodule test mining disturbance to benthic ecosystems includes a data acquisition module, an ecological baseline model construction module, a disturbance simulation module, an ecological impact assessment module, a decision support module, a feedback learning module and a visualization module, among which;

[0068] The data acquisition module monitors the ecological data of the test area in real time through sensor networks and remote sensing technology, including temperature, salinity, sediment characteristics, biological community structure and biodiversity;

[0069] The ecological baseline model building module uses historical ecological data and existing biodiversity information to build an ecological baseline model for the test mining area, which is used to compare and evaluate ecological changes before and after mining disturbances, ensuring that the model considers the impact of different depths and terrains on ecology;

[0070] The disturbance simulation module uses numerical simulation methods to predict the disturbance of different trial mining schemes, including the impact on changes in water flow patterns, sediment resuspension and biological habitats, so as to evaluate the potential impact of disturbances of different trial mining schemes on ecological functions;

[0071] The ecological impact assessment module constructs an assessment model based on the ecological data collected by the data acquisition module and the output of the disturbance simulation module to assess the impact of mining activities on benthic organisms, including species abundance, changes in community structure, and loss of ecological functions;

[0072] The decision support module provides suggestions and management strategies based on the assessment results of the ecological impact assessment module to reduce the damage of mining activities to the ecosystem. The suggestions and management strategies include adjusting the mining intensity and time window and formulating ecological restoration measures.

[0073] The feedback learning module collects ecological data after the test mining, iteratively updates the assessment model through the gradient boosting algorithm, improves the assessment accuracy and adaptability, and realizes dynamic monitoring and assessment;

[0074] The visualization module is used to present the real-time monitored ecological data and assessment results in a visualized form, so as to facilitate relevant decision makers and stakeholders to understand the ecological impacts and management recommendations.

[0075] Optionally, the data acquisition module includes:

[0076] Arrange the sensor network, select multiple monitoring points in the test mining area, configure water temperature and salinity sensors, ensure that the distance between sensors does not exceed 50 meters, so as to achieve high-density data collection, continuously monitor the temperature and salinity data of the water body through water temperature and salinity sensors, set the sampling frequency to once an hour, to ensure real-time reflection of water environment changes;

[0077] Sediment sampling technology was used to randomly select multiple sampling points in the test area. Sediment samples were collected using sediment sampling tubes according to the stratified sampling method (e.g., 0-5 cm, 5-10 cm, 10-15 cm depth). The collected sediment samples were subjected to laboratory analysis, including particle size distribution, chemical composition (e.g., heavy metal content, nutrient content), and organic matter content, to obtain sediment characteristic data;

[0078] Conduct biodiversity surveys using standard plot survey methods, set the area of ​​each plot to 10 square meters, and randomly arrange at least 10 plots in the trial sampling area. In each plot, record all observed species and their individual numbers, and use the species identification manual to classify species to ensure accurate recording of the abundance of each species;

[0079] Through the analysis of biological community structure, the species diversity of each site is evaluated using diversity indices (such as the Shannon index), while the community evenness is calculated to analyze the relative distribution of different species in the ecosystem;

[0080] The collected ecological data (including water temperature, salinity, sediment characteristics, biodiversity and community structure) are transmitted to a pre-set central processing unit to ensure that the data format is unified for subsequent processing. In the central processing unit, a comprehensive data repository is established to integrate ecological data from different sensors and sample sites to ensure easy access and traceability of the data;

[0081] Regularly update and calibrate the collected ecological data, and conduct a comprehensive review every month to ensure the accuracy and timeliness of the data and to promptly reflect the changes in the ecological environment in the test mining area;

[0082] The data acquisition module can comprehensively monitor the ecological data of the test and sampling area, and collect data on water environment, sediment characteristics, biodiversity and community structure. This provides an accurate and rich data basis for the subsequent construction of the ecological baseline model and ecological impact assessment, and enhances the scientificity and effectiveness of the assessment system.

