Protection area management planning method and system based on aquatic product resource survey data

Abstract

The invention relates to the technical field of aquatic product resource management, in particular to a protection area management planning method and system based on aquatic product resource survey data, and the method comprises the steps of data collection and preprocessing, data fusion and feature extraction, aquatic product resource evaluation and analysis, protection area management planning making, dynamic monitoring and adjustment and decision support and visual display. The method comprises the following steps: deploying aquatic product resource investigation equipment, remote sensing equipment and environment monitoring equipment, acquiring aquatic product resource data in real time, identifying key feature variables, performing partition evaluation on aquatic product resources by combining a clustering analysis method, formulating a protection area management plan, and performing resource change trend prediction through dynamic monitoring and a machine learning algorithm. Dynamic adjustment of protection area management is realized, a visual tool is used to display a resource change trend and a management state, and real-time decision support is provided for a decision department. According to the method, the management capability of the aquatic product resource protection area can be effectively improved, and a scientific guarantee is provided for ecological protection and sustainable utilization of resources.

Description

Technical Field

[0001] The present invention relates to the technical field of aquatic resource management, and in particular to a method and system for planning management of a protected area based on aquatic resource survey data. Background Art

[0002] Aquatic resource protection areas are usually used to restrict fishing activities, restore ecosystems, and ensure the growth and reproduction of aquatic species. In order to achieve effective aquatic resource management, scientific data collection, accurate resource assessment, and timely dynamic monitoring and adjustment have become indispensable links. Modern technologies, especially remote sensing technology, water quality monitoring technology, environmental sensing technology, and machine learning algorithms, have been widely used in the monitoring, analysis, and management of aquatic resources.

[0003] The current management of aquatic resource protection areas mostly relies on manual monitoring and regular surveys, and there are information islands between most monitoring equipment and technologies. The data sources are not unified, and the data is missing or not timely, resulting in inaccurate resource assessment results and difficulty in meeting the needs of dynamic management. In the existing technology, although remote sensing equipment and water quality monitoring sensors are widely used in data collection, due to the lag of data processing methods and the difficulty of multi-source data fusion, it is often impossible to efficiently extract key characteristic variables from a large amount of complex data, resulting in the inability to conduct real-time and accurate assessment of the dynamic changes of aquatic resources. Traditional protection area management plans often require long-term manual intervention to make adjustments, lack intelligent dynamic management capabilities, and are difficult to cope with the rapid changes in aquatic resources and sudden environmental problems. Summary of the invention

[0004] The invention provides a protection zone management planning method and system based on aquatic resource survey data.

[0005] The protected area management planning method based on aquatic resource survey data includes the following steps:

[0006] S1, data collection and preprocessing: by deploying aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment, aquatic resource data are collected in real time. Aquatic resource data include water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors. The collected aquatic resource data are preprocessed, including data cleaning and data standardization;

[0007] S2, data fusion and feature extraction: using multivariate data fusion technology to fuse aquatic resource data, combined with deep learning algorithms to extract features, and identify key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity;

[0008] S3, aquatic resource assessment and analysis: Based on the key characteristic variables extracted in S2, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human interference, so as to divide the protected area into regions and evaluate the ecological status of each region;

[0009] S4, Development of the protected area management plan: Based on the assessment results of S3 and in combination with the principle of sustainable use of aquatic resources, a protected area management plan is developed, including the demarcation of protected area boundaries, the priority of conservation measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration;

[0010] S5, Dynamic Monitoring and Adjustment: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the reserve, combine machine learning algorithms to predict resource change trends in the reserve, and dynamically adjust the management plan of the reserve based on the prediction results;

[0011] S6, Decision support and visualization: Combine assessment results, planning schemes and dynamic monitoring data to display the management status of the protected area, resource change trends and adjustment suggestions through visualization tools, providing a scientific basis for relevant decision-making departments.

[0012] Optionally, the S1 includes:

[0013] S11, aquatic resources survey equipment: including temperature probes, conductivity sensors, pH sensors, aquatic organism detectors and fishing vessel positioning equipment, including;

[0014] The temperature probe is used to collect temperature data of water bodies;

[0015] Conductivity sensors are used to collect salinity data of water bodies;

[0016] pH sensors are used to collect data on the pH value of water bodies;

[0017] Aquatic life detectors are used to collect data on the distribution of aquatic life;

[0018] Fishing vessel positioning equipment is used to collect fishery data, including fishing location and time, and obtain catch data;

[0019] Remote sensing equipment: including satellite remote sensing sensors and drone remote sensing technology. The satellite remote sensing sensors are used to obtain geographical information of a large area of ​​water bodies, and the collected data include water surface temperature, vegetation coverage and water changes. The drone remote sensing technology is equipped with high-resolution cameras and infrared sensors to photograph water bodies and surrounding areas, obtain the location of pollution sources, the concentration of pollutants on the water surface and changes in water boundaries;

[0020] Environmental monitoring equipment: including water flow rate sensors, sediment analyzers and pollutant monitoring instruments. The water flow rate sensors are used to collect water flow rate, the sediment analyzers are used to collect the particle size, water content and heavy metal content of bottom sediments and provide sediment characteristic data, and the pollutant monitoring instruments are used to monitor pollutant concentration data in water areas, including heavy metals, pesticide residues and nutrient salt concentrations;

[0021] S12, data cleaning: cleaning the collected aquatic resources data to remove abnormal data, duplicate data and missing values;

[0022] S13, data standardization: standardize the cleaned data to ensure the consistency of dimensions between different data types and avoid deviations caused by differences in data dimensions.

