Sea grass bed ecosystem plankton and environmental parameter online intelligent monitoring system and method

Abstract

The invention discloses an online intelligent monitoring system and method for plankton and environmental parameters of a sea grass bed ecosystem, and relates to the technical field of sea grass bed ecological monitoring, the intelligent monitoring system comprises a sea grass bed underwater intelligent monitoring terminal, a data communication transmission module and an intelligent analysis and visualization platform decision system; and the sea grass bed underwater intelligent monitoring terminal is used for shooting planktons in real time, intelligently identifying, counting and monitoring multiple environmental parameters, acquiring sea grass bed images and monitoring the planktons, the environmental parameters and the sea grass bed in real time. By integrating the high-resolution microscopic camera, the intelligent image recognition technology and various environmental parameter sensors, the plankton type and density, water temperature, salinity, dissolved oxygen, pH value and other key environmental parameters are monitored in real time, and compared with a traditional manual sampling and laboratory analysis method, the system greatly improves the monitoring efficiency and reduces the monitoring cost. Personal errors are reduced, and the accuracy and reliability of monitoring data are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of seagrass bed ecological monitoring, and particularly relates to a seagrass bed ecosystem plankton and environmental parameter online intelligent monitoring system and method. BACKGROUND

[0002] Seagrass is the only class of angiosperms that can live in seawater on the earth, seagrass gathers and grows in large areas to form a seagrass bed, and the seagrass ecosystem, together with mangroves and coral reefs, is known as the three typical nearshore marine ecosystems on the earth, and has extremely high ecological service functions, the seagrass bed not only can absorb nutrients and improve water quality, but also can fix the seabed, resist wind and waves, and protect the coast, and can also provide habitats, breeding sites and food sources for many animals, and has extremely important significance for the shallow coastal and estuarine ecosystems, plankton, as an important biological component of the water ecosystem, is the natural bait of aquatic animals such as fish, and is also an important link in the production and transmission of nutrients in water, and plays an important role in maintaining the complexity and stability of the food web, the seagrass bed, as an important nursery ground, provides abundant food sources for a variety of marine organisms, mainly including primary producers represented by phytoplankton and planktonic animals feeding on primary producers; Research has found that the seagrass bed significantly affects the community structure of plankton, seagrass leaves are excellent attachment bases for a large number of epiphytes, and these epiphytes are important food sources for many planktonic animals such as endopods and copepods, and the planktonic animals are preyed on by higher trophic level animals such as fish in the seagrass bed, therefore, the ecological characteristics such as plant density and biomass of the seagrass bed determine the complexity of the seagrass habitat structure, and also significantly affect the community structure of plankton; Plankton plays an important role in the material cycle and biogeochemical process in the nearshore, and is crucial for maintaining the stability of the ecosystem, the community composition of plankton can be used as an early indicator for effectively identifying the ecological status of seagrass, and is used for more comprehensive and timely understanding of the environmental pressure faced by the seagrass ecosystem, and therefore, it is of great significance to monitor the plankton in the seagrass bed, and it is of great significance to online monitor the spatiotemporal variation characteristics of plankton and key environmental factors in the seagrass bed and its adjacent sea area, to deeply understand the ecological function of the seagrass bed, to real-time understand the plankton and environmental status in the sea area near the seagrass bed, and to realize the scientific protection of the seagrass bed habitat.

[0003] The existing plankton monitoring is mainly through on-site net sampling, and then the sample is sent to the laboratory for biological species identification and counting under the microscope by biological species identification personnel. This work is time-consuming and labor-intensive, low in efficiency, and requires high technical requirements for experimental personnel. The identification results of different experimental personnel often have differences, and in-situ, real-time and online continuous observation cannot be realized, lacking timeliness and spatial information. The traditional environmental monitoring parameters are also analyzed by sending samples to the laboratory after on-site sampling, and the results are slow and low in efficiency. The on-site probe monitoring is usually measured by independent sensors, and the data is scattered and not integrated and related to ecological changes. The monitoring means lacks intelligent analysis capability and cannot realize real-time ecological anomaly early warning. SUMMARY

[0004] The present application aims to provide a seaweed bed ecosystem plankton and environmental parameter online intelligent monitoring system and method to solve the problems raised in the above background.

