A data-driven oyster reef ecological restoration effect evaluation method and system

Abstract

The application discloses a data-driven oyster reef ecological restoration effect evaluation method and system, and relates to the technical field of data processing.The method comprises the following steps: establishing a multi-modal data set; after feature extraction, a feature index set is established, an oyster health comprehensive index is constructed, and a system service index is constructed; disturbance observation of the control area and the restoration area is performed by using the disturbance event; ecological resilience evaluation is performed by using the disturbance observation result and the multi-modal data set; an ecological resilience index is established; a structured causal diagram is established; attribution analysis of the restoration area and the control area is performed; the average treatment effect of the restoration measures on the oyster health comprehensive index and the system service index is constructed; after correction of the oyster health comprehensive index and the system service index, the ecological resilience index is combined to output the oyster reef ecological restoration effect evaluation result.The technical problem of inaccurate oyster reef ecological restoration effect evaluation in the prior art is solved, and the technical effect of improving the accuracy of the restoration effect evaluation is achieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a data-driven method and system for evaluating the effectiveness of oyster reef ecological restoration. Background Technology

[0002] Oyster reefs, as typical coastal ecosystems, possess vital ecological functions and economic value. They not only provide habitats for diverse aquatic organisms but also improve water quality, sequester carbon, and resist coastal erosion. However, due to environmental changes, global oyster reef resources have declined significantly, making ecological restoration a critical issue that urgently needs to be addressed. Existing methods for assessing the effectiveness of oyster reef restoration often rely on single biological or physicochemical indicators, lacking comprehensive utilization of multi-source information. This makes it difficult to fully reflect the health status of individual oysters, ecosystem service functions, and ecological resilience in the restoration area, leading to inaccurate assessment results and failing to provide a reliable basis for optimizing restoration measures. Summary of the Invention

[0003] This application provides a data-driven method and system for evaluating the ecological restoration effect of oyster reefs, which solves the technical problem of inaccurate evaluation of the ecological restoration effect of oyster reefs in the prior art.

[0004] The first aspect of this application provides a data-driven method for evaluating the effectiveness of oyster reef ecological restoration, the method comprising:

[0005] After configuring control and restoration areas, biological, physicochemical, acoustic, image, and microbiome data of individual oysters within the oyster reef were collected to establish a multimodal dataset. Feature extraction was performed on the multimodal dataset to establish a feature index set. This feature index set was used to construct an oyster health comprehensive index and system service indicators. Disturbance events were configured, and disturbance observations were performed in both the control and restoration areas. The results of these observations, along with the multimodal dataset, were used to perform an ecological resilience assessment and establish an ecological resilience index. Using the oyster health comprehensive index and system service indicators as outcome variables, and the multimodal dataset as causal input, a structured causal graph was established. Attribution analysis was performed on the restoration and control areas based on the structured causal graph. The average treatment effect of restoration measures on the oyster health comprehensive index and system service indicators was constructed. Based on the average treatment effect, the oyster health comprehensive index and system service indicators were corrected, and the ecological resilience index was combined to output the evaluation results of the oyster reef ecological restoration effect.

[0006] A second aspect of this application provides a data-driven system for evaluating the effectiveness of oyster reef ecological restoration, the system comprising:

[0007] Data Acquisition Module: After configuring the control and restoration areas, biological, physicochemical, acoustic, image, and microbiome data of individual oysters within the oyster reef are collected to establish a multimodal dataset. Feature Extraction Module: After extracting features from the multimodal dataset, a feature index set is established. The feature index set is used to construct an oyster health comprehensive index and system service indicators. Resilience Assessment Module: Disturbance events are configured, and disturbance observations are performed in the control and restoration areas using these events. The results of the disturbance observations and the multimodal dataset are used to perform ecological resilience assessment and establish an ecological resilience index. Attribution Analysis Module: The oyster health comprehensive index and system service indicators are used as outcome variables, and the multimodal dataset is used as causal input to establish a structured causal graph. Attribution analysis is performed in the restoration and control areas based on the structured causal graph. The average treatment effect of restoration measures on the oyster health comprehensive index and system service indicators is constructed. After correcting the oyster health comprehensive index and system service indicators based on the average treatment effect, the ecological resilience index is combined to output the evaluation results of the oyster reef ecological restoration effect.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] After configuring control and restoration zones, biological, physicochemical, acoustic, image, and microbiome data of individual oysters within the oyster reef were collected to establish a multimodal dataset. Feature extraction was performed on the multimodal dataset to establish a feature index set. This feature index set was then used to construct a comprehensive oyster health index and system service indicators. Next, disturbance events were configured, and disturbance observations were performed in both the control and restoration zones. The results of these observations, along with the multimodal dataset, were used to perform an ecological resilience assessment and establish an ecological resilience index. Finally, using the comprehensive oyster health index and system service indicators as outcome variables, and the multimodal dataset as causal input, a structured causal graph was constructed. Attribution analysis was performed on the restoration and control zones based on this graph. The average treatment effect of restoration measures on the comprehensive oyster health index and system service indicators was constructed. Based on this average treatment effect, the comprehensive oyster health index and system service indicators were corrected, and the ecological resilience index was combined to output the evaluation results of the oyster reef ecological restoration effect. This invention addresses the technical problem of inaccurate assessment of oyster reef ecological restoration effects in existing technologies, achieving the technical effect of improving the accuracy of oyster reef ecological restoration effect assessment by combining multimodal data-driven approaches, causal attribution analysis, and ecological resilience evaluation. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A schematic diagram of a data-driven method for evaluating the effectiveness of oyster reef ecological restoration, provided in an embodiment of this application;

