Marine aquaculture area planning system based on remote sensing mapping

Abstract

The present invention provides a marine aquaculture area planning system based on remote sensing mapping, which relates to the field of data processing technology, including: a geographic information module for integrating and managing remote sensing data to construct a comprehensive database containing various geographic information; screening the comprehensive database to generate a preliminary screened marine aquaculture area; a three-dimensional modeling module for constructing a three-dimensional terrain model of a target sea area based on the preliminary screened marine aquaculture area using water depth information and seabed terrain data in remote sensing data; superimposing seawater temperature, salinity, and water quality parameters on the three-dimensional terrain model in the form of a three-dimensional layer to form a three-dimensional marine aquaculture environment model; and a breeding suitability assessment module for calculating the breeding suitability assessment results of each area based on the three-dimensional marine aquaculture environment model. The present invention can intuitively and realistically display the terrain characteristics of the target sea area.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, in particular to a marine aquaculture area planning system based on remote sensing mapping. Background Art

[0002] In the past, in the planning of marine aquaculture areas, two-dimensional plane maps were usually used to present the general situation of the sea area. This display method is indeed concise and clear, and can roughly show the basic characteristics and layout of the sea area. However, it also inevitably has some limitations, especially in showing the complex and changeable three-dimensional spatial characteristics of the sea area.

[0003] Specifically, the environmental parameters involved in marine aquaculture areas, such as water depth, seabed topography, water temperature, salinity, and water quality, are actually distributed and evolved in three-dimensional space. These parameters are crucial for assessing the suitability of aquaculture areas. However, traditional two-dimensional plane maps are somewhat inadequate in showing the vertical changes and distribution of these parameters, thus affecting the comprehensive and in-depth assessment of the aquaculture environment. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a marine aquaculture area planning system based on remote sensing mapping, which constructs a three-dimensional terrain model using the water depth and seabed topography information in the remote sensing data, and superimposes parameters such as seawater temperature, salinity, and water quality on it in the form of three-dimensional layers, forming an intuitive and comprehensive three-dimensional marine aquaculture environment model that can maximize the use of marine resources.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] Marine aquaculture area planning system based on remote sensing mapping, including:

[0007] A remote sensing data acquisition module is used to acquire remote sensing data of the target sea area, wherein the remote sensing data includes sea water temperature, salinity, water depth, water quality and seabed topography information;

[0008] Geographic information module, used to integrate and manage remote sensing data to build a comprehensive database containing various geographic information; screen the comprehensive database to generate preliminary screened marine aquaculture areas;

[0009] The 3D modeling module is used to construct a 3D terrain model of the target sea area based on the initially screened marine aquaculture area using the water depth information and seabed terrain data in the remote sensing data; the seawater temperature, salinity, and water quality parameters are superimposed on the 3D terrain model in the form of 3D layers to form a 3D marine aquaculture environment model;

[0010] Aquaculture suitability assessment module, used to calculate the aquaculture suitability assessment results of each area based on the three-dimensional marine aquaculture environment model;

[0011] The planning optimization module is connected to the aquaculture suitability assessment module and is used to generate an optimized marine aquaculture area planning scheme based on the aquaculture suitability assessment results.

[0012] Furthermore, remote sensing data of the target sea area is obtained, including:

[0013] The target sea area is divided into multiple grids, each grid represents a survey point, and the process of ants moving on the grid and selecting the next survey point represents path selection;

[0014] An initial pheromone value is assigned to each path between grids, and each ant selects the next survey point based on the pheromone concentration and heuristic information of the grids around the current position;

[0015] After each ant completes a path selection, it updates the pheromone on the path according to the acquired data quality and path length, and obtains the final survey plan through multiple iterations;

[0016] According to the final survey plan, remote sensing data of the target sea area is obtained.

[0017] Furthermore, the comprehensive database was screened to generate preliminary screened marine aquaculture areas, including:

[0018] Extracting data related to marine aquaculture from a comprehensive database, including seawater temperature, salinity, water depth, water quality indicators including dissolved oxygen, pH and nutrient concentration, and seafloor topography information;

[0019] The number of clusters K is determined by the elbow rule, and K data points are randomly selected from the comprehensive database as the initial cluster centers;

[0020] Assign data points to corresponding cluster centers to form K clusters, and recalculate the center of each cluster until the preset number of iterations is reached to obtain the clustering result;

[0021] Use the silhouette coefficient to evaluate the clustering results to obtain the evaluation results;

[0022] Based on the assessment results, identify cluster areas for farming;

[0023] A preliminary screening is carried out based on the clustering areas of aquaculture, as well as the preset screening area area and shape regularity to obtain the preliminary screened marine aquaculture area.

[0024] Further, preliminary screening is performed based on the clustering areas of aquaculture, as well as the preset screening area area and shape regularity to obtain the preliminary screened marine aquaculture areas, including:

[0025] Set the filter conditions and population size, where the population size refers to the number of individuals in each generation;

[0026] Each cultured cluster area is represented as an individual, and the boundary coordinates of the cultured cluster area are used as the gene code of the individual, and the initial population is randomly generated to make the individuals in the population diverse;

[0027] Define the fitness function used to evaluate the quality of each individual;

[0028] Calculate the fitness value of each individual according to the fitness function, determine the corresponding individual as the parent according to the fitness value, and randomly pair the selected parent individuals;

[0029] Perform crossover operation at a certain crossover rate to generate new offspring individuals, perform mutation operation on the new offspring individuals at a certain mutation rate to generate new gene mutations, and iterate until the preset number of iterations is reached to obtain the final individual;

[0030] The aquaculture clustering areas corresponding to the final individuals are marked as the initially screened marine aquaculture areas.

[0031] Furthermore, based on the initially screened marine aquaculture areas, the water depth information and seabed topography data in the remote sensing data are used to construct a three-dimensional terrain model of the target sea area, including:

[0032] Extracting a discrete point set from the water depth information and seabed topography data, each point in the discrete point set contains its geographic coordinates and elevation value;

[0033] Automatically constructs a triangulated irregular network based on an input point set to generate a series of interconnected triangles, each defined by three adjacent points;

[0034] Define a grid on the target area to store the elevation value of each point;

[0035] For each point in the grid, find the triangle it is in, and use the elevation values ​​of the three vertices of the triangle to perform interpolation calculations to obtain the elevation values ​​corresponding to each grid point;

[0036] A three-dimensional seabed terrain model is created based on the elevation values ​​corresponding to each grid point. The three-dimensional seabed terrain model is a surface composed of multiple triangles, and each triangle represents a unit in the grid.