[0083] Optionally, the ecological baseline model construction module specifically includes:

[0084] Collect historical ecological data, including previous biodiversity survey results, species abundance, community structure, sediment characteristics, water temperature, and salinity data in the test mining area;

[0085] Integrate existing biodiversity information and compile data on species distribution and ecological function from regional or global databases, including existing species lists and distribution data on habitat types;

[0086] Using the real-time ecological data provided by the data acquisition module, we conduct a detailed analysis of the ecological environment at different depths and terrain conditions within the pilot mining area, ensuring that depth gradients and terrain features (such as slope and seabed structure) are taken into account in the model;

[0087] Based on historical ecological data and real-time ecological data, the support vector machine regression algorithm is used to construct an ecological baseline model. The specific steps are as follows:

[0088] (1) Clean and preprocess the collected historical ecological data, real-time data, and existing biodiversity information, including filling missing values, removing outliers, standardizing data (e.g., standardizing parameters such as temperature, salinity, and sediment characteristics to the same dimension), and normalizing the data so that the values ​​of all input features are within the same numerical range;

[0089] (2) Select key features related to the ecological status of the test mining area as input variables, including water temperature, salinity, sediment characteristics, species abundance, etc., and eliminate redundant and low-correlation variables based on feature selection algorithms (such as chi-square test, information gain or mutual information method) to improve the training efficiency and prediction accuracy of the model;

[0090] (3) Divide the preprocessed data set into a training set and a test set (e.g., 70% for training and 30% for testing). Use the support vector machine regression algorithm, select a suitable kernel function (e.g., radial basis kernel function, RBF), and set appropriate hyperparameters (e.g., C, ε, etc.). Use the training set to train the ecological baseline model to fit the nonlinear relationship between ecosystem variables (e.g., temperature, salinity, species abundance, etc.) and ecological status.

[0091] (4) Adjust the hyperparameters of the ecological baseline model through cross-validation (such as k-fold cross-validation) to further optimize the model's predictive performance, and use grid search or random search to adjust the parameters to ensure the generalization ability of the model;

[0092] (5) Use the test set to verify the trained ecological baseline model and calculate the model performance indicators (such as mean square error (MSE) and coefficient of determination (R²)) to evaluate the accuracy and robustness of the model. If the model error is large, further parameter adjustment or selection of different features for modeling is required;

[0093] (6) Based on the trained ecological baseline model, output the ecological baseline status of the test mining area at different depths and terrain conditions, and predict the potential change trend of the ecosystem under different disturbance scenarios. The ecological baseline model will take into account the influence of multiple factors such as regional hydrology, sediments and biological communities, and provide benchmark data for subsequent disturbance simulation and ecological impact assessment;

[0094] When constructing the model, ecological theory is combined to consider the spatial heterogeneity of the ecosystem (such as the spatial pattern of species distribution) and temporal changes (such as seasonal fluctuations) to ensure that the model reflects the multi-dimensional nature of the ecosystem;

[0095] Conduct model validation by comparing and analyzing the ecological data around the test mining area or other known areas to evaluate the accuracy and effectiveness of the model. If necessary, conduct on-site verification to correct model deviations;

[0096] The constructed ecological baseline model is input into the central processing unit to support subsequent disturbance simulation and ecological impact assessment, and serves as a comparative benchmark for evaluating ecological changes before and after mining disturbance;

[0097] The ecological baseline model construction module is modeled in detail through the support vector machine regression algorithm. It adopts systematic steps including data preprocessing, feature selection, model training and optimization to construct an ecological baseline model that adapts to different depths and terrain conditions. Through this method, it can accurately reflect the complex ecosystem characteristics of the test mining area, and provide reliable benchmark data for subsequent disturbance simulation and ecological impact assessment, thereby enhancing the accuracy and scientificity of the assessment system.

[0098] Optionally, the disturbance simulation module specifically includes:

[0099] Select the numerical simulation method, establish a three-dimensional ocean circulation model, and numerically simulate the water flow pattern in the test area. The specific steps are as follows:

[0100] (1) Collect basic hydrological data of the test mining area, including current speed, direction, seawater temperature, salinity distribution, tidal changes, seasonal climate changes, wind speed and direction, etc. At the same time, collect topographic data (such as seabed topography, slope, depth changes, etc.) to provide a basis for setting boundary conditions of subsequent models;

[0101] (2) According to the area, depth and complexity of the test mining area, the appropriate spatial resolution is selected for grid division. The three-dimensional ocean circulation model uses the finite difference method to divide the study area into multiple small grid cells. Each grid cell represents a calculation point. At the boundary of the area, the degree of grid refinement is set according to the actual situation to ensure higher resolution in key areas (such as around the mining area and areas sensitive to sediment disturbance);

[0102] (3) Based on the collected hydrogeological data, the boundary conditions of the three-dimensional ocean circulation model are set, including:

[0103] (3.1) External boundary conditions: sea surface meteorological conditions (such as wind speed, temperature, air pressure), ocean current data away from the test mining area, tidal conditions, etc.;

[0104] (3.2) Internal boundary conditions: sediment characteristics within the test mining area (e.g., particle size, density, sedimentation rate, etc.), and the interaction between the bottom sediment and the water column;

[0105] At the same time, the initial state of the model (such as initial water flow velocity, temperature, salinity, etc.) is set to ensure that the model can reflect the basic environmental conditions in the area at the beginning;

[0106] (4) The three-dimensional ocean circulation model is based on the Navier-Stokes equations. It describes the movement of fluids in the ocean by considering the transfer of momentum, mass, and heat of the water flow. The model solves the changes in the flow field through non-static time steps and calculates the velocity, direction, vortex, and turbulence of the water flow.

