Method for comprehensive evaluation of marine ecological protection and restoration project based on multi-dimensional analysis

Abstract

The application discloses a kind of based on multi-dimensional analysis's marine ecological protection restoration project comprehensive evaluation method, it is related to marine ecological analysis field, this method is by constructing target area map model and setting monitoring point, obtains multi-dimensional monitoring data and generates ecological characteristic vector;The relative distance and deviation of monitoring point and contrast characteristic vector are calculated, and the repair expected goodness of fit is obtained;Filter low goodness of fit monitoring point and integrate ecological data set;Based on GAN model training generates optimized simulation characteristic vector;Analysis simulation parameter and evaluate ecological evolution trend, complete comprehensive evaluation.The application realizes multi-dimensional, high-precision ecological evaluation, improves the accuracy of repair effect prediction and the scientificity of evaluation result, provides reliable support for marine ecological protection restoration decision, solves the problem that existing method monitors one-sidedly, and the like.

Description

Technical Field

[0001] This invention relates to the field of marine ecological analysis, and more specifically, to a method for comprehensive evaluation of marine ecological protection and restoration projects based on multidimensional analysis. Background Technology

[0002] While theoretical research on marine ecological protection and restoration has been continuously improving and maturing in recent years, and some progress has been made in marine ecological protection and restoration work, many problems still exist, such as an incomplete restoration system and a lack of unified assessment standards. In particular, there are still many gaps in judging the scientific validity, rationality, and feasibility of restoration plans. Unscientific and unreasonable assessments of plans directly lead to a low capacity for adjustment of marine ecological protection and restoration projects, resulting in wasted human, material, and financial resources. In addition, existing technologies lack multi-dimensional analytical methods for the evolution of ecological characteristics between marine monitoring areas, making it difficult to comprehensively assess the scientific validity and practicality of marine restoration plans. For marine monitoring platforms with limited monitoring resources and small amounts of collected data, it is difficult to improve their comprehensive assessment capabilities and achieve an efficient and comprehensive restoration plan assessment process.

[0003] Therefore, there is an urgent need for a comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis. Summary of the Invention

[0004] This invention overcomes the shortcomings of existing technologies and proposes a method for comprehensive evaluation of marine ecological protection and restoration projects based on multidimensional analysis.

[0005] The first aspect of this invention provides a comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, comprising: S11: Construct a map model based on the target marine monitoring area, set multiple monitoring points, conduct underwater monitoring of the monitoring points through monitoring units, and obtain remote sensing data of the monitoring points to conduct a comprehensive assessment of biodiversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions, and obtain ecological multi-dimensional feature vectors. S12: Based on multiple monitoring points, perform expected ecological multi-dimensional parameter analysis and set a comparison feature vector. For each monitoring point, perform relative distance analysis between the ecological multi-dimensional feature vector and the comparison feature vector, and calculate the relative distance deviation between the monitoring point and adjacent monitoring points to obtain the expected compliance of restoration for each monitoring point. S13: Mark the monitoring points where the expected compliance with the restoration is less than the expected value as the first monitoring point, and integrate the ecological multi-dimensional feature vectors of the first monitoring point and an adjacent monitoring point before and after ecological restoration to obtain the ecological dataset; S14: Construct a generative model based on GAN, use the ecological dataset as real data for simulation training to obtain a simulated vector set, optimize the simulated vector set by judging the degree of consistency between the preset loss function and the expected repair, and generate simulated feature vectors. S15: Perform ecological multi-dimensional parameter analysis on the simulated feature vector, generate simulated ecological multi-dimensional parameters, and evaluate the marine ecological evolution trend of the monitoring points within the preset range based on the simulated ecological multi-dimensional parameters, and give a comprehensive score for marine restoration.

[0006] In this solution, S11 specifically refers to: Acquire information on the outline, extent, and distribution of ecological vegetation of the target marine monitoring area; Construct a three-dimensional visualization map model based on the regional information; Based on the ecological restoration plan for the target marine monitoring area, multiple monitoring points are set in the map model.

