Coral reef ecological restoration effect evaluation method and system based on ecological diffraction prediction

Abstract

The invention discloses a coral reef ecological restoration effect evaluation method and system based on ecological diffraction prediction. According to the method, firstly, water quality parameters of a coral reef ecological restoration area are obtained, the maximum reliable communication distance of an underwater wireless sensor network is determined, and therefore the effective monitoring range of ecological diffraction is determined; acquiring in-situ ecological monitoring data in a monitoring range, and analyzing and extracting ecological parameter change characteristics by using a time sequence; performing ecological parameter diffraction simulation based on the features, identifying a diffusion path and performing change prediction to obtain ecological diffraction prediction data; and carrying out regional ecological state clustering on the prediction data by adopting a fuzzy clustering algorithm so as to determine the ecological restoration effect of the restoration region. According to the method, dynamic monitoring and intelligent evaluation of the coral reef restoration effect can be realized, the method has the advantages of high prediction precision and high applicability, and scientific decision support can be provided for coral reef ecological restoration engineering.

Description

Technical Field

[0001] This invention relates to the field of ecological restoration technology, and in particular to a method and system for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. Background Technology

[0002] Coral reef ecosystems, as one of the most biodiverse and ecologically important marine ecosystems in the world, play an irreplaceable role in maintaining marine biological resources, protecting coastlines, and supporting fisheries and tourism.

[0003] Traditional methods for assessing the effectiveness of coral reef ecological restoration primarily rely on fixed-point monitoring and periodic surveys, and evaluate the ecological restoration status of the restored area based on statistical comparisons or index calculations. While these methods can intuitively reflect the ecological improvement within the restored area, they have significant limitations: firstly, they fail to fully consider the ecological impact of the restored area on surrounding areas; secondly, existing assessment methods are mostly based on static or discrete time-point data, making it difficult to capture the dynamic evolution and spatial propagation characteristics of ecological parameters over time, resulting in an inability to accurately predict the long-term trend and spatial extent of restoration effects.

[0004] Furthermore, due to the complexity of the underwater monitoring environment, the deployment of sensor networks is significantly affected by water quality parameters, and there is a dynamic relationship between the communication reliability and the monitoring range. However, existing technologies often ignore this constraint and directly adopt a fixed monitoring radius, resulting in incomplete data collection or biased evaluation results.

[0005] To address the aforementioned issues, this invention proposes a method and system for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. This method enables the extraction of ecological state change characteristics, identification of diffusion paths, and quantitative evaluation of effectiveness in the restoration area and its surrounding areas, thereby overcoming the shortcomings of traditional methods and providing more comprehensive and accurate evaluation support for coral reef ecological restoration. Summary of the Invention

[0006] To address at least one of the aforementioned technical problems, this invention proposes a method and system for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction.

[0007] The first aspect of this invention provides a method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction, comprising: Acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; In-situ ecological monitoring data within the effective monitoring range is obtained, and ecological parameter change characteristics are extracted from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data. Based on the time-series variation characteristics of the ecological parameters, ecological parameter diffraction simulation is performed on the target coral reef restoration area to identify the diffusion path of the ecological parameters. Based on the diffusion path, ecological parameter changes are predicted to obtain ecological diffraction prediction data. The ecological diffraction prediction data is clustered into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological state clustering results.

[0008] In this solution, the steps of acquiring water quality parameter data of the target coral reef restoration area, determining the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determining the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance are as follows: Obtain water quality parameter data for the target coral reef restoration area, including water turbidity, salinity, temperature, pH, and dissolved oxygen. The wireless transmission performance data of underwater monitoring sensors in the target coral reef restoration area is acquired. The underwater monitoring sensors include camera sensors and sonar sensors. The wireless transmission performance data includes signal transmission power and operating frequency. Based on the wireless transmission performance data and water quality parameter data, determine the signal transmission attenuation coefficient of the underwater monitoring sensor under the water quality conditions of the target coral reef restoration area as a function of distance; Obtain the location information of the data receiving server of the underwater monitoring sensor, and construct a signal reception attenuation map of the data receiving server for the underwater monitoring sensor data based on the location information of the data receiving server and the attenuation coefficient. A communication link is established between the data receiving server and the underwater monitoring sensor. An underwater wireless sensor network is constructed based on the communication link. The maximum reliable communication distance of the underwater wireless sensor network is determined based on the signal reception attenuation spectrum. The effective monitoring range of ecological diffraction in the target coral reef restoration area is determined based on the maximum reliable communication distance.