[0037] Furthermore, the seawater temperature, salinity and water quality parameters are superimposed on the three-dimensional terrain model in the form of three-dimensional layers to form a three-dimensional marine aquaculture environment model, including:

[0038] For each grid point in the three-dimensional terrain model, the distance between each grid point and all measured data points is calculated respectively, wherein the measured data point refers to the location point where data is obtained during the actual measurement process, and each measured data point has a definite geographical location;

[0039] The inverse of the distance is used as the weight to perform weighted averaging on the measured parameter values ​​to obtain a weighted average value, wherein the measured parameter value is the specific value of the environmental parameter directly measured at the measured data point, specifically including seawater temperature, salinity and water quality parameters;

[0040] The weighted average value is taken as the environmental monitoring value of the corresponding grid point;

[0041] For each environmental monitoring value, create a new three-dimensional layer data structure, the data structure of each layer corresponds to the grid structure of the three-dimensional terrain model, so that each grid point has a corresponding environmental monitoring value; fill the environmental monitoring value of each grid point into the corresponding three-dimensional layer;

[0042] The seawater temperature, salinity and water quality parameters at each grid point are assigned corresponding colors, and the generated three-dimensional layers of seawater temperature, salinity and water quality parameters are superimposed on the three-dimensional seabed terrain model to form a three-dimensional marine aquaculture environment model.

[0043] Furthermore, based on the three-dimensional marine aquaculture environment model, the aquaculture suitability assessment results of each area are calculated, including:

[0044] Identify key environmental indicators for assessing aquaculture suitability;

[0045] Standardize key environmental indicators to obtain standardized data;

[0046] Assign appropriate weights to each standardized data point based on the importance of the farmed species to each key environmental indicator;

[0047] For each grid point in the three-dimensional marine aquaculture environmental model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight.

[0048] Furthermore, for each grid point in the three-dimensional marine aquaculture environmental model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight, including:

[0049] For each grid point in the three-dimensional marine aquaculture environment model, according to its corresponding environmental monitoring value and weight, Calculate the aquaculture suitability assessment results for each grid point;

[0050] in, is the farming suitability score of the grid point; It is The weight of each environmental parameter; It is Environmental parameter monitoring values; It is Environmental parameter monitoring values; It is for Monitoring value Standardized processing; It is The nonlinear weight coefficients of the parameters; It is parameters and The interaction weights of the parameters; It is A nonlinear transformation function with parameters; is the interaction term between parameters; It is parameters and The quadratic interaction coefficients of the parameters; are the interaction terms between all parameters; and is the index variable; is the total number of environmental parameters, where

[0051] ;

[0052] ;

[0053] in, It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value; It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value.

[0054] Furthermore, based on the aquaculture suitability assessment results, an optimized marine aquaculture regional planning scheme is generated, including:

[0055] Randomly select K data points from the data set of aquaculture suitability assessment results as initial cluster centers;

[0056] For each point in the data set, calculate the Euclidean distance between it and each cluster center, and assign each point to the corresponding cluster center to form K initial clusters;

[0057] For each cluster, calculate the average value of all data points within it and use the average value as the new cluster center. Repeat the operation until the preset number of iterations is reached to generate the final clustering result.

[0058] According to the final clustering results, the characteristics of each cluster are analyzed to determine its corresponding suitability level, and according to the suitability level, a marine aquaculture regional planning scheme is generated.

[0059] Furthermore, key environmental indicators include seawater temperature, salinity, water quality parameters, and seafloor topographic characteristics.

[0060] The above scheme of the present invention includes at least the following beneficial effects.

[0061] The remote sensing data acquisition module can efficiently and accurately obtain diversified remote sensing data of the target sea area, including key information such as sea water temperature, salinity, water depth, water quality and seabed topography.

[0062] The data preprocessing module can improve the quality and availability of data and ensure the accuracy and reliability of analysis results by preprocessing the original remote sensing data.

[0063] The geographic information module can integrate and manage pre-processed data sets to build a comprehensive database containing a variety of geographic information. It is not only convenient for data storage, query and update, but also can quickly generate preliminary marine aquaculture area recommendations through comprehensive analysis and screening, greatly improving the efficiency and accuracy of planning work.

[0064] The three-dimensional terrain model is constructed by using the water depth information and seabed terrain data in the remote sensing data, which can intuitively and realistically show the terrain characteristics of the target sea area. At the same time, the seawater temperature, salinity, water quality and other parameters are superimposed on the terrain model in the form of three-dimensional layers, forming a more complex and realistic three-dimensional marine aquaculture environment model, which helps to understand and analyze the detailed characteristics of the aquaculture environment in detail.

[0065] Based on the three-dimensional marine aquaculture environment model, the aquaculture suitability assessment results of each area can be calculated, which helps to formulate more reasonable and feasible aquaculture plans according to the aquaculture conditions in different areas, thereby optimizing resource allocation and improving aquaculture efficiency.

[0066] The planning optimization module, combined with the aquaculture suitability assessment results, can generate optimized marine aquaculture area planning schemes, which can further improve the overall benefits of marine aquaculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of a marine aquaculture area planning system based on remote sensing mapping provided by an embodiment of the present invention.

[0068] Figure 2It is a schematic diagram of a process of acquiring remote sensing data of a target sea area in a marine aquaculture area planning system based on remote sensing mapping provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0070] like Figure 1 and Figure 2 As shown, an embodiment of the present invention proposes a marine aquaculture area planning system based on remote sensing mapping, comprising:

[0071] A remote sensing data acquisition module is used to acquire remote sensing data of the target sea area, wherein the remote sensing data includes sea water temperature, salinity, water depth, water quality and seabed topography information;

[0072] Geographic information module, used to integrate and manage remote sensing data to build a comprehensive database containing various geographic information; screen the comprehensive database to generate preliminary screened marine aquaculture areas;

[0073] The 3D modeling module is used to construct a 3D terrain model of the target sea area based on the initially screened marine aquaculture area using the water depth information and seabed terrain data in the remote sensing data; the seawater temperature, salinity, and water quality parameters are superimposed on the 3D terrain model in the form of 3D layers to form a 3D marine aquaculture environment model;

[0074] Aquaculture suitability assessment module, used to calculate the aquaculture suitability assessment results of each area based on the three-dimensional marine aquaculture environment model;

[0075] The planning optimization module is connected to the aquaculture suitability assessment module and is used to generate an optimized marine aquaculture area planning scheme based on the aquaculture suitability assessment results.

[0076] In the embodiment of the present invention, the remote sensing data acquisition module can comprehensively collect multi-dimensional information such as seawater temperature, salinity, water depth, water quality and seabed topography of the target sea area. These data are not only comprehensive, but also have high accuracy and objectivity because they are obtained by remote sensing mapping. The data preprocessing module can efficiently process a large amount of remote sensing data and convert it into a data set that can be used for analysis. The geographic information module can further integrate these data, build a comprehensive database, and quickly identify preliminary marine aquaculture areas through the screening function, greatly improving the efficiency and accuracy of planning work.

[0077] The 3D modeling module can construct a 3D terrain model of the target sea area based on remote sensing data, and superimpose key seawater parameters on it in the form of 3D layers to form a 3D marine aquaculture environment model. This intuitive visualization method helps planners to have a more comprehensive understanding of the marine environment and make more reasonable planning decisions. The aquaculture suitability assessment module can evaluate the aquaculture conditions in each area based on the 3D marine aquaculture environment model, which not only helps to identify the most suitable areas for aquaculture, but also helps to avoid potential risk areas and improve the survival rate and yield of aquaculture. The planning optimization module can generate an optimized marine aquaculture area planning scheme based on the results of the aquaculture suitability assessment. This can not only improve the utilization efficiency of marine resources.