[0007] In this solution, S11 further includes: For each monitoring point, high-resolution geographic remote sensing data is acquired, and based on the underwater monitoring unit, image sets of the monitoring point at different underwater depths are collected; Vegetation conditions are analyzed based on remote sensing data. NDVI and EVI parameters are introduced for calculation, and vegetation density and coverage are evaluated to obtain vegetation density and vegetation coverage. Based on the image set, an image recognition module is introduced to identify and count underwater organisms, obtaining the number of phytoplankton species and the number of underwater organism species. The activity trajectory of the target organisms is statistically analyzed within a unit of time to calculate the activity distance and activity frequency of the underwater organisms. Water quality parameters are obtained through monitoring units, including water temperature, turbidity, dissolved oxygen, pH value, ammonia nitrogen concentration, and nitrate concentration. Ecological multidimensional feature vectors are set based on ecological diversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions.

[0008] In this solution, S12 specifically refers to: Based on the marine ecological status and expected restoration status of the monitoring points, multi-dimensional ecological parameters are set for each monitoring point. Generate comparative feature vectors based on the expected multi-dimensional parameters of the ecosystem; For each monitoring point, the relative distance between the ecological multi-dimensional feature vector and the comparison feature vector is calculated. The calculation process incorporates Manhattan distance calculation to obtain the relative distance of each monitoring point. Select a monitoring point and mark it as a repair monitoring point. Calculate the average deviation of the relative distance between the repair monitoring point and its neighboring monitoring points, and set the expected repair consistency of the repair monitoring point based on the average deviation. All monitoring points are set as repair monitoring points to calculate the expected degree of conformity for repair.

[0009] In this solution, S13 specifically refers to: The monitoring points where the expected degree of repair is less than the expected value are marked as the first monitoring points; Obtain the ecological multi-dimensional feature vectors of the first monitoring point and one of its adjacent monitoring points before and after ecological restoration, to obtain the first dataset and the second dataset; The first dataset and the second dataset are integrated to obtain the ecological dataset.

[0010] In this solution, S14 specifically refers to: Construct a generative model based on GAN, which includes a generator G1 and a discriminator G2; The ecological dataset was cleaned and imported into G1 as real data; In G1, feature learning is performed on real data to generate new simulated feature vectors in a loop. G2 is used to determine the authenticity of the simulated feature vectors and optimize the model parameters. During the adversarial training process between G1 and G2, mean squared error loss is introduced as the first loss to judge the difference between simulated data and real data. The simulated feature vector is used as the ecological multi-dimensional feature vector of the first monitoring point to calculate the repair expectation consistency, which is marked as the first consistency. Whether the first consistency is less than the expected value is used as the second loss and is used to judge the authenticity of the simulated data for the second time. Perform repetitive adversarial training until the generated simulated data matches the first loss and the second loss. After recurrent adversarial training, a simulated feature vector with a certain amount of data is obtained by generating a model.

[0011] In this solution, S15 specifically refers to: Ecological multi-dimensional parameter analysis is performed on the simulated feature vector to generate simulated ecological multi-dimensional parameters; In the map model, the intermediate area is marked based on the first monitoring point and one of its adjacent monitoring points; Simulated ecological multidimensional parameters are used as expected ecological parameters for the intermediate region, and the marine ecological evolution trend of monitoring points within the preset range is evaluated. For each monitoring point, a trend analysis of marine ecological evolution within a preset range is conducted, and a comprehensive score is given for marine restoration projects.

[0012] In this scheme, each monitoring point includes a corresponding ecological multi-dimensional feature vector and a comparative feature vector.