[0009] In this scheme, the acquisition of in-situ ecological monitoring data within the effective monitoring range, and the extraction of ecological parameter change characteristics from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data, specifically includes: The effective monitoring range is divided into N sub-regions according to a preset grid size, and video image data and sonar detection data of each sub-region are periodically acquired according to the underwater wireless sensor network. Based on the video image data, the coral coverage area and coral species of each sub-region in each monitoring period are identified, and the ratio of coral coverage area to the total area of ​​the sub-region is calculated to obtain coral coverage time series data. Based on the video image data and sonar detection data, identify the types of fish appearing in each sub-region during each monitoring period, count the number of each type of fish, calculate the fish density per unit area, and obtain fish density time series data. Based on the sonar detection data and video image data, identify the species of macrobenthic invertebrates appearing in each sub-region during each monitoring period, count the number of each type of macrobenthic invertebrate, calculate the density of macrobenthic invertebrates per unit area, and obtain time series data of macrobenthic invertebrate habitat density. Based on the video image data, identify the area covered by macrobenthic algae and the species of macrobenthic algae in each sub-region during each monitoring period, calculate the ratio of macrobenthic algae coverage area to the total area of ​​the sub-region, and obtain time series data of macrobenthic algae coverage rate. The time series data of coral coverage, fish density, macrobenthic invertebrate density, and macrobenthic algae coverage in each sub-region were normalized respectively. The processed time series data of each ecological parameter were then divided into multiple continuous subsequence windows based on a sliding time window. Fast Fourier Transform is performed on the time series data of each ecological parameter in each subsequence window to extract the variation amplitude, variation period and variation trend features of each ecological parameter in the time domain and frequency domain, so as to obtain the time series variation feature data of ecological parameters in each subsequence window.

[0010] In this scheme, the ecological parameter diffraction simulation of the target coral reef restoration area is performed based on the temporal variation characteristic data of the ecological parameters to identify the diffusion paths of the ecological parameters. Ecological parameter changes are then predicted based on these diffusion paths to obtain ecological diffraction prediction data. Specifically: Based on the temporal variation characteristic data of the ecological parameters, the trend characteristics of each ecological parameter in the time domain and the periodic characteristics of each ecological parameter in the frequency domain are extracted for each sub-region, and an ecological parameter state vector is constructed with coral coverage, fish density, macrobenthic invertebrate density and macrobenthic algae coverage as variables. A two-dimensional plane coordinate system is constructed for the target coral reef restoration area. The ecological parameter state vector of each sub-region is mapped to the two-dimensional plane coordinate system according to the corresponding position coordinates. The two-dimensional plane coordinate system is then divided into grids according to the sub-region range to form the ecological parameter state value of each grid point. According to a preset time step, construct an ecological parameter state value distribution map for each grid point at each time step to obtain an ecological parameter state value distribution map set. Based on the ecological parameter state value distribution map set, construct a state transition map of the ecological state space of each sub-region. Based on the state transition diagram, ecological parameter diffraction simulation was performed on the target coral reef restoration area. Based on the ecological parameter state value distribution map, the change in ecological parameter state value of each grid point between adjacent time steps was extracted. Combined with the spatial distance between grid points, the state gradient vector of each ecological parameter between adjacent grid points was calculated. Based on the state gradient vector, identify the regions where ecological parameter state values ​​rise from the target coral reef restoration area to the non-restoration area, and determine the ecological parameter diffusion path from the target coral reef restoration area to the non-restoration area based on the regions where ecological parameter state values ​​rise. The ecological parameter rise time series data of each sub-region in the ecological parameter diffusion path are obtained, and the ecological parameter rise time series data are imported into a long short-term memory network to predict the changes of ecological parameters in the future within a preset time period, thereby obtaining ecological diffraction prediction data.

[0011] In this scheme, the step of performing regional ecological state clustering on the ecological diffraction prediction data based on the fuzzy clustering algorithm to obtain the ecological state clustering results is as follows: Based on the ecological diffraction prediction data, determine the stability of ecological parameter changes within the effective monitoring range of ecological diffraction in the future preset time period, identify ecologically stable time points where the stability of ecological parameter changes is greater than the preset stability, and construct an ecological state feature vector from the ecological diffraction prediction data of each sub-region at the stable time point. A fuzzy clustering algorithm is introduced. The number of clusters k in the fuzzy clustering algorithm is initialized. The ecological state feature vectors of k sub-regions are randomly selected as cluster centers. The Euclidean distance from the ecological state feature vector of each sub-region to each cluster center is calculated. The membership value of each sub-region to each cluster is calculated based on the Euclidean distance. Each sub-region is assigned to the cluster center with the largest membership value to form a cluster. The mean value of the ecological state feature vector within each cluster is calculated, and the cluster center is updated based on the mean value. The membership calculation and cluster center update steps are executed iteratively until the change in cluster centers between two adjacent iterations is less than a preset threshold, thus obtaining the ecological state clustering results within the effective monitoring range of ecological diffraction.