[0005] To solve the above technical problems, the technical solution adopted by the present application is: In a first aspect, a seaweed bed ecosystem plankton and environmental parameter online intelligent monitoring system is provided. The intelligent monitoring system comprises a seaweed bed underwater intelligent monitoring terminal, a data communication transmission module, and an intelligent analysis and visualization platform decision system. The seaweed bed underwater intelligent monitoring terminal is used for real-time shooting of plankton and intelligent identification and statistics, monitoring of multiple environmental parameters, and acquisition of seaweed bed images for real-time monitoring of plankton, environmental parameters and seaweed bed. The data communication transmission module is used for transmitting monitoring data to a water surface relay station and then back to the intelligent analysis and visualization platform decision system, ensuring real-time and stable data transmission and improving monitoring timeliness. The intelligent analysis and visualization platform decision system is used for storing and analyzing plankton and environmental parameter data in combination with machine learning technology, real-time display of monitoring data, and discovery of abnormal conditions and early warning based on intelligent analysis results of monitoring data.

[0006] Further improvements of the technical solution of the present application are that the seaweed bed underwater intelligent monitoring terminal comprises a plankton monitoring module, an environmental parameter monitoring module and a seaweed coverage monitoring module. The plankton monitoring module is used for capturing plankton images by using a high-resolution microscopic camera and identifying species and counting density of plankton. The environmental parameter monitoring module is used for real-time monitoring of environmental parameters including water temperature, salinity, dissolved oxygen, pH, turbidity, chlorophyll a and nutrient salt. The seagrass coverage monitoring module is used to use a monitoring camera to capture images of seagrass beds, extract seagrass monitoring data on seagrass distribution area, height and coverage, and intuitively present the growth status and distribution range of the seagrass beds, which helps to understand the ecological characteristics of the seagrass beds and their changing trends.

[0007] A further improvement of the technical solution of the present invention is that: the intelligent analysis and visualization platform decision system includes an intelligent analysis platform, a visualization platform and an abnormality warning platform; The intelligent analysis platform is used to store and analyze plankton and environmental parameter data using machine learning technology to deeply mine data information; The visualization platform is used to display various monitoring data as well as real-time images of seagrass beds, seagrass bed area, seagrass height, and coverage parameters in real time, making it easier for managers to intuitively understand the status of the seagrass bed ecosystem; The abnormal warning platform is used to issue early warnings in a timely manner when abnormal situations are found based on the results of intelligent analysis, prompting relevant management departments to take corresponding measures to effectively prevent and respond to ecological problems and ensure the stability of the seagrass bed ecosystem.

[0008] A further improvement of the technical solution of the present invention is that the seagrass bed underwater intelligent monitoring terminal specifically includes: The underwater intelligent seagrass bed monitoring terminal automatically begins operating within a typical seagrass bed area based on a preset monitoring frequency. Its high-resolution microscopic camera focuses on plankton for real-time photography. Simultaneously, its onboard environmental parameter sensors collect a variety of environmental data, including water temperature, salinity, dissolved oxygen, and pH. Based on the actual conditions of the seagrass bed, additional monitoring cameras capable of monitoring indicators such as seagrass coverage area, height, and coverage are added to the edge of the seagrass bed to capture images of the seagrass bed. During the filming process, a high-resolution microscopic camera captures plankton images. After the plankton passes through the optical path, the morphological characteristics of the plankton are recorded in combination with high-speed background imaging technology. The plankton image data and environmental parameter data are then integrated to form a complete data set containing plankton and environmental information; The integrated plankton image data and environmental parameter data are sent to the surface relay station through the data communication transmission module, and then transmitted back from the relay station to the intelligent analysis platform, and then stored in the corresponding database to ensure the safe storage of the data and its availability for review at any time.

[0009] A further improvement of the technical solution of the present invention is that the intelligent analysis platform specifically includes: The intelligent analysis platform receives plankton image data, environmental parameter data, and seagrass coverage monitoring data from the seagrass bed underwater intelligent monitoring terminal through the data communication transmission module, and verifies the integrity and accuracy of the data to ensure that no data is lost or damaged; The verified data is subjected to feature extraction, the morphological features in the plankton image, the change trend in the environmental parameter data and the spatial features in the seagrass coverage data are extracted, and then the extracted features are integrated to form a comprehensive feature data set; The historical data and known ecological knowledge are utilized, the machine learning technology of the decision tree model is combined, and a seagrass bed ecological analysis model is trained; According to the trained seagrass bed ecological analysis model, the data in the current comprehensive feature data set is analyzed, a seagrass bed ecological health score is output, an analysis result is generated, and the correlation and change trend between the plankton and the environmental parameters are displayed.