[0013] A second aspect of the present invention also provides a comprehensive evaluation system for marine ecological protection and restoration projects based on multidimensional analysis. The system includes: a memory, a processor, and a data interface. The memory includes a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When executed by the processor, the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis performs the following steps: S11: Construct a map model based on the target marine monitoring area, set multiple monitoring points, conduct underwater monitoring of the monitoring points through monitoring units, and obtain remote sensing data of the monitoring points to conduct a comprehensive assessment of biodiversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions, and obtain ecological multi-dimensional feature vectors. S12: Based on multiple monitoring points, perform expected ecological multi-dimensional parameter analysis and set a comparison feature vector. For each monitoring point, perform relative distance analysis between the ecological multi-dimensional feature vector and the comparison feature vector, and calculate the relative distance deviation between the monitoring point and adjacent monitoring points to obtain the expected compliance of restoration for each monitoring point. S13: Mark the monitoring points where the expected compliance with the restoration is less than the expected value as the first monitoring point, and integrate the ecological multi-dimensional feature vectors of the first monitoring point and an adjacent monitoring point before and after ecological restoration to obtain the ecological dataset; S14: Construct a generative model based on GAN, use the ecological dataset as real data for simulation training to obtain a simulated vector set, optimize the simulated vector set by judging the degree of consistency between the preset loss function and the expected repair, and generate simulated feature vectors. S15: Perform ecological multi-dimensional parameter analysis on the simulated feature vector, generate simulated ecological multi-dimensional parameters, and evaluate the marine ecological evolution trend of the monitoring points within the preset range based on the simulated ecological multi-dimensional parameters, and give a comprehensive score for marine restoration.

[0014] A third aspect of the present invention also provides a computer-readable storage medium comprising a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis is executed by a processor, it implements the steps of the comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis as described in any of the preceding claims.

[0015] This invention discloses a method for comprehensive evaluation of marine ecological protection and restoration projects based on multidimensional analysis, relating to the field of marine ecological analysis. This method involves constructing a target area map model and setting monitoring points to obtain multidimensional monitoring data and generate ecological feature vectors; calculating the relative distance and deviation between monitoring points and comparative feature vectors to obtain the expected consistency of restoration; screening monitoring points with low consistency and integrating the ecological dataset; training an optimized simulated feature vector based on a GAN model; analyzing the simulated parameters and evaluating the ecological evolution trend to complete the comprehensive evaluation. This invention achieves multidimensional and high-precision ecological assessment, improves the accuracy of restoration effect prediction and the scientific nature of the assessment results, provides reliable support for marine ecological protection and restoration decision-making, and solves the problems of one-sided monitoring and insufficient prediction in existing methods. Attached Figure Description

[0016] Figure 1 A flowchart of a comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, according to the present invention, is shown. Figure 2 The flowchart illustrating the construction process of the ecological multi-dimensional feature vector of the present invention is shown. Figure 3 The diagram shows a block diagram of a comprehensive evaluation system for marine ecological protection and restoration projects based on multidimensional analysis, according to the present invention. Detailed Implementation

[0017] To better understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. In the embodiments of the present invention, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0019] Figure 1 The flowchart of a comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, according to the present invention, is shown.

[0020] like Figure 1 As shown, the first aspect of this invention provides a comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, including: S11: Construct a map model based on the target marine monitoring area, set multiple monitoring points, conduct underwater monitoring of the monitoring points through monitoring units, and obtain remote sensing data of the monitoring points to conduct a comprehensive assessment of biodiversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions, and obtain ecological multi-dimensional feature vectors. S12: Based on multiple monitoring points, perform expected ecological multi-dimensional parameter analysis and set a comparison feature vector. For each monitoring point, perform relative distance analysis between the ecological multi-dimensional feature vector and the comparison feature vector, and calculate the relative distance deviation between the monitoring point and adjacent monitoring points to obtain the expected compliance of restoration for each monitoring point. S13: Mark the monitoring points where the expected compliance with the restoration is less than the expected value as the first monitoring point, and integrate the ecological multi-dimensional feature vectors of the first monitoring point and an adjacent monitoring point before and after ecological restoration to obtain the ecological dataset; S14: Construct a generative model based on GAN, use the ecological dataset as real data for simulation training to obtain a simulated vector set, optimize the simulated vector set by judging the degree of consistency between the preset loss function and the expected repair, and generate simulated feature vectors. S15: Perform ecological multi-dimensional parameter analysis on the simulated feature vector, generate simulated ecological multi-dimensional parameters, and evaluate the marine ecological evolution trend of the monitoring points within the preset range based on the simulated ecological multi-dimensional parameters, and give a comprehensive score for marine restoration.

[0021] According to an embodiment of the present invention, S11 specifically includes: Acquire information on the outline, extent, and distribution of ecological vegetation of the target marine monitoring area; Construct a three-dimensional visualization map model based on the regional information; Based on the ecological restoration plan for the target marine monitoring area, multiple monitoring points are set in the map model.

