Evaluation System for the Ecological Restoration Capacity and Potential of Deep-Sea Mining Based on Biological Attachment Substrates

Abstract

The present invention relates to the field of deep - sea mining ecological restoration technology, and specifically relates to an evaluation system for the ecological restoration ability and potential of deep - sea mining based on biological attachment substrates, including a data acquisition module, a biological attachment substrate identification module, and a deep - sea ecological dynamic monitoring module. Among them, the data acquisition module collects water quality parameters of the deep - sea mining area; the biological attachment substrate identification module identifies and analyzes the population distribution, density, and morphology of biological attachment substrates, and evaluates the growth and health status of biological attachment substrates; the deep - sea ecological dynamic monitoring module evaluates the impact of environmental changes on the restoration ability of biological attachment substrates by analyzing the dynamic changes of microclimate and sediment in the mining area. The present invention can accurately predict the progress and potential of ecological restoration, providing strong data support for scientific decision - making on deep - sea ecological restoration and environmental protection measures.

Description

Technical Field

[0001] The present invention relates to the technical field of deep - sea mining ecological restoration, and particularly to an evaluation system for the ecological restoration ability and potential of deep - sea mining based on biological attachment substrates. Background Art

[0002] With the increasing demand for deep - sea mineral resource development, the scale and frequency of deep - sea mining activities have gradually increased. However, the environmental disturbance and pollution problems generated during deep - sea mining have had a significant impact on the health and stability of the marine ecosystem, especially the biological attachment substrates. As an important part of the marine ecosystem, biological attachment substrates not only provide habitats for a variety of marine organisms but also play a key role in material cycling and biodiversity maintenance. Therefore, conducting effective ecological restoration ability assessment during deep - sea mining activities to ensure the sustainable restoration of biological attachment substrates is an important research direction for ensuring the healthy development of the deep - sea ecosystem.

[0003] Currently, most deep - sea ecological restoration assessment systems adopt single - parameter monitoring methods, lacking dynamic acquisition and analysis of multi - dimensional environmental data, making it difficult to comprehensively reflect the ecological changes in deep - sea mining areas. At the same time, traditional monitoring systems generally have problems of data lag and insufficient accuracy, being unable to reflect the changes in key environmental factors such as water quality and sediment in real time, resulting in a deviation between the evaluation results and the actual situation. In addition, the analysis methods for the health and restoration status of biological attachment substrates are limited, and most assessment systems fail to comprehensively consider the growth rate, distribution density of biological attachment substrates and the impact of environmental changes, making it difficult to accurately predict the ecological restoration potential and affecting the ecological management and decision - making of deep - sea mining activities.

[0004] The purpose of the present invention is to provide an evaluation system for the ecological restoration ability and potential of deep - sea mining based on biological attachment substrates, which not only improves the timeliness and accuracy of monitoring but also can provide scientific and objective decision - making support for the ecological protection and sustainable development of deep - sea mining activities. Summary of the Invention

[0005] The present invention provides an evaluation system for the ecological restoration ability and potential of deep - sea mining based on biological attachment substrates.

[0006] The evaluation system for the ecological restoration ability and potential of deep - sea mining based on biological attachment substrates includes a data acquisition module, a biological attachment substrate identification module, and a deep - sea ecological dynamic monitoring module, wherein;

[0007] The data acquisition module collects water quality parameters in the deep - sea mining area through multiple sensors, including the temperature, depth, and salinity of the ocean water body;

[0008] The biological attachment substrate recognition module recognizes and analyzes the population distribution, density, and morphology of the biological attachment substrate, and evaluates the growth and health status of the biological attachment substrate in combination with the collected water quality parameters;

[0009] The deep-sea ecological dynamic monitoring module monitors the environmental data of the deep-sea mining area in real time through sensors, including microclimate (dissolved oxygen, pH) and sediment (particle size, heavy metal ions). By analyzing the dynamic changes of the microclimate and sediment in the mining area, it evaluates the impact of environmental changes on the recovery ability of the biological attachment substrate, specifically including:

[0010] Environmental data collection: Use deep-sea sensors to collect various environmental data of the deep-sea mining area in real time, including dissolved oxygen, pH, particle size, and heavy metal ions;

[0011] Data preprocessing: Preprocess the collected environmental data, including noise filtering and standardization processing;

[0012] Analysis and evaluation of environmental changes: Analyze the preprocessed environmental data to evaluate the impact of the dynamic changes of the microclimate and sediment in the deep-sea mining area on the recovery ability of the biological attachment substrate.