[0023] Optionally, S2 includes:

[0024] S21, data fusion: Data from different data sources (including water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors) are fused by weighted averaging to generate a unified data set;

[0025] S22, feature extraction: Based on the generated data set, a convolutional neural network is used for feature extraction. The architecture of the convolutional neural network includes several convolutional layers, pooling layers, and fully connected layers;

[0026] S23, feature output: key feature variables related to aquatic resource protection are identified through convolutional neural networks, including aquatic community structure, habitat distribution, and environmental carrying capacity;

[0027] S24, feature importance assessment: importance analysis of the extracted features was performed, and the SHAP value was used to assess the contribution of each feature to aquatic resource protection;

[0028] S25, screening key features: Through SHAP value evaluation, features with high contribution (the SHAP value of a feature accounts for more than 20% of all features, defined as high contribution) are taken as key features, including aquatic community structure, habitat distribution and environmental carrying capacity, to screen out the variables with the most conservation significance.

[0029] Optionally, the S3 includes:

[0030] S31, resource richness assessment: Based on the extracted key characteristic variables, a preliminary zoning assessment of aquatic resources was conducted using cluster analysis methods;

[0031] S32, evaluation indicators: The evaluation indicators of aquatic resource richness include population density, species diversity index and water quality index;

[0032] S33, Application of assessment results: Different water areas are divided according to the assessment results of aquatic resource richness to provide a basis for protection measures and resource management.

[0033] Optionally, S3 further includes:

[0034] S34, Ecological sensitivity assessment: Based on the extracted key characteristic variables, the ecological sensitivity of the aquatic resource area was assessed using the analytic hierarchy process;

[0035] S35, disturbance assessment: Based on the impact of human activities on aquatic resources, the human activity index model is used to assess the disturbance;

[0036] S36, evaluation indicators: Ecological sensitivity and disturbance evaluation indicators include ecological sensitivity index and human activity index;

[0037] S37, Application of assessment results: Formulate management strategies for protected areas based on the results of ecological sensitivity and disturbance assessments.

[0038] Optionally, the S4 includes:

[0039] S41, demarcation of protected area boundaries: based on the results of the aquatic resource assessment in S3, the boundaries of the protected area shall be demarcated in combination with the regional resource richness, ecological sensitivity and human activity interference factors;

[0040] S42, Priority setting of protection measures: Based on the results of ecological sensitivity and human interference assessment, combined with the principle of sustainable use of aquatic resources, priority settings for protection measures within the protected area are established.

[0041] Optionally, S4 further includes:

[0042] S43, Restriction and guidance of fishery activities: Based on the disturbance assessment results and resource abundance, formulate targeted fishery management measures;

[0043] S44, Establishment of a timetable for ecological restoration: Based on the results of the ecological sensitivity assessment and combined with the recovery capacity of aquatic resources, establish a timetable for ecological restoration.

[0044] Optionally, the S5 includes:

[0045] S51, prediction of resource change trend: Based on the real-time monitored aquatic resource data and the extracted key characteristic variables, the XGBoost regression model is used to predict the change trend of aquatic resources in the protected area;

[0046] S52, dynamic adjustment based on prediction results: According to the prediction results of the XGBoost regression model, the management plan of the protected area is adjusted dynamically in a timely manner.

[0047] Optionally, the S6 includes:

[0048] S61, Dynamic resource change trend display: Display the dynamic trend of aquatic resource changes through visualization tools;

[0049] S62, Decision support and risk assessment: Based on the displayed resource change trends and management status, the visualization platform will provide scientific basis for decision-makers to evaluate the effectiveness of different management measures, such as fishing restrictions and ecological restoration measures.

[0050] The protected area management planning system based on aquatic resource survey data is used to implement the above-mentioned protected area management planning method based on aquatic resource survey data, and includes the following modules:

[0051] Data collection module: used to collect aquatic resource data in real time through aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment. The aquatic resource data includes water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors. The collected aquatic resource data is preprocessed, including data cleaning and data standardization.

