A method and system for controlling filamentous cyanobacteria

Abstract

This invention discloses a method and system for controlling filamentous cyanobacteria, relating to the field of cyanobacterial bloom control. The method includes: real-time acquisition of water quality parameters and meteorological data from a reservoir; prediction of filamentous cyanobacteria density and assessment of bloom risk level based on a machine learning model and the water quality parameters and meteorological data; calculation of a target control rate based on the prediction results and a preset risk threshold, and back-calculation of the theoretically required daily light intake; optimization of sediment concentration and resuspension frequency based on a dynamic model of extinction coefficient to ensure that the actual daily light intake does not exceed the theoretically required daily light intake; and dynamic adjustment of parameters through sediment resuspension operations to achieve the target control rate. This application's solution, through the integration of data-driven and ecological regulation, solves the problems of low efficiency, high environmental risk, and poor adaptability of traditional methods, promoting the evolution of eutrophic water body management towards intelligence, precision, and sustainability.

Description

Technical Field

[0001] This invention relates to the field of cyanobacterial bloom control, and particularly to a method and system for controlling filamentous cyanobacteria.

[0002] Filamentous cyanobacterial blooms are a typical ecological problem in eutrophic waters. Their outbreaks lead to decreased water transparency, depletion of dissolved oxygen, and release of algal toxins, seriously threatening the safety of aquatic ecosystems and human health. In recent years, with the intensification of eutrophication, filamentous cyanobacteria, adapting to low light, low temperature, or nitrogen-phosphorus imbalances, have gradually replaced traditional blooming algae species, becoming the dominant population. Studies have shown that the seasonal dominance of filamentous cyanobacteria is closely related to a decrease in the nitrogen-phosphorus ratio and changes in non-algal turbidity.

[0003] The core challenge in controlling filamentous cyanobacteria in water source reservoirs lies in strictly limiting the addition of chemical agents and maintaining ecological stability. Since water source reservoirs are directly related to drinking water safety, chemical algaecides may produce toxic residues or derivative pollutants, and are therefore strictly prohibited. Currently, methods suitable for controlling filamentous cyanobacteria in water source reservoirs mainly include biological methods, such as microbial agents and phytoalveolar allelopathic effects. However, while these methods are environmentally friendly, they suffer from drawbacks such as long treatment cycles and significant susceptibility to environmental factors. For example, while using garlic juice to inhibit cyanobacteria is effective, it requires frequent preparation of extracts and may negatively impact the water's sensory characteristics due to the garlic odor. Furthermore, traditional techniques for extracting bioactive components from filamentous cyanobacteria suffer from low efficiency and insufficient purity, severely limiting the effectiveness of filamentous cyanobacteria control. Therefore, based on these challenges, this invention proposes a method and system for controlling filamentous cyanobacteria. Summary of the Invention

[0004] Purpose of the invention

[0005] To address the aforementioned problems, the present invention aims to provide a method and system for controlling filamentous cyanobacteria, which addresses the issues of low efficiency, high environmental risk, and operational complexity in existing filamentous cyanobacteria control technologies. This method improves the accuracy of algal bloom risk early warning, optimizes algae control parameters, reduces the cost of artificial intervention, and avoids secondary pollution from chemical agents or biological agents. It is suitable for the long-term ecological restoration of mesotrophic reservoirs.

[0006] Technical solution

[0007] To achieve the above objectives, this invention provides a method and system for controlling filamentous cyanobacteria. The method utilizes an unmanned surface vessel (USV) cruise system to collect water quality parameters and spatial location data in real time. It then uses an XGBoost model to predict algae density and determine risk levels. A linear relationship established through illumination control experiments is used to inversely deduce the theoretical daily light threshold. Based on a dynamic model of sediment resuspension parameters and extinction coefficients designed using orthogonal experiments, an optimized scheme is selected that ensures the actual daily light exposure does not exceed the theoretically required daily light exposure while minimizing cost. Finally, the algae control vessel performs adaptive resuspension operations, dynamically adjusting sediment concentration and release frequency. The system integrates water quality monitoring, data processing, parameter optimization, and execution feedback modules to achieve fully automated control throughout the entire process.

[0008] In a first aspect, the present invention provides a method for controlling filamentous cyanobacteria, comprising:

[0009] Real-time collection of water quality parameters and meteorological data from the reservoir, including pH, water temperature, dissolved oxygen, turbidity, and chlorophyll concentration;

[0010] Based on machine learning models and the water quality parameters and meteorological data, the density of filamentous cyanobacteria is predicted and the risk level of algal blooms is determined.