[0012] Figure 2 This is a schematic diagram of a data-driven oyster reef ecological restoration effect evaluation system provided in an embodiment of this application.

[0013] Figure labeling: Data acquisition module 11, feature extraction module 12, resilience assessment module 13, attribution analysis module 14. Detailed Implementation

[0014] This application provides a data-driven method and system for evaluating the effectiveness of oyster reef ecological restoration, which solves the technical problem of inaccurate evaluation of oyster reef ecological restoration effectiveness in the prior art.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0016] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0017] Example 1, as Figure 1 As shown, this application provides a data-driven method for evaluating the effectiveness of oyster reef ecological restoration, wherein the method includes:

[0018] After configuring the control and restoration areas, biological, physicochemical, acoustic, image, and microbiome data of individual oysters in the oyster reef were collected to establish a multimodal dataset.

[0019] Furthermore, the biological data includes oyster individual density, survival rate, and shell size distribution; the physicochemical data includes water temperature, salinity, pH value, dissolved oxygen, and nutrient concentration; the acoustic data includes acoustic data of multi-channel underwater acoustic signals; the image data includes data on reef coverage and crack information based on underwater image recognition; and the microbiome data includes data on microbial diversity and functional gene abundance obtained through high-throughput sequencing.

[0020] In this embodiment of the application, a control area and a restoration area are reasonably configured in the sea area to be evaluated. The control area is a natural oyster reef or degraded reef area that has not undergone artificial restoration measures, and the restoration area is an oyster reef area where ecological restoration engineering measures have been implemented. Subsequently, multi-source data collection was carried out simultaneously in the control and restoration areas, including: collecting biological data of individual oysters, specifically by using underwater sampling and fixed-point monitoring to count oyster density, survival rate, shell size distribution, and shell growth rate; collecting physicochemical data, specifically by deploying multi-parameter water quality monitors and automatic samplers to record continuous or timed water physicochemical indicators such as water temperature, salinity, pH value, dissolved oxygen content, and nutrient concentration; collecting acoustic data, specifically by deploying multi-channel underwater acoustic acquisition devices around the reef to record long-term acoustic signals of oyster filter feeding behavior and environmental background sounds; collecting image data, specifically by using underwater cameras, ROVs (remotely operated underwater vehicles), or structured light imaging equipment to obtain image information such as reef surface coverage, crack information, and attachment distribution; and collecting microbiome data, specifically by collecting water samples, sediment samples, and biological samples from individual oysters and the reef surface, and using high-throughput sequencing technology to obtain data on microbial diversity, community composition, and functional gene abundance. By acquiring the aforementioned multi-source data, a comprehensive data support system covering oyster individuals, environmental conditions, community activity, structural characteristics, and microbial functions is formed, thus providing sufficient basis for subsequent feature extraction and restoration effect evaluation.

[0021] After feature extraction from the multimodal dataset, a feature index set is established. The oyster health comprehensive index is constructed using the feature index set, and system service indicators are also constructed.

[0022] By extracting features from multimodal datasets, a set of feature indicators was established. For example, key physiological characteristics such as oyster individual survival rate, density change rate, and shell growth rate were extracted from biological data; environmental characteristics such as dissolved oxygen fluctuation rate and nutrient concentration trends were extracted from physicochemical data; dynamic behavioral characteristics such as frequency band energy distribution and filter-feeding-related voiceprint ratios were extracted from acoustic data; structural characteristics such as reef coverage, fissure rate, and attachment distribution were extracted from image data; and community functional characteristics such as community diversity index and functional gene abundance index were extracted from microbiome data. Based on this, a comprehensive oyster health index was constructed by weighted fusion of features from different dimensions to quantitatively characterize the overall health level of individual oysters and the community. Simultaneously, by combining the covariance relationship between the comprehensive oyster health index and physicochemical environmental factors, reef structural characteristics, and microbial functional characteristics, system service indicators were constructed to quantify the systemic ecological service effects of oyster reefs in water purification, sediment stability, and carbon sequestration.