[0052] Data fusion and feature extraction module: It uses multivariate data fusion technology to fuse aquatic resource data, combines deep learning algorithms to extract features, and identifies key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity;

[0053] Aquatic resource assessment module: Based on the extracted key characteristic variables, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human interference, so as to divide the protected area into regions and assess the ecological status of each region;

[0054] Reserve Planning Module: Based on the results of aquatic resource assessment and in combination with the principle of sustainable use of aquatic resources, formulate a reserve management plan, including the demarcation of reserve boundaries, the priority of protection measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration;

[0055] Dynamic monitoring and adjustment module: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the protected area, combine machine learning algorithms to predict resource change trends in the protected area, and dynamically adjust the management plan of the protected area based on the prediction results;

[0056] Decision support and visualization module: Use visualization tools to display the changing trends of aquatic resources, the management status of protected areas and adjustment suggestions, and provide data support and decision-making basis for relevant decision-making departments.

[0057] Beneficial effects of the present invention:

[0058] The present invention collects comprehensive water quality parameters, environmental factors, aquatic biological distribution and fishery catch data in real time by integrating aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment. It can effectively cover various resource data in different waters to ensure the comprehensiveness and real-time nature of resource monitoring. Combined with multivariate data fusion technology and using deep learning algorithms to extract key feature variables, it can accurately identify key factors related to aquatic resource protection, such as aquatic biological community structure, habitat distribution, etc., thereby providing reliable data support for subsequent resource assessment and formulation of protection measures.

[0059] The present invention uses cluster analysis to evaluate aquatic resources in different regions. It can make detailed evaluations of aquatic resource conditions in different regions based on indicators such as resource richness, ecological sensitivity, and human activity interference, and help formulate targeted management plans for protected areas. According to the evaluation results, the boundaries of protected areas are automatically delineated, ecological protection priorities are set, and restrictions and guidance measures for fishery activities are formulated, which can ensure that the planning of protected areas is scientific, targeted, and operational, and effectively promote the sustainable use of aquatic resources and ecological environmental protection.

[0060] The present invention uses real-time monitoring data and machine learning models to dynamically predict the changing trends of aquatic resources, and adjusts the management plan of the protected area in real time based on the prediction results, ensuring that the management plan of the protected area can respond to resource changes and environmental changes in a timely manner. Through visualization tools, the changing trends of aquatic resources, the management status of the protected area and adjustment suggestions are displayed, providing real-time and accurate decision-making support for decision-making departments, improving the transparency and emergency response capabilities of decision-making departments to resource changes, enabling them to quickly make response decisions in a changing environment, and effectively ensuring the sustainability of aquatic resources and the ecological security of protected areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] 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.

[0062] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0063] Figure 2 Schematic diagram of a system flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0064] 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.

[0065] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0066] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0067] like Figure 1 As shown in the figure, the protected area management planning method based on aquatic resource survey data includes the following steps:

[0068] S1, data collection and preprocessing: by deploying aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment, aquatic resource data are collected in real time. Aquatic resource data include water quality parameters (such as temperature, salinity, pH value), aquatic organism distribution data, fishery catch data and environmental factors (such as water flow speed, sediment characteristics). The collected aquatic resource data are preprocessed, including data cleaning and data standardization;

[0069] S2, data fusion and feature extraction: using multivariate data fusion technology to fuse aquatic resource data, combined with deep learning algorithms to extract features, and identify key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity;

[0070] S3, aquatic resource assessment and analysis: Based on the key characteristic variables extracted in S2, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human interference, so as to divide the protected area into regions and evaluate the ecological status of each region;

[0071] S4, Development of the protected area management plan: Based on the assessment results of S3 and in combination with the principle of sustainable use of aquatic resources, a protected area management plan is developed, including the demarcation of protected area boundaries, the priority of conservation measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration;

[0072] S5, Dynamic Monitoring and Adjustment: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the reserve, combine machine learning algorithms to predict resource change trends in the reserve, and dynamically adjust the management plan of the reserve based on the prediction results;

[0073] S6, Decision support and visualization: Combine assessment results, planning schemes and dynamic monitoring data to display the management status of the protected area, resource change trends and adjustment suggestions through visualization tools, providing a scientific basis for relevant decision-making departments.

[0074] S1 includes:

[0075] S11, aquatic resources survey equipment: including temperature probes, conductivity sensors, pH sensors, aquatic organism detectors and fishing vessel positioning equipment, including;

[0076] The temperature probe is used to collect temperature data of water bodies;

[0077] Conductivity sensors are used to collect salinity data of water bodies;

[0078] pH sensors are used to collect data on the pH value of water bodies;

[0079] Aquatic life detectors are used to collect data on the distribution of aquatic life;

[0080] Fishing vessel positioning equipment is used to collect fishery data, including fishing location and time, and obtain catch data;

[0081] Remote sensing equipment: including satellite remote sensing sensors and drone remote sensing technology. Satellite remote sensing sensors are used to obtain geographical information of a large area of ​​water bodies. The collected data include water surface temperature, vegetation coverage and water changes. Drone remote sensing technology is equipped with high-resolution cameras and infrared sensors to photograph water bodies and surrounding areas, obtain the location of pollution sources, the concentration of pollutants on the water surface and changes in water boundaries;

[0082] Environmental monitoring equipment: including water flow rate sensors, sediment analyzers and pollutant monitoring instruments. Water flow rate sensors are used to collect water flow rate. Sediment analyzers are used to collect the particle size, water content and heavy metal content of bottom sediments and provide sediment characteristic data. Pollutant monitoring instruments are used to monitor pollutant concentration data in water areas, including heavy metals, pesticide residues and nutrient salt concentrations.