[0010] The further improvement of the technical scheme of the present application is that the calculation process of the seagrass bed ecological health score is: The density of each kind of plankton and the current value of each environmental parameter in the current monitoring period are extracted, and the reference density of each kind of plankton and the reference value of each environmental parameter are obtained, the reference value is obtained from the historical data, and the average value when the ecological system is in a healthy state is selected; For each kind of plankton, the ratio of the density to the reference density is calculated, the density ratio is added by 1 and the natural logarithm is taken, the plankton density part is calculated, and then the values of all the plankton density parts are summed to obtain the total sum of the plankton density parts; For each environmental parameter, the ratio of the current value to the reference value of the environmental parameter is calculated, the square root of the environmental parameter ratio is taken, the environmental parameter part is calculated, and the values of all the environmental parameter parts are summed to obtain the total sum of the environmental parameter parts; The total sum of the plankton density parts and the total sum of the environmental parameter parts are added, divided by the total sum of the number of plankton species and the number of environmental parameters, multiplied by 100, and the seagrass bed ecological health score is obtained.

[0011] The further improvement of the technical scheme of the present application is that the expression of the seagrass bed ecological health score is: ; In the formula, P is the seagrass bed ecological health score, Df is the density of the fth plankton, unit: pieces per cubic meter, Df is the reference density of the fth plankton, unit: pieces per cubic meter, is the current value of the gth environmental parameter, The reference value of the gth environmental parameter is z, the number of plankton species, p is the number of monitored environmental parameters, and the value range of P is 0 to 100, wherein 0 represents that the ecological health condition is extremely poor, 100 represents that the ecological health condition is extremely good, and when the value of P gradually increases, it indicates that the ecological health condition of the seagrass bed gradually improves; when the value of P gradually decreases, it indicates that the ecological health condition of the seagrass bed gradually deteriorates.

[0012] The further improvement of the technical scheme of the present application is that the visualization platform specifically comprises: The visualization platform receives various monitoring data from the intelligent analysis platform in real time through the data communication transmission module, including plankton image data, environmental parameter data and seagrass coverage monitoring data, at the same time, receives real-time pictures of the seagrass bed, area, height and coverage parameter information of the seagrass bed, and integrates different types of data to ensure the integrity and consistency of the data; The integrated data is processed and format-converted to be converted into a format suitable for front-end display, and at the same time, the real-time picture is processed by streaming media to ensure the fluency and real-time performance of the picture; The processed data and picture are displayed to the management personnel in real time through the visualization platform, and real-time data updating function is provided to enable the management personnel to obtain the latest ecological information of the seagrass bed.

[0013] The further improvement of the technical scheme of the present application is that the abnormality early warning platform specifically comprises: The abnormality early warning platform continuously receives and monitors the analysis result data stream from the intelligent analysis platform, and tracks the indicators of the plankton species and density and the environmental parameters in real time; The real-time monitored data is compared with the abnormality determination threshold value preset in the abnormality early warning platform, and the abnormality of the plankton and the environmental parameters is determined, such as excessive density of red tide algae or abnormal content of nutrient salt, to ensure that the determination result is accurate and reliable and the false alarm rate is reduced; Once the abnormality is determined to exist, the abnormality early warning platform generates an early warning notice containing the type of abnormality, the severity, the location and the time, and sends the early warning notice to the relevant management department through various communication channels (SMS, email, system push), to ensure that the early warning notice can be quickly received and responded by the relevant management department, and at the same time, the feedback of the relevant management department is received to further process and analyze the early warning notice and optimize the early warning mechanism.

[0014] In the second aspect, an online intelligent monitoring method for plankton and environmental parameters of a seagrass bed ecosystem is realized based on the online intelligent monitoring system for plankton and environmental parameters of the seagrass bed ecosystem, and comprises the following steps: S1, collecting plankton image, environmental parameter and seagrass coverage data by using the underwater intelligent monitoring terminal of the seagrass bed; S2, the collected monitoring data is sent to the water surface relay station through the data communication transmission module, and then is returned to the intelligent analysis platform; S3, the monitoring data is analyzed by using the machine learning technology, the seagrass bed ecological analysis model is trained, and the correlation and change trend between the plankton in the seagrass bed area and the environmental parameters are mined; S4, the monitoring data and the analysis result are displayed in real time through the visualization platform; S5, the abnormal early warning platform monitors and analyzes the result, generates and sends an early warning notice to the management department when an abnormality is found.

[0015] Due to the adoption of the above technical solutions, the present application has the following technical progress compared with the prior art: The present application provides an online intelligent monitoring system and method for plankton and environmental parameters in a seagrass bed ecosystem, which realizes real-time monitoring of key environmental parameters such as plankton species and density, water temperature, salinity, dissolved oxygen, pH value, etc. by integrating high-resolution microscopic cameras, intelligent image recognition technology and various environmental parameter sensors. Compared with traditional manual sampling and laboratory analysis methods, the system greatly improves the monitoring efficiency, reduces human error and ensures the accuracy and reliability of the monitoring data.