[0012] In this scheme, determining the ecological restoration effectiveness of the target coral reef restoration area based on the ecological state clustering results specifically involves: Extract the membership degree values ​​of all sub-regions to the optimal ecological state cluster from the ecological state clustering results, identify the sub-regions with membership degree values ​​greater than the preset membership degree threshold as ecological restoration effective areas, calculate the total area of ​​all ecological restoration effective areas, and obtain the actual effective area of ​​ecological restoration. Obtain the expected ecological diffraction restoration area of ​​the target coral reef restoration area, calculate the ratio of the actual effective ecological restoration area to the expected ecological diffraction restoration area, and obtain the ecological restoration area achievement rate. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological restoration area achievement rate.

[0013] A second aspect of the present invention also provides a coral reef ecological restoration effectiveness evaluation system based on ecological diffraction prediction. The system includes a memory and a processor. The memory includes a program for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. When the processor executes the program, the program performs the following steps: Acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; In-situ ecological monitoring data within the effective monitoring range is obtained, and ecological parameter change characteristics are extracted from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data. Based on the time-series variation characteristics of the ecological parameters, ecological parameter diffraction simulation is performed on the target coral reef restoration area to identify the diffusion path of the ecological parameters. Based on the diffusion path, ecological parameter changes are predicted to obtain ecological diffraction prediction data. The ecological diffraction prediction data is clustered into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological state clustering results.

[0014] This invention discloses a method and system for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. The method first acquires water quality parameters of the coral reef ecological restoration area and determines the maximum reliable communication distance of the underwater wireless sensor network, thereby determining the effective monitoring range of ecological diffraction. Within the monitoring range, in-situ ecological monitoring data is collected, and time series analysis is used to extract the characteristics of ecological parameter changes. Based on these characteristics, ecological parameter diffraction simulation is performed to identify diffusion paths and predict changes, obtaining ecological diffraction prediction data. A fuzzy clustering algorithm is used to cluster the predicted data into regional ecological states, thereby determining the effectiveness of ecological restoration in the restoration area. This invention enables dynamic monitoring and intelligent evaluation of coral reef restoration effects, possessing advantages such as high prediction accuracy and strong applicability, and can provide scientific decision support for coral reef ecological restoration projects. Attached Figure Description

[0015] Figure 1 A flowchart of a method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to the present invention is shown. Figure 2 The flowchart illustrating the ecological state clustering results obtained by this invention is shown. Figure 3 The flowchart illustrating the determination of ecological restoration effectiveness according to the present invention is shown; Figure 4 A block diagram of a coral reef ecological restoration effectiveness assessment system based on ecological diffraction prediction according to the present invention is shown. Detailed Implementation

[0016] To better understand the above-mentioned objectives, 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. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0017] 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.

[0018] Figure 1 The flowchart of a method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to the present invention is shown.

[0019] like Figure 1 As shown, the first aspect of this invention provides a method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction, comprising: S102, acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; S104, acquire in-situ ecological monitoring data within the effective monitoring range, and extract ecological parameter change characteristics from the in-situ ecological monitoring data based on time series analysis to obtain ecological parameter time series change characteristic data; S106, Based on the time-series change characteristic data of the ecological parameters, perform ecological parameter diffraction simulation on the target coral reef restoration area, identify the diffusion path of the ecological parameters, predict the change of ecological parameters according to the diffusion path, and obtain ecological diffraction prediction data. S108, Based on the fuzzy clustering algorithm, the ecological diffraction prediction data is clustered into regional ecological states to obtain ecological state clustering results; S110, Determine the ecological restoration effectiveness of the target coral reef restoration area based on the ecological state clustering results.

[0020] It should be noted that by acquiring in-situ ecological monitoring data within the effective monitoring range and using time series analysis to extract the characteristics of ecological parameter changes, the periodicity, trend, and time-domain and frequency-domain characteristics of ecological parameters are revealed. Based on the time-series change characteristics of ecological parameters, ecological parameter diffraction simulation can identify the diffusion paths of ecological parameters and predict their changing trends, thereby quantifying the radiation effect of the restored area on the surrounding environment. This breaks through the limitations of traditional assessment methods that are limited to the interior of the restored area, achieving a scientific prediction and visual representation of the spatial transmission capacity of ecological restoration effects. By using fuzzy clustering algorithms to cluster the regional ecological state of the ecological diffraction prediction data, and determining the ecological restoration effectiveness of the target area based on the ecological state clustering results, the actual effective range of the restoration effect and the degree of achievement of the expected goals can be comprehensively quantified, achieving an overall effectiveness assessment from local restoration to regional radiation effects. Ecological diffraction refers to the fact that during the ecological restoration process, the restored area can not only restore its own ecological functions but also transmit positive ecological effects to surrounding areas through species dispersal, water body improvement, and food web reconstruction, thereby driving the improvement of the ecological environment in surrounding areas that were not directly restored.