[0083] S12, data cleaning: Clean the collected aquatic resource data to remove abnormal data, duplicate data and missing values. The specific cleaning methods include:

[0084] Outlier detection: Identify outliers in data through statistical analysis and rule detection. For example, outliers can be identified based on data distribution (such as mean ± 3 times standard deviation) and marked or corrected.

[0085] Missing value filling: Use interpolation methods (such as linear interpolation or KNN interpolation) to fill in missing data. For each missing value, use the weighted average of its surrounding adjacent data points to fill in the missing part. The calculation formula is:

[0086] ;

[0087] in, is the filling value for missing data, is the observed value of the surrounding K neighboring data points, is the weight corresponding to the adjacent data points;

[0088] Deduplication: Check and delete duplicate records through data comparison methods to ensure the uniqueness of each data point;

[0089] S13, data standardization: standardize the cleaned data to ensure the consistency of dimensions between different data types and avoid deviations caused by differences in data dimensions.

[0090] S2 includes:

[0091] S21, data fusion: Data from different data sources (including water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors) are fused by weighted averaging to generate a unified data set;

[0092] Weighted average method: Assume that the weights of different data sources are , then the fused data is:

[0093] ;

[0094] in, is the fused data, is the input data of the ith data source, and the weight satisfy ;

[0095] S22, feature extraction: Based on the generated data set, a convolutional neural network is used for feature extraction. The architecture of the convolutional neural network includes several layers of convolutional layers, pooling layers, and fully connected layers. The structure is as follows:

[0096] (1) Input layer: Input the fused aquatic resources data in the form of a matrix or three-dimensional tensor (such as temperature, salinity, pH value and other parameters);

[0097] (2) Convolutional layer: Use convolution kernels to perform convolution operations on the input data to extract local features. For example, the convolution kernel The correlation between temperature and salinity can be identified, and the convolution operation formula is:

[0098] ;

[0099] in, is the convolution result, is the convolution kernel, For input data;

[0100] (3) Pooling layer: The maximum pooling operation is used to reduce the dimension of the data while retaining the key features. The pooling operation is:

[0101] ;

[0102] (4) Fully connected layer: The features extracted by the convolutional layer and the pooling layer are input into the fully connected layer to generate the final feature vector and output the key features;

[0103] S23, feature output: key feature variables related to aquatic resource protection are identified through convolutional neural networks, including aquatic community structure, habitat distribution and environmental carrying capacity, among which;

[0104] Aquatic community structure: Identify the diversity and richness of community structure based on the distribution characteristics of different aquatic species;

[0105] Habitat distribution: infer the suitability and distribution of habitats based on parameters such as water temperature, salinity, and pH value;

[0106] Environmental carrying capacity: Based on water quality parameters and biological distribution in the water body, the environmental carrying capacity of the water body is estimated, that is, the maximum capacity of the water body to support aquatic biological communities;

[0107] S24, feature importance assessment: The extracted features were analyzed for importance, and the SHAP value was used to assess the contribution of each feature to aquatic resource protection. The SHAP value formula is expressed as:

[0108] ;

[0109] in, For feature subset The model output is: For specific features, is the set of all features;

[0110] S25, screening key features: Through SHAP value evaluation, features with high contribution (SHAP value of a feature accounts for more than 20% of all features, defined as high contribution) are selected as key features, including aquatic community structure, habitat distribution and environmental carrying capacity, to screen out the variables with the most conservation significance;

[0111] Through data fusion combined with convolutional neural network feature extraction, key features related to aquatic resource protection can be effectively extracted from multi-source data, such as aquatic community structure, habitat distribution and environmental carrying capacity. These features provide accurate ecological data support for the division and management of protected areas. Through SHAP value evaluation, we can further ensure the key role of these features in resource protection and improve the scientific nature and implementation effect of aquatic resource protection.

[0112] S3 includes:

[0113] S31, resource richness assessment: Based on the extracted key characteristic variables, a preliminary zoning assessment of aquatic resources is conducted through cluster analysis, including:

[0114] Conduct a comprehensive analysis of data on water resources density, species diversity, and water quality indicators to form a preliminary basis for assessment;

[0115] The K-means cluster analysis method was selected to divide the water area into multiple areas according to resource richness, which facilitated the subsequent resource management and formulation of protection measures;

[0116] The cluster analysis process includes the following steps:

[0117] Step 1: Data preprocessing: Standardize the extracted key feature variables to ensure data consistency and eliminate dimensional differences;

[0118] Step 2: Initialize the cluster center: Select the initial cluster center according to the resource characteristics of the water area; the cluster center can be selected by random initialization method or by using the distribution characteristics of the data;

[0119] Step 3: Assign data points: assign the characteristic data of each water area to the cluster center closest to it to form a preliminary grouping;

