Marine water environment abnormal state secondary and derivative probability modeling and estimating method

Abstract

The invention discloses a marine water environment abnormal state secondary and derivation probability modeling and estimating method, which belongs to the field of state modeling estimation, and comprises the following steps: acquiring real-time data flow of marine environment parameters, performing segmentation processing by adopting a sliding window mechanism, and reducing data dimension by utilizing principal component analysis. Then, constructing a graph structure model based on a time sequence, and capturing correlation and a space-time dependency relationship among parameters; and performing nonlinear mapping on the graph structure model by adopting a radial basis function core, and capturing complex nonlinear characteristics among the marine environment parameters. And finally, classifying the abnormal states by using a multi-class support vector machine algorithm, and outputting secondary and derivative probability estimation results of the abnormal states in real time. According to the method, abnormal events in the marine environment can be found in time, dynamic modeling support can be provided for marine environment monitoring, and the accuracy and real-time performance of marine environment monitoring are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of state modeling and estimation, and in particular relates to a secondary and derivative probability modeling and estimation method for abnormal states of marine water environment. Background Art

[0002] In the process of secondary and derivative probability modeling and estimation of abnormal state of marine water environment, how to effectively perform sliding modeling is a key technical issue. Due to the dynamic change characteristics of marine environmental parameters, traditional static modeling methods are difficult to accurately capture the evolution trend of abnormal state. Although sliding modeling can update model parameters in real time, it still faces many challenges in practical applications. First, the size of the sliding window directly affects the accuracy and efficiency of modeling. A window that is too small may make the model sensitive to noise, while a window that is too large may introduce too much historical data, reducing the real-time performance of the model. Secondly, sliding modeling needs to consider the correlation and spatiotemporal dependence between marine environmental parameters. Ignoring these relationships may cause the model to misjudge secondary and derivative events of abnormal state. In addition, the high dimensionality and nonlinear characteristics of marine environmental data also bring difficulties to sliding modeling. How to effectively select and extract features in the sliding window and build a robust nonlinear model is an urgent problem to be solved. In summary, in the modeling and estimation of secondary and derivative probability of abnormal state of marine water environment, how to design an adaptive sliding modeling method while considering factors such as window size selection, parameter correlation, high dimensionality and nonlinearity of data is a complex and key technical problem that requires further research and exploration. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a secondary and derivative probability modeling and estimation method for abnormal state of marine water environment, comprising:

[0004] Acquire the real-time data stream of the ocean environment parameters, and use the sliding window mechanism to segment the time series information in the data stream to obtain the data within the window;

[0005] Using principal component analysis to reduce the dimensionality of the high-dimensional data in the window, extracting the main characteristic components while retaining key information, and obtaining reduced-dimensional data;

[0006] Constructing a time series-based graph structure model according to the dimension reduction data, capturing the correlation and spatiotemporal dependency between the marine environmental parameters based on the graph structure model, and determining the interaction intensity between the marine environmental parameters;

[0007] Using radial basis function kernel to perform nonlinear mapping on the graph structure model, constructing a nonlinear mapping relationship, capturing the nonlinear characteristics between the marine environment parameters, and obtaining a nonlinear mapping result;

[0008] According to the nonlinear mapping result, the support vector machine algorithm is used to classify the abnormal state to determine whether there is an abnormal event in the current window; and through the sliding window mechanism, the secondary and derivative probability estimation results of the abnormal state are output in real time.

[0009] Preferably, the real-time data stream of the ocean environment parameters is obtained, and the time series information in the data stream is processed in segments using a sliding window mechanism. The process of obtaining the data in the window includes:

[0010] The data stream is segmented using a sliding window mechanism, and the data stream is divided into multiple time windows according to a preset window size and sliding step size;

[0011] Extracting time series information from the data in each time window, wherein the time series information includes the change trend characteristics and value range characteristics of each marine environmental parameter in the current window;

[0012] Based on the time series information, a time series analysis algorithm is used to model and predict the data in the window to obtain prediction results of the marine environmental parameters;

[0013] Aggregate and merge the prediction results in each time window to obtain a comprehensive prediction result for the entire data stream;

[0014] The prediction results are compared with the preset thresholds. If the prediction results exceed the normal range, the early warning mechanism is triggered and an alarm message is sent to relevant departments to indicate possible abnormal marine environment conditions.

[0015] Continuously monitor the real-time data stream, move the sliding window forward continuously, analyze and predict the data in the new time window, and dynamically adjust the size and sliding step of the sliding window based on historical data and prediction results.

[0016] Preferably, the principal component analysis method is used to reduce the dimension of the high-dimensional data in the window, extract the main characteristic components while retaining the key information, and the process of obtaining the reduced-dimensional data includes:

[0017] Acquire high-dimensional feature information of the data in the window, construct a principal component analysis model, and perform dimensionality reduction processing on the high-dimensional data through the principal component analysis model;

[0018] Through the principal component analysis method, the high-dimensional data in the window is decomposed to extract the main characteristic components of the data, and the number of principal components is determined according to the size of the eigenvalues;

[0019] According to the number of principal components, the original high-dimensional data is subjected to dimensionality reduction mapping, and the data is mapped from the high-dimensional space to the low-dimensional space. During the dimensionality reduction process, the key information and characteristic information of the data are retained by retaining the principal components;

[0020] Reconstruct the data after dimensionality reduction to obtain reconstructed data with the same dimension as the original data, and compare it with the original data to evaluate the degree of information retention of the dimensionality reduction process;

[0021] According to the effect of dimensionality reduction, adjust and optimize the parameters of the principal component analysis model, adjust the number of principal components and optimize the data preprocessing method;

[0022] The optimized principal component analysis model is applied to the adjusted window data to obtain the final dimensionality reduction processing result.

[0023] Preferably, the process of capturing the correlation and spatiotemporal dependency between the ocean environment parameters based on the graph structure model and determining the interaction strength between the ocean environment parameters includes:

[0024] Based on the reduced-dimensional marine environmental parameter data, a time series graph structure model is constructed, in which nodes represent marine environmental parameters and edges represent the correlation and spatiotemporal dependency between parameters.