[0016] The present application provides an online intelligent monitoring system and method for plankton and environmental parameters in a seagrass bed ecosystem, which combines machine learning technology to intelligently analyze monitoring data, mine potential rules and trends behind the data, and at the same time, an abnormal early warning platform can monitor and warn abnormal fluctuations in indicators such as plankton species and density, environmental parameters, etc. according to a preset judgment threshold, so as to timely discover ecological problems and provide strong support for the rapid response and effective intervention of the management department, thereby effectively preventing and responding to ecological risks. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0018] Figure 1 It is a system function module schematic diagram of the present application. Figure 2 It is a method flowchart schematic diagram of the present application. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] Example 1, as Figure 1 As shown, the present invention provides an online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem. The intelligent monitoring system includes an underwater intelligent monitoring terminal for a seagrass bed, a data communication transmission module, and an intelligent analysis and visualization platform decision system. The underwater intelligent seagrass bed monitoring terminal is used to capture plankton in real time and intelligently identify and count it, monitor multiple environmental parameters, and obtain seagrass bed images for real-time monitoring of plankton, environmental parameters, and seagrass beds. The terminal includes a plankton monitoring module, an environmental parameter monitoring module, and a seagrass coverage monitoring module. Among them, the plankton monitoring module is used to capture plankton images with a high-resolution microscope camera, identify the species and count the density of plankton, accurately grasp the changes in the community structure of plankton in the seagrass bed, and improve the accuracy and efficiency of plankton species identification and counting. The plankton monitoring module specifically includes: extracting plankton image data captured by a high-resolution microscope camera, analyzing the plankton image data in the seagrass bed area, identifying the species of plankton, and counting the density of plankton. For the identification of plankton species, the captured plankton images are analyzed using intelligent image recognition technology, and the morphological characteristics of the plankton, including cell structure, body shape and color, are compared with the existing plankton The plankton image database is compared to calculate the similarity score of plankton with the plankton in the plankton image database, and then the plankton species are identified, which improves the accuracy and efficiency of species identification and reduces the error and time cost of manual identification. For the statistics of plankton density, the number of different plankton species in the same shooting area is counted, and the number of individuals of each plankton is calculated to obtain the density data of plankton, so as to realize the quantitative analysis of the plankton population. The species identification results and density statistics of plankton are integrated to form a structured data format, and the data is sent to the intelligent analysis platform through the data communication transmission module to ensure the timeliness and integrity of the data. The expression of plankton similarity score is: ; Where, The similarity score of the i-th plankton is c, which is a cell structure characteristic value of the plankton, and the value range is 0 to 10, and the larger the value is, the more complex the cell structure is; s is a size characteristic value of the plankton, and the value range is 0 to 5, and the larger the value is, the larger the size is; h is a color characteristic value of the plankton, and the value range is 0 to 10, and the larger the value is, the darker the color is, 、 、 respectively represent the cell structure characteristic value, the size characteristic value and the color characteristic value of the i-th plankton in the database, and the more similar the characteristics of the plankton and the i-th plankton in the database are, the closer the value of the product is to 1, and vice versa. The expression of the plankton density is: ; In the formula, is the density of the j-th plankton in the shooting area A, is the number of the j-th plankton, and the value range is 0 to n (n is the maximum number of plankton in the shooting area), and the larger the value is, the more the number of the plankton is; A is the area of the shooting area, and the value range is 0 to m (m is the total area of the monitoring area), and the larger the value is, the larger the monitoring area is, and the more the number of the j-th plankton in the shooting area is, the larger the value of the product is, and vice versa. The environmental parameter monitoring module is used for real-time monitoring of environmental parameters including water temperature, salinity, dissolved oxygen, pH, turbidity, chlorophyll a and nutrient salt, and the environmental parameter monitoring module specifically comprises: the environmental parameter monitoring module is equipped with various environmental parameter sensors, and works in the seagrass bed area according to the set time interval, starts to collect multi-dimensional environmental parameter data of water temperature, salinity, dissolved oxygen, pH, turbidity, chlorophyll a and nutrient salt, and records the collected environmental parameter data in the form of digital signal, ensures the accuracy and real-time performance of the data, performs filtering and denoising preprocessing operation on the collected multi-dimensional environmental parameter data, removes abnormal values and interference signals, improves the reliability and usability of the data, synchronizes and integrates the data of various sensors at the same time, ensures the consistency and integrity of the data, formats the preprocessed environmental parameter data into a standard data format, integrates different types of environmental parameter data to form