[0120] Step 4: Update the cluster center: calculate the mean of each category and update the location of the cluster center;

[0121] Step 5, iterative calculation: repeat steps 3 and 4 until the cluster center position no longer changes or the preset number of iterations is reached;

[0122] S32, Evaluation indicators: The evaluation indicators of aquatic resource richness include population density, species diversity index and water quality index, among which;

[0123] Population density: the number of aquatic organisms per unit area, reflecting the resource potential of the water area;

[0124] Species diversity index: Species diversity calculated based on the Shannon-Weiner index, reflecting the ecological health of the water body;

[0125] Water quality index: Combined with water quality parameters such as temperature, salinity, pH value, etc., to comprehensively analyze the resource richness of the water area;

[0126] S33, Application of assessment results: Different water areas are divided according to the results of the aquatic resource richness assessment to provide a basis for protection measures and resource management, including:

[0127] For areas with high resource abundance, it is recommended to focus on protection and consider restricting fishing activities;

[0128] For areas with low resource richness, consider ecological restoration or adjust protection strategies;

[0129] Through cluster analysis methods, water areas can be scientifically divided according to their resource richness, and targeted protection measures can be formed, laying the foundation for the rational utilization and sustainable development of aquatic resources.

[0130] S3 also includes:

[0131] S34, Ecological Sensitivity Assessment: Based on the extracted key characteristic variables, the ecological sensitivity of the aquatic resource area is assessed using the hierarchical analysis method, including:

[0132] (1) Determine the evaluation indicators: Determine the evaluation indicators of ecological sensitivity based on factors such as the stability of the habitat environment of aquatic organisms, water pollution index, and ecological restoration capacity;

[0133] (2) Constructing a hierarchical structure: The evaluation criteria and specific indicators of ecological sensitivity are layered, with the top layer being ecological sensitivity, the second layer being the evaluation criteria (such as water quality changes, species adaptability, etc.), and the third layer being the specific evaluation items (such as various water quality changes, species protection levels, etc.);

[0134] (3) Calculation of sensitivity index: Based on the analytic hierarchy process, through expert questionnaires and data analysis, the weights and scores of various evaluation indicators are combined to calculate the ecological sensitivity index of each water area;

[0135] S35, Disturbance Assessment: Based on the impact of human activities on aquatic resources, the human activity index model is used to assess the degree of disturbance, including:

[0136] (1) Assess regional interference factors: Obtain data on the intensity of human activities in each region, such as fishing intensity, pollution source emissions, and shipping frequency, through satellite remote sensing sensors, drone remote sensing technology, and ground monitoring data;

[0137] (2) Quantifying the interference degree: After standardizing each interference factor, the overall interference degree of human activities is calculated using the weighted average method to form an interference degree index;

[0138] S36, Evaluation indicators: Ecological sensitivity and disturbance evaluation indicators include ecological sensitivity index and human activity index, among which;

[0139] Ecological sensitivity index: a comprehensive score calculated based on the analytic hierarchy process model, reflecting the fragility and susceptibility of the ecological environment in a region to disturbance;

[0140] Human Activity Index: It comprehensively considers the impact of various human activities on water bodies and assesses the ecological disturbance of the region;

[0141] S37, Application of assessment results: Based on the results of ecological sensitivity and disturbance assessment, formulate management strategies for the protected area, including:

[0142] Areas with high ecological sensitivity and low disturbance should be given priority protection and human interference should be limited;

[0143] For areas with low ecological sensitivity and high disturbance, consider strengthening ecological restoration and adopting stricter management measures;

[0144] Through comprehensive assessment of ecological sensitivity and interference, key protection areas can be identified and decision support can be provided for the rational use of aquatic resources, ensuring that the aquatic ecological environment is effectively protected and sustainably utilized.

[0145] S4 includes:

[0146] S41, Delineation of the boundaries of the protected area: Based on the results of the S3 aquatic resource assessment, combined with the regional resource richness, ecological sensitivity and human activity interference factors, the boundaries of the protected area shall be delineated, including:

[0147] (1) Data analysis: Based on the results of cluster analysis, areas with high resource richness and high ecological sensitivity were selected as the core areas of the reserve;

[0148] (2) Boundary determination: Based on the ecological characteristics of the water body, the specific boundaries of the protected area shall be determined to ensure that important ecological areas such as key habitats and breeding areas of aquatic resources are covered;

[0149] (3) Scientific computing and model application: Use geographic information system technology combined with ecological sensitivity analysis to accurately define the scope of the protected area and ensure that the ecological functions of the protected area are maintained to the greatest extent;

[0150] S42, Priority setting of protection measures: Based on the results of ecological sensitivity and human disturbance assessment, combined with the principle of sustainable use of aquatic resources, priority of protection measures in the protected area is set, including:

[0151] (1) Assessment of key factors: Assess the urgency and necessity of implementing conservation measures in each region based on the recovery potential of aquatic resources, the fragility of habitats, and the impact of human activities;

[0152] (2) Prioritization: Different areas within the protected area are classified, with priority given to areas with fragile ecology and less human interference, and the most stringent protection measures adopted;

[0153] (3) Strategy formulation: Formulate specific protection measures, including restrictions on fishing activities, control of catches, and management of pollution sources, to ensure the long-term stability of ecological functions;

[0154] By scientifically defining the boundaries of the protected area and rationally setting priorities for protection measures, we can ensure that the ecological environment within the protected area is scientifically and rationally protected while maximizing the sustainable use of aquatic resources.

