A method and system for predicting marine biological outbreaks based on real-time monitoring

Abstract

The present invention relates to the field of biological outbreak prediction technology, specifically a method and system for predicting marine biological outbreaks based on real-time monitoring. The method comprises the following steps: using a marine microsensor array to collect environmental and plankton data, process interference and noise, normalize parameters and adjust ecological baselines, analyze the relationship between environmental and biological responses between nodes, identify key areas and changing trends, and determine the expansion characteristics of plankton. The present invention combines real-time data collection with dynamic normalization of multiple parameters, and integrates a joint discrimination mechanism that integrates spatial distribution and time series data to achieve synchronous linkage between environmental factors and plankton responses. Relying on ecological baseline reference, the method identifies key marine change signals, automatically screens for abnormal responses within the monitoring network, and tracks expansion trends. This method effectively reflects the spatiotemporal evolution trends of risk areas. Through dynamic assessment of the entire process, it enables rapid identification and proactive warning of potential outbreaks, providing a reliable data foundation for ecological intervention and scientific management.

Description

Technical Field

[0001] The present invention relates to the technical field of biological outbreak prediction, and in particular to a method and system for predicting marine biological outbreaks based on real-time monitoring. Background Art

[0002] The field of biological outbreak prediction primarily involves technologies such as ecological and environmental monitoring, data collection and processing, and prediction of species reproduction and expansion. These include real-time monitoring of environmental variables (such as water temperature, salinity, and climate change), monitoring the dynamic changes in marine populations, establishing early warning systems for biological outbreaks, and tracking the growth, migration, and outbreak trends of marine organisms in real time, thereby providing support for fisheries management, marine ecological protection, and disaster prevention and control. Traditional marine outbreak prediction methods typically involve regularly collecting water quality and biological population data, combining this with statistical analysis of historical data, and then using models based on historical patterns or simple algorithms to predict the likelihood of an outbreak.

[0003] Existing technologies use a periodic data collection method, which often makes it difficult to detect local mutation signals in a timely manner due to the long time intervals. They rely on historical statistics and simple models, resulting in delayed response to biological change trends in the marine area. The limited distribution of equipment easily creates spatial monitoring blind spots, static parameter processing, and a lack of dynamic coupling capabilities for environmental and biological data. In the face of sudden environmental disturbances, they are unable to capture key processes and are unable to meet the real-time requirements of cold source system risk warnings, resulting in losses in disaster response due to slow signals. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a method and system for predicting marine biological outbreaks based on real-time monitoring.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for predicting marine biological outbreaks based on real-time monitoring, comprising the following steps:

[0006] S1: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration data are analyzed, the plankton fluorescence intensity information within the time period is compiled, the positioning accuracy of the node geographic coordinates is determined, and data missing is identified to obtain a spatial monitoring data set;

[0007] S2: Based on the spatial monitoring data set, filter the interference data during the equipment operation period, analyze the fluctuation range of each parameter during measurement, remove the observation results affected by noise, normalize the environmental parameters and biological response parameters, and obtain normalized dynamic parameters;

[0008] S3: Based on the normalized dynamic parameters, the correlation between the plankton fluorescence intensity of each node and the environmental parameters is calculated, the synchronous change trend is determined, the influence ratio of the environmental parameters is allocated, and the node factor linkage coefficient is adjusted to obtain the environmental linkage influence factor;

[0009] S4: Based on the environmental linkage influencing factors, the mean fluorescence intensity of nodes in each sea area is calculated, the regional node factor influence distribution is compared, and it is determined whether the regional response exceeds the ecological reference baseline, the key areas are identified, and the risk active area identification is obtained.

[0010] The improvements of the present invention are that the spatial monitoring data set includes a monitoring coordinate system, a data integrity identifier, and a plankton distribution representation; the normalized dynamic parameters include parameter normalization information, an ecological baseline reference item, and a data consistency index; the environmental linkage influencing factors include factor action ratios, parameter linkage attributes, and change response sequences; the risk active area identifier includes an active area classification, an abnormal response category, and an area dynamic label.

[0011] The present invention is improved in that the steps of acquiring the spatial monitoring data set are specifically as follows:

[0012] S111: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration monitoring data are analyzed, the geographic coordinate information of each node is jointly compared, and the plankton fluorescence intensity information in the same time period is associated to obtain the node time series environmental record group;

[0013] S112: Based on the node time series environment record group, determine the correspondence between the spatial coordinates of each group of data and the actual layout of the nodes in the monitoring area, filter out data groups with spatial position offsets, exclude data with inaccurate positioning or abnormal correlation, and obtain spatial positioning matching data;

[0014] S113: Based on the spatial positioning matching data, the parameter integrity of each node time series is compared, the missing segments of plankton fluorescence intensity and environmental parameters are identified, the changes in continuous segments before and after the data are missing are analyzed, the data subgroups with critical fluctuations or missing data exceeding the limit are identified, and the valid sequences are sorted to obtain the spatial monitoring data set.

[0015] The present invention is improved in that the step of obtaining the normalized dynamic parameters is specifically as follows:

[0016] S211: Analyze the environmental and biological data of each node during device operation based on the spatial monitoring data set, filter and remove data items caused by device abnormality, external interference, or signal abnormality, and obtain an interference elimination data set;

[0017] S212: Based on the interference elimination data set, compare the time series fluctuation of each environmental parameter and biological response parameter at each node, determine the data change amplitude and fluctuation range, and summarize the change trend of each node within the measurement period to obtain multi-parameter dynamic fluctuation information;

[0018] S213: Calculate the normalized expression factor of each parameter compared to the ecological baseline of the same region based on the multi-parameter dynamic fluctuation information, optimize the normalization processing method of each parameter, and obtain the normalized dynamic parameter.

[0019] The present invention is improved in that the step of obtaining the environmental linkage influencing factor is specifically as follows:

[0020] S311: Based on the normalized dynamic parameters, the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node is analyzed, the linear correlation between the difference parameter and the fluorescence intensity is calculated, the influence of the environmental parameters of each node on the dynamics of plankton is determined, and the correlation degree of the parameters between the nodes is generated;

[0021] S312: Based on the inter-node parameter correlation, the environmental parameter with the best correlation with the plankton fluorescence intensity in the monitoring node is screened, the variation range of the parameter in the time series is calculated, the mutual influence ratio between the parameter and other environmental parameters is optimized, and the environmental parameter weight distribution ratio is obtained;

[0022] S313: Based on the environmental parameter weight distribution ratio, the linkage relationship of the environmental parameters of each monitoring node is analyzed, and the interaction between each environmental factor is adjusted to obtain the environmental linkage influence factor.