[0023] Furthermore, after feature extraction from the multimodal dataset, a feature index set is established. This feature index set is then used to construct an oyster health comprehensive index, and system service indicators are also constructed, including:

[0024] After modal stratification of the multimodal dataset, independent normalization is performed on each sub-dataset to establish stratified feature subsets. Principal component analysis is performed on the stratified feature subsets to determine the contribution factors of the stratified feature factors, and weighting of the stratified feature subsets is performed based on the contribution factors. Survival rate, shell growth rate, and community density are extracted from the biological subset of the stratified feature subsets as the first health dimension. Biodiversity index and functional gene richness are extracted from the microbiome subset as the second health dimension. Frequency band complexity and the ratio of typical filter-feeding sound signals are extracted from the voiceprint subset as the third health dimension. The first, second, and third health dimensions are weighted and fused according to the weighted multimodal coupling weights to establish a comprehensive oyster health index.

[0025] After feature extraction from the multimodal dataset, it was stratified into different data groups based on different dimensions, such as biological, microbiome, and voiceprint subsets. Independent normalization was performed on each subset to eliminate differences in dimensions and measurement scales, resulting in standardized stratified feature subsets. Principal component analysis was then performed on each subset to determine the contribution rate of key feature factors. Weights were assigned to each subset based on these contribution rates to obtain a reasonable multimodal weight distribution. Based on this, oyster survival rate, shell growth rate, and community density were extracted from the biological subset as the first health dimension; microbial diversity index and functional gene richness index were extracted from the microbiome subset as the second health dimension; and frequency band complexity and the ratio of typical filter-feeding sound signals were extracted from the voiceprint subset as the third health dimension. Finally, the first, second, and third health dimensions were weighted and fused according to the aforementioned multimodal coupling weights to establish a comprehensive oyster health index that reflects the individual survival status of oysters, community activity, and microbial functional support.

[0026] Furthermore, after establishing a comprehensive oyster health index, it includes:

[0027] Nitrogen and phosphorus removal efficiency change rate indices were extracted from the physicochemical subset, and filter feeding efficiency correlation factors were obtained from the oyster health comprehensive index. Water purification efficiency indices were established based on these indices. Matrix coverage and fissure rate indices were extracted from the image subset, and community density factors were obtained from the oyster health comprehensive index. Sediment stability indices were established based on these indices. Carbon cycling functional gene abundance was extracted from the microbiome subset, and after obtaining the community density factor from the oyster health comprehensive index, a carbon sink rate indice was established. Covariance analysis was performed on the water purification efficiency indices, sediment stability indices, carbon sink rate indices, and the oyster health comprehensive index to quantify the coupling degree between individual oyster health and system service functions, establishing system service indices.

[0028] System service indicators were constructed based on a multimodal dataset and the Oyster Health Comprehensive Index. Specifically, for the physicochemical subset, nitrogen and phosphorus concentration data collected by a continuous water quality monitor were used, combined with flow rate measurements at the inlet and outlet sections of the remediation and control areas, to calculate the rate of change in nitrogen and phosphorus removal efficiency. A linear regression model was then performed based on the filter-feeding efficiency correlation factor in the Oyster Health Comprehensive Index (estimated through acoustic signature and individual density) to generate a water purification efficiency index. Secondly, for the image subset, underwater image segmentation algorithms (such as convolutional neural network image segmentation models) were applied to extract the matrix coverage and fissure rate features of the reef surface. Combined with the community density factor in the Oyster Health Comprehensive Index, a multiple regression method was used to establish a sediment stability index to quantify the inhibitory effect of oyster reef structure on sediment resuspension. Thirdly, for the microbiome subset, functional gene annotation results from high-throughput sequencing data were used to screen for the abundance of functional genes related to carbon cycling (such as genes related to carbon fixation, methane metabolism, and cellulose degradation). Combined with the community density factor in the Oyster Health Comprehensive Index, a weighted index method was used to calculate the carbon sink rate index. Finally, using covariance analysis, the water purification efficiency index, sediment stability index, and carbon sink rate index were statistically coupled with the oyster health comprehensive index to obtain the coupling degree value between individual oyster health and system service function. In this way, oyster reef system service indexes were established to achieve a comprehensive evaluation of the restoration effect.

[0029] Configure disturbance events, perform disturbance observations in the control and restoration areas using the disturbance events, perform ecological resilience assessments using the disturbance observation results and multimodal datasets, and establish an ecological resilience index.

[0030] Furthermore, the disturbance events include biological invasion events, instantaneous release of pollutants, and extreme temperature changes.