[0013] Optionally, the data collection module includes:

[0014] Temperature data collection: Measure the temperature of the water body in the deep-sea mining area in real time through a temperature sensor, and record the water temperature changes at each specified location and depth;

[0015] Depth data collection: Monitor the water depth in the deep-sea mining area in real time through a depth sensor to capture the depth changes in the deep-sea water area;

[0016] Salinity data collection: Measure the salinity of the water body in the deep-sea mining area through a salinity sensor.

[0017] Optionally, the biological attachment substrate recognition module includes:

[0018] Image collection and preliminary processing of biological attachment substrate: Collect the image data of the biological attachment substrate in the deep-sea mining area in real time through an underwater image collection device, and perform preliminary processing on the collected image data, including denoising, image enhancement, and segmentation;

[0019] Recognition of biological attachment substrate: Use a convolutional neural network (CNN) model to recognize the preliminarily processed image data, analyze the population distribution, density, and morphology of the biological attachment substrate, and judge the distribution of the biological attachment substrate in different regions;

[0020] Analysis of the growth and health status of biological attachment substrates: Based on the results of biological attachment substrate recognition, by analyzing the correlation between water quality parameters and the growth of biological attachment substrates, the growth rate and health status of biological attachment substrates under different water quality conditions are evaluated.

[0021] Optionally, the biological attachment substrate image acquisition and preliminary processing include:

[0022] Underwater image acquisition: Real-time acquisition of image data of biological attachment substrates in the deep-sea mining area through an underwater camera;

[0023] Image denoising: Using the Gaussian filtering algorithm to suppress noise in the acquired image data;

[0024] Image enhancement: Using histogram equalization to improve the contrast and details of the image data;

[0025] Image segmentation: Using the Otsu threshold method to separate the biological attachment substrate area in the image data from the background.

[0026] Optionally, the convolutional neural network (CNN) model includes:

[0027] Multi-scale feature extraction: Extract multi-scale features of the image through convolutional kernels of different scales ( , , ) and splice the convolutional results of all scales to obtain a multi-scale feature map ;

[0028] Fully connected layer: Flatten the multi-scale feature map into a one-dimensional feature vector F, and input the flattened feature vector F into the fully connected layer to generate a feature representation ;

[0029] Pixel classification: For each pixel point in the comprehensive feature map , use the Softmax classifier to classify;

[0030] Segmentation result: By taking the maximum value of the classification probability of each pixel, the segmentation result is obtained ;

[0031] Distribution and density calculation: According to the segmentation result, the distribution and density information of the biological attachment substrate are statistically analyzed. The segmentation result comes with the category information of each pixel and is directly used to judge the spatial distribution of the biological attachment substrate. By counting the number of pixels belonging to the biological attachment substrate category, the density D of the biological attachment substrate is calculated.

[0032] Optionally, the analysis of the growth and health status of the biological attachment substrate includes:

[0033] Growth rate calculation: By analyzing the change in the density of the biological attachment substrate at different time points, calculate its growth rate G;

[0034] Water quality correlation analysis: Use the Pearson correlation coefficient r to analyze the correlation between water quality parameters and the density of the biological attachment substrate;

[0035] Health status assessment: Combining the growth rate and water quality correlation results, by comparing with the healthy threshold and the unhealthy threshold as well as the correlation threshold to comprehensively evaluate the health status of the biological attachment substrate. If and , it is indicated as healthy. If or , it is indicated as unhealthy.