[0023] The present invention is improved in that the steps of obtaining the risk active area identifier are specifically as follows:

[0024] S411: Based on the environmental linkage influencing factors, collect the plankton fluorescence intensity data of each node, classify the nodes in the same sea area according to the geographical distribution of the different nodes, compare the fluorescence intensity fluctuations between the nodes, calculate the equilibrium level of the plankton fluorescence intensity of the nodes, and perform mean processing to obtain the fluorescence response level distribution of the sea area;

[0025] S412: Based on the distribution of fluorescence response levels in the sea area, extract the factor effect ratio of the nodes in each sea area, sort out the parameter linkage attributes of the nodes, calculate the sum of the factor attributes within the node group, compare the merging relationship of the number of node groups to the factor data, and obtain the regional linkage influence intensity sequence;

[0026] S413: Based on the regional linkage impact intensity sequence and combined with the regional response reference interval of the ecological reference baseline, identify the areas where biological response performance is critical and obtain the risk active area identification.

[0027] The present invention is improved in that the steps further include:

[0028] S5: Based on the risk active area identification, analyze the changes in plankton fluorescence intensity in continuous time periods, calculate the average of node change amplitudes, screen continuously growing nodes, compare the synchronous expansion conditions of the change trends, and obtain plankton expansion characteristics;

[0029] The plankton expansion characteristics include spatial expansion information, aggregation evolution results, and change time series characteristics.

[0030] The present invention is improved in that the steps of acquiring the plankton extended characteristics are specifically as follows:

[0031] S511: Based on the risk active area identifier, analyze the plankton fluorescence intensity change data in continuous time periods, calculate the change amplitude between adjacent sampling periods, and count the change range of the node in each time period to obtain the floating fluctuation range;

[0032] S512: Based on the floating fluctuation range, select nodes that show a continuous growth trend in each sampling period, and according to the expansion of the fluctuation in the continuous monitoring period, determine which nodes show stable expansion in the period, and obtain an expansion trend node group;

[0033] S513: Based on the expansion trend node group, compare the fluorescence intensity change trends of each node in the same time period, analyze the synchronous variability between the nodes, and combine the geographic spatial relationship to determine whether there is a phenomenon of common expansion between the nodes in time and space, and obtain the plankton expansion characteristics.

[0034] A marine biological outbreak prediction system based on real-time monitoring, the system comprising:

[0035] The environmental monitoring module uses a microsensor array deployed in the sea area to analyze the collected water temperature, salinity, dissolved oxygen, pH, and nitrate concentration data, organize the plankton fluorescence intensity information for the corresponding time period, determine the positioning accuracy of each set of data in the node's geographic spatial coordinates, and identify missing data items to obtain a spatial monitoring data set;

[0036] The data correction module, based on the spatial monitoring data set, screens the interference data corresponding to the equipment operation period in each data set, analyzes the fluctuation range of each parameter during the equipment measurement period, removes the noise affecting the key observation results, normalizes each environmental parameter and biological response parameter, and adjusts the parameter distribution based on the ecological baseline of the same area to obtain the normalized dynamic parameters;

[0037] The linkage relationship determination module calculates the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node based on the normalized dynamic parameters, determines the synchronous change trend of plankton and environmental parameters, allocates the influence ratio of the differential environmental parameters, adjusts the linkage coefficient of each node factor, and obtains the environmental linkage influence factor;

[0038] The risk area identification module calculates the average fluorescence intensity of nodes in each sea area based on the environmental linkage influencing factors, compares the factor influence distribution of nodes in each area, determines whether the regional response exceeds the ecological reference baseline, identifies the key areas of biological response, and obtains the risk active area identification;

[0039] The expansion feature determination module analyzes the changes in the fluorescence intensity of plankton in continuous time periods based on the risk active area identification, calculates the average level of change of each node, screens nodes with continuously increasing change amplitudes, compares the change trends between nodes to see whether they meet the synchronous expansion conditions, and obtains the expansion features of plankton.

[0040] Compared with the prior art, the advantages and positive effects of the present invention are:

[0041] In the present invention, through real-time collection and multi-parameter dynamic normalization, the joint discrimination mechanism of spatial distribution and time series data is integrated to achieve the synchronous linkage between environmental factors and plankton responses. Relying on the ecological baseline reference, key change signals of the sea area are identified, and abnormal responses are automatically screened and expansion trends are tracked in the monitoring network, effectively reflecting the spatiotemporal evolution trends of risk areas. Through dynamic evaluation of the entire process, rapid identification and forward-looking warning of potential outbreaks are achieved, providing a reliable data basis for ecological intervention and scientific management, and significantly improving the active monitoring capabilities of the spread and aggregation processes of marine biological groups. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the main steps of the present invention;

[0043] Figure 2 This is a flowchart for obtaining a space monitoring data set in the present invention;

[0044] Figure 3 This is a flow chart for obtaining normalized dynamic parameters in the present invention;

[0045] Figure 4 This is a flow chart for obtaining environmental linkage influencing factors in the present invention;

[0046] Figure 5 This is a flowchart for obtaining risk active area identification in the present invention;

[0047] Figure 6 The figure is a flow chart for obtaining the extended characteristics of plankton in the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0050] Example

[0051] See also Figure 1 The present invention provides a technical solution: a method for predicting marine biological outbreaks based on real-time monitoring, comprising the following steps:

[0052] S1: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration data are analyzed, the plankton fluorescence intensity information of the corresponding time period is compiled, the positioning accuracy of each set of data in the node's geographic spatial coordinates is determined, and missing data items are identified to obtain a spatial monitoring data set;

[0053] S2: Based on the spatial monitoring data set, the interference data corresponding to the equipment operation period in each data set is screened, the fluctuation range of each parameter during the equipment measurement period is analyzed, the noise affecting the key observation results is removed, and each environmental parameter and biological response parameter is normalized. The parameter distribution is adjusted in combination with the ecological baseline of the same area to obtain the normalized dynamic parameters;

[0054] S3: Based on the normalized dynamic parameters, the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node is calculated to determine the synchronous change trend of plankton and environmental parameters, the influence ratio of different environmental parameters is allocated, and the linkage coefficient of each node factor is adjusted to obtain the environmental linkage influence factor;

[0055] S4: Based on the environmental linkage influencing factors, the average fluorescence intensity of nodes in each sea area is calculated, and the factor influence distribution of nodes in each area is compared to determine whether the regional response exceeds the ecological reference baseline, identify the key areas of biological response, and obtain the risk active area identification;

[0056] S5: Based on the identification of risk-active areas, analyze the changes in plankton fluorescence intensity in continuous time periods, calculate the average level of change for each node, screen nodes with continuously increasing change, compare whether the change trends between nodes meet the synchronous expansion conditions, and obtain the plankton expansion characteristics.