[0031] In this embodiment, controlled disturbance events are configured in the control and remediation areas to simulate extreme scenarios in the real environment and to assess ecological resilience. Specifically, the disturbance events include biological invasion events, instantaneous pollutant release events, and extreme temperature change events. Biological invasion events are simulated by artificially introducing a certain density of invasive shellfish or crustaceans into the experimental waters to simulate competitive crowding effects; instantaneous pollutant release events are simulated by adding high-concentration nutrient solutions or short-term high-load suspended particulate matter to the target sea area to simulate the outbreak input of red tides or land-based pollution; extreme temperature change events are simulated by deploying controllable heating or cooling devices in local areas to rapidly raise or lower the water temperature in a short period of time to simulate extreme high temperatures in summer or extreme low temperatures in winter. During the disturbance process, multiple time-series observation windows are configured, and online water quality monitoring instruments, acoustic monitoring equipment, image acquisition devices, and microbial sampling tools are deployed to dynamically record the physiological state of oyster individuals, environmental physicochemical parameters, community acoustic characteristics, and changes in the microbial community before, during, and after the disturbance. Subsequently, the collected disturbance observation results were compared and analyzed with the ground state multimodal dataset. The disturbance resistance index (the decrease in health index under the disturbance intensity), the recovery index (the recovery speed of health index after disturbance), and the overcompensation index (whether the level after disturbance exceeds the level before disturbance) were calculated respectively. An ecological resilience index was established by weighted synthesis method to quantitatively characterize the ecological stability and recovery capacity of oyster reefs under different disturbance scenarios.

[0032] Furthermore, perturbation events are configured, and perturbation observations are performed in the control and restoration areas using these events. The results of these perturbation observations and multimodal datasets are then used to perform ecological resilience assessments and establish ecological resilience indices, including:

[0033] Controllable disturbance events were set up in both the remediation and control areas. These events included short-term nutrient pulses, sediment load disturbances, acoustic interference, and physical disturbances. The intensity of these disturbances was set based on the statistical distribution of historical extreme environmental events. After the disturbances were executed, multiple time-series observation windows were configured to perform disturbance observations in both the control and remediation areas, and disturbance observation results were established. The multimodal dataset was used as the ground-state data, and the disturbance observation results were used as the disturbance results. The resilience index, recovery index, and overcompensation index were extracted to establish an ecological resilience index.

[0034] Controlled disturbance events were set up in both the remediation and control areas. These events included short-term nutrient pulses, sediment loading disturbances, acoustic interference, and physical disturbances. The intensity of the disturbances was determined based on the statistical distribution of historical extreme environmental events in the target sea area to ensure the environmental realism and representativeness of the disturbance conditions. Specifically, short-term nutrient pulses simulated the risk of red tide outbreaks by artificially adding high-concentration nitrogen and phosphorus nutrient solutions; sediment loading disturbances simulated storm runoff or seabed disturbance by suspending sediment particles in the water; acoustic interference simulated ship or construction noise by playing high-intensity low-frequency noise through underwater speakers; and physical disturbances simulated typhoon surges or trawl damage by mechanical paddling or localized scouring. After the disturbances were implemented, multi-time-series observation windows were established before, during, and after the disturbances. These windows utilized multi-parameter water quality probes, acoustic monitoring arrays, underwater camera systems, and microbial sampling tools to continuously monitor the individual oyster conditions, environmental physicochemical conditions, acoustic signatures of the oyster community, and microbial community structure, generating disturbance observation results. Subsequently, using the pre-disturbance multimodal dataset as the ground state data and the disturbance observation data as the disturbance result, the health index change curve and time series were constructed to calculate the oyster reef's resistance index (index decline magnitude), resilience index (recovery speed), and overcompensation index (whether it exceeds the ground state level after recovery) under disturbance. Based on the weighted fusion method, an ecological resilience index was established to achieve a quantitative assessment of the ecological stability and resilience of the restoration area and the control area under different disturbance conditions.

[0035] Using the oyster health comprehensive index and system service indicators as outcome variables, and a multimodal dataset as causal input, a structured causal graph was established. Attribution analysis was performed on the restoration area and the control area based on the structured causal graph. The average treatment effect of restoration measures on the oyster health comprehensive index and system service indicators was constructed. After correcting the oyster health comprehensive index and system service indicators based on the average treatment effect, the ecological resilience index was combined to output the evaluation results of the oyster reef ecological restoration effect.

[0036] Using the oyster health index and system service indicators as outcome variables and a multimodal dataset as causal input variables, a structured causal graph was constructed using causal modeling methods. Specifically, firstly, biological, physicochemical, acoustic, image, and microbiome features from the multimodal dataset were utilized, combined with spatial information from the restoration and control areas, to construct a node set. Then, structured learning algorithms (such as constraint-based PC algorithms or rating-based GES algorithms) were used to identify causal edge relationships between variables, forming a causal network structure for oyster reef restoration. Subsequently, parameter learning was performed on the causal graph to obtain the probability strength of each causal path. Based on this, a comparative analysis was conducted between the restoration and control areas using a causal inference framework (such as a latent outcome model), calculating the average treatment effect (ATE) of restoration measures on the oyster health index and system service indicators to quantitatively identify the direct contribution of restoration measures. Furthermore, a correspondence was established between the ATE and the oyster health index and system service indicators, and the corrected health index and service indicator values ​​were obtained through causal-driven error elimination and normalization correction. Finally, the revised oyster health comprehensive index, system service indicators and the aforementioned ecological resilience index will be jointly analyzed to comprehensively output the evaluation results of oyster reef ecological restoration effect, so as to achieve causal attribution, quantitative evaluation and scientific judgment of the effect of restoration measures.