[0078] In a preferred embodiment of the present invention, obtaining remote sensing data of a target sea area includes:

[0079] The target sea area is divided into multiple grids, each grid represents a survey point, and the process of ants moving on the grid and selecting the next survey point represents path selection;

[0080] An initial pheromone value is assigned to each path between grids, and each ant selects the next survey point based on the pheromone concentration and heuristic information of the grids around the current position;

[0081] After each ant completes a path selection, it updates the pheromone on the path according to the acquired data quality and path length, and obtains the final survey plan through multiple iterations;

[0082] According to the final survey plan, remote sensing data of the target sea area is obtained.

[0083] In the embodiment of the present invention, the survey path can be intelligently optimized through the ant algorithm. When each ant selects the next survey point, it will comprehensively consider the pheromone concentration and heuristic information, which makes the selection of the survey path both global and local optimal, thereby effectively reducing repeated surveys and missed areas, and improving survey efficiency. The ant algorithm has the characteristics of adaptive adjustment. In each iteration process, the pheromone on the path is dynamically updated according to the acquired data quality and path length, which enables the algorithm to continuously adjust the survey strategy according to the actual situation to better adapt to the complex environment of the target sea area. The ant algorithm is essentially a parallel search algorithm. Multiple ants perform path search at the same time, which not only speeds up the search speed, but also increases the robustness of the algorithm. Even if some survey points are abnormal or the data quality is poor, the algorithm can still find a feasible survey path through the search of other ants. By optimizing the survey path and adaptive adjustment capabilities, the method can cover the target sea area more comprehensively, thereby obtaining more comprehensive and accurate remote sensing data. The optimized survey path and efficient parallel search capability mean that unnecessary survey times and human and material resources can be reduced, thereby reducing the overall survey cost.

[0084] When applied specifically, the above steps specifically include the following steps:

[0085] Determine the latitude and longitude range or geographic coordinate boundary of the target sea area to be surveyed; divide the target sea area into multiple grids according to certain rules (such as equal spacing), and each grid will be regarded as a potential survey point. Assign a unique identifier (such as number, coordinates, etc.) to each grid so that it can be accurately identified and located in subsequent steps.

[0086] Assign an initial pheromone value to each path between two adjacent grids, which can be fixed; construct a pheromone matrix to store and update the pheromone values ​​on all paths, and each element of the matrix represents the pheromone concentration on the corresponding path.

[0087] The size of the pheromone matrix is ​​related to the number and layout of the target sea area grids. If the target sea area is divided into N grids, the pheromone matrix is ​​an N×N matrix. At the beginning of the algorithm, an initial pheromone value is assigned to the path between each two adjacent grids. This value can be fixed, such as set to 1 or a predetermined constant, which means that all paths have the same pheromone concentration at the beginning. Each element of the pheromone matrix represents the pheromone concentration on the corresponding path. For example, if the element pheromone[i][j] in the matrix represents the pheromone value on the path between grid i and grid j.

[0088] At the beginning of each iteration of the algorithm, a group of ants is initialized and randomly placed on the grid; each ant selects the next survey point to move to based on the pheromone concentration and heuristic information (such as distance) of the grid around the current position, which is achieved by calculating a probability value that is proportional to the product of the pheromone concentration and the heuristic information. Specifically, it includes:

[0089] Record the grid number or coordinates of the current ant; determine the set of movable grids around it (adjacent grids) based on the current ant's position; for each movable grid, obtain its pheromone concentration value and heuristic information value (such as the distance to the target point or the expected data quality).

[0090] For each movable grid, use the product of the pheromone concentration and the heuristic information as the attractiveness of the grid. Divide the attractiveness of each grid by the sum of the attractiveness of all movable grids to get the probability of the grid being selected. Based on the calculated probability value, use the roulette method to select a grid as the next survey point. First calculate the cumulative sum of the probabilities of all grids, and then generate a random number. The grid in which the random number falls within the cumulative probability interval is selected. Move the ant to the next selected survey point. Update the pheromone concentration as needed (globally update after the ant completes a full path, or locally update after each step of the ant). Repeat the above steps until the ant completes a full survey path or reaches the predetermined number of iterations.

[0091] According to the calculated probability value, the grid with the highest probability is selected as the next survey point, and the ant is moved to the grid. After the ant completes a path selection, the quality of the acquired remote sensing data is evaluated, including:

[0092] When the ant completes a path selection and reaches the target survey point, it uses remote sensing survey equipment (such as satellite sensors, drone cameras, etc.) to collect remote sensing data of the point. Make sure that the collected data contains necessary metadata, such as collection time, equipment parameters, etc.

[0093] Import remote sensing data from survey equipment or storage media into the data processing system, verify the integrity of the data, and ensure that there is no file damage or data loss; check the metadata of the data, including the acquisition time, location, equipment information, etc., to ensure the accuracy and traceability of the data. Identify the noise in the image, such as salt and pepper noise, stripe noise, etc., and apply the median filter to remove or reduce the noise in the image. Adjust the parameters of the filter according to the type and degree of noise to achieve the best denoising effect.

[0094] According to the calibration files or related documents of remote sensing equipment, obtain the coefficients and parameters required for radiation calibration; convert the pixel value (DN value) of the image into a radiation brightness value or reflectivity value with physical significance; verify the accuracy of calibration by comparing the reflectivity or radiation brightness value of known objects. Use remote sensing images to identify stable features in the sea area, such as islands, reefs, obvious bends in the coastline, or fixed facilities in the sea area (such as lighthouses, buoys, etc.). Use image processing software to accurately mark control points on the identified stable sea features and record the coordinate information of each control point in the image. Pixel coordinates or geographic coordinate systems can be used.

[0095] Ensure that the control points are evenly distributed throughout the farming area to capture the geometric distortion at different locations, and select a sufficient number of control points to improve the accuracy and reliability of geometric correction.

[0096] According to the distortion characteristics of the sea area image, a geometric transformation model is selected, such as a polynomial transformation or a local transformation model. The coordinate information of the marked control points is input into the selected geometric transformation model. For the polynomial transformation, the original coordinates and the corresponding target coordinates of each control point are provided. Using the coordinate information of the control points, the parameters of the geometric transformation model are solved by a mathematical optimization method (such as the least squares method) so that the solved model parameters can accurately describe the geometric relationship between the images.

[0097] Determine the size, resolution, and coordinate system of the geometrically corrected image to meet the needs of marine aquaculture area planning. Select a resampling method, such as bilinear interpolation or cubic convolution interpolation, to maintain image quality during the geometric correction process. Use the solved geometric transformation model parameters to map each pixel of the original remote sensing image to the corresponding position of the output image. For non-integer coordinate positions, use the selected resampling method for interpolation to generate geometrically corrected image pixel values. After geometric transformation and resampling, a new geometrically corrected remote sensing image is generated.