[0107] (4.1) Calculate water flow velocity: solve the momentum equation of water flow to obtain the velocity distribution of the water body;

[0108] (4.2) Calculate the change of flow field: predict the change of water flow by coupling the continuity equation and momentum equation;

[0109] (4.3) Calculate the physical properties of water bodies: such as the distribution of temperature and salinity, and its interaction with sediments;

[0110] (5) Setting different disturbance sources in the 3D ocean circulation model. These disturbance sources can come from test mining activities, such as the intensity of mining operations, the location of the mining area, and the water disturbances generated during the mining process (such as changes in water flow velocity, fluctuations in dissolved oxygen concentration, and suspension of particulate matter). By simulating these disturbances, the impact of test mining activities on water flow patterns and water quality can be predicted;

[0111] (5.1) Disturbance source setting: By adding disturbance sources related to the trial mining plan (such as mining equipment, mining depth, mining intensity, etc.) to the model, the disturbance to the water flow during the mining process is simulated;

[0112] (5.2) Changes in water flow patterns: Simulate the changes in water flow velocity and direction caused by disturbance sources, especially the impact in the test mining area and its surrounding areas;

[0113] (5.3) Sediment disturbance: Analyze the degree of disturbance of the underlying sediments by mining activities and predict the sediment resuspension effect;

[0114] (6) Based on the set initial conditions, boundary conditions and disturbance sources, the model is simulated in time stepping mode to calculate the changes in water flow at different time nodes. By setting an appropriate time step, multiple simulations are performed to predict the long-term impact of mining activities on water flow patterns and examine the dynamic evolution of changes in water flow patterns;

[0115] (7) The simulation results output includes data such as water velocity distribution, flow direction distribution, and vortex generation under different trial mining schemes. At the same time, combined with the changes in these water flow patterns, the impact of water flow on sediment resuspension and benthic habitat is further analyzed to provide a preliminary assessment of the potential impact of water flow pattern changes on the ecosystem;

[0116] (8) Verify the accuracy of the ROMS model by comparing it with the actual observation data. If there is a large deviation between the model's prediction results and the actual observation data, adjust the model parameters, grid resolution, boundary conditions, etc. to further improve the model's accuracy.

[0117] In a three-dimensional ocean circulation model, simulate the impact of different trial mining plans (such as mining intensity, mining time, mining area, etc.) on water flow patterns, including seawater flow velocity, flow direction, water temperature and salinity;

[0118] Based on the simulation results, the impact of different trial mining schemes on water flow patterns was analyzed, including changes in flow velocity, the generation of vortices, and the turbulence of water flow, with a focus on analyzing the possibility of disturbance and suspension effects of water flow disturbance on bottom sediments;

[0119] Assess the impact of water flow disturbance on the ecosystem by analyzing the changes in water flow patterns and evaluating its impact on aquatic habitats, especially the destruction of benthic habitats and changes in habitat structure;

[0120] By using a three-dimensional ocean circulation model to numerically simulate water flow patterns, the disturbance simulation module can accurately predict the impact of different trial mining plans on water flow patterns and evaluate the potential impact of water flow changes on benthic habitats. This method provides high-precision data support for subsequent ecological function assessments.

[0121] Optionally, the disturbance simulation module further includes:

[0122] Select numerical simulation methods, use k-ε turbulence model to simulate sediment resuspension process, collect sediment characteristic data (such as particle size, sediment density, organic matter content in sediment, etc.) and relevant parameters of water flow (such as flow velocity, flow direction, shear force, etc.) in the test mining area, including:

[0123] (1) Set initial conditions and boundary conditions:

[0124] (1.1) Initial conditions: In the k-ε turbulence model, the initial conditions for the flow field are first set. The conditions include the initial velocity, flow direction, turbulent kinetic energy and turbulent dissipation rate of the water flow. The specific data can be obtained through field measurements or historical data. The initial velocity and flow direction can be set based on hydrological data, and the turbulent kinetic energy and turbulent dissipation rate can be obtained through experiments or preliminary estimates.