[0037] The revised oyster health index, system service indicators, and ecological resilience index were jointly analyzed. Specifically, time series alignment and scale normalization were performed on the three types of indicators to ensure the comparability of data from different sources within the same analytical framework. Multivariate statistical modeling methods (such as principal component analysis and covariance structure modeling) or machine learning fusion algorithms (such as random forest regression and Bayesian network fusion) were used to jointly model the revised oyster health index, system service indicators, and ecological resilience index, identifying the coupling relationships and comprehensive contributions among them. A comprehensive evaluation score was generated through weighted fusion, where weights were allocated based on the contribution of each indicator to the explained variance or expert experience. The comprehensive evaluation score was used as the output of the oyster reef ecological restoration effect assessment, achieving a comprehensive quantitative judgment of the overall ecological health status, system service functions, and resilience to disturbances in the restoration area.

[0038] Furthermore, attribution analysis of the remediation and control areas was conducted based on structured causal diagrams to construct the average treatment effects of remediation measures on the comprehensive health index and system service indicators of oysters, including:

[0039] Based on the average treatment effect channel, perform a comparative analysis of the average treatment effect in the repair area and the control area; perform sensitivity perturbation identification of the results of the comparative analysis of the average treatment effect, and generate the average treatment effect.

[0040] Based on the established structured causal graph, causal attribution analysis was performed on data from the remediation and control areas to construct the average treatment effect of remediation measures on the comprehensive health index and system service indicators of oysters. Specifically, based on the average treatment effect channel, multimodal data from the remediation and control areas were input into the causal inference model. The potential outcome method or propensity score matching method was used to conduct a comparative analysis of the differences between the remediation and control areas in the comprehensive health index and system service indicators of oysters, obtaining the average treatment effect value of the remediation measures. Subsequently, sensitivity perturbation identification was performed on the results of the average treatment effect comparative analysis. This involved perturbation simulation of key input variables (such as oyster density, nutrient concentration, and voiceprint complexity) to detect the sensitivity range of the result indicators, identifying potential confounding biases and uncertainties in causal inference. Finally, the average treatment effect was corrected and verified based on the sensitivity perturbation identification results, generating a robustly corrected average treatment effect value.

[0041] Furthermore, adjustments were made to the oyster health composite index and system service indicators based on the average treatment effect, including:

[0042] The average treatment effect is correlated with the oyster health comprehensive index and system service indicators. After eliminating misjudgments under causal drive using the correlation, the indicators are normalized, and the results of the normalization are used to generate the evaluation results of the oyster reef ecological restoration effect.

[0043] After obtaining the average treatment effect of restoration measures on the comprehensive oyster health index and system service indicators, the original indicators were corrected based on this average effect to improve the accuracy of the assessment results. Specifically, a correspondence was established between the average treatment effect and the comprehensive oyster health index and system service indicators, respectively. By establishing a causal mapping function, the direction and magnitude of the shift of restoration measures on different indicators were determined. The correspondence was used to eliminate misjudgments in the original indicator values ​​under causal drive, that is, by correcting spurious correlations caused by confounding variables, and eliminating unrealistic effects caused by environmental fluctuations or random errors. After completing the misjudgment elimination, the corrected comprehensive oyster health index and system service indicators were normalized to enable quantitative comparison and integration on a unified scale. Finally, the normalized indicator data was used to conduct joint analysis with the ecological resilience index to generate the assessment results of the oyster reef ecological restoration effect.

[0044] Furthermore, the combined ecological resilience index outputs the assessment results of oyster reef ecological restoration effectiveness, including:

[0045] Establish a mapping between restoration measures and average treatment effects, and create a mapping data set; use the mapping data set as matching data, perform matching anomaly identification in the expert database, and create matching anomaly signals; conduct attention verification of the control area and restoration area based on the matching anomaly signals, and update the attention verification results to the mapping data set to carry out subsequent oyster reef ecological restoration management.

[0046] Specifically, a mapping relationship between restoration measures and average treatment effects is established, mapping different types of restoration measures (such as artificial reef deployment, oyster seedling replenishment, and environmental control) to their corresponding average treatment effect results to form a mapping data set. This mapping data set is then input into an expert knowledge database as matching data. A matching anomaly identification mechanism based on a rule engine or machine learning algorithm is invoked to identify potential anomalies by comparing them with standard experience results or historical evaluation samples, and outputting matching anomaly signals. Upon detecting matching anomaly signals, further verification is performed on the restoration and control areas, i.e., through supplementary sampling or intensified monitoring, focusing on verifying suspicious indicators (such as sudden drops in oyster density, abnormal fluctuations in nutrient levels, etc.). Finally, the results of the verification are fed back to update the mapping data set, correcting and improving the relationship between restoration measures and effects to support the dynamic management of subsequent oyster reef ecological restoration.