[0011] The target control rate is calculated based on the prediction results and the preset risk threshold, and the theoretically required daily sunlight intake is calculated in reverse.

[0012] The sediment concentration and resuspension times are optimized based on the dynamic model of extinction coefficient to ensure that the actual daily light intake does not exceed the theoretically required daily light intake.

[0013] The target control rate is achieved by dynamically adjusting parameters through bottom sediment resuspension operations performed by the algae control vessel.

[0014] Furthermore, the real-time acquisition process employs a Z-shaped path planning algorithm to cover the convex locations of the reservoir boundary, and the acquisition trajectory is matched spatiotemporally with water quality parameters via GPS positioning.

[0015] Furthermore, the input variables of the machine learning model also include the mixing layer depth and meteorological conditions (such as solar radiation), and the output is the density prediction value of filamentous cyanobacteria. The model training data covers the seasonal monitoring results of the reservoir.

[0016] Furthermore, the theoretical control rate is calculated by predicting algal density values, and the theoretical light intensity required for algal control is further calculated.

[0017] Furthermore, the method adjusts the underwater light intensity through a gradient light-transmitting film, and the formula for calculating the control rate is:

[0018]

[0019] In the formula, Control rate; For the first Algae density in the sky; For the first Algae density in the sky.

[0020] Furthermore, the dynamic model of the extinction coefficient satisfies:

[0021]

[0022] In the formula, Extinction coefficient; , , The concentration of the sediment; This refers to the sediment settling time. The extinction coefficient of natural water bodies;

[0023] The actual daily light received is dynamically calculated using the extinction coefficient and the mixing layer depth. The calculation logic includes:

[0024] The turbidity of water is determined by both natural turbidity and artificial sediment. The higher the sediment concentration, the greater the extinction coefficient.

[0025] The greater the wind speed, the weaker the water temperature stratification, the stronger the turbulence, and the greater the depth of the mixing layer.

[0026] Furthermore, the optimization of the sediment resuspension parameters includes:

[0027] The sediment concentration range was designed to be 0.1-8.0 g / L through orthogonal experiments, and the resuspension frequency was 1-5 times / day.

[0028] Using actual daily light intake as the optimization objective, we select the combination that satisfies the condition that the actual daily light intake is no greater than the theoretically required daily light intake and has the lowest cost.

[0029] Furthermore, it also includes a dynamic mixing layer depth optimization step, which calculates the mixing layer depth by real-time monitoring of water temperature gradient, turbidity, and meteorological data, combined with fluid dynamics equations, and optimizes the vertical distribution strategy of sediment resuspension. The mixing layer depth is calculated based on the turbulent kinetic energy equation.

[0030]

[0031] In the formula, The depth of the mixing layer; It is the von Kármán constant; The friction speed; The turbulent kinetic energy dissipation rate; This represents the vertical gradient of water temperature.

[0032] This step significantly improves the efficiency of extinction coefficient regulation by accurately matching the actual light intensity distribution, ensuring the scientific nature and stability of the light threshold control for algal cells, thereby enhancing the spatiotemporal adaptability of algae control strategies.

[0033] Furthermore, it also includes a step to enhance extinction by optimizing the particle size distribution of sediment. This is achieved by establishing a particle size-extinction contribution rate function to optimize the particle size distribution ratio of sediment, and by utilizing the Mie scattering effect of fine particles and the shading effect of coarse particles to synergistically enhance light attenuation. The extinction gain equation for the particle size distribution is as follows:

[0034]

[0035] In the formula, For graded extinction gain; The average extinction coefficient of the ungraded sediment.

[0036] This step upgrades single concentration control to multi-dimensional optimization of "particle size composition, shading performance, and sedimentation behavior," providing a scalable physical regulation pathway for the treatment of filamentous cyanobacteria.

[0037] In a second aspect, the present invention also provides a control system for filamentous cyanobacteria, the system being based on the method described in the first aspect above, comprising:

[0038] The unmanned vessel module integrates a water quality sensor, a GPS positioning unit, and a Z-shaped cruise path planning algorithm.

[0039] The data processing module is used to run machine learning models and calculate the target control rate;

[0040] The parameter optimization module generates sediment resuspension parameters based on a dynamic model of the extinction coefficient.