[0057] The spatial monitoring data set includes the monitoring coordinate system, data integrity identification, and plankton distribution representation. The normalized dynamic parameters include parameter normalization information, ecological baseline reference items, and data consistency indicators. The environmental linkage influencing factors include factor action ratios, parameter linkage attributes, and change response sequences. The risk active area identification includes active area classification, abnormal response category, and regional dynamic label. The plankton expansion characteristics include spatial expansion information, aggregation evolution results, and change time series characteristics.

[0058] In S1, the microsensor array refers to a monitoring system composed of multiple microsensors (such as buoys, underwater sensors, etc.) deployed in the sea area and distributed at different geographical locations. The sensors can collect physical and chemical environmental parameters and biological related information in real time; the plankton fluorescence intensity information refers to the fluorescence signal data reflecting the number, activity or distribution status of plankton in the water body obtained by detecting the plankton at each node position using a special fluorescence sensor or fluorescence detection equipment; the node geographic spatial coordinates refer to the spatial location of each monitoring node (that is, each sensor device) actually deployed in the sea area, which is usually uniquely identified by geographic parameters such as longitude, latitude and depth; the data item missing situation refers to the phenomenon that during the collection process, some monitoring nodes fail to obtain certain parameters or have data gaps due to equipment failure, environmental interference or signal loss.

[0059] In S2, the equipment operation period refers to the specific time interval when the sensor equipment is actually put into operation and collects data, which is usually a continuous or intermittent period of automatic sampling of the equipment at regular intervals; interference data refers to data anomalies, distortions or erroneous records caused by factors such as equipment failure, abnormal changes in the external environment, electromagnetic interference, equipment drift, etc. during the collection process; the fluctuation range during the measurement period refers to the normal variation range of each environmental parameter (such as water temperature, salinity, etc.) or biological response parameter (such as fluorescence signal, etc.) in a statistical sense during the equipment collection period, which is used to judge the validity of the data; the key noise impact refers to the data distortion caused by noise in the observation results. The noise sources are instrument noise, background stray light, ocean current disturbances, etc. The key data affected by noise refers to Data that is judged to be severely interfered with by noise and cannot be used for subsequent analysis; environmental parameters refer to parameters that directly reflect the physical and chemical state of water bodies, including water temperature, salinity, dissolved oxygen, pH, nitrate concentration, etc.; biological response parameters refer to parameters that can directly reflect the physiological state, distribution or activity of plankton, the most typical of which is the fluorescence intensity of plankton, but can also be particle size count, density, etc.; the ecological baseline of the same area refers to the normal range or benchmark level of various environmental and biological parameters obtained from long-term statistics of the current sea area or the same historical location, which is used as a reference for subsequent data normalization or standardization; parameter distribution refers to the statistical distribution characteristics of various parameters (environmental parameters, biological response parameters) in the entire monitoring interval and at each node, such as mean, variance, distribution range, etc.

[0060] In S3, correlation refers to the statistical correlation between plankton fluorescence intensity and environmental parameters (such as water temperature, salinity, and dissolved oxygen), which is usually represented by a correlation coefficient (such as the Pearson correlation coefficient) to reflect the degree of consistency in the changing trends of the two; the synchronous change trend refers to whether the response parameters of plankton and a certain environmental parameter show a change pattern in the same direction and synchronization within the same time period, such as rising or falling at the same time; the influence ratio of different environmental parameters refers to the contribution of different environmental parameters to the change in plankton fluorescence intensity in the analysis of each node, which is quantified by statistical weight distribution (such as the proportion distributed after normalization of the correlation coefficient); the linkage coefficient of the node factor refers to the influence relationship coefficient formed by weight distribution between different environmental factors and plankton parameters at a single monitoring node, which describes the contribution of the linkage of each factor to the biological response.

[0061] In S4, factor influence distribution refers to the statistical weight or contribution ratio of all node environmental factors to plankton response in the same area, reflecting the pattern of different environmental factors in the area affecting biological changes; regional response refers to the overall level of plankton response parameters (such as fluorescence intensity, etc.) integrated from all nodes in units of region, which is a key indicator for judging the state of biological activity in the sea area; ecological reference baseline refers to the standardized judgment line set based on historical data or scientific research for current analysis to determine whether the regional response is abnormal or has an outbreak risk; the area with key response performance refers to the spatial partition where, after statistical analysis, the plankton response parameters are abnormally high and biological outbreaks or abnormal aggregations are very likely to occur.

[0062] In S5, the changes in continuous time periods refer to the dynamic changes of plankton response parameters (such as fluorescence intensity) over time within the continuous sampling or observation period; the average level of node change amplitude refers to the statistical average of the change amplitude of plankton response parameters in a continuous time series at each node, reflecting the strength of the response dynamics; the continuously growing node refers to the monitoring node where the plankton response parameters continue to show an increasing trend in the continuous sampling period after analysis; the synchronous expansion condition refers to the coordination or consistency of the change trends of plankton response parameters at multiple nodes in space and time, indicating that there is a risk of large-scale biological aggregation or outbreak in the sea area.

[0063] A node refers to a microsensor unit or sensor monitoring point deployed in the sea area for real-time collection of environmental parameters and plankton distribution data. Each node represents a clear geographical location, usually an actual monitoring coordinate point; a device is a physical sensor at each node, that is, a microsensor or monitoring terminal deployed in the sea area. A node is the concept of data spatial location, and a device is the actual sensing hardware at that spatial location.

[0064] See also Figure 2 ,The steps for obtaining the spatial monitoring dataset are as follows:

[0065] S111: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration monitoring data are analyzed, the geographic coordinate information of each node is jointly compared, and the plankton fluorescence intensity information in the same time period is associated to obtain the node time series environmental record group;

[0066] The microsensor array regularly and in real time collects environmental parameters such as water temperature, salinity, dissolved oxygen, pH value and nitrate concentration in seawater. The data is collected by sensor equipment and marked with timestamps. In order to analyze the impact of biological activity, each monitoring node also obtains plankton fluorescence intensity information within the same time period. The data is captured by a dedicated fluorescence sensor. Then, the position of all monitoring nodes is accurately located using geographic coordinates (such as longitude, latitude and depth) information to ensure that the data corresponds to the node location. Assuming that the water temperature data of a certain monitoring point is 18°C, the dissolved oxygen concentration is 6mg / L, the plankton fluorescence intensity is 150, the time is 18:00 on June 27, 2025, and the location coordinates are longitude 112°30′ and latitude 30°45′, all information is combined into a node time series environmental record group to form a data set for subsequent analysis and processing.