[0047] In summary, the embodiments of this application have at least the following technical effects:

[0048] After configuring control and restoration zones, biological, physicochemical, acoustic, image, and microbiome data of individual oysters within the oyster reef were collected to establish a multimodal dataset. Feature extraction was performed on the multimodal dataset to establish a feature index set. This feature index set was then used to construct a comprehensive oyster health index and system service indicators. Next, disturbance events were configured, and disturbance observations were performed in both the control and restoration zones. The results of these observations, along with the multimodal dataset, were used to perform an ecological resilience assessment and establish an ecological resilience index. Finally, using the comprehensive oyster health index and system service indicators as outcome variables, and the multimodal dataset as causal input, a structured causal graph was constructed. Attribution analysis was performed on the restoration and control zones based on this graph. The average treatment effect of restoration measures on the comprehensive oyster health index and system service indicators was constructed. Based on this average treatment effect, the comprehensive oyster health index and system service indicators were corrected, and the ecological resilience index was combined to output the evaluation results of the oyster reef ecological restoration effect. This invention addresses the technical problem of inaccurate assessment of oyster reef ecological restoration effects in existing technologies, achieving the technical effect of improving the accuracy of oyster reef ecological restoration effect assessment by combining multimodal data-driven approaches, causal attribution analysis, and ecological resilience evaluation.

[0049] Example 2, based on the same inventive concept as the data-driven oyster reef ecological restoration effect evaluation method in the foregoing examples, such as... Figure 2 As shown, this application provides a data-driven system for evaluating the ecological restoration effects of oyster reefs, wherein the system includes:

[0050] Data Acquisition Module 11: After configuring the control and restoration areas, collect biological, physicochemical, acoustic, image, and microbiome data of individual oysters within the oyster reef to establish a multimodal dataset; Feature Extraction Module 12: After extracting features from the multimodal dataset, establish a feature index set, construct an oyster health comprehensive index using the feature index set, and construct system service indicators; Resilience Assessment Module 13: Configure disturbance events, perform disturbance observations in the control and restoration areas using the disturbance events, perform ecological resilience assessments using the disturbance observation results and the multimodal dataset, and establish an ecological resilience index; Attribution Analysis Module 14: Use the oyster health comprehensive index and system service indicators as outcome variables, and the multimodal dataset as causal input to establish a structured causal graph. Based on the structured causal graph, perform attribution analysis in the restoration and control areas, construct the average treatment effect of restoration measures on the oyster health comprehensive index and system service indicators, perform corrections to the oyster health comprehensive index and system service indicators based on the average treatment effect, and output the oyster reef ecological restoration effect assessment results in conjunction with the ecological resilience index.

[0051] Furthermore, the data acquisition module 11 is used to perform the following methods:

[0052] The biological data includes oyster individual density, survival rate, and shell size distribution; the physicochemical data includes water temperature, salinity, pH value, dissolved oxygen, and nutrient concentration; the acoustic data includes acoustic data of multi-channel underwater acoustic signals; the image data includes data on reef coverage and crack information based on underwater image recognition; and the microbiome data includes data on microbial diversity and functional gene abundance obtained through high-throughput sequencing.

[0053] Furthermore, the feature extraction module 12 is used to perform the following method:

[0054] After modal stratification of the multimodal dataset, independent normalization is performed on each sub-dataset to establish stratified feature subsets. Principal component analysis is performed on the stratified feature subsets to determine the contribution factors of the stratified feature factors, and weighting of the stratified feature subsets is performed based on the contribution factors. Survival rate, shell growth rate, and community density are extracted from the biological subset of the stratified feature subsets as the first health dimension. Biodiversity index and functional gene richness are extracted from the microbiome subset as the second health dimension. Frequency band complexity and the ratio of typical filter-feeding sound signals are extracted from the voiceprint subset as the third health dimension. The first, second, and third health dimensions are weighted and fused according to the weighted multimodal coupling weights to establish a comprehensive oyster health index.

[0055] Furthermore, the feature extraction module 12 is used to perform the following method:

[0056] Nitrogen and phosphorus removal efficiency change rate indices were extracted from the physicochemical subset, and filter feeding efficiency correlation factors were obtained from the oyster health comprehensive index. Water purification efficiency indices were established based on these indices. Matrix coverage and fissure rate indices were extracted from the image subset, and community density factors were obtained from the oyster health comprehensive index. Sediment stability indices were established based on these indices. Carbon cycling functional gene abundance was extracted from the microbiome subset, and after obtaining the community density factor from the oyster health comprehensive index, a carbon sink rate indice was established. Covariance analysis was performed on the water purification efficiency indices, sediment stability indices, carbon sink rate indices, and the oyster health comprehensive index to quantify the coupling degree between individual oyster health and system service functions, establishing system service indices.