[0021] According to an embodiment of the present invention, the steps of acquiring water quality parameter data of the target coral reef restoration area, determining the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determining the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance are as follows: Obtain water quality parameter data for the target coral reef restoration area, including water turbidity, salinity, temperature, pH, and dissolved oxygen. The wireless transmission performance data of underwater monitoring sensors in the target coral reef restoration area is acquired. The underwater monitoring sensors include camera sensors and sonar sensors. The wireless transmission performance data includes signal transmission power and operating frequency. Based on the wireless transmission performance data and water quality parameter data, determine the signal transmission attenuation coefficient of the underwater monitoring sensor under the water quality conditions of the target coral reef restoration area as a function of distance; Obtain the location information of the data receiving server of the underwater monitoring sensor, and construct a signal reception attenuation map of the data receiving server for the underwater monitoring sensor data based on the location information of the data receiving server and the attenuation coefficient. A communication link is established between the data receiving server and the underwater monitoring sensor. An underwater wireless sensor network is constructed based on the communication link. The maximum reliable communication distance of the underwater wireless sensor network is determined based on the signal reception attenuation spectrum. The effective monitoring range of ecological diffraction in the target coral reef restoration area is determined based on the maximum reliable communication distance.

[0022] It should be noted that due to the complex and variable nature of the aquatic environment, especially the significant spatiotemporal variations in water quality parameters such as turbidity, salinity, and temperature, the transmission characteristics of wireless signals are greatly affected. Traditional monitoring network deployment methods using fixed communication distances often lead to inaccurate signal attenuation calculations and unreasonable delineation of the effective monitoring range, resulting in data loss or monitoring blind spots, and failing to provide a complete and reliable data foundation for assessing ecological diffraction effects. By comprehensively acquiring water quality parameters and sensor wireless transmission performance data, the signal attenuation coefficient under specific water quality conditions is calculated. This allows for the construction of a signal reception attenuation map based on the location and attenuation characteristics of the data receiving server. The underwater wireless sensor network communication link constructed based on this attenuation map determines the maximum reliable communication distance of the network, thereby adaptively delineating the effective monitoring range of ecological diffraction. This not only significantly improves the integrity and reliability of monitoring data and avoids monitoring blind spots caused by signal attenuation, but more importantly, it provides precise physical boundary guarantees for the spatial radiation range of subsequent assessments of ecological restoration effects. The effective monitoring range includes the target coral reef restoration area and the area surrounding the restoration area that the underwater wireless sensor network can effectively monitor. The communication link refers to the transmission and reception frequency information of the wireless signal.

[0023] According to an embodiment of the present invention, the step of acquiring in-situ ecological monitoring data within the effective monitoring range, and extracting ecological parameter change characteristics from the in-situ ecological monitoring data based on time series analysis to obtain ecological parameter time series change characteristic data, specifically includes: The effective monitoring range is divided into N sub-regions according to a preset grid size, and video image data and sonar detection data of each sub-region are periodically acquired according to the underwater wireless sensor network. Based on the video image data, the coral coverage area and coral species of each sub-region in each monitoring period are identified, and the ratio of coral coverage area to the total area of ​​the sub-region is calculated to obtain coral coverage time series data. Based on the video image data and sonar detection data, identify the types of fish appearing in each sub-region during each monitoring period, count the number of each type of fish, calculate the fish density per unit area, and obtain fish density time series data. Based on the sonar detection data and video image data, identify the species of macrobenthic invertebrates appearing in each sub-region during each monitoring period, count the number of each type of macrobenthic invertebrate, calculate the density of macrobenthic invertebrates per unit area, and obtain time series data of macrobenthic invertebrate habitat density. Based on the video image data, identify the area covered by macrobenthic algae and the species of macrobenthic algae in each sub-region during each monitoring period, calculate the ratio of macrobenthic algae coverage area to the total area of ​​the sub-region, and obtain time series data of macrobenthic algae coverage rate. The time series data of coral coverage, fish density, macrobenthic invertebrate density, and macrobenthic algae coverage in each sub-region were normalized respectively. The processed time series data of each ecological parameter were then divided into multiple continuous subsequence windows based on a sliding time window. Fast Fourier Transform is performed on the time series data of each ecological parameter in each subsequence window to extract the variation amplitude, variation period and variation trend features of each ecological parameter in the time domain and frequency domain, so as to obtain the time series variation feature data of ecological parameters in each subsequence window.

[0024] It should be noted that by converting continuously monitored coral coverage, fish density, and benthic biodiversity index into standardized time series data, and by using a sliding time window combined with fast Fourier transform, the changing trends, amplitude characteristics in the time domain, and periodic patterns in the frequency domain can be extracted simultaneously, which significantly enhances the ability to identify short-term fluctuations and long-term trends in the process of ecosystem restoration.