[0098] According to the characteristics of remote sensing data, key quality assessment indicators are selected, such as data resolution, signal-to-noise ratio, contrast, clarity, cloud cover, etc. For each assessment indicator, a reasonable threshold is set according to actual needs; for example, for data resolution, the minimum resolution requirement can be set according to application needs; for cloud cover, the maximum allowable cloud percentage can be set.

[0099] Select remote sensing data processing software, such as ENVI, ERDAS Imagine, or ArcGIS. Import the remote sensing data to be evaluated into the processing software. Perform appropriate preprocessing, such as format conversion, projection definition, etc., based on the data type and format. Use the tools in the software to measure the actual resolution of the remote sensing data. Use the statistical analysis function in the software to calculate the signal-to-noise ratio of the remote sensing data. Use image processing functions to analyze the contrast and clarity of the remote sensing data, which can be evaluated based on methods such as grayscale histograms and edge detection of the image. Use cloud detection algorithms or visual interpretation to estimate the percentage of cloud cover in the remote sensing data. Compare the indicator value of each survey point with the preset threshold or range; based on the comparison results, divide the data quality into different levels, such as excellent, good, medium, and poor. Perform statistical analysis on the evaluation results to identify the overall situation and potential problems of data quality.

[0100] The length of the path taken by the ants is calculated based on the actual distance between the grids; the pheromone update rules are formulated based on the data quality and path length. Generally speaking, the pheromone on the path with higher data quality and shorter path length should be increased, and vice versa. According to the update rules, the pheromone matrix is ​​adjusted accordingly to reflect the survey results of the ants in the current iteration.

[0101] Repeat the above steps multiple times to optimize the survey path through continuous iteration. In each iteration, the ants will select a new survey path based on the updated pheromone matrix and heuristic information. Set a termination condition (such as reaching the maximum number of iterations) and stop the iteration when the condition is met. Select the best survey path combination from all iterations as the final survey plan, which can be determined based on the total pheromone concentration and average data quality of the path.

[0102] According to the final survey plan, remote sensing survey equipment (such as satellites, drones, etc.) is deployed at the selected survey points. The remote sensing survey equipment is started to collect data from the target sea area. The collected data is transmitted back to the data center through appropriate communication methods (such as satellite communication, wireless network, etc.).

[0103] In a preferred embodiment of the present invention, the comprehensive database is screened to generate a preliminary screened marine aquaculture area, including:

[0104] Extracting data related to marine aquaculture from a comprehensive database, including seawater temperature, salinity, water depth, water quality indicators including dissolved oxygen, pH and nutrient concentration, and seafloor topography information;

[0105] The number of clusters K is determined by the elbow rule, and K data points are randomly selected from the comprehensive database as the initial cluster centers;

[0106] Assign data points to corresponding cluster centers to form K clusters, and recalculate the center of each cluster until the preset number of iterations is reached to obtain the clustering result;

[0107] Use the silhouette coefficient to evaluate the clustering results to obtain the evaluation results;

[0108] Based on the assessment results, identify cluster areas for farming;

[0109] A preliminary screening is carried out based on the clustering areas of aquaculture, as well as the preset screening area area and shape regularity to obtain the preliminary screened marine aquaculture area.

[0110] In an embodiment of the present invention, by extracting multidimensional data related to marine aquaculture (such as seawater temperature, salinity, water depth, water quality indicators and seabed topography information) from a comprehensive database, comprehensive and objective data support can be provided for the screening of aquaculture areas. This method reduces the subjective interference of human factors and makes the decision more scientific and accurate. The elbow rule is used to determine the number of clusters, and combined with iterative calculation, the data points can be efficiently divided into different clustering areas. This clustering method helps to identify potential marine aquaculture areas with similar environmental characteristics, thereby improving the efficiency and accuracy of screening. By using the silhouette coefficient to evaluate the clustering results, the quality of clustering can be quantitatively evaluated, thereby optimizing the clustering process. This evaluation mechanism helps to ensure that the marine aquaculture areas finally screened are consistent and representative in terms of environmental characteristics. Preliminary screening is performed according to the preset screening area area and shape regularity, making the screening process more flexible and customizable. This flexibility enables the method to adapt to marine aquaculture projects of different scales and needs, thereby improving its practicality and wide applicability.

[0111] When applied specifically, the above steps specifically include the following implementation process:

[0112] Connect to a comprehensive database through a database query language (such as SQL); select fields closely related to marine aquaculture from the database, including seawater temperature, salinity, water depth, water quality indicators (dissolved oxygen, pH value, nutrient concentration) and seabed topography information; export the selected data to a format suitable for subsequent analysis and processing, such as CSV or Excel files.

[0113] The exported data is cleaned and standardized to eliminate the influence of outliers and dimensional differences on the clustering results. By plotting clustering cost curves (such as SSE curves) under different K values, the optimal number of clusters K is determined according to the inflection point of the curve. K data points are randomly selected from the preprocessed data as the initial cluster centers. Using clustering algorithms such as K-means, the data points are assigned to the nearest cluster centers to form K clusters. The center of each cluster is then recalculated and the process is repeated until the preset number of iterations is reached or the cluster center no longer changes significantly. Record the cluster label to which each data point belongs, as well as the coordinates of the center point and the member list of each cluster.

[0114] For each data point, calculate its average distance to other points in the cluster to which it belongs (cohesion) and the average distance to the nearest point in a different cluster (separation). Calculate the silhouette coefficient based on these two distances to evaluate the compactness and separation of the clusters. Statistically analyze the distribution of the silhouette coefficients of all data points to determine the quality of the clustering effect. If the silhouette coefficients are generally high, it means that the clustering effect is good; if there are a large number of data points with low silhouette coefficients, it may be necessary to adjust the K value or re-cluster. Based on the evaluation results of the silhouette coefficient, you can adjust the K value, select different clustering algorithms, or modify the iteration stop conditions to optimize the clustering results.

[0115] Based on the cluster assessment results, select cluster areas with high aquaculture potential. These areas usually have suitable seawater temperature, salinity, water depth and water quality indicators. Use mapping tools or GIS software to display the selected high-potential cluster areas on the map in an intuitive way. This helps users understand the distribution and relative position of each area more clearly.

[0116] In a preferred embodiment of the present invention, preliminary screening is performed based on the clustered areas of aquaculture, and the preset screening area area and shape regularity to obtain the preliminary screened marine aquaculture area, including:

[0117] Set the filter conditions and population size, where the population size refers to the number of individuals in each generation;

[0118] Each cultured cluster area is represented as an individual, and the boundary coordinates of the cultured cluster area are used as the gene code of the individual, and the initial population is randomly generated to make the individuals in the population diverse;

[0119] Define the fitness function used to evaluate the quality of each individual;

[0120] Calculate the fitness value of each individual according to the fitness function, determine the corresponding individual as the parent according to the fitness value, and randomly pair the selected parent individuals;

[0121] Perform crossover operation at a certain crossover rate to generate new offspring individuals, perform mutation operation on the new offspring individuals at a certain mutation rate to generate new gene mutations, and iterate until the preset number of iterations is reached to obtain the final individual;

[0122] The aquaculture clustering areas corresponding to the final individuals are marked as the initially screened marine aquaculture areas.