[0022] In this embodiment of the invention, the monitoring points are generally set based on an even distribution of the target ocean area, and the distance between the monitoring points is generally large, in order to balance the needs of monitoring resources and monitoring data volume, and to minimize redundant monitoring points, especially for monitoring platforms with available resources.

[0023] Figure 2 The flowchart illustrating the construction process of the ecological multi-dimensional feature vector of the present invention is a simplified schematic diagram.

[0024] According to an embodiment of the present invention, S11 further includes: For each monitoring point, high-resolution geographic remote sensing data is acquired, and based on the underwater monitoring unit, image sets of the monitoring point at different underwater depths are collected; Vegetation conditions are analyzed based on remote sensing data. NDVI and EVI parameters are introduced for calculation, and vegetation density and coverage are evaluated to obtain vegetation density and vegetation coverage. Based on the image set, an image recognition module is introduced to identify and count underwater organisms, obtaining the number of phytoplankton species and the number of underwater organism species. The activity trajectory of the target organisms is statistically analyzed within a unit of time to calculate the activity distance and activity frequency of the underwater organisms. Water quality parameters are obtained through monitoring units, including water temperature, turbidity, dissolved oxygen, pH value, ammonia nitrogen concentration, and nitrate concentration. Ecological multidimensional feature vectors are set based on ecological diversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions.

[0025] In this embodiment of the invention, the underwater monitoring unit includes an underwater camera, a water quality detection device, and a communication module. The underwater monitoring unit can also acquire surface image information. The study of water quality parameters is not limited to the parameters mentioned above. Here, vegetation density and vegetation coverage are used to reflect vegetation conditions, such as mangrove and coastal wetland vegetation conditions; the number of phytoplankton species and the number of underwater biological species are used to reflect biodiversity; activity distance and activity frequency are used to reflect the distribution of underwater biological activity; and water quality parameters are used to reflect water quality conditions. All of the above data serve as multi-dimensional ecological parameters and can be subsequently transformed into feature vectors. Vegetation density analysis can be based on a density assessment of the number of locations with vegetation within a certain range of the monitoring point. In the multi-dimensional ecological feature vector, multiple (four) vectors can be generated based on various different categories of parameters (such as ecological diversity, underwater biological activity distribution, vegetation conditions, and water quality conditions), or multi-dimensional ecological feature vectors can be generated based on all parameters. In the subsequent vector comparison analysis, specific comparison analysis is performed based on vectors of the same dimension and the same parameter category.

[0026] The statistical analysis of the activity trajectory of target organisms within a unit of time, and the calculation of the activity distance and frequency of underwater organisms, mainly analyzes the activity of target underwater organisms in the core area of ​​the monitoring point, and analyzes the activity trajectory within a certain period of time to calculate the number of activities and swimming distance, which is used to reflect the degree of ecological activity.

[0027] According to an embodiment of the present invention, step S12 specifically includes: Based on the marine ecological status and expected restoration status of the monitoring points, multi-dimensional ecological parameters are set for each monitoring point. Generate comparative feature vectors based on the expected multi-dimensional parameters of the ecosystem; For each monitoring point, the relative distance between the ecological multi-dimensional feature vector and the comparison feature vector is calculated. The calculation process incorporates Manhattan distance calculation to obtain the relative distance of each monitoring point. Select a monitoring point and mark it as a repair monitoring point. Calculate the average deviation of the relative distance between the repair monitoring point and its neighboring monitoring points, and set the expected repair consistency of the repair monitoring point based on the average deviation. All monitoring points are set as repair monitoring points to calculate the expected degree of conformity for repair.

[0028] In this embodiment of the invention, the expected ecological multi-dimensional parameters include parameters such as biodiversity, distribution of underwater biological activity, vegetation conditions, and water quality. For example, for water quality parameters, the following parameters can be set: water temperature 25℃, turbidity 4 NTU, dissolved oxygen 7 mg / L, pH 7.8, ammonia nitrogen concentration 0.03 mg / L, and nitrate concentration 0.05 mg / L. A feature vector is generated based on these multi-dimensional parameters. This comparative feature vector is used to define an ideal state. Subsequently, a deviation analysis (ecological dimension) relative to the expected state is performed between the monitoring point and neighboring points. The relative distance is used to assess whether the ecological change trend conforms to the actual trend, and relevant matching parameters are used for analysis. The remediation monitoring point is either randomly selected from multiple monitoring points or a point is selected from the monitoring points for evaluation according to a certain analysis order. The expected ecological multidimensional parameters can be set based on the marine conditions, ecological status, vegetation condition, and restoration goals of the monitoring point. For the setting of expected activity parameters, information on biodiversity and underwater biological activity distribution in the ideal marine area (or a successfully restored marine area) can be referenced, providing a certain degree of relative reference value. Relative distance reflects the relative deviation of the monitoring point's ecological characteristics from the expected state.