[0125] (1.2) Boundary conditions: The setting of boundary conditions includes:

[0126] (1.21) External boundary conditions: factors such as wind speed, air pressure, tidal fluctuations on the sea surface, and water flow boundaries away from the mining area;

[0127] (1.22) Internal boundary conditions: physical properties of bottom sediments, including particle size distribution, density, particle diameter and morphology. In addition, the interaction between water and bottom sediments, especially the suspension and deposition rate of particles, also need to be set as boundary conditions.

[0128] (2) Establish the turbulent kinetic energy equation and the turbulent dissipation rate equation: In the model, the intensity of turbulence is determined by the turbulent kinetic energy (k) and the turbulent dissipation rate ( ) The two jointly decide, the specific steps are as follows:

[0129] (2.1) Turbulent kinetic energy equation: The turbulent kinetic energy equation describes the change of turbulent kinetic energy in the fluid, including the source term of turbulence (such as shear stress of water flow) and loss term (such as friction). The equation is expressed as:

[0130] ;

[0131] Where t represents the time of water turbulence change, represents the velocity component of the water flow in the j direction, Represents the coordinate component of the jth direction in the three-dimensional space coordinates, represents the momentum diffusion coefficient of turbulence, represents the production term of turbulence (i.e. the contribution of water shear force to turbulent kinetic energy), represents the turbulent dissipation rate;

[0132] (2.2) Turbulence dissipation rate ( ) equation: The turbulence dissipation rate equation describes the dissipation process of turbulent kinetic energy, that is, the loss of turbulent energy in the fluid. The equation is expressed as:

[0133] ;

[0134] in, and is a constant of the model, controlling the generation and dissipation of turbulence;

[0135] (3) Calculate the resuspension of sediment particles:

[0136] (3.1) Resuspension of sediment particles: The k-ε turbulence model is used to calculate the effect of turbulent kinetic energy in the water flow on the sediment particles. The turbulence intensity in the water flow directly determines the suspension capacity of the particles. Based on the results of the k-ε turbulence model, it is calculated whether the sediment particles will be disturbed and resuspended. The movement trajectory of the particles in the water and the possibility of resuspension are evaluated mainly by calculating the flow velocity, shear stress, and the sedimentation velocity of the particles.

[0137] (3.2) Particle motion calculation: Based on the results of the k-ε turbulence model, the movement and diffusion of sediment particles are calculated. According to the particle size, density, flow velocity and shear force of the water flow, it is determined whether the sediment particles will be disturbed from the seabed and enter the water body. The resuspended particles may diffuse with the water flow and affect the environmental quality of the benthic habitat;

[0138] In the process of simulating the resuspension of sediments using the k-ε turbulence model, different disturbance sources of test mining schemes are set, such as bottom disturbance during test mining, changes in water flow velocity, etc., to simulate the resuspension of sediment particles under different disturbance sources. By simulating different intensities, operating depths and mining methods of mining operations, the resuspension degree of sediment particles under different test mining schemes is predicted, and it is evaluated whether these disturbances will lead to large-scale diffusion of sediment particles and potential impacts on the ecological environment.

[0139] The k-ε turbulence model is used to simulate the process of sediment resuspension in water flow, and the impact of different trial mining schemes on benthic habitats is analyzed. The resuspension effect of sediment particles under different trial mining schemes is simulated and calculated to analyze the potential harm of sediment to benthic habitats, especially the impact on the growth, reproduction and habitat quality of organisms. If the particle suspension concentration is too high, it may lead to water quality deterioration, destruction of benthic habitats and loss of ecological functions.

[0140] By selecting the k-ε turbulence model to simulate the sediment resuspension process, the disturbance simulation module can accurately predict the disturbance of sediments caused by different trial mining schemes and evaluate their potential impacts on benthic habitats. The model can describe the turbulent effects in the water flow and the suspension and deposition process of sediment particles, providing accurate numerical data for subsequent ecological impact assessments.