[0123] In the embodiment of the present invention, through the application of genetic algorithm, the optimal solution can be searched in a global scope to avoid falling into the local optimum. This global optimization capability helps to find the area that best meets the preset conditions in multiple breeding cluster areas, and improves the accuracy and efficiency of screening. The genetic algorithm effectively maintains the diversity of the population by randomly generating the initial population and introducing crossover and mutation operations in the iterative process. This diversity helps the algorithm to explore a wider solution space during the search process, so that it is more likely to find the global optimal solution. By defining the fitness function to evaluate the quality of each individual, it can be easily adjusted according to different screening conditions and requirements. At the same time, the genetic algorithm itself has good scalability and can be easily combined with other optimization methods or strategies to further improve the screening effect. After setting the initial parameters and fitness function, the algorithm of the present invention can automatically perform iterative search, reduce the need for manual intervention, and improve the automation level of the screening process. Through multiple iterations and the selection mechanism of survival of the fittest, the genetic algorithm can gradually approach the optimal solution. At the same time, since the algorithm takes into account the diversity of the population during the search process, the results obtained have high reliability and stability.

[0124] When applied in practice, the specific implementation process of the above steps is as follows:

[0125] Screening criteria are set based on the actual needs and constraints of marine aquaculture. These criteria may include the minimum and maximum area of ​​the aquaculture area, the complexity or regularity of the shape, the water depth range, water quality indicators, etc.

[0126] Sets the number of individuals in the population, which affects the search power and efficiency of the genetic algorithm. The population size is usually determined based on the complexity of the problem and the available computing resources. A larger population can provide more genetic diversity, but it also increases the computational cost.

[0127] Encode the boundary coordinates of each farming cluster region into the genes of the individual. This can be achieved in a variety of ways, such as using a series of point coordinates to represent the outline of the region. Randomly select individuals from the set of farming cluster regions to form an initial population. Ensure that the individuals in the population are diverse, which increases the possibility of the algorithm exploring different solution spaces.

[0128] Define a fitness function that quantifies the suitability of each individual (i.e., farming cluster) for farming conditions. If the fitness function includes multiple factors, each factor needs to be assigned a weight to reflect its relative importance to the overall suitability.

[0129] The fitness of each individual in the population is evaluated using the defined fitness function. This involves converting the genetic code of the individual (i.e. the boundary coordinates of the breeding area) into actual breeding conditions and applying the fitness function for calculation. Based on the fitness value of the individual, the most fit individual is selected as the parent. This can be achieved through different selection strategies, such as roulette selection, tournament selection, etc. The purpose of selection is to ensure that excellent genes can be passed on to the next generation. Among them, the specific calculation formula of the fitness function is:

[0130] ;

[0131] in, Indicates The actual area of ​​the breeding area; Indicates the target area, that is, the area of ​​the ideal breeding area. and Respectively represent the minimum and maximum thresholds of the breeding area; Indicates The perimeter of the breeding area; Indicates The actual water depth of the aquaculture area; Indicates the target water depth, i.e. the water depth of the ideal breeding area; and Respectively represent the minimum and maximum thresholds of water depth; Indicates The breeding area The suitability value of each water quality indicator ranges from 0 to 1; Indicates the total number of water quality indicators; , , and Represents weight.

[0132] Randomly select two parent individuals and perform crossover at a certain crossover rate (i.e., the probability of performing a crossover operation). The crossover operation involves exchanging some genes of two parent individuals to produce new offspring individuals. This helps to combine the excellent characteristics of the parents. Mutate the offspring individuals at a certain mutation rate (i.e., the probability of performing a mutation operation). The mutation operation involves randomly changing certain parts of the individual's genes to introduce new genetic mutations. This helps the algorithm jump out of the local optimal solution and explore a wider solution space.

[0133] Repeat the above steps to continuously optimize the population through multiple generations of evolution. In each generation, excellent individuals are selected according to the fitness function, and new individuals are generated through crossover and mutation. Set a preset number of iterations as the termination condition. When this number is reached, the algorithm stops iterating and outputs the best individual in the current population. The aquaculture cluster area corresponding to this individual is the marine aquaculture area that has been initially screened.

[0134] In a preferred embodiment of the present invention, based on the initially screened marine aquaculture area, a three-dimensional terrain model of the target sea area is constructed using water depth information and seabed topography data in remote sensing data, including:

[0135] Extracting a discrete point set from the water depth information and seabed topography data, each point in the discrete point set contains its geographic coordinates and elevation value;

[0136] Automatically constructs a triangulated irregular network based on an input point set to generate a series of interconnected triangles, each defined by three adjacent points;

[0137] Define a grid on the target area to store the elevation value of each point;

[0138] For each point in the grid, find the triangle it is in, and use the elevation values ​​of the three vertices of the triangle to perform interpolation calculations to obtain the elevation values ​​corresponding to each grid point;

[0139] A three-dimensional seabed terrain model is created based on the elevation values ​​corresponding to each grid point. The three-dimensional seabed terrain model is a surface composed of multiple triangles, and each triangle represents a unit in the grid.

[0140] In an embodiment of the present invention, by utilizing the water depth information and seabed terrain data in remote sensing data, a discrete point set can be extracted more accurately, thereby constructing a more realistic and detailed three-dimensional seabed terrain model. This model can not only accurately reflect the ups and downs of the seabed terrain, but also provide an important reference for the site selection, planning and management of marine aquaculture areas. The present invention adopts a method of automatically constructing an irregular triangulated network, which can quickly generate interconnected triangular grids. This automated processing method not only improves the modeling efficiency, but also reduces human intervention and errors, making the model building process more efficient and reliable. By defining a grid for storing the elevation value of each point and performing interpolation calculations on each point in the grid, the present invention can flexibly adapt to the terrain characteristics of different sea areas. No matter how complex and changeable the seabed terrain is, the method can effectively generate a corresponding three-dimensional model to meet the needs of various application scenarios. The generated three-dimensional seabed terrain model is intuitive and easy to understand, which helps decision makers to fully grasp the terrain conditions of the target sea area.

[0141] When applied in practice, the specific implementation process of constructing a three-dimensional terrain model of the target sea area is as follows:

[0142] Extract discrete point sets from water depth information and seabed topography data, each point contains its geographic coordinates (longitude, latitude) and elevation value (water depth or seabed topography height). Store the extracted discrete point sets in an appropriate format (such as CSV, Shapefile, etc.).

[0143] Read the discrete point set extracted in the previous step as input; use a suitable triangulation algorithm (such as Delaunay triangulation, constrained Delaunay triangulation, etc.) to automatically triangulate the input point set. Generate a series of interconnected triangles according to the algorithm. Each triangle is defined by three adjacent points, ensuring that the sides of the triangle do not cross and maximize the minimum internal angle. Optimize the generated triangulated network, such as removing narrow triangles, smoothing edges, etc., to improve the stability and aesthetics of the model, and store the constructed irregular triangulated network in an appropriate format.