[0067] S112: Based on the node time series environment record group, determine the correspondence between the spatial coordinates of each data set and the actual layout of the nodes in the monitoring area, filter out data sets with spatial position offsets, exclude data with inaccurate positioning or abnormal correlation, and obtain spatial positioning matching data;

[0068] According to the node time series environment record group, the spatial coordinates of each set of data are judged to correspond to the actual layout of the nodes in the monitoring area. In this step, the geographic coordinates of each monitoring point need to be compared with the coordinate information in the preset monitoring area. By calculating the distance between the geographic coordinates, the geographic information system (GIS) technology is used to determine whether the coordinates are offset. If there is a significant gap between the data coordinates of a monitoring point and the actual preset coordinates (for example, the calculated distance exceeds the set error range), it is considered that there is a problem with the positioning of the data and it is marked as offset data. For example, if a node should be at the predetermined longitude 113°00′ and latitude 31°10′, but the actual collected coordinate position is displayed as longitude 113°10′ and latitude 31°15′, there is a deviation of 10 kilometers between the two, indicating that the position of this node has a large deviation from the actual layout. Therefore, this part of the data will be eliminated to obtain spatial positioning matching data.

[0069] S113: Based on the spatial positioning matching data, the parameter integrity of each node time series is compared, the missing segments of plankton fluorescence intensity and environmental parameters are identified, the changes in the consecutive segments before and after the data are missing are analyzed, the data subgroups with critical fluctuations or excessive missing data are identified, and the valid sequences are sorted to obtain the spatial monitoring data set;

[0070] Compare the integrity of the time series parameters of each node. First, the data of each monitoring node needs to be compared in time series to check whether the various environmental parameters are missing or abnormal in the same time period. For each monitoring node, by comparing the water temperature, salinity, dissolved oxygen, pH and other data within the time period, find out which time points have data missing or abnormal fluctuations. Then, analyze the changes in the continuous data before and after the missing data. If the data changes significantly before and after the loss, for example, the change range of the data before and after is large, it needs to be paid special attention. Specifically, suppose that the plankton fluorescence intensity data of a node is missing between 16:00 and 18:00, and the fluctuation range of the data before and after is 20 and 80 respectively, indicating that the data missing is caused by abnormal environmental changes or equipment failure. At this time, the missing data subset will be marked as abnormal, and the data of the corresponding time period of other nodes will be checked and sorted out, and the data will be filled or corrected to ensure a complete and accurate spatial monitoring data set.

[0071] See also Figure 3 , the specific steps for obtaining normalized dynamic parameters are:

[0072] S211: Based on the spatial monitoring data set, analyze the environmental and biological data of each node during device operation, filter and remove data items caused by device abnormalities, external interference, or signal abnormalities, and obtain an interference elimination data set;

[0073] The environmental data (such as water temperature, salinity, dissolved oxygen, pH, and nitrate concentration) and biological data (such as plankton fluorescence intensity) collected by each node during device operation are analyzed. During the analysis, the device operation data of each node is first examined one by one to check for equipment failure, external interference (such as electromagnetic interference), or signal anomalies. Specifically, by observing the fluctuation pattern of the data and comparing it with the normal fluctuation range of environmental conditions, it is possible to identify data anomalies that do not conform to physical laws. For example, under normal equipment operation, the water temperature should remain within a certain range (for example, the water temperature fluctuation amplitude is ±0.5°C). However, if the water temperature data of a node suddenly changes drastically (for example, an instantaneous fluctuation of 2°C), it indicates that the sensor is faulty or has been subjected to external interference. Similarly, if the plankton fluorescence intensity data shows an abnormal and sharp increase in a short period of time, while other nodes do not show similar changes, it is due to signal transmission interruption or device failure. By removing the abnormal data, a more accurate interference-free data set can be obtained, thus ensuring data quality and reliability.

[0074] S212: Based on the interference-removed data set, compare the time series fluctuations of each environmental parameter and biological response parameter at each node, determine the data change amplitude and fluctuation range, and summarize the change trend of each node within the measurement period to obtain multi-parameter dynamic fluctuation information;

[0075] Based on the interference-removed data set, the time series fluctuations of each environmental parameter and biological response parameter at each node were compared. First, the environmental parameter and biological response data for each node were arranged in time series. Then, the fluctuation amplitude and fluctuation range of each parameter within the measurement period were analyzed. Specifically, for data such as water temperature, dissolved oxygen, and plankton fluorescence intensity, the fluctuation range was determined by calculating the maximum and minimum values ​​in each time period, and the fluctuation amplitude was calculated. If the data fluctuation amplitude of a node exceeded the normal range (for example, the water temperature fluctuation exceeded 1°C), the node was marked as having large data fluctuations and required further analysis. Based on the calculation results of the fluctuation amplitude, the change trend of each node throughout the measurement period can be summarized. For example, at a certain node, the plankton fluorescence intensity continued to increase over a period of time (for example, the plankton fluorescence intensity increased from 50 to 150), while other environmental parameters (such as water temperature and dissolved oxygen) remained relatively stable, indicating that the node was at the peak of plankton proliferation. Therefore, through this fluctuation analysis, the dynamic fluctuation information of each node in different time periods can be obtained, which will provide data support for further ecological prediction and risk assessment.

[0076] S213: Based on the dynamic fluctuation information of multiple parameters, the formula is used:

[0077] ;

[0078] Calculate the normalized expression factor of each parameter compared with the ecological baseline of the same area, optimize the normalization processing method of each parameter, and obtain the normalized dynamic parameters, among which, Indicates the Node Normalized expression factor of the parameter, For the Node The original observation data of the parameters, For the The parameter is expressed as the mean value under the ecological baseline reference of the region. For the The variance of the parameter under the reference is expressed as, For the The error suppression factor added during parameter normalization, For the The maximum and minimum interval difference of the parameter in all nodes, For the The number of observations in which the node is classified as operating normally after interference removal.

[0079] The normalized expression factor refers to a dimensionless quantity that reflects the degree of deviation of the parameter status of each monitoring point from the reference baseline after different nodes and different parameters (including environmental parameters and biological response parameters) are normalized with the ecological baseline of the same region. That is, it is the standardized deviation of each parameter at each node, which is used for subsequent spatial and temporal linkage analysis and risk assessment.