[0029] The expected fit for repair is calculated as follows: , Where P represents the expected repair consistency at a certain repair monitoring point, and N is the number of adjacent monitoring points for a certain repair monitoring point. These are the relative distances between the repair monitoring points and the relative distances between the i-th adjacent monitoring points, respectively.

[0030] Adjacent monitoring points are monitoring points that are geographically adjacent, or monitoring points within a certain preset range centered on the restoration monitoring point.

[0031] It is worth noting that a higher degree of agreement indicates that the monitoring data within a certain range of the monitoring point is more consistent with the actual evolutionary trend. Furthermore, through agreement analysis, it is possible to assess which adjacent monitoring points have ecological characteristics that deviate from the actual evolutionary trend or do not conform to the actual situation. A high degree of agreement suggests a certain degree of ecological degradation. Moreover, it is difficult to analyze the evolutionary trend of ecological characteristics in the intermediate area between monitoring points based on existing data from the monitoring points, making it difficult to comprehensively assess the scientific validity and practicality of marine restoration plans. For marine monitoring platforms with limited monitoring resources and a small amount of collected data, it is difficult to improve their comprehensive assessment capabilities. Increasing monitoring resources will undoubtedly greatly increase the consumption of human and material resources, making it difficult to achieve efficient and intelligent comprehensive assessment of marine restoration.

[0032] Based on this, the present invention uses multi-dimensional ecological data for relative expectation assessment and analyzes the deviation of the ecological expectations between the monitoring point and other neighboring points. It then selects neighboring monitoring points with low expectation consistency. Furthermore, it vectorizes and simulates feature generation based on the relevant ecological datasets of neighboring monitoring points to predict the ecological evolution trend of the intermediate region between actual neighboring monitoring points. In addition, it uses a GAN model to learn and simulate the monitoring point datasets before and after restoration, using the consistency as the screening criterion for simulated data to generate simulated ecological feature data for the intermediate region and predict and characterize its ecological status. This effectively achieves a comprehensive assessment of marine restoration and provides a clear direction for the optimization of subsequent restoration schemes.

[0033] The ecological datasets here are generally ecological data collected over multiple restoration cycles. Before and after ecological restoration, the data can be ecological data from before restoration to the restoration stage, or ecological data collected throughout the entire restoration project and all stages.

[0034] Here, if the expected degree of remediation is high, a more accurate value can be obtained by using linear or manual assessment based on existing monitoring data. If the degree of remediation is low, multi-dimensional feature generation is required to assess the remediation status and trend of the intermediate area in order to meet the accuracy analysis of the ecological restoration status.

[0035] According to an embodiment of the present invention, step S13 specifically includes: The monitoring points where the expected degree of repair is less than the expected value are marked as the first monitoring points; Obtain the ecological multi-dimensional feature vectors of the first monitoring point and one of its adjacent monitoring points before and after ecological restoration, to obtain the first dataset and the second dataset; The first dataset and the second dataset are integrated to obtain the ecological dataset.

[0036] In this embodiment of the invention, the first dataset and the second dataset correspond to the first monitoring point and one of its adjacent monitoring points, and are both feature vector data. Here, there is a certain intermediate region between the first monitoring point and one of its adjacent monitoring points geographically, which is used to simulate the ecological characteristics of the intermediate region in the subsequent simulation features. The expected value is generally set to 50%.