[0025] The time series graph structure model is trained using a graph neural network to learn and capture the complex interaction relationship between marine environmental parameters;

[0026] During the training process, the attention mechanism is introduced to dynamically adjust the connection weights between nodes at different time steps and spatial positions to highlight the mutual influence between key parameters;

[0027] Inference is performed on the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position;

[0028] According to the interaction strength, a causal relationship diagram between the marine environmental parameters is constructed to obtain the causal dependency and action path between the parameters;

[0029] For the key nodes and paths in the causal graph, a graph attention network is used to further mine the high-order interaction patterns and long-range dependencies between parameters;

[0030] The prediction results of graph neural network and graph attention network are integrated to judge the interaction strength between different marine environmental parameters.

[0031] Preferably, the process of inferring the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position includes:

[0032] According to the spatiotemporal distribution of marine environmental parameters, the input data structure of the graph neural network model is constructed, where the node represents each spatiotemporal position and the edge represents the connection relationship between adjacent spatiotemporal positions;

[0033] The input data is fed into a pre-trained graph neural network model, the hidden state vector of each node is calculated through forward propagation, and the information of adjacent nodes is aggregated through an attention mechanism;

[0034] In the output layer of the graph neural network, a fully connected layer is used to map the hidden state vector of each node to the predicted value of the ocean environment parameter at the corresponding spatiotemporal location;

[0035] Calculate the difference between the predicted value of each spatiotemporal position and the predicted value of the adjacent spatiotemporal position as the interaction strength between the spatiotemporal position and the adjacent position;

[0036] According to the magnitude of the interaction intensity, the degree of mutual influence between different marine environmental parameters is judged, and the greater the intensity, the stronger the correlation between the two parameters;

[0037] The interaction intensity matrix is ​​normalized to obtain the relative interaction intensity distribution under different combinations of spatiotemporal positions and environmental parameters;

[0038] Visualize the normalized interaction intensity matrix to generate a heat map or network diagram.

[0039] Preferably, the radial basis function kernel is used to perform nonlinear mapping on the graph structure model, a nonlinear mapping relationship is constructed, and the nonlinear characteristics between the marine environment parameters are captured. The process of obtaining the nonlinear mapping result includes:

[0040] A graph structure model is constructed based on the marine environment parameter data, where nodes represent parameters and edges represent the relationship between parameters.

[0041] The radial basis function kernel is used to perform nonlinear mapping on the graph structure model to capture the nonlinear characteristic relationship between the marine environmental parameters. Through nonlinear mapping, the original graph structure model is mapped to a high-dimensional feature space to obtain a nonlinear mapping result.

[0042] According to the nonlinear mapping results, a nonlinear relationship model between marine environmental parameters is constructed;

[0043] Using a support vector machine algorithm to train the nonlinear relationship model to obtain a trained nonlinear relationship model;

[0044] The trained nonlinear relationship model is used to predict new marine environmental parameter data and obtain prediction results;

[0045] The prediction results are compared with the actual observed data, and after evaluating the prediction performance of the nonlinear relationship model, the model is continuously iterated and optimized.

[0046] Preferably, the trained nonlinear relationship model is used to predict new marine environmental parameter data, and the process of obtaining the prediction result includes:

[0047] Based on historical parameter data related to the marine environment, a nonlinear relationship prediction model is constructed using a machine learning algorithm;

[0048] During the model training process, the model hyperparameters are optimized through the cross-validation method, and the trained nonlinear relationship model is saved;

[0049] Obtain new marine environmental parameter data, perform data cleaning and normalization preprocessing operations on the data; input the preprocessed new data into the trained nonlinear relationship model, and the model automatically performs predictive analysis and calculation;

[0050] Obtain the prediction result data from the model output and perform post-processing of denormalization and data format conversion on the prediction results.

[0051] Preferably, according to the nonlinear mapping result, the support vector machine algorithm is used to classify the abnormal state, and the process of judging whether there is an abnormal event in the current window includes:

[0052] Get the data in the current time window, pre-process the data, remove noise and irrelevant information, and obtain a pure data set;

[0053] According to a preset nonlinear mapping function, feature extraction is performed on the clean data set to obtain a feature vector capable of characterizing an abnormal state;

[0054] The feature vector is input into a pre-trained support vector machine model for classification prediction to obtain a judgment result of whether there is an abnormality in the current time window;

[0055] If the judgment result shows that there is an abnormality, an abnormal alarm is triggered and the relevant information of the abnormal event is sent to the administrator for further processing;

[0056] If the judgment result shows that there is no abnormality, continue to obtain data of the next time window and repeat the above steps to achieve continuous monitoring of the abnormal state;

[0057] Based on the administrator's feedback, the support vector machine model is updated and optimized in real time, and the anomaly detection result data is stored in the database to form a historical record.

[0058] Preferably, the process of outputting secondary and derivative probability estimation results of abnormal states in real time through the sliding window mechanism includes:

[0059] Obtain real-time monitoring data of the marine environment as the input data source of the sliding window mechanism;

[0060] For the acquired monitoring data, a sliding window mechanism is used to divide the data into several time windows;

[0061] For the monitoring data in each time window, anomaly detection algorithms are used to determine whether there is an abnormal state;

[0062] If an abnormal state is detected in the current time window, the probability of secondary abnormalities and derivative abnormalities occurring in the abnormal state is estimated according to a pre-established probability model, and the probability is used as the abnormal state estimation result of the current time window;

[0063] As the sliding window continues to move, the estimated results of the secondary probability and the derived probability of the abnormal state are updated in real time, and the updated abnormal state probability estimation results are output in real time.

[0064] Compared with the prior art, the present invention has the following advantages and technical effects:

[0065] The present invention obtains the real-time data stream of marine environmental parameters, adopts the sliding window mechanism for segmented processing, and uses principal component analysis to reduce the data dimension. Subsequently, a graph structure model based on time series is constructed to capture the correlation and spatiotemporal dependency between parameters. The present invention innovatively uses radial basis function to perform nonlinear mapping on the graph structure model, effectively capturing the complex nonlinear characteristics between marine environmental parameters. Finally, a multi-class support vector machine algorithm is used to classify abnormal states, and the secondary and derivative probability estimation results of abnormal states are output in real time. This method can not only detect abnormal events in the marine environment in a timely manner, but also provide dynamic modeling support for marine environmental monitoring, significantly improving the accuracy and real-time performance of marine environmental monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0067] Figure 1 It is a schematic diagram of the overall method flow of an embodiment of the present invention;

[0068] Figure 2 A simplified flowchart of an embodiment of the present invention;

[0069] Figure 3 The figure is another flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0071] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0072] like Figure 1-3 As shown, this embodiment provides a method for modeling and estimating secondary and derivative probabilities of abnormal conditions in marine water environment, including:

[0073] Obtain real-time data streams of ocean environmental parameters, use a sliding window mechanism to segment the time series information in the data stream, and obtain data within the window;

[0074] The principal component analysis method is used to reduce the dimension of the high-dimensional data in the window, extract the main characteristic components while retaining the key information, and obtain the reduced-dimensional data;

[0075] A time series-based graph structure model is constructed based on the dimension reduction data. The correlation and spatiotemporal dependency between the marine environmental parameters are captured based on the graph structure model, and the interaction intensity between the marine environmental parameters is determined.