[0080] There are two monitoring parameters with different dimensions: water temperature (℃) and fluorescence intensity, which correspond to two monitoring nodes respectively. The normalization of water temperature parameter is:

[0081] For the water temperature parameter, the original value of the water temperature at a node is 18.2℃, and the baseline mean water temperature in this area is 18.5℃, standard deviation The error suppression factor is 0.3℃ The maximum and minimum interval differences are 0.05°C The number of observations of the node when the equipment is operating normally is 0.2℃ is 10, and is calculated by substituting into the formula:

[0082] ;

[0083] Normalization of fluorescence intensity parameters:

[0084] For the fluorescence intensity parameter, the original value of the fluorescence intensity of a node is 15.4, and the baseline mean fluorescence intensity in this area is 16.2, and the corresponding standard deviation is 0.5, the error suppression factor The maximum and minimum interval differences are 0.02. 0.4, the number of observations of the node when the device is operating normally is 10, and is calculated by substituting into the formula:

[0085] ;

[0086] The results show that the normalized dynamic parameters of water temperature and fluorescence intensity are 0.765 and 1.441, respectively. The normalized dynamic parameters reflect the degree of deviation of the environmental and biological response parameters of each monitoring node from the ecological baseline of the area. Specifically, the normalized dynamic parameter of water temperature is 0.765, indicating that the water temperature of the node deviates less from the baseline value of the same area, while the normalized dynamic parameter of fluorescence intensity is 1.441, indicating that the fluorescence intensity of the plankton at the node deviates more from the baseline value. Numerical results such as 0.765 and 1.441 will become an important reference in subsequent analysis, helping to identify whether there are potential abnormal trends or risk areas. For example, if the normalized parameter value of fluorescence intensity of a node is significantly higher than that of other nodes, it means that the plankton activity in the area is abnormal, indicating ecological changes or outbreak risks.

[0087] See also Figure 4 , the specific steps for obtaining environmental linkage impact factors are:

[0088] S311: Based on the normalized dynamic parameters, the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node is analyzed, the linear correlation between the difference parameter and the fluorescence intensity is calculated, the influence of the environmental parameters of each node on the dynamics of plankton is determined, and the correlation degree of the parameters between nodes is generated;

[0089] Analyze the correlation between the fluorescence intensity of plankton and environmental parameters such as water temperature, salinity, and dissolved oxygen at each monitoring node. In this process, the monitoring data of each node are first collected and normalized to ensure that different types of parameters can be compared at the same scale. Then, the linear correlation between the environmental parameters (such as water temperature, salinity, and dissolved oxygen) and the fluorescence intensity of plankton at each node is calculated to obtain the degree of mutual influence between the parameters. For example, if there is a strong linear relationship between the fluorescence intensity of plankton and water temperature (such as by calculating the Pearson correlation coefficient, If a correlation of 0.85 is obtained for each monitoring node, it indicates that water temperature has a greater impact on the dynamic changes of plankton. Conversely, if there is almost no correlation between salinity changes and plankton fluorescence intensity (the correlation coefficient is close to 0), it indicates that salinity has a smaller impact on plankton changes. In this way, the specific degree of influence of different environmental parameters on the dynamic changes of plankton can be determined, and the parameter correlation between nodes can be generated. Assuming that at a certain monitoring node, water temperature has a greater impact on plankton fluorescence intensity, while dissolved oxygen has a smaller impact, then the parameter correlation between nodes will focus on the connection between water temperature and plankton fluorescence intensity.

[0090] S312: Based on the correlation between the parameters between the nodes, the environmental parameter with the best correlation with the plankton fluorescence intensity in the monitoring node is screened, the variation range of the parameter in the time series is calculated, the mutual influence ratio between the parameter and other environmental parameters is optimized, and the weight distribution ratio of the environmental parameters is obtained;

[0091] To screen the environmental parameters with the best correlation with plankton fluorescence intensity, we first need to sort the correlation between the environmental parameters and plankton fluorescence intensity in each node and find the most relevant environmental parameters. For example, if the correlation coefficient between water temperature and plankton fluorescence intensity is the highest, then water temperature will be considered the most relevant parameter. Then, calculate the variation of the environmental parameter in the time series. This can be obtained by calculating the maximum and minimum values ​​of the parameter in each monitoring period. For example, assuming that the water temperature changes from 18°C ​​to 22°C in the time series of a certain node, the variation of the water temperature is 4°C. Then, based on the existing To identify the optimal environmental parameter, it is necessary to optimize the mutual influence ratio between this parameter and other environmental parameters. For example, if the influence of water temperature on the fluorescence intensity of plankton accounts for the majority (e.g. 70%), while the influence ratios of other environmental parameters (such as salinity and dissolved oxygen) are smaller, it is necessary to adjust and distribute the weights of the parameters on plankton changes. Ultimately, by optimizing the influence ratios of each environmental parameter, the weight distribution ratio of the environmental parameters of the node can be obtained. For example, the water temperature of a certain node accounts for 70%, dissolved oxygen accounts for 20%, and salinity accounts for 10%. The weight distribution ratio reflects the relative influence of different environmental parameters on the dynamics of plankton.

[0092] S313: Based on the weight distribution ratio of environmental parameters, analyze the linkage relationship of environmental parameters of each monitoring node and adjust the interaction between each environmental factor. The formula is:

[0093] ;

[0094] The environmental linkage impact factor is obtained, among which, Indicates the Among the monitoring nodes The environmental linkage influencing factors of the environmental factors, Indicates the Among the monitoring nodes Pearson correlation coefficients between environmental factors and plankton fluorescence intensity, Indicates the Among the monitoring nodes The weight distribution ratio of each environmental factor is used to characterize the normalized influence ratio of the environmental parameter on the change of fluorescence intensity. Indicates the Among the monitoring nodes The variation range of the normalized data of an environmental factor in a continuous time period reflects the dynamic change of the parameter. Indicates the The maximum variation range of the correlation coefficient of an environmental factor at all monitoring nodes is used to describe the difference in the correlation between the factor and the fluorescence intensity between different nodes. Indicates the The average level of the current normalized data of the environmental factor in all monitoring nodes, Indicates the The ecological baseline average level of each environmental factor at all monitoring nodes.

[0095] The environmental linkage influencing factor refers to a numerical factor obtained through composite calculation at each monitoring node by comprehensively considering the correlation between plankton fluorescence intensity and major environmental parameters (such as water temperature, salinity, dissolved oxygen, etc.), the proportion of the influence of each parameter on plankton changes, and the dynamic changes of parameters in different time periods. It is used to reflect the linkage strength and comprehensive effect between specific environmental parameters and plankton responses, and is used to comprehensively evaluate and quantitatively analyze the linkage driving force of environmental changes on plankton outbreak trends.

[0096] Based on the normalized dynamic parameters and weight distribution ratio of each monitoring node, the linkage effect of each environmental factor is analyzed. , consider the An environmental factor (water temperature), the correlation coefficient between the water temperature at this node and the fluorescence intensity of plankton is 0.75, weight is 0.6, normalized data change range is 0.05, the correlation coefficient changes is 0.1, the average normalized value 0.65, the ecological baseline value is 0.5, substitute it into the formula for calculation:

[0097] ;

[0098] Calculate the numerator:

[0099] ;

[0100] Calculate the denominator:

[0101] ;

[0102] ;

[0103] Get the environmental linkage impact factor:

[0104] ;

[0105] The results show that the environmental linkage impact factor of water temperature on plankton fluorescence intensity is 0.698, which means that water temperature has a more significant influence at monitoring node 1 and is strongly correlated with plankton dynamics. 0.698 indicates that water temperature plays a certain dominant role in the changes in plankton fluorescence intensity at this node, and its variation amplitude has a certain stability under the influence of other environmental factors (such as salinity and dissolved oxygen). Therefore, the numerical results can be used as one of the bases for judging the potential risk of biological outbreaks at this node, and can help further analyze whether the environmental factors at this node have reached the risk threshold requiring intervention, or whether more precise control measures are needed to reduce the impact of biological outbreaks.