[0037] According to an embodiment of the present invention, step S14 specifically includes: Construct a generative model based on GAN, which includes a generator G1 and a discriminator G2; The ecological dataset was cleaned and imported into G1 as real data; In G1, feature learning is performed on real data to generate new simulated feature vectors in a loop. G2 is used to determine the authenticity of the simulated feature vectors and optimize the model parameters. During the adversarial training process between G1 and G2, mean squared error loss is introduced as the first loss to judge the difference between simulated data and real data. The simulated feature vector is used as the ecological multi-dimensional feature vector of the first monitoring point to calculate the repair expectation consistency, which is marked as the first consistency. Whether the first consistency is less than the expected value is used as the second loss and is used to judge the authenticity of the simulated data for the second time. Perform repetitive adversarial training until the generated simulated data matches the first loss and the second loss. After recurrent adversarial training, a simulated feature vector with a certain amount of data is obtained by generating a model.

[0038] In this embodiment of the invention, the simulated feature vectors generated by the final trained generative model are used for subsequent analysis. The simulated feature vectors generated during intermediate training are only used as simulated data for training and evaluation. The improved generative model employed here, in addition to the first loss (mean squared error), adds a second loss (correction of expected fit) to determine whether the generated data conforms to a certain actual trend, and this second loss is used to update the model parameters.

[0039] According to an embodiment of the present invention, S15 specifically includes: Ecological multi-dimensional parameter analysis is performed on the simulated feature vector to generate simulated ecological multi-dimensional parameters; In the map model, the intermediate area is marked based on the first monitoring point and one of its adjacent monitoring points; Simulated ecological multidimensional parameters are used as expected ecological parameters for the intermediate region, and the marine ecological evolution trend of monitoring points within the preset range is evaluated. For each monitoring point, a trend analysis of marine ecological evolution within a preset range is conducted, and a comprehensive score is given for marine restoration projects.

[0040] In this embodiment of the invention, the preset range includes the range formed by the first monitoring point, one of the adjacent monitoring points, and the intermediate area.

[0041] Here, the first monitoring point can be analyzed with multiple adjacent monitoring points to form multiple intermediate areas for comprehensive assessment of the remediation project. This effectively expands the assessment scope, identifies potential risks, improves the overall assessment capability of the entire area, and enables in-process optimization in the remediation project.

[0042] According to an embodiment of the present invention, each monitoring point includes a corresponding ecological multi-dimensional feature vector and a comparative feature vector.

[0043] It is worth noting that in actual marine monitoring platforms, the assessment of restoration projects often requires monitoring and evaluation after the overall project is completed. During the project, it is difficult to predict water quality changes, especially with smaller monitoring platforms where data collection is limited. This makes it difficult to assess potential risks and quickly predict marine ecological evolution trends, and also to identify areas with potential ecological fluctuations. This often relies on human experience, resulting in limited practicality and scientific rigor. Therefore, this invention analyzes the expected consistency of each monitoring point to identify intermediate areas with potential anomalies. By generating a model to simulate ecological characteristics, it matches actual ecological evolution trends, effectively improving the comprehensive assessment capability of marine ecological restoration projects.

[0044] According to an embodiment of the present invention, it further includes: Based on the ecological restoration plan, a restoration route for the area is set, and monitoring points are searched along the restoration route. The relative distances between the monitoring points along the route are serialized, and the order is referenced to the starting point of the route to obtain the expected deviation sequence. The ARIMA algorithm is introduced to calculate the autocorrelation and partial autocorrelation functions of the expected deviation sequence and determine the p, d, and q parameters; The ARIMA algorithm is used to predict the expected deviation sequence, and the deviation trend of the ecological characteristics of the restoration route from the expected restoration state is evaluated based on the predicted data.

[0045] Understandably, the repair route for the designated area can be set based on the repair plan's repair route or the priority of the repair area. Monitoring points for the search path can be searched within a certain radius of the route. Predictive analysis using the expected deviation sequence can determine the trend of the repair area's route under the current repair status and assess the directionality of the overall repair effectiveness.

[0046] p represents the autoregressive order of the time series, d represents the differencing order of the time series, and q represents the moving average order of the time series.

[0047] According to an embodiment of the present invention, the Figure 3 The diagram shows a block diagram of a comprehensive evaluation system for marine ecological protection and restoration projects based on multidimensional analysis, according to the present invention.