[0036] Optionally, the environmental data collection includes:

[0037] Dissolved oxygen data collection: Real-time collect the dissolved oxygen concentration in the water body through a dissolved oxygen sensor;

[0038] pH data collection: Use a pH sensor to monitor the pH value of the water body in real time;

[0039] Particle size data collection: Measure the particle size distribution of suspended particles in the water through a particle size analysis sensor to provide water turbidity and particle information;

[0040] Heavy metal ion data collection: Use a heavy metal ion sensor to detect the concentration of heavy metal ions in the water body, including cadmium, lead, and mercury.

[0041] Optionally, the data preprocessing includes:

[0042] Noise filtering: Adopt a moving average filtering algorithm to filter the noise of the collected environmental data;

[0043] Normalization processing: Perform normalization processing on the environmental data after noise filtering.

[0044] Optionally, the environmental change analysis and evaluation includes:

[0045] Environmental change trend analysis: Adopt a linear regression algorithm to perform trend analysis on the preprocessed environmental data to capture the microclimate and sediment dynamic changes in the deep-sea mining area;

[0046] Assessment of the impact of dynamic changes on biological attachment substrates: Based on the results of environmental change trend analysis and combined with the correlation analysis of the recovery ability of biological attachment substrates, the impact of environmental changes on biological attachment substrates is evaluated. Using the correlation analysis method, the correlation coefficient between environmental changes and the recovery ability (growth rate) of biological attachment substrates is calculated. 。

[0047] Advantages of the present invention:

[0048] In the present invention, through the data acquisition module, the biological attachment substrate recognition module, and the deep-sea ecological dynamic monitoring module, the key environmental parameters in the deep-sea mining area are comprehensively monitored. The data acquisition module can efficiently and real-time collect water quality data such as temperature, depth, and salinity, ensuring the high timeliness and accuracy of the data, avoiding the data lag problem in traditional monitoring methods, and providing scientific and reliable basic data support for the assessment of ecological restoration.

[0049] In the present invention, through the biological attachment substrate recognition module based on image processing and convolutional neural network models, not only can the image data of biological attachment substrates be collected and processed in real time, but also the population distribution, density, morphology, etc. of biological attachment substrates can be identified through multi-scale feature extraction and pixel-level segmentation. Combining water quality data analysis, the growth rate and health status of biological attachment substrates are provided, and the distribution and recovery status of biological attachment substrates are provided efficiently and accurately, which can accurately predict the progress and potential of ecological restoration, and provide strong data support for scientific decision-making on deep-sea ecological restoration and environmental protection measures.

[0050] In the present invention, through environmental change analysis and assessment, combined with the real-time monitoring of microclimate and sediment dynamic changes, the impact of environmental changes on the recovery ability of biological attachment substrates can be dynamically analyzed. Through trend analysis and correlation assessment, the promotion or inhibition effect of environmental factors can be quantified, and key influencing factors can be identified in a timely manner, realizing the dynamic and accurate assessment of the ecological restoration status. Description of the drawings

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a schematic diagram of the system function module of the embodiment of the present invention;

[0053] Figure 2 It is a schematic diagram of the deep-sea ecological dynamic monitoring module of the embodiment of the present invention. Detailed implementation manners

[0054] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the accompanying drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0055] As Figure 1 - Figure 2 shown, the deep-sea mining ecological restoration ability and potential evaluation system based on biological attachment substrates includes a data acquisition module, a biological attachment substrate identification module, and a deep-sea ecological dynamic monitoring module, where;

[0056] The data acquisition module collects water quality parameters of the deep-sea mining area through multiple sensors, including the temperature, depth, and salinity of the ocean water body;

[0057] The biological attachment substrate identification module identifies and analyzes the population distribution, density, and morphology of biological attachment substrates, and combines the collected water quality parameters to evaluate the growth and health status of biological attachment substrates;

[0058] The deep-sea ecological dynamic monitoring module real-time monitors the environmental data of the deep-sea mining area through sensors, including microclimate (dissolved oxygen, pH) and sediment (particle size, heavy metal ions). By analyzing the dynamic changes of the microclimate and sediment in the mining area, it evaluates the impact of environmental changes on the restoration ability of biological attachment substrates, specifically including:

[0059] Environmental data collection: Use deep-sea sensors to real-time collect various environmental data of the deep-sea mining area, including dissolved oxygen, pH, particle size, and heavy metal ions;

[0060] Data preprocessing: Preprocess the collected environmental data, including noise filtering and standardization processing;

[0061] Analysis and evaluation of environmental changes: Analyze the preprocessed environmental data to evaluate the impact of the dynamic changes of the microclimate and sediment in the deep-sea mining area on the restoration ability of biological attachment substrates;

[0062] Through the above content, real-time collect and analyze the environmental data of the deep-sea mining area, covering microclimate changes and sediment changes, combined with the analysis of the type, distribution, and growth stability of biological attachment substrates, comprehensively evaluate the ecological restoration situation, dynamically analyze environmental changes, and can accurately evaluate the impact of deep-sea mining activities on the restoration ability of biological attachment substrates, improving the timeliness, accuracy, and forward-looking of the evaluation, and providing more scientific and practical decision-making support for the ecological restoration of deep-sea mining areas.

[0063] The data acquisition module includes:

[0064] Temperature data acquisition: The temperature of the water body in the deep - sea mining area is measured in real - time through temperature sensors, and the water temperature changes at each specified location and depth are recorded;

[0065] Depth data acquisition: The water depth in the deep - sea mining area is monitored in real - time through depth sensors to capture the depth changes in the deep - sea water area;

[0066] Salinity data acquisition: The salinity of the water body in the deep - sea mining area is measured through salinity sensors;

[0067] Through the above, it is possible to continuously monitor the temperature, depth changes, and salinity fluctuations of the water body at different depths and positions. Through an efficient data acquisition system, environmental changes can be captured in real - time, ensuring the high timeliness and accuracy of the data, avoiding data lag and inaccuracy problems in traditional monitoring methods, and providing a scientific basis for the ecological impact assessment of deep - sea mining activities.

[0068] The biological attachment substrate identification module includes:

[0069] Biological attachment substrate image acquisition and preliminary processing: Image data of biological attachment substrates in the deep - sea mining area are collected in real - time through underwater image acquisition equipment, and the collected image data are preliminarily processed, including denoising, image enhancement, and segmentation;

[0070] Biological attachment substrate identification: The preliminarily processed image data are identified through a Convolutional Neural Network (CNN) model to analyze the population distribution, density, and morphology of biological attachment substrates, so as to judge the distribution of biological attachment substrates in different regions;

[0071] Biological attachment substrate growth and health status analysis: Based on the results of biological attachment substrate identification, by analyzing the correlation between water quality parameters and the growth of biological attachment substrates, the growth rate and health status of biological attachment substrates under different water quality conditions are evaluated;

[0072] Through the above, it is possible to identify and analyze the population distribution, density, and morphology of biological attachment substrates in real - time, thereby effectively evaluating their growth and stability. By correlating water quality parameters with the growth status of biological attachment substrates, the progress and potential of ecological restoration can be accurately predicted, and more objective and real - time monitoring data can be provided to support scientific decision - making on ecological restoration and environmental protection measures in the deep - sea mining area, promoting the sustainable development of deep - sea mining activities.

[0073] Biological attachment substrate image acquisition and preliminary processing includes:

[0074] Underwater image acquisition: Image data of biological attachment substrates in the deep - sea mining area are collected in real - time through underwater cameras;

[0075] Image denoising: The Gaussian filtering algorithm is used to suppress the noise in the collected image data to improve the image quality and reduce the interference caused by factors such as water flow and light changes, which is expressed as:

[0076] ;

[0077] Among them, is the pixel value of the denoised image, is the neighborhood pixel value in the image relative to the pixel position , is the Gaussian kernel, and k is the radius of the filtering window;

[0078] Image enhancement: Histogram equalization is used to improve the contrast and details of the image data, making the morphological features of the biological attachment base more obvious, which is expressed as:

[0079] ;

[0080] Among them, r is the pixel value of the input image, s is the pixel value of the enhanced image, is the maximum pixel value in the input image, is the minimum pixel value in the input image, and L is the number of gray levels, which is used to determine the brightness range of the image;