[0076] The radial basis function kernel graph structure model is used for nonlinear mapping, a nonlinear mapping relationship is constructed, the nonlinear characteristics between the marine environmental parameters are captured, and the nonlinear mapping results are obtained;

[0077] According to the nonlinear mapping results, the support vector machine algorithm is used to classify the abnormal state and determine whether there is an abnormal event in the current window; and through the sliding window mechanism, the secondary and derivative probability estimation results of the abnormal state are output in real time.

[0078] Furthermore, the real-time data stream of the marine environmental parameters is obtained, and the time series information in the data stream is processed in segments using a sliding window mechanism. The process of obtaining the data within the window includes:

[0079] The data stream is segmented using a sliding window mechanism, which divides the data stream into multiple time windows according to the preset window size and sliding step size.

[0080] Extract time series information from the data in each time window, which includes the change trend characteristics and value range characteristics of each marine environmental parameter in the current window;

[0081] Based on the time series information, the time series analysis algorithm is used to model and predict the data in the window to obtain the prediction results of the marine environmental parameters;

[0082] Aggregate and merge the prediction results in each time window to obtain a comprehensive prediction result for the entire data stream;

[0083] The prediction results are compared with the preset thresholds. If the prediction results exceed the normal range, the early warning mechanism is triggered and an alarm message is sent to relevant departments to indicate possible abnormal marine environment conditions.

[0084] Continuously monitor the real-time data stream, move the sliding window forward continuously, analyze and predict the data in the new time window, and dynamically adjust the size and sliding step of the sliding window based on historical data and prediction results.

[0085] Specifically, this embodiment uses a sliding window mechanism to process data streams for real-time monitoring of marine environmental parameters. This method can effectively capture the dynamic changes of the marine environment. For example, for parameters such as seawater temperature, salinity, and dissolved oxygen, the window size can be set to 24 hours and the sliding step size can be set to 1 hour. In this way, the data analyzed each time contains information from the most recent day and is updated every hour, which not only ensures the timeliness of the data, but also reflects the changing trend over a longer period of time. In each time window, the system extracts time series information, including the changing trend and numerical range of the parameters. For example, the surface water temperature in a certain sea area shows obvious day and night changes within a 24-hour window, with the highest temperature during the day reaching 28°C and the lowest temperature at night being 22°C, showing a periodic fluctuation as a whole. This information is crucial for understanding the thermodynamic characteristics of local sea areas.

[0086] This embodiment is based on the extracted time series information. When using the time series analysis algorithm for modeling and prediction, algorithms such as autoregressive moving average model (ARMA) or long short-term memory network (LSTM) can be used. ARMA model is suitable for relatively stable marine environment, such as temperature changes in deep sea areas. LSTM network is more suitable for processing complex nonlinear relationships, such as changes in water quality parameters in coastal areas affected by multiple factors such as tides and climate. These algorithms can predict changes in marine environmental parameters in the next few hours or even days. The aggregation and fusion of prediction results is a key step. For example, when predicting sea level height, the results of multiple time windows are comprehensively considered. If the short-term forecast shows that the sea level rises rapidly, and the long-term trend is also rising, then a higher warning level is given. This multi-scale analysis method can effectively reduce false alarms and improve the accuracy of early warnings.

[0087] The triggering of the early warning mechanism is based on preset thresholds. For example, when the predicted seawater pH value is lower than 7.5 or higher than 8.5, the system automatically sends an alarm to the marine environment management department. This helps to timely detect and respond to ocean acidification or alkalization problems and protect the health of the marine ecosystem. At the same time, the sliding window parameters can be dynamically adjusted based on historical data and forecast results. In calm weather, the window size is increased to capture longer-term changes; and before a typhoon arrives, the window size is reduced and the sliding step length is reduced to more closely monitor rapidly changing sea conditions. This adaptive mechanism greatly improves the flexibility and applicability of the system. Through this comprehensive and dynamic analysis method, real-time monitoring of marine environmental parameters can provide important decision-making support for marine resource management, marine operation safety and marine ecological protection. It can not only detect abnormal situations in a timely manner, but also predict potential environmental changes, providing sufficient time and basis for relevant departments to take preventive measures.

[0088] Furthermore, the principal component analysis method is used to reduce the dimension of the high-dimensional data in the window, extract the main characteristic components while retaining the key information, and the process of obtaining the reduced-dimensional data includes:

[0089] Obtain high-dimensional feature information of the data in the window, build a principal component analysis model, and perform dimensionality reduction processing on the high-dimensional data through the principal component analysis model;

[0090] Through the principal component analysis method, the high-dimensional data in the window is decomposed to extract the main characteristic components of the data, and the number of principal components is determined according to the size of the eigenvalues;

[0091] According to the number of principal components, the original high-dimensional data is mapped from high-dimensional space to low-dimensional space. In the process of dimensionality reduction, the key information and characteristic information of the data are retained by retaining the principal components.

[0092] Reconstruct the data after dimensionality reduction to obtain reconstructed data with the same dimension as the original data, and compare it with the original data to evaluate the degree of information retention of the dimensionality reduction process;

[0093] According to the effect of dimensionality reduction, adjust and optimize the parameters of the principal component analysis model, adjust the number of principal components and optimize the data preprocessing method;

[0094] The optimized principal component analysis model is applied to the adjusted window data to obtain the final dimensionality reduction processing result.