[0106] See also Figure 5 , the specific steps for obtaining the risk active area identification are:

[0107] S411: Based on the environmental linkage influencing factors, the fluorescence intensity data of plankton at each node is collected. Based on the geographical distribution of different nodes, the nodes in the same sea area are classified. The fluorescence intensity fluctuations between nodes are compared, and the equilibrium level of the fluorescence intensity of the plankton at the nodes is calculated. The average value is processed to obtain the fluorescence response level distribution of the sea area.

[0108] By collecting the plankton fluorescence intensity data of each node and combining it with the geographical distribution of the difference nodes, the nodes are classified according to the sea area where they are located. The node data in each sea area will be grouped according to the geographical location (such as longitude and latitude) to ensure that the geographical location of each node is compared in the same area. Then, by comparing the fluctuation of plankton fluorescence intensity between nodes, when it is specifically implemented, for each node, the fluctuation range of its plankton fluorescence intensity over a period of time is calculated. For example, the fluctuation range of water temperature and plankton fluorescence intensity between June 30 and July 2, 2024 is 10-100, and then compared with the fluctuation range of other nodes in the same area. By comparing the data, we can determine whether there are significant differences. Through this comparison, we can identify abnormal changes in the fluorescence intensity of plankton at certain nodes. Next, for each node, by calculating the equilibrium level of its plankton fluorescence intensity data, we can ensure that the fluorescence intensity data of the node can reflect normal ecological changes. For example, at a certain node, the mean value of the plankton fluorescence intensity is 60, while at another node it is 90, which reflects the abnormal fluctuation of the node. Finally, through mean processing, the fluorescence intensity levels of all nodes are unified to obtain the fluorescence response level distribution of each node in the sea area, which is used as the basis for evaluating the activity intensity of plankton in the area.

[0109] S412: Based on the distribution of fluorescence response levels in the sea area, extract the factor effect ratio of each sea area node, sort out the parameter linkage attributes of the nodes, calculate the sum of the factor attributes within the node group, compare the merging relationship of the number of node groups to the factor data, and obtain the regional linkage influence intensity sequence;

[0110] The factor effect ratios of nodes in each sea area were extracted. For each node, the relationship strength between the environmental factors involved (such as water temperature, salinity, and dissolved oxygen) and the fluorescence intensity of plankton was calculated. Specifically, the influence ratio of each node's environmental factors on the fluorescence intensity of plankton was calculated. For example, if the water temperature of a certain node had a 70% effect on the fluorescence intensity of plankton, dissolved oxygen accounted for 20%, and salinity accounted for 10%. The factor effect ratios helped analyze the relationships between nodes. Next, the parameter linkage properties of each node were sorted, and the variation pattern of each factor in the time series was analyzed. The water temperature of a certain node varied greatly over different time periods, while the salinity changed less, indicating that water temperature had a more significant impact on the fluorescence intensity of plankton at that node. Then, by calculating the sum of factor attributes within the node group and comparing the linkage relationships of factors between different node groups, the interactions between nodes and the distribution characteristics of environmental factors within the region can be more accurately determined. Finally, the merging relationship of the node group number on the factor data was compared. For example, if multiple nodes showed similar factor effect ratios and linkage properties, it can be inferred that the region where the node was located had a similar ecological state. Through comprehensive analysis, a regional linkage influence strength series was obtained, which can help identify ecological hotspots within the sea area.

[0111] S413: Based on the regional linkage impact intensity sequence and the regional response reference interval of the ecological reference baseline, identify the key areas of biological response performance using the formula:

[0112] ;

[0113] Get the risk active area identification, where Indicates the Identification of active risk areas in each sea area, Indicates the The average fluorescence response level of a sea area refers to the balanced level of plankton fluorescence intensity of the classification nodes in the area. Indicates the The sum of the factor action ratios of each sea area is the cumulative result of the factor action ratios of all nodes in the region. Indicates the The parameter linkage attribute balance level of a sea area is the average level of the node parameter linkage attributes in the area. Indicates the The total number of nodes in the sea area, Indicates the The deviation term of the response sequence of the change of each sea area, Indicates the The number of nodes participating in abnormal dynamic statistics in each sea area, Indicates the The first sea area The abnormal response category of each node, Indicates the The first sea area The regional dynamic label of each node refers to the classification characteristic parameter of the node spatial behavior response. Indicates the The number of valid dynamic tags in each sea area.

[0114] The identification of risk-active areas refers to the spatial divisions in the sea area where the fluorescence response of plankton and the linkage of environmental parameters are prominent and abnormal dynamic characteristics are obvious through real-time monitoring and comprehensive analysis, and risk marking numbers are assigned to them for key risk warnings and spatial positioning management.

[0115] Based on the regional linkage impact intensity sequence and the regional response reference interval of the ecological reference baseline, the response of plankton in the region was identified and screened, and the risk active area identification of each region was calculated using the formula. The following was obtained through monitoring data: (mean fluorescence response level), (the sum of the factor effect proportions), (parameter linkage attribute balance level), (total number of nodes), (variation response sequence deviation term), (Number of nodes participating in abnormal dynamic statistics), and The corresponding node data are:

[0116] Node 1: , ;

[0117] Node 2: , ;

[0118] Node 3: , ;

[0119] (Number of valid dynamic tags);

[0120] Calculate the data by plugging it into the formula. Start by calculating the first part of the formula:

[0121] ;

[0122] Compute the second part of the sum:

[0123] ;

[0124] Adding the two parts together yields the risk-active area identifier:

[0125] ;

[0126] The results show that the risk active area identification It indicates that the plankton activity in this sea area is high, with a certain degree of biological response activity and risk of environmental changes, reflecting the linkage between the plankton response and environmental factors in this sea area during the monitoring period. If this value is within the preset risk active zone classification range, it indicates that there is a potential risk of plankton outbreak in this area, which requires key monitoring and further intervention. The first part of the formula (i.e. ) reflects the degree of linkage between the fluorescence intensity of plankton in this sea area and environmental factors. Combined with the number of nodes and the deviation of the response to changes, it provides an estimate of the activity of the sea area in terms of plankton response. The second part (i.e. ) further corrects the activity estimate of the area by taking a weighted average of the abnormal responses and dynamic labels of the nodes in the area, taking into account the changing characteristics and response intensity of different nodes in the area; the risk active area identification is a quantitative indicator that comprehensively reflects the linkage between plankton response and environmental factors, indicating whether the sea area is in a high-risk biological outbreak area. The higher the value, the more active the plankton response in the area and the greater the risk.