[0025] According to an embodiment of the present invention, the step of performing ecological parameter diffraction simulation on the target coral reef restoration area based on the temporal variation characteristic data of the ecological parameters, identifying the diffusion paths of the ecological parameters, and predicting the changes in ecological parameters based on the diffusion paths to obtain ecological diffraction prediction data, specifically includes: Based on the temporal variation characteristic data of the ecological parameters, the trend characteristics of each ecological parameter in the time domain and the periodic characteristics of each ecological parameter in the frequency domain are extracted for each sub-region, and an ecological parameter state vector is constructed with coral coverage, fish density, macrobenthic invertebrate density and macrobenthic algae coverage as variables. A two-dimensional plane coordinate system is constructed for the target coral reef restoration area. The ecological parameter state vector of each sub-region is mapped to the two-dimensional plane coordinate system according to the corresponding position coordinates. The two-dimensional plane coordinate system is then divided into grids according to the sub-region range to form the ecological parameter state value of each grid point. According to a preset time step, construct an ecological parameter state value distribution map for each grid point at each time step to obtain an ecological parameter state value distribution map set. Based on the ecological parameter state value distribution map set, construct a state transition map of the ecological state space of each sub-region. Based on the state transition diagram, ecological parameter diffraction simulation was performed on the target coral reef restoration area. Based on the ecological parameter state value distribution map, the change in ecological parameter state value of each grid point between adjacent time steps was extracted. Combined with the spatial distance between grid points, the state gradient vector of each ecological parameter between adjacent grid points was calculated. Based on the state gradient vector, identify the regions where ecological parameter state values ​​rise from the target coral reef restoration area to the non-restoration area, and determine the ecological parameter diffusion path from the target coral reef restoration area to the non-restoration area based on the regions where ecological parameter state values ​​rise. The ecological parameter rise time series data of each sub-region in the ecological parameter diffusion path are obtained, and the ecological parameter rise time series data are imported into a long short-term memory network to predict the changes of ecological parameters in the future within a preset time period, thereby obtaining ecological diffraction prediction data.

[0026] It is important to note that transforming time-series features into ecological parameter state vectors that can be expressed and evolved in the spatial domain, and forming a gridded ecological state distribution map in a two-dimensional plane coordinate system, allows the spatiotemporal changes of ecological parameters to be intuitively characterized through state evolution. As the time step progresses, the ecological parameter state values ​​at different grid points exhibit dynamic changes in the time domain. These changes are described in an orderly manner through the state transition diagram, further forming state gradient vectors between adjacent grid points. These gradient vectors reflect the spatial trends and directions of ecological parameter changes, and thus can be used to identify the diffusion effects from the restored area to surrounding areas. When the ecological parameters in certain areas show a continuous increase and exhibit a gradient structure radiating outward from the core area in the state space, it can be determined that an ecological diffusion path exists in that area. This path essentially reflects the spatial propagation law of ecological diffraction effects. Combining time-series prediction models to predict future trends of ecological parameters along diffusion paths not only reveals the dynamics of ecological restoration within the restored area but also scientifically deduces the diffusion and transmission process of restoration effects in adjacent unrestored areas. A state transition diagram (STP) is a graphical representation used in ecological parameter diffraction simulations to describe the evolution of ecological states between different time steps. It uses the ecological parameter state values ​​of each sub-region or grid point at a specific time step as nodes, and the changes in state values ​​between adjacent time steps as edges. This characterizes the transition patterns and spatial diffusion trends of parameters in the ecosystem over time, intuitively reflecting the dynamic trajectory of ecological parameters in the restoration area and its surrounding regions. In a Long Short-Term Memory (LSTM) network, the time-series data of each sub-region in the ecological parameter diffusion path are first input into the model. The network selectively receives and updates new ecological feature information through an input gate, filters out historical information that has no significant impact on future predictions through a forget gate, and simultaneously uses an output gate to pass the nonlinearly transformed state vector to the next time step. This approach maintains long-term dependency characteristics while also considering short-term dynamic changes, ultimately enabling the model to capture the periodicity, trends, and abrupt changes of ecological parameters in the time dimension and predict the changes in ecological parameters of each sub-region within a preset future time period based on the learned temporal patterns.

[0027] Figure 2 The flowchart illustrating the ecological state clustering results obtained by this invention is shown.