[0155] S4 also includes:

[0156] S43, Restriction and guidance of fishery activities: Based on the disturbance assessment results and resource abundance, formulate targeted fishery management measures, including:

[0157] (1) Restrictions on fishing activities: Implement fishing restrictions in areas with low resource abundance and high ecological sensitivity, clearly define the upper limit of fishing volume, the demarcation of no-fishing zones, and the limitation of fishing seasons;

[0158] (2) Guidance of fishery activities: In areas where fishery activities have little impact, measures to guide fishery activities should be formulated, such as optimizing the allocation of fishery resources and encouraging the use of low-impact fishing techniques, so as to strike a balance between resource utilization and ecological protection;

[0159] (3) Monitoring and control: Using real-time fishery data, dynamically adjust restrictions and guidance measures on fishery activities to ensure that fishery activities do not cause overexploitation and ecological burden on aquatic resources in the protected area;

[0160] S44, Ecological Restoration Timetable: Based on the results of the ecological sensitivity assessment and the recovery capacity of aquatic resources, a timetable for ecological restoration will be developed, including:

[0161] (1) Restoration target setting: Based on the results of resource richness and ecological sensitivity assessment, determine the ecological restoration targets for each region, including species diversity restoration, water quality improvement, etc.;

[0162] (2) Phased plan: formulate short-term, medium-term and long-term ecological restoration plans, and clarify the specific goals and implementation measures for each stage, such as habitat restoration, pollution control, and ecological restoration projects;

[0163] (3) Timetable and monitoring: Set a timetable for each restoration goal, specify restoration indicators at different stages, and coordinate with the ecological monitoring system to conduct dynamic evaluation and adjustment to ensure the effectiveness of restoration measures;

[0164] By effectively restricting and guiding fishery activities and formulating a scientific ecological restoration timetable, we can promote the restoration and improvement of the ecological environment while protecting aquatic resources, ensuring a balance between ecological protection and sustainable use.

[0165] S5 includes:

[0166] S51, prediction of resource change trend: Based on the real-time monitored aquatic resource data and the extracted key characteristic variables, the XGBoost regression model is used to predict the change trend of aquatic resources in the protected area. The specific steps include:

[0167] Feature selection and construction: Select characteristic variables related to the changing trends of aquatic resources, including water quality parameters, aquatic organism distribution, fishery catch data and environmental factors;

[0168] Model training: The XGBoost regression model is used to train the collected historical aquatic resource data and real-time aquatic resource data. The basic expression of the XGBoost regression model is as follows:

[0169] ;

[0170] in, is the predicted resource change value, For the The weight of a tree, For the Trees for input features The predicted output is is the total number of trees;

[0171] Model tuning and validation: Improve the accuracy and robustness of the model through cross-validation and parameter tuning (such as tree depth, learning rate, etc.);

[0172] S52, dynamic adjustment based on prediction results: According to the prediction results of the XGBoost regression model, the management plan of the protected area is dynamically adjusted in a timely manner. The specific steps include:

[0173] Resource change assessment: Evaluate the changing trend of aquatic resources based on the forecast results, such as the increase or decrease of fishery resources, the deterioration or recovery of the ecological environment, etc.;

[0174] Adjusting protected area management measures: Based on the predicted trend of change, adjust the management measures for fishery activities, the priority of protection measures, and the fishing volume in the protected area. For example, in areas where fishery resources are decreasing, fishing restrictions can be strengthened; in areas where resources are abundant or recovering well, restrictions can be moderately relaxed;

[0175] By dynamically predicting the changing trends of protected area resources through machine learning-based prediction models, potential resource changes can be discovered in a timely manner, and real-time adjustments can be made to protected area management measures based on the prediction results. This can improve the adaptability and flexibility of management and ensure the sustainable protection of resources.

[0176] S6 includes:

[0177] S61, Dynamic resource change trend display: Use visualization tools to display the dynamic trend of aquatic resource changes. The specific steps include:

[0178] Trend chart display: Based on the prediction results in S5 and the real-time monitored aquatic resource data, time series charts, heat maps and other visualization methods are used to display the resource change trends in different waters, such as the increase and decrease of fishery resources and changes in the state of the ecosystem;

[0179] Multi-dimensional data visualization: Display multi-dimensional data through dashboards, 3D views, GIS geographic information systems, etc., including resource distribution, habitat status, spatial layout of fishery activity areas and protected areas, etc.;

[0180] Dynamic update: As real-time monitoring data is continuously updated, the visual display is also updated to ensure the timeliness and accuracy of the displayed content;

[0181] S62, Decision support and risk assessment: Based on the displayed resource change trends and management status, the visualization platform will provide scientific basis for decision-makers to evaluate the effects of different management measures, such as catch limits and ecological restoration measures;

[0182] By combining dynamic monitoring data, assessment results and management plans, and using visualization tools to display the changing trends, management status and adjustment suggestions of aquatic resources, the transparency and real-time nature of protected area management by decision-makers can be effectively improved.