[0127] See also Figure 6 , the specific steps for obtaining the extended features of plankton are:

[0128] S511: Based on the risk active area identification, analyze the plankton fluorescence intensity change data in continuous time periods, calculate the change amplitude between adjacent sampling periods, and count the change range of the node in each time period to obtain the floating fluctuation range;

[0129] First, the plankton fluorescence intensity of each monitoring node in different time periods is collected, and the variation range between adjacent sampling periods is calculated. For example, the fluorescence intensity of a node increases from 50 to 60 in the first sampling period (such as June 1 to June 2), and the fluorescence intensity in the second sampling period (such as June 2 to June 3) increases from 60 to 80. Then the variation range of the node between the two time periods is 10 and 20, respectively. Next, the fluorescence intensity variation range of each node in each time period is statistically analyzed, and the fluctuation range of each node is further calculated. For example, the variation range of a node ranges from 5 to 25, indicating that the fluorescence intensity of the node fluctuates greatly. Finally, by calculating and sorting out the floating fluctuation ranges of all nodes, the fluctuation characteristics of plankton in each area can be obtained, providing data support for subsequent expansion trend analysis.

[0130] S512: Based on the floating fluctuation range, select nodes that show a continuous growth trend in each sampling period. According to the expansion of the fluctuation in the continuous monitoring period, determine which nodes show stable expansion in the period, and obtain the expansion trend node group;

[0131] A time series comparison is performed on the data of each monitoring node to identify which nodes show a continuous increase in fluorescence intensity over multiple consecutive sampling periods. For example, assuming that the fluorescence intensity of a node from June 1 to June 2, from June 2 to June 3, and from June 3 to June 4 is 50, 60, and 75, respectively, showing a continuous growth trend, then the node meets the continuous growth standard. Then, based on the expansion of fluctuations within consecutive monitoring periods, further judgment is made on which nodes show stable expansion. For example, if the fluctuation amplitude of a node is stable between 10 and 15, and the fluorescence intensity increases during each sampling period, it can be considered a stable expansion node. Stable expansion nodes will be classified as expansion trend nodes and serve as the focus of subsequent analysis.

[0132] S513: Based on the expansion trend node group, compare the fluorescence intensity change trends of each node in the same time period, analyze the synchronous variability between nodes, and combine the geographic spatial relationship to determine whether there is a phenomenon of common expansion between nodes in time and space, and obtain the plankton expansion characteristics;

[0133] The changes in plankton fluorescence intensity of each node in the same time period were compared, and the change trends between different nodes were analyzed. For example, from June 1 to June 2, the fluorescence intensity of node A increased from 50 to 60, while the fluorescence intensity of node B increased from 45 to 55, which indicated that both nodes showed a certain growth trend in the same time period. Then, by analyzing the synchronous variability between nodes, we determined which nodes expanded together in time and space. If node A and node B showed similar change trends in the same time period, and the two nodes were geographically located in relatively close areas, it can be inferred that there was a phenomenon of synchronous expansion between them. For example, if node A and node B were located at different monitoring points in the same sea area, and the change trends of fluorescence intensity were highly consistent within the same time period, it indicated that they shared similar ecological conditions and thus expanded together. Combined with geographic spatial relationships, the plankton expansion characteristics were obtained, which can help evaluate the spatial distribution of biological expansion and potential risk areas.

[0134] A marine biological outbreak prediction system based on real-time monitoring, the system comprising:

[0135] The environmental monitoring module uses a microsensor array deployed in the sea area to analyze the collected water temperature, salinity, dissolved oxygen, pH, and nitrate concentration data, organize the plankton fluorescence intensity information for the corresponding time period, determine the positioning accuracy of each set of data in the node's geographic spatial coordinates, and identify missing data items to obtain a spatial monitoring data set;

[0136] The data correction module, based on the spatial monitoring data set, screens the interference data corresponding to the equipment operation period in each data set, analyzes the fluctuation range of each parameter during the equipment measurement period, removes the noise affecting the key observation results, normalizes each environmental parameter and biological response parameter, and adjusts the parameter distribution based on the ecological baseline of the same area to obtain the normalized dynamic parameters;

[0137] The linkage relationship determination module calculates the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node based on normalized dynamic parameters, determines the synchronous change trend of plankton and environmental parameters, allocates the influence ratio of different environmental parameters, adjusts the linkage coefficient of each node factor, and obtains the environmental linkage impact factor;

[0138] The risk area identification module calculates the average fluorescence intensity of nodes in each sea area based on environmental linkage influencing factors, compares the factor influence distribution of nodes in each area, determines whether the regional response exceeds the ecological reference baseline, identifies the key areas of biological response, and obtains the risk active area identification;

[0139] The expansion feature determination module analyzes the changes in plankton fluorescence intensity in continuous time periods based on the risk active area identification, calculates the average level of change of each node, screens nodes with continuously increasing change amplitudes, compares whether the change trends between nodes meet the synchronous expansion conditions, and obtains the plankton expansion characteristics.

[0140] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for predicting marine biological outbreaks based on real-time monitoring, characterized in that: The following steps are involved: S1: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration data are analyzed, the plankton fluorescence intensity information within the time period is compiled, the positioning accuracy of the node geographic coordinates is determined, and data missing is identified to obtain a spatial monitoring data set; S2: Based on the spatial monitoring data set, filter the interference data during the equipment operation period, analyze the fluctuation range of each parameter during measurement, remove the observation results affected by noise, normalize the environmental parameters and biological response parameters, and obtain normalized dynamic parameters; S3: Based on the normalized dynamic parameters, the correlation between the plankton fluorescence intensity of each node and the environmental parameters is calculated, the synchronous change trend is determined, the influence ratio of the environmental parameters is allocated, and the node factor linkage coefficient is adjusted to obtain the environmental linkage influence factor; S4: Based on the environmental linkage influencing factors, the mean fluorescence intensity of nodes in each sea area is calculated, the regional node factor influence distribution is compared, and it is determined whether the regional response exceeds the ecological reference baseline, the key areas are identified, and the risk active area identification is obtained; The steps for obtaining the risk active area identifier are as follows: S411: Based on the environmental linkage influencing factors, collect the plankton fluorescence intensity data of each node, classify the nodes in the same sea area according to the geographical distribution of the different nodes, compare the fluorescence intensity fluctuations between the nodes, calculate the equilibrium level of the plankton fluorescence intensity of the nodes, and perform mean processing to obtain the fluorescence response level distribution of the sea area; S412: Based on the distribution of fluorescence response levels in the sea area, extract the factor effect ratio of the nodes in each sea area, sort out the parameter linkage attributes of the nodes, calculate the sum of the factor attributes within the node group, compare the merging relationship of the number of node groups to the factor data, and obtain the regional linkage influence intensity sequence; S413: Based on the regional linkage impact intensity sequence and combined with the regional response reference interval of the ecological reference baseline, identify the areas with key biological response performance and obtain the risk active area identification; S5: Based on the risk active area identification, analyze the changes in plankton fluorescence intensity in continuous time periods, calculate the average of node change amplitudes, screen continuously growing nodes, compare the synchronous expansion conditions of the change trends, and obtain plankton expansion characteristics; The plankton expansion characteristics include spatial expansion information, aggregation evolution results, and change time series characteristics; The spatial monitoring dataset includes a monitoring coordinate system, a data integrity identifier, and a plankton distribution representation; the normalized dynamic parameters include parameter normalization information, an ecological baseline reference item, and a data consistency index; the environmental linkage influencing factors include factor action ratios, parameter linkage attributes, and a change response sequence; and the risk active area identifier includes an active area classification, an abnormal response category, and an area dynamic label.