[0144] Define a regular grid system on the target sea area to store the elevation value of each point. The resolution of the grid should be determined according to the requirements and data accuracy. For each point in the grid, determine the triangle in which it is located, which is achieved through a search algorithm (such as nearest neighbor search, KD tree, etc.). Use the elevation values ​​of the three vertices of the triangle to perform interpolation calculations (such as linear interpolation, barycentric coordinate interpolation, etc.) to obtain the elevation value of each grid point. Store the calculated elevation value in the data structure corresponding to the grid point.

[0145] Read the elevation value of each grid point stored in the previous step as input data; based on the elevation value of each grid point, use 3D modeling software or library (such as OpenGL, Blender, 3D Studio Max, etc.) to create a 3D seafloor terrain model. The model is composed of a surface composed of multiple triangles, and each triangle represents a unit in the grid. Export the constructed 3D seafloor terrain model to common 3D file formats (such as OBJ, FBX, STL, etc.) for display and analysis on different platforms and applications.

[0146] In a preferred embodiment of the present invention, seawater temperature, salinity, and water quality parameters are superimposed on a three-dimensional terrain model in the form of a three-dimensional layer to form a three-dimensional marine aquaculture environment model, including:

[0147] For each grid point in the three-dimensional terrain model, the distance between each grid point and all measured data points is calculated respectively, wherein the measured data point refers to the location point where data is obtained during the actual measurement process, and each measured data point has a definite geographical location;

[0148] The reciprocal of the distance is used as the weight to perform weighted averaging on the measured parameter values ​​to obtain a weighted average value, wherein the measured parameter value is the specific value of the environmental parameter directly measured at the measured data point, specifically including seawater temperature, salinity and water quality parameters;

[0149] The weighted average value is taken as the environmental monitoring value of the corresponding grid point;

[0150] For each environmental monitoring value, create a new three-dimensional layer data structure, the data structure of each layer corresponds to the grid structure of the three-dimensional terrain model, so that each grid point has a corresponding environmental monitoring value; fill the environmental monitoring value of each grid point into the corresponding three-dimensional layer;

[0151] The seawater temperature, salinity and water quality parameters at each grid point are assigned corresponding colors, and the generated three-dimensional layers of seawater temperature, salinity and water quality parameters are superimposed on the three-dimensional seabed terrain model to form a three-dimensional marine aquaculture environment model.

[0152] In an embodiment of the present invention, by presenting key environmental indicators such as seawater temperature, salinity, and water quality parameters in the form of a three-dimensional layer and combining it with a three-dimensional seabed terrain model, a multi-dimensional comprehensive visualization of environmental information is achieved. This model is not only intuitive, but also can fully reflect the actual situation of the marine aquaculture environment. Based on a high-precision three-dimensional environmental model, aquaculture managers can more accurately assess the environmental suitability of different regions. For example, areas with the best conditions such as temperature, salinity, and water quality can be selected for aquaculture to improve aquaculture efficiency and product quality. The model can be used to monitor changes in the marine aquaculture environment in real time and promptly discover potential environmental problems such as abnormal temperature, salinity fluctuations, or water pollution. This helps to take timely countermeasures, reduce aquaculture risks, and ensure aquaculture safety. Through a comprehensive analysis of the marine aquaculture environment, marine resources can be used more effectively to avoid waste of resources. For example, the aquaculture types and densities can be reasonably adjusted according to the environmental characteristics of different regions to maximize the utilization of resources.

[0153] The following is the specific implementation process corresponding to each step, which is used to superimpose seawater temperature, salinity, and water quality parameters on the 3D terrain model in the form of 3D layers to construct a 3D marine aquaculture environment model:

[0154] Load the 3D terrain model grid data and measured data points (including location and environmental parameter values); for each grid point in the 3D terrain model, perform the following operations:

[0155] a. Get grid point coordinates: Extract the geographic coordinates (such as longitude and latitude) of the grid point.

[0156] b. Calculate the distance: Calculate the geographic distance between the grid point and all measured data points respectively. This can be achieved through the distance calculation formula under the geographic coordinate system (such as the Haversine formula); store the calculated distance value in an appropriate data structure for subsequent use.

[0157] For each grid point, the initial weight sum is 0, and the weighted sum of each environmental parameter (seawater temperature, salinity, water quality parameters) is 0. For each grid point, traverse all measured data points and perform the following operations:

[0158] a. Calculate weight: Take the inverse of the distance between the measured data point and the grid point as the weight. If the distance is 0 (i.e. the measured data point coincides with the grid point), assign a very large weight value or use the measured value directly.

[0159] b. Accumulate weights and parameter values: Add the weight to the sum of weights, and multiply the weight by the corresponding measured parameter value (seawater temperature, salinity, water quality parameter) and add it to the weighted sum of each parameter.

[0160] The weighted sum of each parameter is divided by the weighted sum to obtain the environmental monitoring value (weighted average seawater temperature, salinity, and water quality parameters) of the grid point. The calculated weighted average is stored in the data structure corresponding to the grid point.

[0161] Define a 3D layer data structure for each environmental monitoring parameter (seawater temperature, salinity, water quality parameters), which corresponds to the grid structure of the 3D terrain model. For each grid point, fill its environmental monitoring value (weighted average seawater temperature, salinity, water quality parameters) into the corresponding 3D layer data structure. Define a color mapping scheme for each environmental monitoring parameter, and map the parameter value to the color space, which can be achieved through a color bar or a color lookup table, so that different parameter values ​​correspond to different colors. According to the color mapping scheme, assign corresponding colors to the environmental monitoring values ​​at each grid point, and apply these colors to the corresponding 3D layer. Using 3D visualization software or library, overlay the 3D layers of seawater temperature, salinity, and water quality parameters with colors on the 3D seabed terrain model to form the final 3D marine aquaculture environment model. Export the constructed 3D marine aquaculture environment model to common 3D file formats (such as OBJ, FBX, etc.), and display and analyze it in appropriate platforms or applications.

[0162] In a preferred embodiment of the present invention, the aquaculture suitability assessment results of each area are calculated based on the three-dimensional marine aquaculture environment model, including:

[0163] Identify key environmental indicators for assessing aquaculture suitability;

[0164] Standardize key environmental indicators to obtain standardized data;

[0165] Assign appropriate weights to each standardized data point based on the importance of the aquaculture species to each key environmental indicator, including seawater temperature, salinity, water quality parameters, and seafloor topography;

[0166] For each grid point in the three-dimensional marine aquaculture environmental model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight.

[0167] In an embodiment of the present invention, by carefully evaluating key environmental indicators (such as seawater temperature, salinity, water quality parameters and seabed topographic features), farmers can more accurately select areas suitable for farming. This targeted selection helps farmed species grow under optimal environmental conditions, thereby improving farming efficiency and yield. Through the assessment of farming suitability, these high-risk areas can be discovered and avoided in a timely manner, reducing uncertainty and potential losses in the farming process. After understanding the suitability of farming in different areas, farmers can allocate resources more reasonably, such as placing more seedlings in areas with high suitability, or exploring other ways of utilization in areas that are not suitable for farming, thereby maximizing the utilization of resources. Through a comprehensive assessment of environmental indicators, the impact of farming activities on the marine ecological environment can be better understood. This helps to formulate more scientific and reasonable farming plans and management strategies to reduce negative impacts on the environment.