[0095] Specifically, this embodiment can effectively extract the main features of high-dimensional data by reducing the dimension through principal component analysis. In marine environmental monitoring, you may face high-dimensional data composed of multiple parameters such as temperature, salinity, dissolved oxygen, etc. Through principal component analysis, these parameters can be reduced to a few principal components, which not only retains key information but also simplifies the data structure. Taking marine water quality monitoring as an example, assume that there are 10 parameters such as temperature, salinity, dissolved oxygen, pH value, turbidity, etc. Through principal component analysis, it may be found that the first three principal components can explain 85% of the total variance of the data. This means that these three principal components can replace the original 10 parameters, greatly reducing the data dimension. In actual operation, the original data needs to be standardized first to eliminate the dimensional differences between different parameters. Then calculate the covariance matrix and solve its eigenvalues ​​and eigenvectors. The size of the eigenvalue reflects the importance of the corresponding principal component, and the number of principal components to be retained can be determined based on the cumulative contribution rate. For example, if the cumulative contribution rate of the first four principal components reaches 90%, you can choose to retain these four principal components. After dimensionality reduction, it is necessary to evaluate the degree of information retention. One method in this embodiment is to reconstruct the reduced-dimensional data back to the original dimension and calculate the mean square error with the original data. If the error is small, it means that the dimensionality reduction effect is good. Another method is to project the data into the space formed by the first two or three principal components through visualization and observe the distribution of the data. The optimization of the principal component analysis model involves multiple aspects. For example, different data preprocessing methods, such as minimum-maximum normalization or Z-score standardization, can be tried to see which method can obtain better dimensionality reduction effect. In addition, the selection criteria of the principal components can also be adjusted, such as trying different cumulative contribution rate thresholds, or using methods such as gravel plots to determine the optimal number of principal components. In marine environmental monitoring, principal component analysis can not only be used for data dimensionality reduction, but also help discover potential relationships between parameters. For example, it may be found that the first principal component is highly correlated with water temperature and dissolved oxygen, which suggests that there may be some physical or biological connection between the two parameters. This discovery can provide clues for further marine ecological research. Data reduced by principal component analysis is easier to visualize and interpret. For example, data from different sea areas or different periods can be projected onto a two-dimensional plane to intuitively observe their distribution and clustering. This visualization method can help quickly identify anomalies or special patterns, providing strong support for marine environmental monitoring and early warning. In general, principal component analysis provides a powerful and flexible tool for the processing of marine environmental data. It can not only effectively reduce the data dimension and simplify the subsequent analysis process, but also help extract key information from complex multidimensional data and discover potential data structures and laws. This is of great significance for improving the efficiency and accuracy of marine environmental monitoring.

[0096] Furthermore, based on the graph structure model, the correlation and spatiotemporal dependency between the marine environmental parameters are captured, and the process of judging the interaction intensity between the marine environmental parameters includes:

[0097] Based on the reduced-dimensional marine environmental parameter data, a time series graph structure model is constructed, in which nodes represent marine environmental parameters and edges represent the correlation and spatiotemporal dependency between parameters.

[0098] A graph neural network is used to train the time series graph structure model to learn and capture the complex interactions between marine environmental parameters;

[0099] During the training process, the attention mechanism is introduced to dynamically adjust the connection weights between nodes at different time steps and spatial positions to highlight the mutual influence between key parameters;

[0100] Inference is performed on the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position;

[0101] According to the interaction intensity, a causal relationship diagram between marine environmental parameters is constructed to obtain the causal dependency and action path between the parameters;

[0102] For the key nodes and paths in the causal graph, a graph attention network is used to further mine the high-order interaction patterns and long-range dependencies between parameters;

[0103] The prediction results of graph neural network and graph attention network are integrated to judge the interaction strength between different marine environmental parameters.

[0104] Specifically, a time series graph structure model is constructed, in which nodes represent different marine environmental parameters, such as water temperature, salinity, dissolved oxygen, etc., and edges represent the correlation and spatiotemporal dependency between these parameters. For example, there may be a negative correlation between water temperature and salinity, because high temperature usually leads to water evaporation, thereby increasing salinity.

[0105] The application of graph neural networks (GNNs) enables the capture of these complex interactions. In this embodiment, by learning from historical data, GNN can identify how changes in water temperature affect dissolved oxygen content, or the relationship between ocean current speed and plankton distribution. The introduction of the attention mechanism further enhances the performance of the model, enabling it to dynamically adjust the weights between different parameters. For example, near the equator, the impact of water temperature on other parameters may be more significant, so the model will give a higher weight to the water temperature node. In the reasoning stage, the specific interaction strength can be obtained. Assume that at a certain time step, the model shows that the intensity of the effect of water temperature on dissolved oxygen is 0.8, while the intensity of the effect on salinity is 0.5, which provides a quantitative basis for understanding the relative importance of parameters. Based on these results, a causal relationship diagram can be constructed to clearly show the causal chain between parameters. For example, it may be found that increased water temperature leads to a decrease in dissolved oxygen, which in turn affects the distribution of fish, forming a complete causal chain.

[0106] The introduction of the Graph Attention Network (GAT) enables the mining of deeper interaction patterns. It may reveal nonlinear relationships between certain parameters, such as the complex relationship between water temperature and plankton population, which may present different patterns within a specific temperature range. GAT can also help discover long-range dependencies, such as finding that changes in water temperature a few months ago have a significant impact on current fish distribution.

[0107] By combining the results of GNN and GAT, the interactions between marine environmental parameters can be comprehensively judged. This method can not only reveal direct cause-effect relationships, but also discover indirect and complex interactions. For example, it may be found that ocean acidification not only directly affects the growth of shellfish, but also indirectly affects the entire food chain by changing the structure of plankton communities. This comprehensive analysis helps to understand the internal mechanisms of marine ecosystems and provide a scientific basis for marine resource management and environmental protection.

[0108] Furthermore, the process of inferring the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position includes:

[0109] According to the spatiotemporal distribution of marine environmental parameters, the input data structure of the graph neural network model is constructed, where the node represents each spatiotemporal position and the edge represents the connection relationship between adjacent spatiotemporal positions;

[0110] The input data is fed into the pre-trained graph neural network model, the hidden state vector of each node is calculated through forward propagation, and the information of adjacent nodes is aggregated through the attention mechanism;

[0111] In the output layer of the graph neural network, a fully connected layer is used to map the hidden state vector of each node to the predicted value of the ocean environment parameter at the corresponding spatiotemporal location;

[0112] Calculate the difference between the predicted value of each spatiotemporal position and the predicted value of the adjacent spatiotemporal position as the interaction strength between the spatiotemporal position and the adjacent position;

[0113] The degree of mutual influence between different marine environmental parameters is determined according to the magnitude of the interaction intensity. The greater the intensity, the stronger the correlation between the two parameters.