[0081] Image segmentation: The Otsu threshold method is used to separate the biological attachment base area in the image data from the background, which is expressed as:

[0082] ;

[0083] Among them, is the between-class variance, and are the weights of the classes respectively, and are the means of the classes;

[0084] Through the above content, it is possible to obtain clear biological attachment base image data in real time in a complex deep-sea environment. Through denoising, image enhancement and segmentation, the quality of the image and the clarity of biological features are improved, effectively overcoming the insufficient light and noise interference in the deep sea, providing higher reliability and accuracy for ecological monitoring, and improving the efficiency of identifying the distribution, density and health status of biological attachment bases.

[0085] The convolutional neural network (CNN) model includes:

[0086] Multi-scale feature extraction: Multi-scale features of the image are extracted through convolutional kernels of different scales ( , , ), and the convolutional results of all scales are concatenated to obtain a multi-scale feature map , the convolution operation at each scale is expressed as:

[0087] ;

[0088] where is the convolution output at scale s, is the convolution kernel weight at scale s, is the value of the input image at the pixel position ;

[0089] Fully connected layer: Flatten the multi-scale feature map into a one-dimensional feature vector F, and input the flattened feature vector F into the fully connected layer to generate a feature representation , which is expressed as:

[0090] ;

[0091] ;

[0092] where is the output feature vector of the fully connected layer for classification, is the weight matrix of the fully connected layer, F is the flattened multi-scale feature vector, is the bias of the fully connected layer;

[0093] Pixel classification: For each pixel point in the comprehensive feature map, use the Softmax classifier to classify , which is expressed as:

[0094] ;

[0095] where is the probability that the input image belongs to class c, is the score of the feature vector of the fully connected layer on class c, and k represents all classes;

[0096] Segmentation result: By taking the maximum value of the classification probability of each pixel, the segmentation result is obtained, which is expressed as:

[0097] ;

[0098] where represents the final classification result (bioattachment base or background) of pixel ;

[0099] Distribution and density calculation: According to the segmentation result, the distribution and density information of the bioattachment base are statistically calculated, and the segmentation result Carrying the category information of each pixel, it is directly used to judge the spatial distribution of the biological attachment substrate. By counting the number of pixels belonging to the biological attachment substrate category, the density D of the biological attachment substrate is calculated, expressed as:

[0100] ;

[0101] where D is the density of the biological attachment substrate, H and W are the height and width of the image respectively, is the indicator function, which takes the value of 1 when the pixel belongs to the biological attachment substrate category c, and 0 otherwise;

[0102] Through the above content, the efficient recognition and accurate segmentation of the biological attachment substrate in the deep - sea environment are realized. The multi - scale feature extraction can capture features at different scales, adapt to the morphological diversity of the biological attachment substrate. The fully - connected layer further integrates these features to make the classification more accurate. The Softmax classifier realizes category segmentation at the pixel level, ensuring the fine division of the image. It can not only identify the type of the biological attachment substrate, but also output its distribution and density information, providing comprehensive ecological monitoring data support.

[0103] The analysis of the growth and health status of the biological attachment substrate includes:

[0104] Growth rate calculation: By analyzing the change in the density of the biological attachment substrate at different time points, its growth rate G is calculated. Let represent the density of the biological attachment substrate at time t, then the growth rate G is expressed as:

[0105] ;

[0106] where G is the growth rate, with the unit of density change amount / time, and respectively represent the densities of the biological attachment substrate at two different time points, is the time interval;

[0107] Water quality correlation analysis: To evaluate the impact of environmental conditions on the stability of the biological attachment substrate, the Pearson correlation coefficient r is used to analyze the correlation between water quality parameters and the density of the biological attachment substrate, expressed as:

[0108] ;

[0109] where X is the water quality parameter, D is the density of the biological attachment substrate, and are the means of X and D respectively;

[0110] Health status assessment: Combining the results of the growth rate and water quality correlation, by comparing with the healthy threshold and the unhealthy threshold and a correlation threshold are compared to comprehensively evaluate the health status of the biological attachment substrate. If and , it indicates health. If or , it indicates unhealthiness;