[0028] According to an embodiment of the present invention, the step of performing regional ecological state clustering on the ecological diffraction prediction data based on the fuzzy clustering algorithm to obtain the ecological state clustering result is specifically as follows: S202, Based on the ecological diffraction prediction data, determine the stability of ecological parameter changes within the effective monitoring range of ecological diffraction in the future preset time period, identify ecologically stable time points where the stability of ecological parameter changes is greater than the preset stability, and construct an ecological state feature vector from the ecological diffraction prediction data of each sub-region at the stable time point. S204, introduce a fuzzy clustering algorithm, initialize the number of clusters k of the fuzzy clustering algorithm, randomly select the ecological state feature vectors of k sub-regions as cluster centers, calculate the Euclidean distance from the ecological state feature vector of each sub-region to each cluster center, and calculate the membership value of each sub-region to each cluster based on the Euclidean distance. S206, each sub-region is assigned to the cluster center with the largest membership value to form a cluster, the mean value of the ecological state feature vector in each cluster is calculated, and the cluster center is updated according to the mean value; S208, iteratively execute the membership calculation and cluster center update steps until the change in cluster centers between two adjacent iterations is less than a preset threshold, and obtain the ecological state clustering results within the effective monitoring range of ecological diffraction.

[0029] It should be noted that clustering the ecological state at ecologically stable time points in the ecological diffraction prediction data using fuzzy clustering algorithms can identify the differences and similarities in the ecological state of the restoration area and its surrounding sub-regions at points where ecological parameters tend to stabilize, thus avoiding bias in clustering results caused by short-term fluctuations or abnormal disturbances. Determining the ecologically stable time points ensures that the input clustering data reflects the true characteristics of the ecosystem that has tended to a steady state during the restoration process, making the clustering results more reliable. Calculating the membership degree of each sub-region to each cluster using fuzzy clustering algorithms not only reveals the continuity and fuzziness of the ecological state but also quantifies the spatial distribution and hierarchy of ecological restoration, providing spatial evidence for assessing the ecological effectiveness of the restoration area and its positive ecological effects on surrounding unrestored areas. The clustering data k is a preset value.

[0030] Figure 3 The flowchart illustrating the determination of ecological restoration effectiveness in accordance with the present invention is shown.

[0031] According to an embodiment of the present invention, determining the ecological restoration effectiveness of the target coral reef restoration area based on the ecological state clustering results specifically includes: S302, extract the membership degree values ​​of all sub-regions to the optimal ecological state cluster from the ecological state clustering results, identify the sub-regions with membership degree values ​​greater than the preset membership degree threshold as ecological restoration effective areas, calculate the total area of ​​all ecological restoration effective areas, and obtain the actual effective area of ​​ecological restoration. S304, obtain the expected ecological diffraction restoration area of ​​the target coral reef restoration area, calculate the ratio of the actual effective ecological restoration area to the expected ecological diffraction restoration area, and obtain the ecological restoration area achievement rate. S306, Determine the ecological restoration effectiveness of the target coral reef restoration area based on the ecological restoration area achievement rate.

[0032] It should be noted that by utilizing the ecological state clustering results and the membership values ​​of sub-regions to the optimal cluster, the areas that actually generate ecological effects during coral reef restoration are identified, i.e., the ecological restoration effective areas. The total area of ​​these areas is then calculated to obtain the actual effective area of ​​ecological restoration. By calculating the ratio of the actual effective area to the preset ecological diffraction restoration area, the ecological restoration area achievement rate can be obtained, thereby enabling the assessment of restoration effectiveness. By quantitatively capturing the diffusion of the ecological diffraction effect in the surrounding areas, the driving force of the restored area on the improvement of the ecological environment of the surrounding unrestored areas can be comprehensively evaluated, achieving a precise assessment of the effectiveness of coral reef ecological restoration. The optimal ecological state cluster refers to the cluster with the best ecological state parameters in the ecological state clustering results.

[0033] Figure 4 A block diagram of a coral reef ecological restoration effectiveness assessment system based on ecological diffraction prediction according to the present invention is shown.

[0034] A second aspect of the present invention also provides a coral reef ecological restoration effectiveness evaluation system based on ecological diffraction prediction. The system includes: a memory 401, a processor 402, and a communication interface 403. The memory includes a program for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. The communication interface is used for data connection and communication between the memory and the processor. When the processor executes the program for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction, it performs the following steps: Acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; In-situ ecological monitoring data within the effective monitoring range is obtained, and ecological parameter change characteristics are extracted from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data. Based on the time-series variation characteristics of the ecological parameters, ecological parameter diffraction simulation is performed on the target coral reef restoration area to identify the diffusion path of the ecological parameters. Based on the diffusion path, ecological parameter changes are predicted to obtain ecological diffraction prediction data. The ecological diffraction prediction data is clustered into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological state clustering results.