[0114] The interaction intensity matrix is ​​normalized to obtain the relative interaction intensity distribution under different combinations of spatiotemporal positions and environmental parameters;

[0115] Visualize the normalized interaction intensity matrix to generate a heat map or network diagram.

[0116] Specifically, the input data structure of the graph neural network model is constructed. Taking seawater temperature, salinity and dissolved oxygen as examples, each observation site can be regarded as a node in the graph, and the connection relationship between adjacent sites is represented as an edge. This structure can effectively capture the spatial distribution characteristics of parameters. In model training, forward propagation calculates the hidden state vector of each node. For example, for a certain observation site, its hidden state may contain comprehensive information about the temperature, salinity and dissolved oxygen at that location. Through the attention mechanism, the model can automatically learn the importance weights between different parameters, so as to more accurately aggregate the information of adjacent nodes. The fully connected layer maps the hidden state vector to a specific predicted value of the marine environment parameter. Assuming that the hidden state vector of a certain site is [0.8, 0.5, 0.3], after being mapped by the fully connected layer, the predicted value of the temperature at that location may be 25°C, the salinity is 35‰, and the dissolved oxygen is 6mg / L.

[0117] Calculating the differences between predictions at adjacent spatiotemporal locations reveals the strength of interaction between parameters. If the predicted values ​​for temperature at two adjacent sites are 25°C and 26°C, respectively, and the predicted values ​​for salinity are 35‰ and 35.5‰, respectively, this may indicate that the spatial variation of temperature is relatively small, while the spatial variation of salinity is large, reflecting the spatial correlation characteristics of different parameters.

[0118] Normalization helps to compare the relative interaction strengths of different parameter combinations. For example, normalizing the interaction strengths of temperature-salinity, temperature-dissolved oxygen, and salinity-dissolved oxygen to the [0,1] interval may yield results of 0.7, 0.5, and 0.8, indicating that salinity-dissolved oxygen has the strongest interaction, followed by temperature-salinity, and temperature-dissolved oxygen is the weakest.

[0119] Visualization is an effective means for this embodiment to intuitively display the dynamic interactions of marine environmental parameters. Heat maps can use different shades of colors to represent the intensity of interaction, for example, dark red represents strong interactions and light yellow represents weak interactions. The network diagram can use the size of the node to represent the importance of the parameter, and the thickness of the edge represents the intensity of the interaction, thereby clearly showing the complex relationship network between the parameters. This method based on graph neural networks can effectively capture the spatiotemporal dependencies of marine environmental parameters, and can better reflect the nonlinear interactions between parameters than traditional methods. By analyzing the interaction intensity of the model output, researchers can deeply understand the inherent mechanisms of marine ecosystems and provide a scientific basis for marine environmental protection and resource management. For example, the strong correlation between temperature and dissolved oxygen found may reveal the potential impact of global warming on the habitat of marine organisms, providing an important reference for the formulation of relevant policies.

[0120] Furthermore, the radial basis function kernel graph structure model is used for nonlinear mapping, a nonlinear mapping relationship is constructed, and the nonlinear characteristics between the marine environmental parameters are captured. The process of obtaining the nonlinear mapping result includes:

[0121] A graph structure model is constructed based on the marine environment parameter data, where nodes represent parameters and edges represent the relationship between parameters.

[0122] The radial basis function kernel is used to perform nonlinear mapping on the graph structure model to capture the nonlinear characteristic relationship between the marine environmental parameters. Through nonlinear mapping, the original graph structure model is mapped to a high-dimensional feature space to obtain a nonlinear mapping result.

[0123] According to the nonlinear mapping results, a nonlinear relationship model between marine environmental parameters is constructed;

[0124] The nonlinear relationship model is trained by using a support vector machine algorithm to obtain a trained nonlinear relationship model;

[0125] The trained nonlinear relationship model is used to predict new marine environmental parameter data and obtain prediction results;

[0126] The prediction results are compared with the actual observed data, and after evaluating the prediction performance of the nonlinear relationship model, the model is continuously iterated and optimized.

[0127] Specifically, collecting marine environmental parameter data to build a graph structure model includes collecting observations of seawater temperature, salinity, dissolved oxygen and other parameters at different time and space points. These parameters are used as nodes of the graph, and the correlations between the parameters are used as edges to form an initial graph structure model.

[0128] The application of radial basis function kernel can effectively capture the nonlinear relationship between parameters. For example, there is a complex nonlinear correlation between seawater temperature and dissolved oxygen. Rising temperature will reduce the dissolved oxygen content, but this relationship is not a simple linear one. Through the radial basis function kernel, this complex relationship can be mapped to a high-dimensional space to more accurately describe the interaction between parameters. After nonlinear mapping, the original simple graph structure is converted into a more complex high-dimensional feature space. In this space, the relationship between marine environmental parameters becomes clearer. For example, the surface water temperature and deep nutrient concentration, which seemed to be unrelated, may show obvious correlation in high-dimensional space, reflecting the influence of the vertical mixing process of the water body. The complex nonlinear relationship model constructed based on the nonlinear mapping results can more comprehensively describe the marine environmental system. This model may reveal some unexpected associations, such as the nonlinear relationship between phytoplankton biomass and ocean current velocity, reflecting the response mechanism of the ecosystem to the physical environment.

[0129] The application of the support vector machine algorithm enables the nonlinear relationship model to have predictive capabilities. Through training, the model learns the inherent laws between marine environmental parameters. For example, it may have mastered how to predict changes in chlorophyll concentration based on water temperature, salinity and nutrient concentration, which is of great significance for studying marine primary productivity. When using the trained model for prediction, new marine environmental parameter data can be input, such as the weather forecast data for a certain sea area in the next week, and the model can give the predicted results of the water quality parameters in the sea area. This has important application value for marine environmental monitoring and early warning.

[0130] Comparison of prediction results with actual observation data is a key step in evaluating model performance. For example, the probability of red tide occurrence predicted by the model can be compared with the actual observation results to calculate the prediction accuracy. If it is found that the model has large prediction deviations in certain situations, such as when a typhoon passes, it is necessary to review the model structure, and more parameters related to extreme weather may need to be introduced to optimize the model. Through this series of steps, not only is a model that can describe the complexity of the marine environment constructed, but it is also given the ability to predict future changes. The advantage of this method is that it can capture complex relationships that are difficult to describe with traditional linear models, providing a powerful tool for marine science research and environmental management.