[0111] The health threshold and the unhealthiness threshold are determined by analyzing the growth rate distribution of the biological attachment substrate under different environmental conditions, specifically including:

[0112] Data collection: Under various different environmental conditions, collect the growth rate G data of the biological attachment substrate to form a sample data set , where represents the growth rate of the i-th sampling;

[0113] Calculate the mean and standard deviation of the growth rate: According to the collected growth rate data set, calculate the mean and the standard deviation , expressed as:

[0114] ;

[0115] ;

[0116] where N is the number of data samples, is the growth rate of the i-th sample;

[0117] Threshold setting: The health threshold is set to the mean plus one standard deviation, and the unhealthiness threshold is set to the mean minus one standard deviation, expressed as:

[0118] ;

[0119] ;

[0120] The setting of the correlation threshold specifically includes:

[0121] Data collection: Collect the correlation data between water quality parameters (temperature, salinity, pH value) and the density of the biological attachment substrate , where is the correlation coefficient of the i-th sampling;

[0122] Calculate the average value and standard deviation of the correlation coefficient: According to the collected data, calculate the mean and the standard deviation , expressed as:

[0123] ;

[0124] ;

[0125] where M is the number of correlation samples, is the correlation coefficient of the i-th sample;

[0126] Correlation threshold setting: Set the correlation threshold as the mean plus half of the standard deviation, expressed as:

[0127] ;

[0128] Through the above content, the correlation between the growth rate of the biological attachment base and environmental conditions is considered, which can dynamically respond to changes in different environments, accurately judge the health status of the biological attachment base. Based on data-driven threshold setting, it effectively avoids the deviation caused by manual setting, provides a reliable and accurate evaluation basis for deep-sea ecological monitoring, and helps to make more scientific ecological protection and restoration decisions.

[0129] Environmental data collection includes:

[0130] Dissolved oxygen data collection: Collect the dissolved oxygen concentration in the water body in real time through a dissolved oxygen sensor;

[0131] pH data collection: Use a pH sensor to monitor the pH value of the water body in real time;

[0132] Particle size data collection: Measure the particle size distribution of suspended particles in the water through a particle size analysis sensor to provide water turbidity and particle information;

[0133] Heavy metal ion data collection: Use a heavy metal ion sensor to detect the concentration of heavy metal ions in the water body, including cadmium, lead, and mercury;

[0134] Through the above content, it can not only reflect the changes in the oxygen content and pH value in the water body, but also capture the suspended particle situation and heavy metal pollution level in the water body, thus providing comprehensive and in-depth support for deep-sea ecological monitoring, helping to detect environmental anomalies in a timely manner, and providing strong data basis for ecological protection and risk management.

[0135] Data preprocessing includes:

[0136] Noise filtering: Use a moving average filtering algorithm to filter the noise of the collected environmental data and remove abnormal data caused by sensor errors or environmental interference, expressed as:

[0137] ;

[0138] where, represents the data point after smoothing, is the original data point, and q is the window radius, which determines the size of the smoothing window (i.e., the window size is );

[0139] Normalization: The environmental data after noise filtering is normalized to eliminate the dimensional differences of different parameters, expressed as:

[0140] ;

[0141] where represents the normalized data value, is the data point after noise filtering, and are the mean and standard deviation of the data respectively;

[0142] Through the above content, the quality and consistency of the collected environmental data are effectively improved. Noise filtering can remove abnormal data caused by sensor errors or environmental interference, making the data more stable and reliable. Normalization adjusts the values of different parameters to the same scale, eliminates dimensional differences, and ensures the accuracy and comparability of environmental data.