[0035] This invention discloses a method and system for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. The method first acquires water quality parameters of the coral reef ecological restoration area and determines the maximum reliable communication distance of the underwater wireless sensor network, thereby determining the effective monitoring range of ecological diffraction. Within the monitoring range, in-situ ecological monitoring data is collected, and time series analysis is used to extract the characteristics of ecological parameter changes. Based on these characteristics, ecological parameter diffraction simulation is performed to identify diffusion paths and predict changes, obtaining ecological diffraction prediction data. A fuzzy clustering algorithm is used to cluster the predicted data into regional ecological states, thereby determining the effectiveness of ecological restoration in the restoration area. This invention enables dynamic monitoring and intelligent evaluation of coral reef restoration effects, possessing advantages such as high prediction accuracy and strong applicability, and can provide scientific decision support for coral reef ecological restoration projects.

[0036] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0037] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0038] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0039] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0040] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0041] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction, characterized in that, Includes the following steps: Acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; In-situ ecological monitoring data within the effective monitoring range is obtained, and ecological parameter change characteristics are extracted from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data. Based on the time-series variation characteristics of the ecological parameters, ecological parameter diffraction simulation is performed on the target coral reef restoration area to identify the diffusion path of the ecological parameters. Based on the diffusion path, ecological parameter changes are predicted to obtain ecological diffraction prediction data. The ecological diffraction prediction data is clustered into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological state clustering results.

2. The method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to claim 1, characterized in that, The process involves acquiring water quality parameter data for the target coral reef restoration area, determining the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determining the effective monitoring range of ecological diffraction in the target coral reef restoration area based on the maximum reliable communication distance. Specifically: Obtain water quality parameter data for the target coral reef restoration area, including water turbidity, salinity, temperature, pH, and dissolved oxygen. The wireless transmission performance data of underwater monitoring sensors in the target coral reef restoration area is acquired. The underwater monitoring sensors include camera sensors and sonar sensors. The wireless transmission performance data includes signal transmission power and operating frequency. Based on the wireless transmission performance data and water quality parameter data, determine the signal transmission attenuation coefficient of the underwater monitoring sensor under the water quality conditions of the target coral reef restoration area as a function of distance; Obtain the location information of the data receiving server of the underwater monitoring sensor, and construct a signal reception attenuation map of the data receiving server for the underwater monitoring sensor data based on the location information of the data receiving server and the attenuation coefficient. A communication link is established between the data receiving server and the underwater monitoring sensor. An underwater wireless sensor network is constructed based on the communication link. The maximum reliable communication distance of the underwater wireless sensor network is determined based on the signal reception attenuation spectrum. The effective monitoring range of ecological diffraction in the target coral reef restoration area is determined based on the maximum reliable communication distance.

3. The method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to claim 1, characterized in that, The process of acquiring in-situ ecological monitoring data within the effective monitoring range, and extracting ecological parameter change characteristics from the in-situ ecological monitoring data based on time series analysis methods to obtain time-series change characteristic data of ecological parameters, specifically involves: The effective monitoring range is divided into N sub-regions according to a preset grid size, and video image data and sonar detection data of each sub-region are periodically acquired according to the underwater wireless sensor network. Based on the video image data, the coral coverage area and coral species of each sub-region in each monitoring period are identified, and the ratio of coral coverage area to the total area of ​​the sub-region is calculated to obtain coral coverage time series data. Based on the video image data and sonar detection data, identify the types of fish appearing in each sub-region during each monitoring period, count the number of each type of fish, calculate the fish density per unit area, and obtain fish density time series data. Based on the sonar detection data and video image data, identify the species of macrobenthic invertebrates appearing in each sub-region during each monitoring period, count the number of each type of macrobenthic invertebrate, calculate the density of macrobenthic invertebrates per unit area, and obtain time series data of macrobenthic invertebrate habitat density. Based on the video image data, identify the area covered by macrobenthic algae and the species of macrobenthic algae in each sub-region during each monitoring period, calculate the ratio of macrobenthic algae coverage area to the total area of ​​the sub-region, and obtain time series data of macrobenthic algae coverage rate. The time series data of coral coverage, fish density, macrobenthic invertebrate density, and macrobenthic algae coverage in each sub-region were normalized respectively. The processed time series data of each ecological parameter were then divided into multiple continuous subsequence windows based on a sliding time window. Fast Fourier Transform is performed on the time series data of each ecological parameter in each subsequence window to extract the variation amplitude, variation period and variation trend features of each ecological parameter in the time domain and frequency domain, so as to obtain the time series variation feature data of ecological parameters in each subsequence window.