[0141] Optionally, the ecological impact assessment module includes:

[0142] Collect ecological data collected by the data collection module, including temperature, salinity, sediment characteristics, community structure and biodiversity data. These data monitor the ecological environment of the test mining area in real time through sensor networks and remote sensing technology, reflecting the ecological status of the test mining area. Specifically, ecological data include but are not limited to changes in water temperature and salinity at different depths and time scales, sediment particle size distribution, and species types and quantities;

[0143] Collect output data from the disturbance simulation module, including simulation results of changes in water flow patterns, sediment resuspension processes and changes in biological habitats. These simulation results provide information on the disturbance of the environment during the implementation of the pilot mining plan, especially the potential impacts on water flow changes, sediment transport and benthic ecosystems;

[0144] An assessment model was constructed by combining the ecological data from the data acquisition module with the output of the disturbance simulation module to establish a comprehensive assessment framework. The assessment model used multidimensional data fusion technology to combine parameters such as species abundance, community structure changes, sediment disturbance and habitat changes to quantitatively assess the potential impact of mining activities on benthic organisms. The assessment model included the following steps:

[0145] (1) Through data standardization and normalization, ecological data from different sources (such as temperature, salinity, and biome data) are converted into unified assessment units to facilitate multi-dimensional comparison and analysis;

[0146] (2) Use the random forest algorithm to build an assessment model. The random forest algorithm is used to associate environmental disturbance factors (such as water flow changes, sediment disturbance, etc.) with ecological parameters (such as species abundance and community structure changes) to automatically select the characteristic variables most relevant to ecological impacts to improve prediction accuracy. By training on historical ecological data and disturbance simulation data, an assessment model that can predict the long-term impact of mining disturbance on benthic ecosystems is constructed;

[0147] According to the assessment model, multiple ecological assessment indicators are set, including changes in species abundance, changes in community structure, and loss of ecological functions, among which:

[0148] (1) Changes in species abundance: measure the impact of mining activities on species population size and biodiversity indicators, and evaluate the impact of mining activities on biological populations by comparing parameters such as species number and individual density before and after trial mining;

[0149] (2) Changes in community structure: This measures the impact of mining activities on the composition of biological communities and their ecological functions. Changes in community structure can be quantified by calculating community diversity indices (such as the Shannon-Wiener index);

[0150] (3) Loss of ecological functions: Assess the extent of loss of ecological functions, mainly considering the impact of mining activities on ecosystem services (such as water purification, carbon cycle, etc.), and assess the changes in ecological functions in combination with the extent of habitat destruction;

[0151] Generate a detailed ecological impact report based on the output of the assessment model. The report includes a quantitative assessment of benthic communities, species abundance and ecological functions, and points out the potential impacts of mining activities on different ecological parameters to provide support for relevant decision-making;

[0152] The ecological impact assessment module can more accurately capture and predict the impact of mining activities on benthic ecosystems. This method can efficiently process and analyze complex ecological data, especially in environments with strong interactions between multi-dimensional variables, thereby enhancing the predictive ability of the assessment model. The assessment results generated by the model can provide ecological risk assessments for mining activities, thereby providing a scientific basis for decision makers and reducing the impact of mining disturbances on benthic organisms and ecosystem functions.

[0153] Optionally, the decision support module specifically includes:

[0154] Receive the assessment results of the ecological impact assessment module, which includes the analysis of the impact of mining activities on benthic ecosystems, covering changes in species abundance, changes in community structure, sediment disturbance, and loss of ecological functions, to ensure that the decision support module can make scientific decisions based on the assessed ecological impact data;

[0155] According to the assessment results, specific decision-making goals are set, such as minimizing the loss of ecological functions, maintaining biodiversity, optimizing benthic habitats, etc. At the same time, constraints are set, including ecological safety requirements, mining intensity, resource consumption, and environmental protection standards during the mining process. These constraints help balance the needs of ecological protection and resource extraction when formulating management strategies;

[0156] Provide management strategies for adjusting mining intensity and time windows. According to the results of ecological impact assessment, analyze the impact of different mining intensities and time windows on benthic ecosystems and propose optimization plans. The specific steps include:

[0157] (1) Based on the prediction of changes in species abundance and community structure, analyze the potential impact of mining intensity on the ecosystem and propose recommendations for adjustable mining intensity;

[0158] (2) Optimize the time window for mining activities based on the results of ecological impact assessments and changes in biological communities to avoid high-intensity mining during species breeding seasons or ecologically sensitive periods;

[0159] (3) By simulating the long-term impacts of different mining intensity and time combinations on the ecosystem, the optimal mining intensity and time window are selected to balance the needs of resource extraction and ecological protection;

[0160] Based on the results of the ecological impact assessment, a suitable ecological restoration plan is proposed to repair the ecological damage caused by mining activities, including:

[0161] (1) Propose targeted ecological restoration measures based on the extent of habitat destruction and changes in biome structure, such as reintroducing species or strengthening habitat protection in areas where species abundance is affected;

[0162] (2) In areas with significant sediment disturbance, it is proposed to restore the bottom sediment structure through artificial deposition or ecological engineering to restore the original ecological function;