[0183] like Figure 2As shown, the protected area management planning system based on aquatic resource survey data is used to implement the above-mentioned protected area management planning method based on aquatic resource survey data, and includes the following modules:

[0184] Data collection module: used to collect aquatic resource data in real time through aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment. The aquatic resource data includes water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors. The collected aquatic resource data is preprocessed, including data cleaning and data standardization.

[0185] Data fusion and feature extraction module: It uses multivariate data fusion technology to fuse aquatic resource data, combines deep learning algorithms to extract features, and identifies key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity;

[0186] Aquatic resource assessment module: Based on the extracted key characteristic variables, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human interference, so as to divide the protected area into regions and assess the ecological status of each region;

[0187] Reserve Planning Module: Based on the results of aquatic resource assessment and in combination with the principle of sustainable use of aquatic resources, formulate a reserve management plan, including the demarcation of reserve boundaries, the priority of protection measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration;

[0188] Dynamic monitoring and adjustment module: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the protected area, combine machine learning algorithms to predict resource change trends in the protected area, and dynamically adjust the management plan of the protected area based on the prediction results;

[0189] Decision support and visualization module: Use visualization tools to display the changing trends of aquatic resources, the management status of protected areas and adjustment suggestions, and provide data support and decision-making basis for relevant decision-making departments.

[0190] 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.

[0191] 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 protected area management planning method based on aquatic resource survey data, characterized in that: The following steps are involved: S1, data collection and preprocessing: by deploying aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment, aquatic resource data are collected in real time. Aquatic resource data include water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors. The collected aquatic resource data are preprocessed, including data cleaning and data standardization; S2, data fusion and feature extraction: using multivariate data fusion technology to fuse aquatic resource data, combined with deep learning algorithms to extract features, and identify key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity; S3, aquatic resource assessment and analysis: Based on the key characteristic variables extracted in S2, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human activity interference, so as to divide the protected area into regions and evaluate the ecological status of each region; S4, Development of the protected area management plan: Based on the assessment results of S3 and in combination with the principle of sustainable use of aquatic resources, a protected area management plan is developed, including the demarcation of protected area boundaries, the priority of conservation measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration; S5, Dynamic Monitoring and Adjustment: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the reserve, combine machine learning algorithms to predict resource change trends in the reserve, and dynamically adjust the management plan of the reserve based on the prediction results; S6, Decision support and visualization: Combine assessment results, planning schemes and dynamic monitoring data to display the management status of the protected area, resource change trends and adjustment suggestions through visualization tools, providing a scientific basis for relevant decision-making departments.

2. The method for planning and managing a protected area based on aquatic resource survey data according to claim 1 is characterized in that: The S1 includes: S11, aquatic resources survey equipment: including temperature probes, conductivity sensors, pH sensors, aquatic organism detectors and fishing vessel positioning equipment, including; The temperature probe is used to collect temperature data of water bodies; Conductivity sensors are used to collect salinity data of water bodies; pH sensors are used to collect data on the pH value of water bodies; Aquatic life detectors are used to collect data on the distribution of aquatic life; Fishing vessel positioning equipment is used to collect fishery data, including fishing location and time, and obtain catch data; Remote sensing equipment: including satellite remote sensing sensors and drone remote sensing technology. The satellite remote sensing sensors are used to obtain geographical information of water bodies, and the collected data include water surface temperature, vegetation coverage and water changes. The drone remote sensing technology is equipped with cameras and infrared sensors to photograph water bodies and surrounding areas, obtain the location of pollution sources, the concentration of pollutants on the water surface and changes in water boundaries; Environmental monitoring equipment: including water flow rate sensors, sediment analyzers and pollutant monitoring instruments. The water flow rate sensors are used to collect water flow rate, the sediment analyzers are used to collect the particle size, water content and heavy metal content of bottom sediments and provide sediment characteristic data, and the pollutant monitoring instruments are used to monitor pollutant concentration data in water areas, including heavy metals, pesticide residues and nutrient salt concentrations; S12, data cleaning: cleaning the collected aquatic resources data to remove abnormal data, duplicate data and missing values; S13, data standardization: standardize the cleaned data to ensure the consistency of dimensions between different data types and avoid deviations caused by differences in data dimensions.