a complete environmental parameter data set, sends the formatted environmental parameter data to the water surface relay station through the data communication transmission module, and then returns to the intelligent analysis platform from the relay station, and then stores the processed environmental parameter data into a special database on the intelligent analysis platform, to ensure the safe storage and ready-to-check of the data. ​​The seaweed coverage monitoring module is used for shooting seaweed bed images by using a monitoring camera, extracting seaweed monitoring data of seaweed distribution area, height and coverage, and intuitively presenting the growth condition and distribution range of the seaweed bed, which helps to understand the ecological characteristics and change trend of the seaweed bed. The seaweed coverage monitoring module specifically comprises: a monitoring camera arranged at the edge position of the seaweed bed, which is automatically started according to a preset time, aimed at the seaweed bed area for shooting, to ensure a clear picture, and the camera has the functions of automatically adjusting the focal length and light compensation to adapt to different underwater environments and guarantee the image quality. When shooting, the whole monitoring area is covered to obtain panoramic images of the seaweed bed. The panoramic images of the seaweed bed are preliminarily processed, including picture stabilization, denoising and format conversion operations, to remove image jitter caused by factors such as water flow during shooting, reduce background noise interference, unify image format and ensure data compatibility. Feature information of seaweed distribution area, height and coverage is extracted from the processed panoramic images of the seaweed bed by using image recognition and analysis technology. Then the extracted feature information is compared with historical data to calculate the seaweed bed growth change trend value and analyze the change trend of the growth condition and distribution range of the seaweed bed. The extracted feature information of seaweed distribution area, height and coverage is integrated to form a structured data format. The data is sent to a water surface relay station through a data communication transmission module and then transmitted back to an intelligent analysis platform for storage. The expression of the seaweed bed growth change trend value is: ; In the formula, T is the seaweed bed growth change trend value, representing the comprehensive change trend of the growth condition and distribution range of the seaweed bed, is the seaweed distribution area feature value extracted in the kth monitoring period, is the seaweed height feature value extracted in the kth monitoring period, is the seaweed coverage feature value extracted in the kth monitoring period, is the historical reference seaweed distribution area feature value corresponding to the kth monitoring period, is the historical reference seaweed height feature value corresponding to the kth monitoring period, is the historical reference seaweed coverage feature value corresponding to the kth monitoring period, and n is the number of monitoring periods. If the T value gradually decreases, it indicates that the growth condition and distribution range of the seaweed bed gradually approach the historical reference state, and the ecological condition tends to be stable or improved. If the T value gradually increases, it indicates that the growth condition and distribution range of the seaweed bed deviates more and more from the historical reference state, and there may be an ecological degradation risk. In addition, the seaweed bed underwater intelligent monitoring terminal specifically comprises: The underwater intelligent monitoring terminal for seagrass beds automatically starts working in typical areas of seagrass beds according to the preset monitoring frequency. Its high-resolution microscope camera is aimed at plankton for real-time photography. At the same time, the environmental parameter sensors it carries synchronously collect multiple environmental data including water temperature, salinity, dissolved oxygen, pH, etc., and by adding monitoring cameras that can monitor seagrass coverage area, height, coverage and other indicators at the edge of the seagrass bed according to the actual situation of the seagrass bed, the seagrass bed image is captured, and then the corresponding monitoring frequency (such as 1h or 30min, etc.) is set according to the monitoring needs of the seagrass bed. It can be powered by cables, solar energy or wave energy, and the monitoring terminal can be fixed on a floating platform or anchored by a buoy. In typical areas of seagrass beds, the direction of the microscope camera is adjusted to better image and shoot plankton, and the focal length can be automatically adjusted. During the shooting process, the high-resolution microscope camera captures the plankton image. After the plankton passes through the optical path, the morphological characteristics of the plankton are recorded in combination with high-speed background imaging technology. The plankton image data and environmental parameter data are then integrated to form a complete data set containing plankton and environmental information. The integrated plankton image data and environmental parameter data are sent to the surface relay station through the data communication transmission module, and then transmitted back from the relay station to the intelligent analysis platform, and then the data is stored in the corresponding database to ensure the secure storage and accessibility of the data at any time. The data communication transmission module is used to transmit monitoring data to the surface relay station and then transmit it back to the intelligent analysis and visualization platform decision-making system to ensure real-time and stable data transmission and improve monitoring timeliness; The intelligent analysis and visualization platform decision system is used to combine machine learning technology to store and analyze plankton and environmental parameter data, display monitoring data in real time, and detect abnormal situations and issue warnings based on the results of intelligent analysis of monitoring data.