[0163] (3) Optimize the sequence and timing of ecological restoration measures based on regional water flow patterns and habitat characteristics to ensure that the restoration process does not negatively impact other ecological parameters;

[0164] Provide feedback mechanisms and dynamic adjustment plans to adjust management strategies based on real-time monitoring data and post-evaluation results, including:

[0165] (1) During the trial mining process, continuously monitor ecological and environmental changes, such as water flow patterns and sediment resuspension, and dynamically adjust the mining plan if unforeseen negative impacts occur;

[0166] (2) Based on the results of the feedback learning module, adjust ecological restoration measures and mining strategies to cope with ecological changes in the actual mining process and ensure long-term ecological balance;

[0167] The decision support module generates detailed decision recommendation reports, including mining intensity adjustment plans, time window optimization plans and ecological restoration measures;

[0168] Based on the assessment results of the ecological impact assessment module, the decision support module proposes a set of scientific and comprehensive management strategies. These strategies reduce the damage of mining activities to the ecosystem by adjusting the mining intensity and time window, and repair the impact of mining on benthic habitats and ecological functions by proposing ecological restoration measures. In addition, the dynamic feedback mechanism can adjust strategies according to real-time data to ensure the balance between the sustainability of mining activities and ecological protection.

[0169] Optionally, the feedback learning module specifically includes:

[0170] After the trial mining, the feedback learning module receives the ecological data monitored in real time by the data acquisition module, including various indicators of the post-mining ecological environment, such as temperature, salinity, sediment characteristics, community structure and biodiversity data. At the same time, it collects the output data of the disturbance simulation module and the ecological impact assessment module for comparative analysis of the long-term impact of mining activities on the benthic ecosystem;

[0171] Preprocess the collected ecological data after the test mining, including data cleaning, noise removal and missing value filling. Then, convert the data to a unified scale through standardization or normalization methods to ensure that data from different sources can be compared and combined with each other, and ensure the validity and consistency of the data in the machine learning model;

[0172] According to the characteristics of the data after the test mining and the requirements of the ecological impact assessment task, the gradient boosting algorithm is selected to iteratively update the assessment model. The specific steps include:

[0173] (1) Based on the ecological data after the test mining, the gradient boosting machine algorithm was selected to evaluate the iterative update of the model. The gradient boosting machine is an ensemble learning method based on decision trees. It can effectively handle nonlinear relationships and complex data and improve the accuracy of the model by gradually adjusting the prediction error of the previous round.

[0174] Feed the iteratively updated assessment model back to the ecological impact assessment module to achieve dynamic update. The specific steps include:

[0175] (1) Through the feedback mechanism, new ecological data and assessment results are incorporated into the assessment model update to form a closed loop to ensure that the assessment model is continuously adjusted and optimized as mining activities progress and the ecological environment changes;

[0176] (2) Ensure that the assessment model can adapt to environmental changes and retrain the assessment model regularly to adapt to long-term ecological change trends and the implementation of different trial mining plans;

[0177] Adjust management strategies and ecological restoration measures for mining activities based on the updated assessment model, and continuously adjust assessment strategies by dynamically monitoring the progress of mining activities and environmental changes to achieve more accurate ecological impact prediction and real-time management;

[0178] The feedback learning module collects ecological data after trial mining and uses the gradient boosting algorithm to iteratively update the assessment model, which can improve the accuracy and adaptability of the model. Through data preprocessing, model optimization, performance evaluation and dynamic updating, the feedback learning module realizes dynamic monitoring and evaluation of ecological impacts, thereby ensuring accurate assessment of benthic ecosystems and real-time adjustment of mining activities.

[0179] Optionally, the visualization module specifically includes:.

[0180] The visualization module receives real-time ecological data from the data acquisition module, including temperature, salinity, sediment characteristics, biome structure, and biodiversity data. These data are collected in real time through sensor networks and remote sensing technology and transmitted to the visualization module for processing and display;

[0181] The visualization module receives assessment output data from the ecological impact assessment module based on ecological data and disturbance simulation results, including species abundance, community structure changes, and ecological function loss;

[0182] Integrate real-time monitoring ecological data with assessment results to form a comprehensive data view. The integration process includes standardizing or normalizing multi-source data to ensure that data from different sources can be displayed consistently.