[0143] Environmental change analysis and assessment include:

[0144] Analysis of environmental change trends: A linear regression algorithm is used to analyze the trends of the preprocessed environmental data to capture the microclimate and sediment dynamic changes in the deep-sea mining area, expressed as:

[0145] ;

[0146] where is the environmental data value at time t, is the intercept, representing the initial environmental state, is the trend coefficient, reflecting the change speed and direction of the environmental data. By calculating the trend coefficient , the rising or falling trend of environmental parameters is judged;

[0147] Assessment of the impact of dynamic changes on biological attachment substrates: Based on the results of the environmental change trend analysis and combined with the correlation analysis of the recovery ability of biological attachment substrates, the impact of environmental changes on biological attachment substrates is evaluated. Using the correlation analysis method, the correlation coefficient between environmental changes and the recovery ability (growth rate) of biological attachment substrates is calculated, expressed as:

[0148] ;

[0149] where is the correlation coefficient of environmental changes, used to measure the impact of the environmental change trend value on the growth rate G of biological attachment substrates, is the environmental change trend value, representing the change trend of environmental data within a certain time period. G is the growth rate of the biological attachment base, defined as the density change rate, which is a key indicator representing the recovery ability. is the environmental change trend value the mean value of the mean value of the growth rate G of the biological attachment base;

[0150] Through the above content, the promotion or inhibition effect of environmental changes on the recovery ability of the biological attachment base can be accurately quantified, helping to identify key influencing factors. By combining dynamic trend analysis and correlation assessment, the complex relationship between environmental conditions and ecological restoration can be captured in real time, providing a comprehensive and reliable decision-making basis for the ecological management of deep-sea mining areas.

[0151] The present invention covers any substitutions, modifications, equivalent methods, and schemes made on the essence and scope of the present invention. To enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention without the description of these details. In addition, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0152] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An evaluation system for the ecological restoration ability and potential of deep-sea mining based on biological attachment substrates, characterized in that, It includes a data acquisition module, a biological attachment substrate recognition module, and a deep-sea ecological dynamic monitoring module, where; The data acquisition module collects water quality parameters of the deep-sea mining area through multiple sensors, including the temperature, depth, and salinity of the ocean water body; The biological attachment substrate recognition module identifies and analyzes the population distribution, density, and morphology of the biological attachment substrate, and combines the collected water quality parameters to evaluate the growth and health status of the biological attachment substrate; The deep-sea ecological dynamic monitoring module monitors the environmental data of the deep-sea mining area in real time through sensors, including the microclimate and sediment. By analyzing the dynamic changes of the microclimate and sediment in the mining area, it evaluates the impact of environmental changes on the recovery ability of the biological attachment substrate. Specifically, it includes: Environmental data acquisition: Use deep-sea sensors to collect various environmental data of the deep-sea mining area in real time, including dissolved oxygen, pH value, particle size, and heavy metal ions; Data preprocessing: Preprocess the collected environmental data, including noise filtering and standardization processing; Analysis and evaluation of environmental changes: Analyze the preprocessed environmental data to evaluate the impact of the dynamic changes of the microclimate and sediment in the deep-sea mining area on the recovery ability of the biological attachment substrate; The biological attachment substrate recognition module includes: Image acquisition and preliminary processing of biological attachment substrate: Use underwater image acquisition equipment to collect image data of the biological attachment substrate in the deep-sea mining area in real time, and perform preliminary processing on the collected image data, including denoising, image enhancement, and segmentation; Recognition of biological attachment substrate: Use a convolutional neural network model to recognize the preliminarily processed image data, analyze the population distribution, density, and morphology of the biological attachment substrate, and judge the distribution of the biological attachment substrate in different regions; Analysis of the growth and health status of biological attachment substrate: Based on the results of the biological attachment substrate recognition, by analyzing the correlation between water quality parameters and the growth of the biological attachment substrate, evaluate the growth rate and health status of the biological attachment substrate under different water quality conditions.

2. The evaluation system for the ecological restoration ability and potential of deep-sea mining based on a biological attachment substrate according to claim 1, wherein The data acquisition module includes: Temperature data acquisition: Use a temperature sensor to measure the temperature of the water body in the deep-sea mining area in real time, and record the water temperature changes at each specified location and depth; Depth data acquisition: Use a depth sensor to monitor the water depth in the deep-sea mining area in real time, and capture the depth changes in the deep-sea water area; Salinity data acquisition: Use a salinity sensor to measure the salinity of the water body in the deep-sea mining area.