3. The method for planning and managing a protected area based on aquatic resource survey data according to claim 2 is characterized in that: The S2 includes: S21, data fusion: data from different data sources are fused by weighted averaging to generate a unified data set; S22, feature extraction: Based on the generated data set, feature extraction is performed using a convolutional neural network. The architecture of the convolutional neural network includes several convolutional layers, pooling layers, and fully connected layers; S23, feature output: key feature variables related to aquatic resource protection are identified through convolutional neural networks, including aquatic community structure, habitat distribution, and environmental carrying capacity; S24, feature importance assessment: importance analysis of the extracted features was performed, and the SHAP value was used to assess the contribution of each feature to aquatic resource protection; S25, screening key features: through SHAP value evaluation, features with high contribution are taken as key features, including aquatic community structure, habitat distribution and environmental carrying capacity.

4. The method for planning and managing a protected area based on aquatic resource survey data according to claim 3 is characterized in that: The S3 includes: S31, resource richness assessment: Based on the extracted key characteristic variables, a preliminary zoning assessment of aquatic resources was conducted using cluster analysis methods; S32, evaluation indicators: The evaluation indicators of aquatic resource richness include population density, species diversity index and water quality index; S33, Application of assessment results: Different water areas are divided according to the assessment results of aquatic resource richness to provide a basis for protection measures and resource management.

5. The method for planning and managing a protected area based on aquatic resource survey data according to claim 4 is characterized in that: The S3 further includes: S34, Ecological sensitivity assessment: Based on the extracted key characteristic variables, the ecological sensitivity of the aquatic resource area was assessed using the analytic hierarchy process; S35, disturbance assessment: Based on the impact of human activities on aquatic resources, the human activity index model is used to assess the disturbance; S36, evaluation indicators: Ecological sensitivity and disturbance evaluation indicators include ecological sensitivity index and human activity index; S37, Application of assessment results: Formulate management strategies for protected areas based on the results of ecological sensitivity and disturbance assessments.

6. The method for planning and managing a protected area based on aquatic resource survey data according to claim 5 is characterized in that: The S4 includes: S41, demarcation of protected area boundaries: based on the results of the aquatic resource assessment in S3, the boundaries of the protected area shall be demarcated in combination with the regional resource richness, ecological sensitivity and human activity interference factors; S42, Priority setting of protection measures: Based on the results of ecological sensitivity and human interference assessment, combined with the principle of sustainable use of aquatic resources, priority settings for protection measures within the protected area are established.

7. The method for planning and managing a protected area based on aquatic resource survey data according to claim 6 is characterized in that: The S4 further comprises: S43, Restriction and guidance of fishery activities: Based on the disturbance assessment results and resource abundance, formulate targeted fishery management measures; S44, Establishment of a timetable for ecological restoration: Based on the results of the ecological sensitivity assessment and combined with the recovery capacity of aquatic resources, establish a timetable for ecological restoration.

8. The method for planning and managing a protected area based on aquatic resource survey data according to claim 7 is characterized in that: The S5 includes: S51, prediction of resource change trend: Based on the real-time monitored aquatic resource data and the extracted key characteristic variables, the XGBoost regression model is used to predict the change trend of aquatic resources in the protected area; S52, dynamic adjustment based on prediction results: According to the prediction results of the XGBoost regression model, the management plan of the protected area is adjusted dynamically in a timely manner.

9. The method for planning and managing a protected area based on aquatic resource survey data according to claim 8 is characterized in that: The S6 includes: S61, Dynamic resource change trend display: Display the dynamic trend of aquatic resource changes through visualization tools; S62, Decision support and risk assessment: Provide scientific basis for decision-making departments based on the displayed resource change trends and management status.

10. A protected area management planning system based on aquatic resource survey data, used to implement a protected area management planning method based on aquatic resource survey data as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: used to collect aquatic resource data in real time through aquatic resource survey equipment, remote sensing equipment and environmental monitoring equipment. The aquatic resource data includes water quality parameters, aquatic organism distribution data, fishery catch data and environmental factors. The collected aquatic resource data is preprocessed, including data cleaning and data standardization. Data fusion and feature extraction module: It uses multivariate data fusion technology to fuse aquatic resource data, combines deep learning algorithms to extract features, and identifies key characteristic variables related to aquatic resource protection, including aquatic community structure, habitat distribution, and environmental carrying capacity; Aquatic resource assessment module: Based on the extracted key characteristic variables, cluster analysis method is used to conduct regional assessment of aquatic resources. The assessment indicators include resource richness, ecological sensitivity and human interference, so as to divide the protected area into regions and assess the ecological status of each region; Reserve Planning Module: Based on the results of aquatic resource assessment and in combination with the principle of sustainable use of aquatic resources, formulate a reserve management plan, including the demarcation of reserve boundaries, the priority of protection measures, the restriction and guidance of fishery activities, and the timetable for ecological restoration; Dynamic monitoring and adjustment module: Use real-time monitoring of aquatic resource data to dynamically monitor changes in aquatic resources in the protected area, combine machine learning algorithms to predict resource change trends in the protected area, and dynamically adjust the management plan of the protected area based on the prediction results; Decision support and visualization module: Use visualization tools to display the changing trends of aquatic resources, the management status of protected areas and adjustment suggestions, and provide data support and decision-making basis for relevant decision-making departments.

Images