[0183] According to the characteristics of the data and the display requirements, select visualization methods, including heat maps, species distribution maps, community structure maps, bar charts, line charts and time series charts, among which;

[0184] (1) Heatmaps display the spatial distribution of environmental parameters such as temperature and salinity, helping decision makers quickly understand environmental changes in mining areas;

[0185] (2) Species distribution maps and community structure maps show the abundance and habitat changes of different species, and intuitively present the spatial distribution and temporal evolution of ecological impacts;

[0186] (3) Ecological function loss diagram: The diagram shows the degree of damage to ecological functions caused by different trial mining plans through bar charts, line charts, etc., which is convenient for assessing the risks of mining activities;

[0187] (4) Time series diagrams show the relationship between the process of mining activities and real-time monitoring data, helping decision makers to evaluate the temporal changes in mining time and ecological impacts;

[0188] The visualization module provides an interactive interface to support decision makers and relevant personnel to dynamically view and manipulate data. Different display perspectives and data sets can be selected according to needs, and the time range, depth level or other parameters can be adjusted to better understand the specific impact of different mining options on the ecological environment.

[0189] 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.

[0190] 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 system for assessing the damage of deep-sea polymetallic nodule mining disturbance to benthic ecosystems, characterized by: It includes data acquisition module, ecological baseline model building module, disturbance simulation module, ecological impact assessment module, decision support module, feedback learning module and visualization module, among which; The data acquisition module monitors the ecological data of the test area in real time through sensor networks and remote sensing technology, including temperature, salinity, sediment characteristics, biological community structure and biodiversity; The ecological baseline model building module uses historical ecological data and existing biodiversity information to build an ecological baseline model for the test mining area, which is used to compare and evaluate ecological changes before and after mining disturbance; The disturbance simulation module uses numerical simulation methods to predict the disturbance of different trial mining schemes, including the impact on changes in water flow patterns, sediment resuspension and biological habitats, so as to evaluate the potential impact of disturbances of different trial mining schemes on ecological functions; The ecological impact assessment module constructs an assessment model based on the ecological data collected by the data acquisition module and the output of the disturbance simulation module to assess the impact of mining activities on benthic organisms, including species abundance, changes in community structure, and loss of ecological functions; The decision support module provides suggestions and management strategies based on the assessment results of the ecological impact assessment module to reduce the damage of mining activities to the ecosystem. The suggestions and management strategies include adjusting the mining intensity and time window and formulating ecological restoration measures. The feedback learning module collects ecological data after the test mining, and iteratively updates the evaluation model through the gradient boosting algorithm to improve the evaluation accuracy and adaptability; The visualization module is used to present the real-time monitored ecological data and evaluation results in a visualized form.

2. The damage assessment system for deep-sea polymetallic nodule test mining disturbance to benthic ecosystems according to claim 1 is characterized in that: The data acquisition module comprises: Arrange a sensor network, select multiple monitoring points within the test mining area, configure water temperature and salinity sensors, and continuously monitor the temperature and salinity data of the water body through the water temperature and salinity sensors; Sediment sampling technology is used to randomly select multiple sampling points in the test area, and sediment samples are collected using sediment sampling tubes according to the stratified sampling method. The collected sediment samples are then subjected to laboratory analysis, including particle size distribution, chemical composition, and organic matter content, to obtain sediment characteristic data; Conduct biodiversity surveys using standard plot survey methods. In each plot, record all species observed and their number of individuals, and classify species using a species identification manual; Through the analysis of biological community structure, the diversity index is used to evaluate the species diversity of each site, and the community evenness is calculated to analyze the relative distribution of different species in the ecosystem; The collected ecological data are transmitted to a preset central processing unit, where a comprehensive data repository is established to integrate the ecological data from different sensors and sample plots.

3. The damage assessment system for deep-sea polymetallic nodule test mining disturbance to benthic ecosystems according to claim 2 is characterized in that: The ecological baseline model construction module specifically includes: Collect historical ecological data, including previous biodiversity survey results, species abundance, community structure, sediment characteristics, water temperature, and salinity data in the test mining area; Integrate existing biodiversity information and compile data on species distribution and ecological function from regional or global databases, including existing species lists and distribution data on habitat types; Using the real-time ecological data provided by the data acquisition module, the ecological environment at different depths and terrain conditions in the test mining area is analyzed to ensure that the depth gradient and terrain characteristics are taken into account in the model; Based on historical ecological data and real-time ecological data, the ecological baseline model is constructed using the support vector machine regression algorithm; Model validation was conducted to evaluate the accuracy and effectiveness of the model by comparing and analyzing the ecological data around the test mining area or other known areas.