[0021] Example 2, as Figure 1 As shown, based on Example 1, the present invention provides a technical solution: preferably, the intelligent analysis and visualization platform decision system includes an intelligent analysis platform, a visualization platform and an abnormal warning platform; The intelligent analysis platform is configured to store and analyze the plankton and environmental parameter data using machine learning techniques, to deeply mine data information, to receive the plankton image data, the environmental parameter data, and the seagrass coverage monitoring data from the seagrass bed underwater intelligent monitoring terminal through the data communication transmission module, to verify the integrity and accuracy of the data, to ensure that the data is not lost or damaged, to extract features from the verified data, to extract morphological features in the plankton image, change trends in the environmental parameter data, and spatial features in the seagrass coverage data, to integrate the extracted features to form a comprehensive feature data set, to train a seagrass bed ecological analysis model using historical data and known ecological knowledge in combination with the machine learning techniques of the decision tree model, to extract the same features from the historical data as in the comprehensive feature data set, to mine the internal relationship between the plankton and the environmental parameters and the correlation between the seagrass coverage changes and the environmental factors by continuously iterating and optimizing the model parameters, to enable the model to have the ability of accurate analysis and prediction, to analyze the data in the current comprehensive feature data set according to the trained seagrass bed ecological analysis model, to output a seagrass bed ecological health score, to generate an analysis result, and to display the correlation and change trends between the plankton and the environmental parameters; The calculation process of the seagrass bed ecological health score is as follows: The density of each kind of plankton and the current value of each environmental parameter in the current monitoring period are extracted, and the reference density of each kind of plankton and the reference value of each environmental parameter are obtained. The reference value is obtained from historical data, and the average value when the ecosystem is in a healthy state is selected. For each kind of plankton, the ratio of its density to the reference density is calculated, the density ratio is added by 1 and the natural logarithm is taken, and the plankton density part is calculated. Then the values of all plankton density parts are summed to obtain the total sum of the plankton density part. For each environmental parameter, the ratio of the current value to the reference value is calculated, and the square root of the environmental parameter ratio is taken to obtain the environmental parameter part. The values of all environmental parameter parts are summed to obtain the total sum of the environmental parameter part. The total sum of the plankton density part and the total sum of the environmental parameter part are added, divided by the total sum of the number of plankton species and the number of environmental parameters, and multiplied by 100 to obtain the seagrass bed ecological health score. The expression of the seagrass bed ecological health score is as follows: ; In the formula, P is the seagrass bed ecological health score, Df is the density of the fth plankton, with the unit of individual / m3, Df is the reference density of the fth plankton, with the unit of individual / m3, is the current value of the gth environmental parameter, The reference value of the gth environmental parameter is z, the number of phytoplankton species, p is the number of monitored environmental parameters, and the value of P ranges from 0 to 100, wherein 0 represents an extremely poor ecological health status, and 100 represents an extremely good ecological health status; when the value of P gradually increases, it indicates that the ecological health status of the seagrass bed gradually improves; when the value of P gradually decreases, it indicates that the ecological health status of the seagrass bed gradually deteriorates; through the score, the overall health status of the seagrass bed ecosystem and its change trend can be intuitively understood; A visualization platform is used to display various monitoring data, real-time seagrass bed images, seagrass bed area, seagrass height, and coverage parameters in real time, so that management personnel can intuitively understand the status of the seagrass bed ecosystem. The visualization platform receives various monitoring data from the intelligent analysis platform in real time through a data communication transmission module, including phytoplankton image data, environmental parameter data, and seagrass coverage monitoring data. At the same time, real-time seagrass bed images, seagrass bed area, height, and coverage parameter information are received, and different types of data are integrated to ensure data integrity and consistency. The integrated data is processed and format-converted to a format suitable for front-end display. For phytoplankton image data, image compression and optimization are performed to ensure image clarity while reducing data volume. For environmental parameter data and seagrass coverage parameters, numerical format unification and unit conversion are performed to meet display standards. At the same time, real-time images are processed as streaming media to ensure smoothness and real-time performance. The processed data and images are displayed in real time to management personnel through the visualization platform, and real-time data updating function is provided to enable management personnel to obtain the latest seagrass bed ecological information. An abnormality warning platform is used to issue a warning in a timely manner when an abnormal situation is found based on the intelligent analysis results, prompt relevant management departments to take appropriate measures, effectively prevent and respond to ecological problems, and ensure the stability of the seagrass bed ecosystem. The abnormality warning platform continuously receives and monitors analysis result data streams from the intelligent analysis platform, tracks the indicators of phytoplankton species and density, and environmental parameters in real time, compares the real-time monitoring data with the abnormality determination threshold values preset in the abnormality warning platform, determines the abnormality of phytoplankton and environmental parameters, such as excessive red tide algae density or abnormal nutrient salt content, ensures the accuracy and reliability of the determination results, and reduces the false alarm rate. Once an abnormal situation is determined to be true, the abnormality warning platform generates a warning notification containing the type of abnormality, severity, location, and time, and sends the warning notification to relevant management departments through various communication channels (SMS, email, system push), ensuring that they can quickly receive and respond. At the same time, feedback from relevant management departments is received, and the warning notification is further processed and analyzed to optimize the warning mechanism.