[0131] Furthermore, the trained nonlinear relationship model is used to predict new marine environmental parameter data. The process of obtaining the prediction results includes:

[0132] Based on historical parameter data related to the marine environment, a nonlinear relationship prediction model is constructed using a machine learning algorithm;

[0133] During the model training process, the model hyperparameters are optimized through the cross-validation method, and the trained nonlinear relationship model is saved;

[0134] Obtain new marine environmental parameter data, perform data cleaning and normalization preprocessing operations on the data; input the preprocessed new data into the trained nonlinear relationship model, and the model automatically performs predictive analysis and calculation;

[0135] Obtain the prediction result data from the model output and perform post-processing of denormalization and data format conversion on the prediction results.

[0136] Specifically, the construction of the nonlinear relationship prediction model of the marine environmental parameter data in this embodiment is a complex task. First, it is necessary to collect historical data, such as seawater temperature, salinity, dissolved oxygen, etc. These data may come from different ocean observation stations or satellite remote sensing. For example, in a certain area, there may be daily seawater temperature, salinity and dissolved oxygen data for the past 10 years.

[0137] This embodiment uses a support vector machine (SVM) to process nonlinear relationships. Specifically, in marine environmental prediction, SVM is used to capture complex relationships between parameters. For example, a radial basis function (RBF) kernel can be used to establish a nonlinear relationship model between seawater temperature and dissolved oxygen. Neural networks, especially deep learning models, are also powerful tools for processing marine environmental data in this embodiment. For example, this embodiment effectively captures the time series characteristics of marine parameters through a long short-term memory network (LSTM), and uses LSTM to predict changes in seawater temperature in the next week.

[0138] In the model training process, cross validation is an important method. For example, this embodiment uses 5-fold cross validation to optimize the kernel function parameters of SVM or the number of hidden layers of LSTM. This helps to improve the generalization ability of the model and avoid overfitting.

[0139] After training is complete, new data needs to be preprocessed. This includes data cleaning, such as removing outliers. For example, if the seawater temperature suddenly rises by 10 degrees on a certain day, this may be a measurement error and needs to be eliminated. Data normalization is also important, which can unify parameters of different scales to the same range, such as normalizing both seawater temperature and salinity to between 0 and 1.

[0140] After the model prediction, post-processing is required. If normalization was performed before, it is now necessary to denormalize. For example, if the normalized seawater temperature predicted by the model is 0.6, it needs to be converted back to the actual temperature value, such as 24°C. Finally, the prediction results can be applied to multiple fields. In terms of marine disaster warning, if the model predicts that the seawater temperature will rise sharply in the next three days, it may indicate the formation of a tropical cyclone, and relevant departments can take precautions in advance. In terms of marine resource assessment, if the model predicts that the dissolved oxygen content in a certain sea area continues to decline, it may affect fish resources, and the fishery department can adjust the fishing plan accordingly. In this way, not only can the changes in a single marine parameter be predicted, but also the mutual influence between multiple parameters can be analyzed, so as to more comprehensively understand and predict changes in the marine environment. This is of great significance to fields such as marine resource management and climate change research.

[0141] Furthermore, according to the nonlinear mapping result, the support vector machine algorithm is used to classify the abnormal state, and the process of judging whether there is an abnormal event in the current window includes:

[0142] Get the data in the current time window, pre-process the data, remove noise and irrelevant information, and obtain a pure data set;

[0143] According to the preset nonlinear mapping function, the clean data set is subjected to feature extraction to obtain a feature vector that can characterize the abnormal state;

[0144] The feature vector is input into the pre-trained support vector machine model for classification prediction to obtain the judgment result of whether there is an abnormality in the current time window;

[0145] If the judgment result shows that there is an abnormality, an abnormal alarm is triggered and the relevant information of the abnormal event is sent to the administrator for further processing;

[0146] If the judgment result shows that there is no abnormality, continue to obtain data of the next time window and repeat the above steps to achieve continuous monitoring of the abnormal state;

[0147] Based on the administrator's feedback, the support vector machine model is updated and optimized in real time, and the anomaly detection result data is stored in the database to form a historical record.

[0148] Specifically, obtaining data within the current time window is the first step in anomaly detection. For example, in marine environmental monitoring, parameters such as water temperature, salinity, and dissolved oxygen may be collected. These raw data often contain noise and irrelevant information and need to be preprocessed. Preprocessing may include removing outliers, filling missing values, etc. Taking water temperature data as an example, abnormally high or low temperature readings may occur due to sensor failure, which need to be identified and eliminated. The choice of nonlinear mapping function is crucial for feature extraction.

[0149] In the present embodiment, wavelet transform is used as a nonlinear mapping function in marine environment monitoring. Wavelet transform can effectively capture the time-frequency characteristics of the signal and is suitable for processing non-stationary marine environment data. Through wavelet transform, feature vectors that can characterize abnormal states, such as abnormal energy distribution in certain frequency bands, can be extracted. The multi-class support vector machine (SVM) model is a powerful classifier suitable for processing high-dimensional feature spaces. In the present embodiment, different types of abnormal states (such as red tide, oil spill, water pollution, etc.) can be used as different categories in marine environment anomaly detection. The SVM model distinguishes these categories by finding the optimal hyperplane to achieve accurate classification of abnormal states. When an abnormality is detected, the system triggers an alarm and notifies the administrator. For example, if the possibility of a red tide is detected, the system immediately sends an alarm to the marine environment management department, including information such as the location, time, and possible impact range of the abnormality. This enables the management department to take timely measures, such as dispatching monitoring vessels for field surveys or issuing early warning information.

[0150] Real-time updating and optimization of the model is key to keeping the system running efficiently. Feedback from administrators, such as field survey results, can be used to adjust model parameters. For example, if the system falsely reports a red tide event, this erroneous sample can be added to the training set and retrained to improve the model's recognition accuracy for similar situations.

[0151] Data storage and historical record building are essential for long-term analysis and model improvement. By analyzing historical data, seasonal patterns or long-term trends of marine environmental anomalies can be discovered. For example, it may be found that certain sea areas are more prone to red tides in certain seasons. This information can be used to optimize monitoring strategies and increase monitoring frequency during high-risk periods. The operation of the entire system forms a closed loop: from data collection, preprocessing, feature extraction, to anomaly detection, alarm triggering, administrator feedback, to model updates and historical data analysis. This closed-loop design ensures that the system can continuously learn and improve and adapt to the complex and changing marine environment. Through continuous optimization, the system can identify potential marine environmental problems earlier and more accurately, providing strong support for marine ecological protection and resource management.