[0168] When applied specifically, the following steps are included:

[0169] Screen key environmental indicators that have a significant and quantifiable impact on aquaculture suitability, such as seawater temperature, salinity, water quality parameters (such as dissolved oxygen, ammonia nitrogen, nitrite, etc.) and seafloor topography characteristics (such as water depth, bottom type, etc.). Collect the original monitoring data of key environmental indicators corresponding to each grid point in the three-dimensional marine aquaculture environmental model. Clean the original data to remove outliers, missing values, and duplicate values ​​to ensure the accuracy and completeness of the data. Use appropriate mathematical methods (such as Z-score standardization, Min-Max standardization, etc.) to standardize each environmental indicator and convert it into dimensionless standardized data for subsequent comprehensive evaluation.

[0170] Conduct statistical analysis on the collected observation data to determine the sensitivity and tolerance range of aquaculture species to various environmental indicators (such as temperature, salinity, water quality parameters, etc.). Evaluate the survival, growth and reproduction capabilities of species under different environmental indicators to determine their adaptability. Analyze the sensitivity and adaptability data of aquaculture species to various environmental indicators; when there is a large amount of historical data or experimental data, statistical analysis methods (such as principal component analysis, entropy weight method, etc.) can be used to determine the objective weight of each environmental indicator. Calculate the weight value of each environmental indicator through the analytic hierarchy process (AHP), and adjust and optimize it according to the actual situation. For each grid point in the three-dimensional marine aquaculture environment model, calculate the aquaculture suitability assessment result of each grid point according to its corresponding environmental monitoring value and weight.

[0171] In a preferred embodiment of the present invention, for each grid point in the three-dimensional marine aquaculture environment model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight, including:

[0172] For each grid point in the three-dimensional marine aquaculture environment model, according to its corresponding environmental monitoring value and weight, Calculate the aquaculture suitability assessment results for each grid point;

[0173] in, is the farming suitability score of the grid point; It is The weight of each environmental parameter; It is Environmental parameter monitoring values; It is Environmental parameter monitoring values; It is for Monitoring value Standardized processing; It is The nonlinear weight coefficients of the parameters; It is parameters and The interaction weights of the parameters; It is A nonlinear transformation function with parameters; is the interaction term between parameters; It is parameters and The quadratic interaction coefficients of the parameters; are the interaction terms between all parameters; and is the index variable; is the total number of environmental parameters, where

[0174] ;

[0175] ;

[0176] in, It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value; It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value.

[0177] In the embodiment of the present invention, the formula can comprehensively consider multiple environmental parameters (such as seawater temperature, salinity, water quality parameters, etc.), rather than just a single indicator, so as to more comprehensively evaluate the aquaculture suitability of each grid point. This multi-parameter comprehensive evaluation method is closer to the complexity of the actual aquaculture environment and improves the accuracy of the evaluation. and interaction weights , and the quadratic interaction coefficient , which can capture the nonlinear relationship and interaction effect between environmental parameters. This treatment method can more finely characterize the impact of environmental factors on aquaculture suitability, especially when there are complex interactions between these factors. By calculating a specific aquaculture suitability score S for each grid point, the formula provides quantitative support for aquaculture decisions. Farmers can choose the most suitable aquaculture area based on the score, thereby optimizing resource allocation and improving aquaculture benefits.

[0178] In a preferred embodiment of the present invention, an optimized marine aquaculture area planning scheme is generated according to the aquaculture suitability assessment results, including:

[0179] Randomly select K data points from the data set of aquaculture suitability assessment results as initial cluster centers;

[0180] For each point in the data set, calculate the Euclidean distance between it and each cluster center, and assign each point to the corresponding cluster center to form K initial clusters;

[0181] For each cluster, calculate the average value of all data points within it and use the average value as the new cluster center. Repeat the operation until the preset number of iterations is reached to generate the final clustering result.

[0182] According to the final clustering results, the characteristics of each cluster are analyzed to determine its corresponding suitability level, and according to the suitability level, a marine aquaculture regional planning scheme is generated.

[0183] In an embodiment of the present invention, by cluster analysis, marine aquaculture areas of different suitability can be clearly divided. Farming in a high suitability area can make full use of the superior natural conditions of the area, such as suitable water temperature, salinity, water depth and water quality, so as to improve the growth rate and survival rate of farmed organisms, and then improve the overall farming efficiency and output. The planning scheme allocates resources according to the suitability level of each area to ensure that more resources are obtained in the high suitability area, which can avoid waste of resources and make farming activities more economical and efficient. By identifying low suitability areas, the planning scheme can help farmers avoid farming under unfavorable natural conditions, thereby reducing farming risks. At the same time, reasonable regional planning can also reduce unnecessary transportation and management costs, improve economic benefits, and reduce the negative impact on the marine environment through reasonable planning.

[0184] The specific steps include:

[0185] Randomly select K data points from the aquaculture suitability assessment result data set as the initial cluster centers. For each point in the data set (i.e., the assessment result of each aquaculture area), calculate the Euclidean distance between it and each cluster center, and assign each point to the cluster center closest to it, thereby forming K initial clusters. For each cluster, calculate the average value of all data points (i.e., the assessment results) within it, and use the average value as the new cluster center. Repeat the above process of assigning and updating cluster centers until the preset number of iterations is reached, thereby generating the final clustering result.

[0186] According to the final clustering results, the characteristics of each cluster are analyzed, including the average value and range of the aquaculture suitability evaluation indicators within it. Based on the characteristics of the cluster, a suitability level label is determined for each cluster, such as "high suitability", "medium suitability" and "low suitability". The location and range of each cluster are marked on the three-dimensional marine aquaculture environment model, and the marine aquaculture areas with different suitability levels are determined.

[0187] Specific aquaculture types, densities and management recommendations are proposed for each suitability level. For example, in high suitability areas, it is recommended to cultivate high-value seafood species, while in low suitability areas, low-density aquaculture or improvement measures may be recommended. According to the suitability level and aquaculture recommendations of each area, resources are rationally allocated and optimized to ensure the sustainability and economic benefits of aquaculture activities.