[0048] A second aspect of the present invention also provides a comprehensive evaluation system for marine ecological protection and restoration projects based on multidimensional analysis. The system includes: a memory 103, a processor 102, and a data interface 101. The data interface is used to achieve data interaction with a monitoring unit terminal 104. The memory includes a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When executed by the processor, the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis performs the following steps: S11: Construct a map model based on the target marine monitoring area, set multiple monitoring points, conduct underwater monitoring of the monitoring points through monitoring units, and obtain remote sensing data of the monitoring points to conduct a comprehensive assessment of biodiversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions, and obtain ecological multi-dimensional feature vectors. S12: Based on multiple monitoring points, perform expected ecological multi-dimensional parameter analysis and set a comparison feature vector. For each monitoring point, perform relative distance analysis between the ecological multi-dimensional feature vector and the comparison feature vector, and calculate the relative distance deviation between the monitoring point and adjacent monitoring points to obtain the expected compliance of restoration for each monitoring point. S13: Mark the monitoring points where the expected compliance with the restoration is less than the expected value as the first monitoring point, and integrate the ecological multi-dimensional feature vectors of the first monitoring point and an adjacent monitoring point before and after ecological restoration to obtain the ecological dataset; S14: Construct a generative model based on GAN, use the ecological dataset as real data for simulation training to obtain a simulated vector set, optimize the simulated vector set by judging the consistency between the preset loss function and the expected repair, and generate simulated feature vectors. S15: Perform ecological multi-dimensional parameter analysis on the simulated feature vector, generate simulated ecological multi-dimensional parameters, and evaluate the marine ecological evolution trend of the monitoring points within the preset range based on the simulated ecological multi-dimensional parameters, and give a comprehensive score for marine restoration.

[0049] When the system of this invention is running, it can realize all the steps of the comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, as described above, according to monitoring needs.

[0050] A third aspect of the present invention also provides a computer-readable storage medium comprising a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis is executed by a processor, it implements the steps of the comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis as described in any of the preceding claims.

[0051] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application can be generated, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic cable, data subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital universal optical disc), or a semiconductor medium (e.g., solid-state drive). In the various embodiments of this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0052] In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone, where A and B can be singular or plural. In the textual description of the embodiments of this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. In this application, "first," "second," and various numerical designations are only for the convenience of description and are not used to limit the scope of the embodiments of this application. For example, they are used to distinguish different messages, rather than to describe a specific order or sequence.

[0053] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0054] Finally, it should be noted that the above description is only a specific implementation of this application, but the protection scope of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the protection scope of this application.

Claims

1. A comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis, characterized in that, include: S11: Construct a map model based on the target marine monitoring area, set multiple monitoring points, conduct underwater monitoring of the monitoring points through monitoring units, and obtain remote sensing data of the monitoring points to conduct a comprehensive assessment of biodiversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions, and obtain ecological multi-dimensional feature vectors. S12: Based on multiple monitoring points, perform expected ecological multi-dimensional parameter analysis and set a comparison feature vector. For each monitoring point, perform relative distance analysis between the ecological multi-dimensional feature vector and the comparison feature vector, and calculate the relative distance deviation between the monitoring point and adjacent monitoring points to obtain the expected compliance of restoration for each monitoring point. Specifically, S12 is as follows: Based on the marine ecological status and expected restoration status of the monitoring points, multi-dimensional ecological parameters are set for each monitoring point. Generate comparative feature vectors based on the expected multi-dimensional parameters of the ecosystem; For each monitoring point, the relative distance between the ecological multi-dimensional feature vector and the comparison feature vector is calculated. The calculation process incorporates Manhattan distance calculation to obtain the relative distance of each monitoring point. Select a monitoring point and mark it as a repair monitoring point. Calculate the average deviation of the relative distance between the repair monitoring point and its neighboring monitoring points, and set the expected repair consistency of the repair monitoring point based on the average deviation. All monitoring points are set as repair monitoring points to calculate the expected repair consistency. S13: Mark the monitoring points where the expected compliance with the restoration is less than the expected value as the first monitoring point, and integrate the ecological multi-dimensional feature vectors of the first monitoring point and an adjacent monitoring point before and after ecological restoration to obtain the ecological dataset; S14: Construct a generative model based on GAN, use the ecological dataset as real data for simulation training to obtain a simulated vector set, optimize the simulated vector set by judging the degree of consistency between the preset loss function and the expected repair, and generate simulated feature vectors. S15: Perform ecological multi-dimensional parameter analysis on the simulated feature vector, generate simulated ecological multi-dimensional parameters, and evaluate the marine ecological evolution trend of the monitoring points within the preset range based on the simulated ecological multi-dimensional parameters, and give a comprehensive score for marine restoration.

2. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 1, characterized in that, Specifically, S11 is: Acquire information on the outline, extent, and distribution of ecological vegetation of the target marine monitoring area; Construct a three-dimensional visualization map model based on the regional information; Based on the ecological restoration plan for the target marine monitoring area, multiple monitoring points are set in the map model.

3. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 2, characterized in that, S11 further includes: For each monitoring point, high-resolution geographic remote sensing data is acquired, and based on the underwater monitoring unit, image sets of the monitoring point at different underwater depths are collected; Vegetation conditions are analyzed based on remote sensing data. NDVI and EVI parameters are introduced for calculation, and vegetation density and coverage are evaluated to obtain vegetation density and vegetation coverage. Based on the image set, an image recognition module is introduced to identify and count underwater organisms, obtaining the number of phytoplankton species and the number of underwater organism species. The activity trajectory of the target organisms is statistically analyzed within a unit of time to calculate the activity distance and activity frequency of the underwater organisms. Water quality parameters are obtained through monitoring units, including water temperature, turbidity, dissolved oxygen, pH value, ammonia nitrogen concentration, and nitrate concentration. Ecological multidimensional feature vectors are set based on ecological diversity, distribution of underwater biological activities, vegetation conditions, and water quality conditions.

4. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 1, characterized in that, Specifically, S13 is as follows: The monitoring points where the expected degree of repair is less than the expected value are marked as the first monitoring points; Obtain the ecological multi-dimensional feature vectors of the first monitoring point and one of its adjacent monitoring points before and after ecological restoration, to obtain the first dataset and the second dataset; The first dataset and the second dataset are integrated to obtain the ecological dataset.

5. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 4, characterized in that, Specifically, S14 is as follows: Construct a generative model based on GAN, which includes a generator G1 and a discriminator G2; The ecological dataset was cleaned and imported into G1 as real data; In G1, feature learning is performed on real data to generate new simulated feature vectors in a loop. G2 is used to determine the authenticity of the simulated feature vectors and optimize the model parameters. During the adversarial training process between G1 and G2, mean squared error loss is introduced as the first loss to judge the difference between simulated data and real data. The simulated feature vector is used as the ecological multi-dimensional feature vector of the first monitoring point to calculate the repair expectation consistency, which is marked as the first consistency. Whether the first consistency is less than the expected value is used as the second loss and is used to judge the authenticity of the simulated data for the second time. Perform repetitive adversarial training until the generated simulated data matches the first loss and the second loss. After recurrent adversarial training, a simulated feature vector with a certain amount of data is obtained by generating a model.

6. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 5, characterized in that, Specifically, S15 is: Ecological multi-dimensional parameter analysis is performed on the simulated feature vector to generate simulated ecological multi-dimensional parameters; In the map model, the intermediate area is marked based on the first monitoring point and one of its adjacent monitoring points; Simulated multi-dimensional ecological parameters are used as expected ecological parameters for the intermediate region, and the marine ecological evolution trend of monitoring points within the preset range is evaluated. For each monitoring point, a trend analysis of marine ecological evolution within a preset range is conducted, and a comprehensive score is given for marine restoration projects.

7. The comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis according to claim 1, characterized in that, Each monitoring point includes a corresponding ecological multi-dimensional feature vector and a comparative feature vector.

8. A comprehensive evaluation system for marine ecological protection and restoration projects based on multidimensional analysis, characterized in that, The system includes: a memory, a processor, and a data interface. The memory includes a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When the processor executes the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis, it implements the steps of the comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis as described in claim 1.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis. When the comprehensive evaluation program for marine ecological protection and restoration projects based on multidimensional analysis is executed by a processor, it implements the steps of the comprehensive evaluation method for marine ecological protection and restoration projects based on multidimensional analysis as described in any one of claims 1 to 7.

Images