[0152] Furthermore, the process of outputting the secondary and derivative probability estimation results of the abnormal state in real time through the sliding window mechanism includes:

[0153] Obtain real-time monitoring data of the marine environment as the input data source of the sliding window mechanism;

[0154] For the acquired monitoring data, a sliding window mechanism is used to divide the data into several time windows;

[0155] For the monitoring data in each time window, anomaly detection algorithms are used to determine whether there is an abnormal state;

[0156] If an abnormal state is detected in the current time window, the probability of secondary abnormalities and derivative abnormalities occurring in the abnormal state is estimated according to the pre-established probability model, and the probability is used as the abnormal state estimation result of the current time window;

[0157] As the sliding window continues to move, the estimated results of the secondary probability and the derived probability of the abnormal state are updated in real time, and the updated abnormal state probability estimation results are output in real time.

[0158] Specifically, the real-time monitoring of the marine environment in this embodiment obtains various types of data, such as water temperature, salinity, dissolved oxygen, etc., through the deployed sensor network. These data are collected at a fixed frequency to form a continuous time series. The sliding window mechanism, as an effective method for processing time series data, divides the data stream into overlapping time periods. For example, a window of 30 minutes can be set and slid once every 5 minutes, which not only ensures the continuity of the data, but also captures environmental changes in a timely manner. In each time window, the anomaly detection algorithm plays a key role. Common methods include statistical analysis, machine learning, etc. Taking water temperature anomaly detection as an example, historical data can be used to establish a normal temperature range model. When the observed value deviates significantly from this range, it is judged to be abnormal. For example, the average water temperature in a sea area in summer is 25°C, and the standard deviation is 1.5°C. If the water temperature is measured at a certain moment to be 30°C, which is obviously beyond the normal range, the system will mark it as an abnormal state. Once an anomaly is detected, the system will evaluate the possibility of causing secondary anomalies and derivative anomalies.

[0159] Secondary anomalies refer to subsequent anomalies that are directly caused by the initial anomaly, while derivative anomalies are chain reactions that are indirectly triggered. Taking water temperature anomalies as an example, it may directly lead to the death of organisms in local sea areas (secondary anomalies), and then cause ecosystem imbalance (derivative anomalies). The probability model is built based on historical data and expert knowledge, taking into account the interaction between various factors. For example, the model may give a probability of 0.7 for the death of organisms due to water temperature anomalies and a probability of 0.4 for ecosystem imbalance. As the sliding window moves continuously, the system continuously updates these probability estimates. This dynamic update mechanism can reflect the real-time changes in the marine environment and provide timely and accurate information support for decision makers. For example, if water temperature anomalies are detected in multiple consecutive time windows and the degree of anomalies gradually increases, the system will increase the probability estimates of secondary and derivative anomalies accordingly, which may rise from the initial 0.7 and 0.4 to 0.9 and 0.6. This method based on sliding windows and probability models has many advantages. First, it can capture the dynamic changes of the marine environment in a timely manner and will not miss important abnormal events. Second, by estimating the probabilities of secondary and derivative anomalies, the system provides a more comprehensive risk assessment and helps prevent potential chain reactions. Finally, the real-time updated probability estimates provide valuable data support for dynamic modeling of the marine environment, helping researchers to gain a deeper understanding of the complexity and fragility of marine ecosystems.

[0160] In general, this embodiment organically combines real-time data collection, anomaly detection and risk assessment, providing strong technical support for marine environmental monitoring and protection. It can not only detect problems in a timely manner, but also predict potential risks, providing a scientific basis for the sustainable use of marine resources and the long-term protection of the ecological environment.

[0161] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for modeling and estimating secondary and derivative probabilities of abnormal marine water environment conditions, characterized in that: include: Acquire the real-time data stream of the ocean environment parameters, and use the sliding window mechanism to segment the time series information in the data stream to obtain the data within the window; Using principal component analysis to reduce the dimensionality of the high-dimensional data in the window, extracting the main characteristic components while retaining key information, and obtaining reduced-dimensional data; Constructing a time series-based graph structure model according to the dimension reduction data, capturing the correlation and spatiotemporal dependency between the marine environmental parameters based on the graph structure model, and determining the interaction intensity between the marine environmental parameters; Using radial basis function kernel to perform nonlinear mapping on the graph structure model, constructing a nonlinear mapping relationship, capturing the nonlinear characteristics between the marine environment parameters, and obtaining a nonlinear mapping result; According to the nonlinear mapping result, a support vector machine algorithm is used to classify the abnormal state and determine whether there is an abnormal event in the current window; And through the sliding window mechanism, the secondary and derivative probability estimation results of the abnormal state are output in real time.

2. The method according to claim 1, characterized in that The real-time data stream of the ocean environment parameters is obtained, and the time series information in the data stream is processed in segments using a sliding window mechanism. The process of obtaining the data in the window includes: The data stream is segmented using a sliding window mechanism, and the data stream is divided into multiple time windows according to a preset window size and sliding step size; Extracting time series information from the data in each time window, wherein the time series information includes the change trend characteristics and value range characteristics of each marine environmental parameter in the current window; Based on the time series information, a time series analysis algorithm is used to model and predict the data in the window to obtain prediction results of the marine environmental parameters; Aggregate and merge the prediction results in each time window to obtain a comprehensive prediction result for the entire data stream; The prediction results are compared with the preset thresholds. If the prediction results exceed the normal range, the early warning mechanism is triggered and an alarm message is sent to relevant departments to indicate possible abnormal marine environment conditions. Continuously monitor the real-time data stream, move the sliding window forward continuously, analyze and predict the data in the new time window, and dynamically adjust the size and sliding step of the sliding window based on historical data and prediction results.