[0188] The above is 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 principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A marine aquaculture area planning system based on remote sensing mapping, characterized in that: include: A remote sensing data acquisition module is used to acquire remote sensing data of the target sea area, wherein the remote sensing data includes sea water temperature, salinity, water depth, water quality and seabed topography information; Geographic information module, used to integrate and manage remote sensing data to build a comprehensive database containing various geographic information; screen the comprehensive database to generate preliminary screened marine aquaculture areas; The 3D modeling module is used to construct a 3D terrain model of the target sea area based on the initially screened marine aquaculture area using the water depth information and seabed terrain data in the remote sensing data; the seawater temperature, salinity, and water quality parameters are superimposed on the 3D terrain model in the form of 3D layers to form a 3D marine aquaculture environment model; Aquaculture suitability assessment module, used to calculate the aquaculture suitability assessment results of each area based on the three-dimensional marine aquaculture environment model; The planning optimization module is connected to the aquaculture suitability assessment module and is used to generate an optimized marine aquaculture area planning scheme based on the aquaculture suitability assessment results; Based on the initially selected marine aquaculture areas, a three-dimensional terrain model of the target sea area is constructed using the water depth information and seabed topography data in remote sensing data, including: Extracting a discrete point set from the water depth information and seabed topography data, each point in the discrete point set contains its geographic coordinates and elevation value; Automatically constructs a triangulated irregular network based on an input point set to generate a series of interconnected triangles, each defined by three adjacent points; Define a grid on the target area to store the elevation value of each point; For each point in the grid, find the triangle it is in, and use the elevation values ​​of the three vertices of the triangle to perform interpolation calculations to obtain the elevation values ​​corresponding to each grid point; According to the elevation values ​​corresponding to each grid point, a three-dimensional seabed terrain model is created. The three-dimensional seabed terrain model is a surface composed of multiple triangles, and each triangle represents a unit in the grid. The seawater temperature, salinity, and water quality parameters are superimposed on the three-dimensional terrain model in the form of a three-dimensional layer to form a three-dimensional marine aquaculture environment model, including: For each grid point in the three-dimensional terrain model, the distance between each grid point and all measured data points is calculated respectively, wherein the measured data point refers to the location point where data is obtained during the actual measurement process, and each measured data point has a definite geographical location; The inverse of the distance is used as the weight to perform weighted averaging on the measured parameter values ​​to obtain a weighted average value, wherein the measured parameter value is the specific value of the environmental parameter directly measured at the measured data point, specifically including seawater temperature, salinity and water quality parameters; The weighted average value is taken as the environmental monitoring value of the corresponding grid point; For each environmental monitoring value, create a new three-dimensional layer data structure, the data structure of each layer corresponds to the grid structure of the three-dimensional terrain model, so that each grid point has a corresponding environmental monitoring value; fill the environmental monitoring value of each grid point into the corresponding three-dimensional layer; The seawater temperature, salinity and water quality parameters at each grid point are assigned corresponding colors, and the generated three-dimensional layers of seawater temperature, salinity and water quality parameters are superimposed on the three-dimensional seabed terrain model to form a three-dimensional marine aquaculture environment model; based on the three-dimensional marine aquaculture environment model, the aquaculture suitability assessment results of each area are calculated, including: Identify key environmental indicators for assessing aquaculture suitability; Standardize key environmental indicators to obtain standardized data; Assign appropriate weights to each standardized data point based on the importance of the farmed species to each key environmental indicator; For each grid point in the three-dimensional marine aquaculture environmental model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight; For each grid point in the three-dimensional marine aquaculture environmental model, the aquaculture suitability assessment result of each grid point is calculated according to its corresponding environmental monitoring value and weight, including: For each grid point in the three-dimensional marine aquaculture environment model, according to its corresponding environmental monitoring value and weight, Calculate the aquaculture suitability assessment results for each grid point; in, is the farming suitability score of the grid point; It is The weight of each environmental parameter; It is Environmental parameter monitoring values; It is Environmental parameter monitoring values; It is for Monitoring value Standardized processing; It is The nonlinear weight coefficients of the parameters; It is parameters and The interaction weights of the parameters; It is A nonlinear transformation function with parameters; is the interaction term between parameters; It is parameters and The quadratic interaction coefficients of the parameters; are the interaction terms between all parameters; and is the index variable; is the total number of environmental parameters, where ； ； in, It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value; It is The minimum value of the environmental parameter monitoring value; It is The maximum value of the environmental parameter monitoring value; based on the aquaculture suitability assessment results, generate an optimized marine aquaculture area planning plan, including: Randomly select K data points from the data set of aquaculture suitability assessment results as initial cluster centers; For each point in the data set, calculate the Euclidean distance between it and each cluster center, and assign each point to the corresponding cluster center to form K initial clusters; For each cluster, calculate the average value of all data points within it and use the average value as the new cluster center. Repeat the operation until the preset number of iterations is reached to generate the final clustering result. According to the final clustering results, the characteristics of each cluster are analyzed to determine its corresponding suitability level, and according to the suitability level, a marine aquaculture regional planning scheme is generated.

2. The marine aquaculture area planning system based on remote sensing mapping according to claim 1 is characterized in that: Acquire remote sensing data of the target sea area, including: The target sea area is divided into multiple grids, each grid represents a survey point, and the process of ants moving on the grid and selecting the next survey point represents path selection; An initial pheromone value is assigned to each path between grids, and each ant selects the next survey point based on the pheromone concentration and heuristic information of the grids around the current position; After each ant completes a path selection, it updates the pheromone on the path according to the acquired data quality and path length, and obtains the final survey plan through multiple iterations; According to the final survey plan, remote sensing data of the target sea area is obtained.

3. The marine aquaculture area planning system based on remote sensing mapping according to claim 2 is characterized in that: The comprehensive database was screened to generate a preliminary screen of marine aquaculture areas, including: Extracting data related to marine aquaculture from a comprehensive database, including seawater temperature, salinity, water depth, water quality indicators including dissolved oxygen, pH and nutrient concentrations, and seafloor topography information; The number of clusters K is determined by the elbow rule, and K data points are randomly selected from the comprehensive database as the initial cluster centers; Assign data points to corresponding cluster centers to form K clusters, and recalculate the center of each cluster until the preset number of iterations is reached to obtain the clustering result; Use the silhouette coefficient to evaluate the clustering results to obtain the evaluation results; Based on the assessment results, identify cluster areas for farming; A preliminary screening is carried out based on the clustering areas of aquaculture, as well as the preset screening area area and shape regularity to obtain the preliminary screened marine aquaculture area.

4. The marine aquaculture area planning system based on remote sensing mapping according to claim 3 is characterized in that: According to the clustering area of ​​aquaculture, as well as the preset screening area area and shape regularity, preliminary screening is carried out to obtain the preliminary screened marine aquaculture area, including: Set the filter conditions and population size, where the population size refers to the number of individuals in each generation; Each cultured cluster area is represented as an individual, and the boundary coordinates of the cultured cluster area are used as the gene code of the individual, and the initial population is randomly generated to make the individuals in the population diverse; Define the fitness function used to evaluate the quality of each individual; Calculate the fitness value of each individual according to the fitness function, determine the corresponding individual as the parent according to the fitness value, and randomly pair the selected parent individuals; Perform crossover operation at a certain crossover rate to generate new offspring individuals, perform mutation operation on the new offspring individuals at a certain mutation rate to generate new gene mutations, and iterate until the preset number of iterations is reached to obtain the final individual; The aquaculture clustering areas corresponding to the final individuals are marked as the initially screened marine aquaculture areas.

5. The marine aquaculture area planning system based on remote sensing mapping according to claim 4 is characterized in that: Key environmental indicators include sea temperature, salinity, water quality parameters and seabed topography characteristics.

Images