[0057] Furthermore, the toughness assessment module 13 is used to perform the following method:

[0058] Controllable disturbance events were set up in both the remediation and control areas. These events included short-term nutrient pulses, sediment load disturbances, acoustic interference, and physical disturbances. The intensity of these disturbances was set based on the statistical distribution of historical extreme environmental events. After the disturbances were executed, multiple time-series observation windows were configured to perform disturbance observations in both the control and remediation areas, and disturbance observation results were established. The multimodal dataset was used as the ground-state data, and the disturbance observation results were used as the disturbance results. The resilience index, recovery index, and overcompensation index were extracted to establish an ecological resilience index.

[0059] Furthermore, the attribution analysis module 14 is used to perform the following methods:

[0060] Based on the average treatment effect channel, perform a comparative analysis of the average treatment effect in the repair area and the control area; perform sensitivity perturbation identification of the results of the comparative analysis of the average treatment effect, and generate the average treatment effect.

[0061] Furthermore, the attribution analysis module 14 is used to perform the following methods:

[0062] Establish a mapping between restoration measures and average treatment effects, and create a mapping data set; use the mapping data set as matching data, perform matching anomaly identification in the expert database, and create matching anomaly signals; conduct attention verification of the control area and restoration area based on the matching anomaly signals, and update the attention verification results to the mapping data set to carry out subsequent oyster reef ecological restoration management.

[0063] Furthermore, the toughness assessment module 13 is used to perform the following method:

[0064] The disturbance events include biological invasion events, instantaneous release of pollutants, and extreme temperature changes.

[0065] Furthermore, the attribution analysis module 14 is used to perform the following methods:

[0066] The average treatment effect is correlated with the oyster health comprehensive index and system service indicators. After eliminating misjudgments under causal drive using the correlation, the indicators are normalized, and the results of the normalization are used to generate the evaluation results of the oyster reef ecological restoration effect.

[0067] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0068] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0069] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A data-driven oyster reef ecological restoration effect evaluation method, characterized in that, The method comprises: After the control area and the repair area are configured, biological data, physical and chemical data, acoustic print data, image data, and microbiome data of oyster individuals in the oyster reef are collected to establish a multi-modal data set; After feature extraction is performed on the multi-modal data set, a feature index set is established, and an oyster health comprehensive index is constructed using the feature index set, and a system service class index is constructed; A disturbance event is configured, and disturbance observation of the control area and the repair area is performed using the disturbance event, ecological resilience evaluation is performed using the disturbance observation results and the multi-modal data set, and an ecological resilience index is established; The oyster health comprehensive index and the system service class index are taken as result variables, and the multi-modal data set is taken as causal input to establish a structured causal diagram, and attribution analysis of the repair area and the control area is performed based on the structured causal diagram, an average treatment effect of the repair measures on the oyster health comprehensive index and the system service class index is constructed, and after the oyster health comprehensive index and the system service class index are corrected based on the average treatment effect, the ecological resilience index outputs an oyster reef ecological restoration effect evaluation result; After the feature extraction is performed on the multi-modal data set, the feature index set is established, and the oyster health comprehensive index is constructed using the feature index set, and the system service class index is constructed, comprising: After the multi-modal data set is modally layered, independent normalization processing is respectively performed, and a layered feature subset is established; Principal component analysis of the layered feature subset is performed to determine a contribution factor of a layered feature factor, and the layered feature subset is weighted based on the contribution factor; Survival rate, shell growth rate, and community density in a biological subset in the layered feature subset are extracted as a first health dimension; Biodiversity index and functional gene richness in a microbiome subset are extracted as a second health dimension; Frequency band complexity and a ratio of typical filter-feeding sound signals in an acoustic print subset are extracted as a third health dimension; Weighted fusion of the first health dimension, the second health dimension, and the third health dimension is performed according to the weighted multi-modal coupling weight, and an oyster health comprehensive index is established; After the oyster health comprehensive index is established, comprising: A nitrogen and phosphorus removal efficiency change rate index in the physical and chemical subset is extracted, and a filter-feeding efficiency correlation factor in the oyster health comprehensive index is obtained, and a water quality purification efficiency index is established according to the nitrogen and phosphorus removal efficiency change rate index and the filter-feeding efficiency correlation factor; Substrate coverage and crack rate indexes in the image subset are extracted, and a community density factor in the oyster health comprehensive index is obtained, and a sediment stability index is established according to the substrate coverage and crack rate indexes and the community density factor; Carbon cycle functional gene abundance in the microbiome subset is extracted, and after the community density factor in the oyster health comprehensive index is obtained, a carbon sink rate index is established; Covariance analysis is performed on the water quality purification efficiency index, the sediment stability index, the carbon sink rate index, and the oyster health comprehensive index to quantify the coupling degree of oyster individual health and system service function, and a system service class index is established.