4. The damage assessment system for deep-sea polymetallic nodule test mining disturbance to benthic ecosystems according to claim 3 is characterized in that: The disturbance simulation module specifically includes: Select numerical simulation methods, establish a three-dimensional ocean circulation model, and numerically simulate the water flow pattern in the test mining area; In a three-dimensional ocean circulation model, simulate the impact of different mining scenarios on water flow patterns, including seawater velocity, direction, water temperature and salinity; Based on the simulation results, the effects of different trial mining schemes on water flow patterns were analyzed, including changes in flow velocity, generation of vortices, and turbulence of water flow; Assess the impact of water flow disturbances on ecosystems by analyzing changes in water flow patterns to assess their impact on aquatic habitats.

5. The system for assessing damage to benthic ecosystems caused by deep-sea polymetallic nodule mining disturbance according to claim 4 is characterized in that: The disturbance simulation module also includes: Select the numerical simulation method and use the k-ε turbulence model to simulate the sediment resuspension process; In the process of simulating the resuspension of sediments with the k-ε turbulence model, different disturbance sources of trial mining schemes were set to simulate the resuspension of sediment particles under different disturbance sources. By simulating different intensities, operating depths and mining methods of mining operations, the resuspension degree of sediment particles under different trial mining schemes was predicted. The k-ε turbulence model was used to simulate the process of sediment resuspension in water flow, and the impact of different trial mining schemes on the benthic habitat was analyzed.

6. The system for assessing damage to benthic ecosystems caused by deep-sea polymetallic nodule mining disturbance according to claim 5, characterized in that: The ecological impact assessment module includes: Collect ecological data collected by the data collection module, including temperature, salinity, sediment properties, biome structure, and biodiversity data; Collect output data from the disturbance simulation module, including simulation results of changes in water flow patterns, sediment resuspension processes, and changes in biological habitats; Construct an assessment model by combining the ecological data from the data acquisition module with the output of the disturbance simulation module to establish a comprehensive assessment framework; According to the assessment model, multiple ecological assessment indicators are set, including changes in species abundance, changes in community structure, and loss of ecological functions; Based on the output of the assessment model, an ecological impact report is generated, which includes a quantitative assessment of benthic communities, species abundance, and ecological functions.

7. The system for assessing damage to benthic ecosystems caused by deep-sea polymetallic nodule mining disturbance according to claim 6, characterized in that: The decision support module specifically includes: Receive the results of the ecological impact assessment module, which includes an analysis of the impacts of mining activities on benthic ecosystems, covering changes in species abundance, changes in community structure, sediment disturbance, and loss of ecological functions; According to the evaluation results, decision-making goals are set, and constraints are set, including ecological safety requirements, mining intensity, resource consumption and environmental protection standards during the mining process; Provide management strategies for adjusting mining intensity and time windows, analyze the impacts of different mining intensities and time windows on benthic ecosystems based on the results of ecological impact assessment, and propose optimization plans; Based on the results of the ecological impact assessment, propose appropriate ecological restoration plans to repair the ecological damage caused by mining activities; Provide feedback mechanisms and dynamic adjustment plans to adjust management strategies based on real-time monitoring data and post-evaluation results; The decision support module generates a decision recommendation report, which includes mining intensity adjustment plan, time window optimization plan and ecological restoration measures.

8. The system for assessing damage to benthic ecosystems caused by deep-sea polymetallic nodule mining disturbance according to claim 7, characterized in that: The feedback learning module specifically includes: After the trial mining, the feedback learning module receives the ecological data monitored in real time from the data collection module; Preprocess the collected ecological data after the test mining, including data cleaning, noise removal and missing value filling; According to the characteristics of the post-test mining data and the requirements of the ecological impact assessment task, the gradient boosting algorithm was selected to iteratively update the assessment model; Feed the iteratively updated assessment model back to the ecological impact assessment module to achieve dynamic updates; Adjust management strategies and ecological restoration measures for mining activities based on the updated assessment model.

9. The system for assessing damage to benthic ecosystems caused by deep-sea polymetallic nodule mining disturbance according to claim 8, characterized in that: The visualization module specifically includes: The visualization module receives real-time ecological data from the data acquisition module, including temperature, salinity, sediment properties, biome structure, and biodiversity data; The visualization module receives assessment output data from the ecological impact assessment module based on ecological data and disturbance simulation results, including species abundance, community structure changes, and ecological function loss; Integrate real-time monitoring ecological data with assessment results to form a comprehensive data view; Select visualization methods based on data characteristics and presentation requirements, including heat maps, species distribution maps, community structure maps, bar charts, line charts, and time series charts; The visualization module provides an interactive interface to support decision makers and relevant personnel to dynamically view and operate data.

Images