3. The evaluation system for the ecological restoration ability and potential of deep - sea mining based on a biological attachment substrate according to claim 1, characterized in that, The image acquisition and preliminary processing of the biological attachment substrate include: Underwater image acquisition: Use an underwater camera to collect image data of the biological attachment substrate in the deep-sea mining area in real time; Image denoising: Use the Gaussian filtering algorithm to suppress the noise of the collected image data; Image enhancement: Use histogram equalization to improve the contrast and details of the image data; Image segmentation: Use the Otsu threshold method to separate the biological attachment substrate area in the image data from the background.

4. The deep-sea mining ecological restoration ability and potential evaluation system based on a biological attachment base according to claim 3, wherein The convolutional neural network model includes: Multi-scale feature extraction: Extract multi-scale features of an image through convolutional kernels of different scales, and splice the convolutional results of all scales to obtain a multi-scale feature map O multi ; Fully connected layer: Flatten the multi-scale feature map O multi into a one-dimensional feature vector F, and input the flattened feature vector F into the fully connected layer to generate a feature representation f c (x, y); Pixel Classification: For each pixel point (x, y) in the comprehensive feature map, use the Softmax classifier to classify f c (x, y); Segmentation result: By taking the maximum value of the classification probability of each pixel, the segmentation result S(x,y) is obtained; Distribution and density calculation: According to the segmentation results, the distribution and density information of the biological attachment base are statistically analyzed. The segmentation result S(x, y) carries the category information of each pixel and is directly used to judge the spatial distribution of the biological attachment base. The density D of the biological attachment base is calculated by counting the number of pixels belonging to the biological attachment base category.

5. The evaluation system for the ecological restoration ability and potential of deep-sea mining based on a biological attachment base according to claim 4, wherein, The analysis of the growth and health status of the biological attachment base includes: Growth rate calculation: By analyzing the change in the density of the biological attachment base at different time points, its growth rate G is calculated; Water quality correlation analysis: The Pearson correlation coefficient r is used to analyze the correlation between water quality parameters and the density of the biological attachment base; Health status assessment: Combining the results of the correlation between growth rate and water quality, by comparing with the healthy threshold T healthy and the unhealthy threshold T unhealthy as well as the correlation threshold T correlation to comprehensively evaluate the health status of the biological attachment base. If G>T healthy and |r|>T correlation , it is indicated as healthy. If G<T unhealthy or |r|<T correlation , it is indicated as unhealthy.

6. The evaluation system for the ecological restoration ability and potential of deep - sea mining based on a biological attachment base according to claim 5, wherein, The environmental data collection includes: Dissolved oxygen data collection: The dissolved oxygen concentration in the water body is collected in real time through a dissolved oxygen sensor; pH data collection: The pH sensor is used to monitor the pH value of the water body in real time; Particle size data collection: The particle size distribution of suspended particles in the water is measured through a particle size analysis sensor to provide water turbidity and particle information; Heavy metal ion data collection: The heavy metal ion sensor is used to detect the concentration of heavy metal ions in the water body, including cadmium, lead, and mercury.

7. The evaluation system for the deep-sea mining ecological restoration ability and potential based on a biological attachment substrate according to claim 6, characterized in that, The data preprocessing includes: Noise filtering: The moving average filtering algorithm is used to filter the noise of the collected environmental data; Standardization processing: The environmental data after noise filtering is standardized.

8. The evaluation system for the ecological restoration ability and potential of deep-sea mining based on a biological attachment substrate according to claim 7, wherein The environmental change analysis and evaluation include: Environmental change trend analysis: The linear regression algorithm is used to analyze the trend of the preprocessed environmental data to capture the microclimate and sediment dynamic changes in the deep-sea mining area; Impact assessment of dynamic changes on the biological attachment base: Based on the results of the environmental change trend analysis, combined with the correlation analysis of the recovery ability of the biological attachment base, the impact of environmental changes on the biological attachment base is evaluated. The correlation analysis method is used to calculate the correlation coefficient r′ between environmental changes and the recovery ability of the biological attachment base.

Images