2. The data-driven oyster reef ecological restoration effect evaluation method according to claim 1, wherein, The biological data includes oyster individual density, survival rate, shell size distribution, the physicochemical data includes water temperature, salinity, pH value, dissolved oxygen, nutrient salt concentration, the voiceprint data includes voiceprint data of multi-channel underwater acoustic signal, the image data includes data of reef coverage and crack information based on underwater image recognition, and the microbiome data includes data of microbial diversity and functional gene abundance obtained by high-throughput sequencing.

3. The data-driven oyster reef ecological restoration effect evaluation method of claim 1, wherein, The configuration disturbance event, the disturbance observation of the control area and the repair area are performed by using the disturbance event, the ecological resilience evaluation is performed by using the disturbance observation result and the multi-modal data set, and the ecological resilience index is established, including: Controllable disturbance events are arranged in the repair area and the control area, and the controllable disturbance events include short-term nutrient salt pulse, sediment load disturbance, acoustic interference and physical disturbance, and the disturbance intensity of the controllable disturbance event is set based on the statistical distribution of historical extreme environmental events; After the disturbance is performed, a multi-time sequence observation window is configured to perform disturbance observation of the control area and the repair area, and disturbance observation results are established; The multi-modal data set is used as the base state data, the disturbance observation result is used as the disturbance result, the anti-disturbance index, the recovery index and the over-compensation index are extracted, and the ecological resilience index is established.

4. The data-driven oyster reef ecological restoration effect evaluation method of claim 1, wherein, The attribution analysis of the repair area and the control area is performed based on the structured causal diagram, the average treatment effect of the repair measures on the oyster health comprehensive index and the system service index is constructed, including: Based on the average treatment effect channel, average treatment effect contrast analysis of the repair area and the control area is performed; Sensitivity disturbance identification of the average treatment effect contrast analysis result is performed, and the average treatment effect is generated.

5. The data-driven oyster reef ecological restoration effect evaluation method according to claim 1, characterized in that, After the joint ecological resilience index outputs the oyster reef ecological restoration effect evaluation result, including: A mapping between the repair measures and the average treatment effect is established, and a mapping data set is established; The mapping data set is used as matching data to perform expert database matching anomaly identification, and a matching anomaly signal is established; According to the matching anomaly signal, attention verification of the control area and the repair area is performed, and the attention verification result is updated to the mapping data set to perform subsequent oyster reef ecological restoration management.

6. The data-driven oyster reef ecological restoration effect evaluation method of claim 1, wherein, The disturbance event includes biological invasion event, pollutant instantaneous release time and extreme temperature change event.

7. The data-driven oyster reef ecological restoration effect evaluation method of claim 1, wherein, The oyster health comprehensive index and the system service index are corrected based on the average treatment effect, including: The average treatment effect is associated with the oyster health comprehensive index and the system service index; After the false judgment under the causal driving is eliminated by using the association, index normalization processing is performed, and the oyster reef ecological restoration effect evaluation result is generated by using the index normalization processing result.

8. A data-driven oyster reef ecological restoration effect evaluation system, characterized in that, A data-driven oyster reef ecological restoration effect evaluation method for implementing any one of claims 1-7, the system comprising: A data acquisition module: after the control area and the repair area are configured, biological data, physicochemical data, voiceprint data, image data and microbiome data of oysters in the oyster reef are collected, and a multi-modal data set is established; The feature extraction module: after feature extraction on the multi-modal data set, a feature index set is established, the oyster health comprehensive index is constructed by using the feature index set, and the system service class index is constructed; The resilience evaluation module: configure the disturbance event, use the disturbance event to perform disturbance observation on the control area and the repair area, use the disturbance observation result and the multi-modal data set to perform ecological resilience evaluation, and establish the ecological resilience index; The attribution analysis module: the oyster health comprehensive index and the system service class index are taken as the result variable, the multi-modal data set is taken as the causal input, a structured causal diagram is established, attribution analysis of the repair area and the control area is performed based on the structured causal diagram, the average treatment effect of the repair measures on the oyster health comprehensive index and the system service class index is constructed, and after the oyster health comprehensive index and the system service class index are corrected based on the average treatment effect, the ecological resilience index is output to output the oyster reef ecological restoration effect evaluation result; The oyster health comprehensive index and the system service class index are taken as the result variable, and the multi-modal data set is taken as the causal input to establish the structured causal diagram, specifically: first, biological, physical and chemical, voiceprint, image and microbiome characteristics in the multi-modal data set are used to construct a node set in combination with spatial information of the repair area and the control area; a causal network structure of the oyster reef restoration is formed by identifying the causal edge relationship between variables through a structured learning algorithm.

Images