3. The method according to claim 1, characterized in that The principal component analysis method is used to reduce the dimension of the high-dimensional data in the window, extract the main characteristic components while retaining the key information, and the process of obtaining the reduced-dimensional data includes: Acquire high-dimensional feature information of the data in the window, construct a principal component analysis model, and perform dimensionality reduction processing on the high-dimensional data through the principal component analysis model; Through the principal component analysis method, the high-dimensional data in the window is decomposed to extract the main characteristic components of the data, and the number of principal components is determined according to the size of the eigenvalues; According to the number of principal components, the original high-dimensional data is subjected to dimensionality reduction mapping, and the data is mapped from the high-dimensional space to the low-dimensional space. During the dimensionality reduction process, the key information and characteristic information of the data are retained by retaining the principal components; Reconstruct the data after dimensionality reduction to obtain reconstructed data with the same dimension as the original data, and compare it with the original data to evaluate the degree of information retention of the dimensionality reduction process; According to the effect of dimensionality reduction, adjust and optimize the parameters of the principal component analysis model, adjust the number of principal components and optimize the data preprocessing method; The optimized principal component analysis model is applied to the adjusted window data to obtain the final dimensionality reduction processing result.

4. The method according to claim 1, characterized in that: Based on the graph structure model capturing the correlation and spatiotemporal dependency between the marine environmental parameters, the process of determining the interaction strength between the marine environmental parameters includes: Based on the reduced-dimensional marine environmental parameter data, a time series graph structure model is constructed, in which nodes represent marine environmental parameters and edges represent the correlation and spatiotemporal dependency between parameters. The time series graph structure model is trained using a graph neural network to learn and capture the complex interaction relationship between marine environmental parameters; During the training process, the attention mechanism is introduced to dynamically adjust the connection weights between nodes at different time steps and spatial positions to highlight the mutual influence between key parameters; Inference is performed on the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position; According to the interaction strength, a causal relationship diagram between the marine environmental parameters is constructed to obtain the causal dependency and action path between the parameters; For the key nodes and paths in the causal graph, a graph attention network is used to further mine the high-order interaction patterns and long-range dependencies between parameters; The prediction results of graph neural network and graph attention network are integrated to judge the interaction strength between different marine environmental parameters.

5. The method according to claim 4, characterized in that The process of inferring the trained graph neural network model to obtain the interaction strength between the ocean environment parameters at each time step and spatial position includes: According to the spatiotemporal distribution of marine environmental parameters, the input data structure of the graph neural network model is constructed, where the node represents each spatiotemporal position and the edge represents the connection relationship between adjacent spatiotemporal positions; The input data is fed into a pre-trained graph neural network model, the hidden state vector of each node is calculated through forward propagation, and the information of adjacent nodes is aggregated through an attention mechanism; In the output layer of the graph neural network, a fully connected layer is used to map the hidden state vector of each node to the predicted value of the ocean environment parameter at the corresponding spatiotemporal location; Calculate the difference between the predicted value of each spatiotemporal position and the predicted value of the adjacent spatiotemporal position as the interaction strength between the spatiotemporal position and the adjacent position; According to the magnitude of the interaction intensity, the degree of mutual influence between different marine environmental parameters is judged, and the greater the intensity, the stronger the correlation between the two parameters; The interaction intensity matrix is ​​normalized to obtain the relative interaction intensity distribution under different combinations of spatiotemporal positions and environmental parameters; Visualize the normalized interaction intensity matrix to generate a heat map or network diagram.

6. The method according to claim 1, characterized in that The process of using radial basis function kernel to perform nonlinear mapping on the graph structure model, constructing a nonlinear mapping relationship, capturing the nonlinear characteristics between the marine environment parameters, and obtaining the nonlinear mapping result includes: A graph structure model is constructed based on the marine environment parameter data, where nodes represent parameters and edges represent the relationship between parameters. The radial basis function kernel is used to perform nonlinear mapping on the graph structure model to capture the nonlinear characteristic relationship between the marine environmental parameters. Through nonlinear mapping, the original graph structure model is mapped to a high-dimensional feature space to obtain a nonlinear mapping result. According to the nonlinear mapping results, a nonlinear relationship model between marine environmental parameters is constructed; Using a support vector machine algorithm to train the nonlinear relationship model to obtain a trained nonlinear relationship model; The trained nonlinear relationship model is used to predict new marine environmental parameter data and obtain prediction results; The prediction results are compared with the actual observed data, and after evaluating the prediction performance of the nonlinear relationship model, the model is continuously iterated and optimized.

7. The method according to claim 6, characterized in that The trained nonlinear relationship model is used to predict new marine environmental parameter data. The process of obtaining the prediction results includes: Based on historical parameter data related to the marine environment, a nonlinear relationship prediction model is constructed using a machine learning algorithm; During the model training process, the model hyperparameters are optimized through the cross-validation method, and the trained nonlinear relationship model is saved; Obtain new marine environmental parameter data, perform data cleaning and normalization preprocessing operations on the data; input the preprocessed new data into the trained nonlinear relationship model, and the model automatically performs predictive analysis and calculation; Obtain the prediction result data from the model output and perform post-processing of denormalization and data format conversion on the prediction results.

8. The method according to claim 1, characterized in that According to the nonlinear mapping result, the support vector machine algorithm is used to classify the abnormal state, and the process of judging whether there is an abnormal event in the current window includes: Get the data in the current time window, pre-process the data, remove noise and irrelevant information, and obtain a pure data set; According to a preset nonlinear mapping function, feature extraction is performed on the clean data set to obtain a feature vector capable of characterizing an abnormal state; The feature vector is input into a pre-trained support vector machine model for classification prediction to obtain a judgment result of whether there is an abnormality in the current time window; If the judgment result shows that there is an abnormality, an abnormal alarm is triggered and the relevant information of the abnormal event is sent to the administrator for further processing; If the judgment result shows that there is no abnormality, continue to obtain data in the next time window and repeat the above steps to achieve continuous monitoring of the abnormal state; According to the feedback from the administrator, the support vector machine model is updated and optimized in real time, and the result data of anomaly detection is stored in the database to form a historical record.

9. The method according to claim 1, characterized in that: The process of outputting secondary and derivative probability estimation results of abnormal states in real time through the sliding window mechanism includes: Obtain real-time monitoring data of the marine environment as the input data source of the sliding window mechanism; For the acquired monitoring data, a sliding window mechanism is used to divide the data into several time windows; For the monitoring data in each time window, anomaly detection algorithms are used to determine whether there is an abnormal state; If an abnormal state is detected in the current time window, the probability of secondary abnormalities and derivative abnormalities occurring in the abnormal state is estimated according to a pre-established probability model, and the probability is used as the abnormal state estimation result of the current time window; As the sliding window continues to move, the estimated results of the secondary probability and the derived probability of the abnormal state are updated in real time, and the updated abnormal state probability estimation results are output in real time.

Images