[0022] In Example 3, as Figure 2As shown, on the basis of embodiments 1-2, the present application also provides an online intelligent monitoring method for phytoplankton and environmental parameters of a seagrass bed ecosystem, which is realized based on an online intelligent monitoring system for phytoplankton and environmental parameters of a seagrass bed ecosystem and includes the following steps: S1, collecting phytoplankton images, environmental parameters and seagrass coverage data by using a seagrass bed underwater intelligent monitoring terminal; S2, sending the collected monitoring data to a water surface relay station through a data communication transmission module, and then returning the monitoring data to an intelligent analysis platform; S3, analyzing the monitoring data by using machine learning technology, training a seagrass bed ecological analysis model, and mining the correlation and change trend between phytoplankton and environmental parameters in the seagrass bed area; S4, real-time displaying the monitoring data and analysis results through a visualization platform; S5, monitoring and analyzing the results by an abnormality early warning platform, and generating and sending an early warning notice to a management department when an abnormality is found.

[0023] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An online intelligent monitoring system for plankton and environmental parameters of seagrass bed ecosystems, characterized by: The intelligent monitoring system includes a seagrass bed underwater intelligent monitoring terminal, a data communication transmission module, and an intelligent analysis and visualization platform decision system; The seagrass bed underwater intelligent monitoring terminal is used to capture plankton in real time and intelligently identify and count them, monitor multiple environmental parameters, and obtain seagrass bed images to conduct real-time monitoring of plankton, environmental parameters, and seagrass beds; The data communication transmission module is used to transmit the monitoring data to the surface relay station and then transmit it back to the intelligent analysis and visualization platform decision system; The intelligent analysis and visualization platform decision system is used to combine machine learning technology to store and analyze plankton and environmental parameter data, display monitoring data in real time, and detect abnormal situations and issue warnings based on the results of intelligent analysis of monitoring data.

2. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 1 is characterized by: The seagrass bed underwater intelligent monitoring terminal includes a plankton monitoring module, an environmental parameter monitoring module and a seagrass coverage monitoring module; The plankton monitoring module is used to capture plankton images using a high-resolution microscopic camera, and perform species identification and density statistics on plankton; The environmental parameter monitoring module is used to monitor environmental parameters including water temperature, salinity, dissolved oxygen, pH, turbidity, chlorophyll a and nutrients in real time; The seagrass coverage monitoring module is used to use a monitoring camera to capture images of seagrass beds, extract seagrass monitoring data such as seagrass distribution area, height and coverage, and intuitively present the growth status and distribution range of the seagrass beds.

3. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 2 is characterized by: The intelligent analysis and visualization platform decision system includes an intelligent analysis platform, a visualization platform and an abnormal warning platform; The intelligent analysis platform is used to store and analyze plankton and environmental parameter data using machine learning technology to deeply mine data information; The visualization platform is used to display various monitoring data and real-time images of seagrass beds, seagrass bed area, seagrass height, and coverage parameters in real time; The abnormal warning platform is used to issue an early warning when an abnormal situation is found based on the intelligent analysis results, prompting relevant management departments to take corresponding measures.

4. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 3 is characterized by: The seagrass bed underwater intelligent monitoring terminal specifically includes: The underwater intelligent seagrass bed monitoring terminal automatically begins operating within a typical seagrass bed area based on a preset monitoring frequency. Its high-resolution microscopic camera focuses on plankton and captures real-time images. Simultaneously, its onboard environmental parameter sensors collect multiple environmental data, including water temperature, salinity, dissolved oxygen, and pH, and use the monitoring camera to capture images of the seagrass bed. During the filming process, a high-resolution microscopic camera captures plankton images. After the plankton passes through the optical path, the morphological characteristics of the plankton are recorded in combination with high-speed background imaging technology. The plankton image data and environmental parameter data are then integrated to form a complete data set containing plankton and environmental information; The integrated plankton image data and environmental parameter data are sent to the surface relay station through the data communication transmission module, and then transmitted back from the relay station to the intelligent analysis platform, and then stored in the corresponding database.

5. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 3 is characterized by: The intelligent analysis platform specifically includes: The intelligent analysis platform receives plankton image data, environmental parameter data, and seagrass coverage monitoring data from the seagrass bed underwater intelligent monitoring terminal through the data communication transmission module, and verifies the integrity and accuracy of the data; Perform feature extraction on the verified data to extract morphological features from plankton images, changing trends from environmental parameter data, and spatial features from seagrass cover data. The extracted features are then integrated to form a comprehensive feature dataset. Using historical data and known ecological knowledge, combined with machine learning techniques such as decision tree models, a seagrass bed ecological analysis model was trained; Based on the trained seagrass bed ecological analysis model, the data in the current comprehensive feature dataset is analyzed, the seagrass bed ecological health score is output, and the analysis results are generated to show the correlation and change trend between plankton and environmental parameters.

6. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 5, characterized in that: The calculation process of the seagrass bed ecological health score is as follows: Extract the density of each plankton species and the current value of each environmental parameter during the current monitoring period, and simultaneously obtain the baseline density of each plankton species and the baseline value of each environmental parameter; For each type of plankton, calculate the ratio of its density to the reference density, add 1 to the density ratio and take the natural logarithm to calculate the plankton density component, and then sum the values ​​of all plankton density components to obtain the total plankton density component; For each environmental parameter, calculate the ratio of the current value of the environmental parameter to the reference value, take the square root of the environmental parameter ratio, calculate the environmental parameter part, sum the values ​​of all environmental parameter parts, and obtain the total of the environmental parameter parts; The sum of the plankton density and the environmental parameters is added together, divided by the sum of the number of plankton species and the number of environmental parameters, and multiplied by 100 to obtain the seagrass bed ecological health score.

7. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 6, characterized in that: The expression of the seagrass bed ecological health score is: ； Where P is the ecological health score of the seagrass bed, is the density of the f-th species of plankton, is the baseline density of the f-th species of plankton, is the current value of the gth environmental parameter, is the baseline value of the gth environmental parameter, z is the number of plankton species, p is the number of monitored environmental parameters, and the value range of P is 0 to 100.

8. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 3 is characterized by: The visualization platform specifically includes: The visualization platform receives various monitoring data from the intelligent analysis platform in real time through the data communication transmission module, including plankton image data, environmental parameter data, and seagrass coverage monitoring data. At the same time, it receives real-time images of seagrass beds, seagrass bed area, height, and coverage parameter information, and integrates different types of data; Process and convert the integrated data into a format suitable for front-end display, and perform streaming media processing on the real-time images; The processed data and images are displayed to managers in real time through a visualization platform, and a real-time data update function is provided so that managers can obtain the latest seagrass bed ecological information.

9. The online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to claim 3, characterized in that: The abnormal warning platform specifically includes: The abnormal warning platform continuously receives and monitors the analysis result data stream from the intelligent analysis platform, and tracks the indicators of plankton species and density, and environmental parameters in real time; Compare the real-time monitoring data with the preset abnormality judgment thresholds in the abnormality warning platform to determine abnormal conditions of plankton and environmental parameters; Once an abnormal situation is determined to be established, the abnormal warning platform generates an early warning notification containing the abnormality type, severity, location and time of occurrence, and sends the early warning notification to the relevant management department through multiple communication channels. At the same time, it receives feedback from the relevant management department and further processes and analyzes the early warning notification.

10. A method for online intelligent monitoring of plankton and environmental parameters of a seagrass bed ecosystem, implemented based on the online intelligent monitoring system for plankton and environmental parameters of a seagrass bed ecosystem according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Use the seagrass bed underwater intelligent monitoring terminal to collect plankton images, environmental parameters and seagrass coverage data; S2. The collected monitoring data is sent to the surface relay station via the data communication transmission module and then transmitted back to the intelligent analysis platform; S3. Use machine learning technology to analyze monitoring data, train seagrass bed ecological analysis models, and explore the correlation and changing trends between plankton and environmental parameters in seagrass beds. S4. Display monitoring data and analysis results in real time through a visualization platform; S5. The abnormal warning platform monitors and analyzes the results, and generates and sends warning notifications to the management department when abnormalities are found.

Images