4. The method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to claim 1, characterized in that, The ecological parameter diffraction simulation of the target coral reef restoration area is performed based on the temporal variation characteristic data of the ecological parameters to identify the diffusion paths of the ecological parameters. Ecological parameter changes are then predicted based on these diffusion paths to obtain ecological diffraction prediction data. Specifically: Based on the temporal variation characteristic data of the ecological parameters, the trend characteristics of each ecological parameter in the time domain and the periodic characteristics of each ecological parameter in the frequency domain are extracted for each sub-region, and an ecological parameter state vector is constructed with coral coverage, fish density, macrobenthic invertebrate density and macrobenthic algae coverage as variables. A two-dimensional plane coordinate system is constructed for the target coral reef restoration area. The ecological parameter state vector of each sub-region is mapped to the two-dimensional plane coordinate system according to the corresponding position coordinates. The two-dimensional plane coordinate system is then divided into grids according to the sub-region range to form the ecological parameter state value of each grid point. According to a preset time step, construct an ecological parameter state value distribution map for each grid point at each time step to obtain an ecological parameter state value distribution map set. Based on the ecological parameter state value distribution map set, construct a state transition map of the ecological state space of each sub-region. Based on the state transition diagram, ecological parameter diffraction simulation was performed on the target coral reef restoration area. Based on the ecological parameter state value distribution map, the change in ecological parameter state value of each grid point between adjacent time steps was extracted. Combined with the spatial distance between grid points, the state gradient vector of each ecological parameter between adjacent grid points was calculated. Based on the state gradient vector, identify the regions where ecological parameter state values ​​rise from the target coral reef restoration area to the non-restoration area, and determine the ecological parameter diffusion path from the target coral reef restoration area to the non-restoration area based on the regions where ecological parameter state values ​​rise. The ecological parameter rise time series data of each sub-region in the ecological parameter diffusion path are obtained, and the ecological parameter rise time series data are imported into a long short-term memory network to predict the changes of ecological parameters in the future within a preset time period, thereby obtaining ecological diffraction prediction data.

5. The method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to claim 1, characterized in that, The process of clustering the ecological diffraction prediction data into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results is as follows: Based on the ecological diffraction prediction data, determine the stability of ecological parameter changes within the effective monitoring range of ecological diffraction in the future preset time period, identify ecologically stable time points where the stability of ecological parameter changes is greater than the preset stability, and construct an ecological state feature vector from the ecological diffraction prediction data of each sub-region at the stable time point. A fuzzy clustering algorithm is introduced. The number of clusters k in the fuzzy clustering algorithm is initialized. The ecological state feature vectors of k sub-regions are randomly selected as cluster centers. The Euclidean distance from the ecological state feature vector of each sub-region to each cluster center is calculated. The membership value of each sub-region to each cluster is calculated based on the Euclidean distance. Each sub-region is assigned to the cluster center with the largest membership value to form a cluster. The mean value of the ecological state feature vector within each cluster is calculated, and the cluster center is updated based on the mean value. The membership calculation and cluster center update steps are executed iteratively until the change in cluster centers between two adjacent iterations is less than a preset threshold, thus obtaining the ecological state clustering results within the effective monitoring range of ecological diffraction.

6. The method for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction according to claim 1, characterized in that, The determination of the ecological restoration effectiveness of the target coral reef restoration area based on the ecological state clustering results specifically includes: Extract the membership degree values ​​of all sub-regions to the optimal ecological state cluster from the ecological state clustering results, identify the sub-regions with membership degree values ​​greater than the preset membership degree threshold as ecological restoration effective areas, calculate the total area of ​​all ecological restoration effective areas, and obtain the actual effective area of ​​ecological restoration. Obtain the expected ecological diffraction restoration area of ​​the target coral reef restoration area, calculate the ratio of the actual effective ecological restoration area to the expected ecological diffraction restoration area, and obtain the ecological restoration area achievement rate. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological restoration area achievement rate.

7. A coral reef ecological restoration effectiveness evaluation system based on ecological diffraction prediction, characterized in that, The coral reef ecological restoration effectiveness evaluation system based on ecological diffraction prediction includes a storage device and a processor. The storage device includes a program for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction. When the processor executes the program for evaluating the effectiveness of coral reef ecological restoration based on ecological diffraction prediction, it performs the following steps: Acquire water quality parameter data of the target coral reef restoration area, determine the maximum reliable communication distance of the underwater wireless sensor network based on the water quality parameter data, and determine the effective monitoring range of ecological diffraction of the target coral reef restoration area based on the maximum reliable communication distance; In-situ ecological monitoring data within the effective monitoring range is obtained, and ecological parameter change characteristics are extracted from the in-situ ecological monitoring data based on time series analysis methods to obtain ecological parameter time series change characteristic data. Based on the time-series variation characteristics of the ecological parameters, ecological parameter diffraction simulation is performed on the target coral reef restoration area to identify the diffusion path of the ecological parameters. Based on the diffusion path, ecological parameter changes are predicted to obtain ecological diffraction prediction data. The ecological diffraction prediction data is clustered into regional ecological states based on the fuzzy clustering algorithm to obtain the ecological state clustering results. The ecological restoration effectiveness of the target coral reef restoration area is determined based on the ecological state clustering results.

Images