2. The method for predicting marine biological outbreaks based on real-time monitoring according to claim 1, characterized in that: The steps for obtaining the spatial monitoring data set are specifically as follows: S111: Based on the microsensor array deployed in the sea area, the collected water temperature, salinity, dissolved oxygen, pH and nitrate concentration monitoring data are analyzed, the geographic spatial coordinate information of each node is jointly compared, and the plankton fluorescence intensity information in the same time period is associated to obtain the node time series environmental record group; S112: Based on the node time series environment record group, determine the correspondence between the spatial coordinates of each group of data and the actual layout of the nodes in the monitoring area, filter out data groups with spatial position offsets, exclude data with inaccurate positioning or abnormal correlation, and obtain spatial positioning matching data; S113: Based on the spatial positioning matching data, the parameter integrity of each node time series is compared, the missing segments of plankton fluorescence intensity and environmental parameters are identified, the changes in continuous segments before and after the data are missing are analyzed, the data subgroups with critical fluctuations or missing data exceeding the limit are identified, and the valid sequences are sorted to obtain the spatial monitoring data set.

3. The method for predicting marine biological outbreaks based on real-time monitoring according to claim 1, characterized in that: The steps for obtaining the normalized dynamic parameters are specifically as follows: S211: Analyze the environmental and biological data of each node during device operation based on the spatial monitoring data set, filter and remove data items caused by device abnormality, external interference, or signal abnormality, and obtain an interference elimination data set; S212: Based on the interference elimination data set, compare the time series fluctuation of each environmental parameter and biological response parameter at each node, determine the data change amplitude and fluctuation range, and summarize the change trend of each node within the measurement period to obtain multi-parameter dynamic fluctuation information; S213: Calculate the normalized expression factor of each parameter compared to the ecological baseline of the same region based on the multi-parameter dynamic fluctuation information, optimize the normalization processing method of each parameter, and obtain the normalized dynamic parameter.

4. The method for predicting marine biological outbreaks based on real-time monitoring according to claim 1, characterized in that: The steps for obtaining the environmental linkage impact factor are specifically as follows: S311: Based on the normalized dynamic parameters, the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node is analyzed, the linear correlation between the difference parameter and the fluorescence intensity is calculated, the influence of the environmental parameters of each node on the dynamics of plankton is determined, and the correlation degree of the parameters between the nodes is generated; S312: Based on the inter-node parameter correlation, the environmental parameter with the best correlation with the plankton fluorescence intensity in the monitoring node is screened, the variation range of the parameter in the time series is calculated, the mutual influence ratio between the parameter and other environmental parameters is optimized, and the environmental parameter weight distribution ratio is obtained; S313: Based on the environmental parameter weight distribution ratio, the linkage relationship of the environmental parameters of each monitoring node is analyzed, and the interaction between each environmental factor is adjusted to obtain the environmental linkage influence factor.

5. The method for predicting marine biological outbreaks based on real-time monitoring according to claim 1, characterized in that: The steps for obtaining the plankton extended characteristics are specifically as follows: S511: Based on the risk active area identifier, analyze the plankton fluorescence intensity change data in continuous time periods, calculate the change amplitude between adjacent sampling periods, and count the change range of the node in each time period to obtain the floating fluctuation range; S512: Based on the floating fluctuation range, select nodes that show a continuous growth trend in each sampling period, and according to the expansion of the fluctuation in the continuous monitoring period, determine which nodes show stable expansion in the period, and obtain an expansion trend node group; S513: Based on the expansion trend node group, compare the fluorescence intensity change trends of each node in the same time period, analyze the synchronous variability between the nodes, and combine the geographic spatial relationship to determine whether there is a phenomenon of common expansion between the nodes in time and space, and obtain the plankton expansion characteristics.

6. A marine biological outbreak prediction system based on real-time monitoring, characterized in that: The system is used to implement the marine biological outbreak prediction method based on real-time monitoring according to any one of claims 1 to 5, and the system comprises: The environmental monitoring module uses a microsensor array deployed in the sea area to analyze the collected water temperature, salinity, dissolved oxygen, pH, and nitrate concentration data, organize the plankton fluorescence intensity information for the corresponding time period, determine the positioning accuracy of each set of data in the node's geographic spatial coordinates, and identify missing data items to obtain a spatial monitoring data set; The data correction module, based on the spatial monitoring data set, screens the interference data corresponding to the equipment operation period in each data set, analyzes the fluctuation range of each parameter during the equipment measurement period, removes the noise affecting the key observation results, normalizes each environmental parameter and biological response parameter, and adjusts the parameter distribution based on the ecological baseline of the same area to obtain the normalized dynamic parameters; The linkage relationship determination module calculates the correlation between the fluorescence intensity of plankton and water temperature, salinity, and dissolved oxygen in each monitoring node based on the normalized dynamic parameters, determines the synchronous change trend of plankton and environmental parameters, allocates the influence ratio of the differential environmental parameters, adjusts the linkage coefficient of each node factor, and obtains the environmental linkage influence factor; The risk area identification module calculates the average fluorescence intensity of nodes in each sea area based on the environmental linkage influencing factors, compares the factor influence distribution of nodes in each area, determines whether the regional response exceeds the ecological reference baseline, identifies the key areas of biological response, and obtains the risk active area identification; The expansion feature determination module analyzes the changes in the fluorescence intensity of plankton in continuous time periods based on the risk active area identification, calculates the average level of change of each node, screens nodes with continuously increasing change amplitudes, compares the change trends between nodes to see whether they meet the synchronous expansion conditions, and obtains the expansion features of plankton.

Images