[0041] The execution module performs bottom sediment resuspension operations via the algae control vessel and provides feedback on adjustment parameters.

[0042] Furthermore, the execution module is linked with the meteorological data platform to pause the resuspension operation during continuous rainfall or a sudden drop in sunlight, and to verify the control effect through historical data.

[0043] Furthermore, the algae control vessel is equipped with an adaptive adjustment module, which is used to monitor the underwater light intensity in real time and compare it with the theoretically required daily light intake, and dynamically adjust the amount of bottom sediment added and the resuspension frequency.

[0044] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the aforementioned filamentous cyanobacteria control method.

[0045] This invention constructs a closed-loop control system for filamentous cyanobacteria based on dynamic water quality monitoring, machine learning prediction, and multimodal regulation. Water quality and meteorological data are collected in real time using an unmanned surface vessel (USV) patrol system. Algal density is predicted and the risk level of algal blooms is assessed using an XGBoost model. A quantitative relationship between algal cell control rate and daily light exposure is established through light control experiments, inversely estimating the theoretical light threshold. Furthermore, sediment resuspension parameters are optimized based on orthogonal experiments and a dynamic extinction coefficient model. The single concentration control is upgraded to a multidimensional optimization of "particle size composition, shading performance, and sedimentation behavior" through a gradation extinction gain equation. This scheme, by integrating data-driven approaches with ecological regulation, solves the problems of low efficiency, high environmental risk, and poor adaptability of traditional methods, promoting the evolution of eutrophic water body management towards intelligence, precision, and sustainability.

[0046] Beneficial effects

[0047] By implementing the filamentous cyanobacteria control method and system provided by the present invention, the following technical effects are achieved:

[0048] (1) This application integrates water quality parameters, meteorological data, and geographic information to construct a machine learning prediction framework to dynamically assess the risk level of filamentous cyanobacterial blooms. Compared with traditional statistical models, this algorithm significantly improves prediction accuracy and generalization ability through feature importance analysis and nonlinear relationship fitting, providing a reliable basis for algae control threshold triggering and reducing human error and delayed response.

[0049] (2) Based on orthogonal experiments and a dynamic model of extinction coefficient, a quantitative optimization relationship between sediment concentration and resuspension times is established. This algorithm solves the problems of low efficiency and high resource waste in traditional trial-and-error methods by selecting the lowest cost and conditional combination of working conditions through multi-objective optimization, and realizes adaptive adjustment of algae control parameters and intensive utilization of resources.

[0050] (3) By monitoring water temperature gradient, turbidity, and meteorological parameters in real time, the depth of the mixing layer is dynamically calculated, and the vertical distribution strategy of sediment resuspension is optimized. This model significantly improves the efficiency of extinction coefficient regulation by accurately matching the actual light intensity distribution, ensuring the scientific nature and stability of the light threshold control for algal cells, thereby enhancing the spatiotemporal adaptability of algae control strategies.

[0051] (4) By regulating the physical gradation, the extinction performance is enhanced, the light scattering and shading effects are strengthened, and the duration of the extinction coefficient is improved. By optimizing the sedimentation dynamics, the shading continuity is maintained, the proportion of fine particles is reduced, and their rapid sedimentation tendency is suppressed, ensuring that the shading layer stably covers the algae-rich area. By expanding the deep-water shading layer, the system adaptability is enhanced, and the gradation is optimized to increase the effective shading layer thickness, solving the core contradiction of the misalignment between the shading layer and the vertical distribution of algae in traditional deep-water reservoirs. This model upgrades single concentration control to multi-dimensional optimization of particle size distribution, shading performance, and sedimentation behavior, providing an engineerable physical regulation path for the treatment of filamentous cyanobacteria. Attached Figure Description

[0052] To make the above-described method and system for controlling filamentous cyanobacteria of the present invention more apparent and understandable, the accompanying drawings used in the specific embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating the method described in this application;

[0054] Figure 2 This shows the system architecture diagram of this application. Detailed Implementation

[0055] Example 1:

[0056] A method for controlling filamentous cyanobacteria is provided, the method flow is as follows: Figure 1 As shown, the process includes: real-time acquisition of water quality parameters and meteorological data of the reservoir, including water quality parameters such as pH, water temperature, dissolved oxygen, turbidity, and chlorophyll concentration; prediction of filamentous cyanobacteria density and assessment of algal bloom risk level based on a machine learning model and the water quality parameters and meteorological data; calculation of the target control rate based on the prediction results and preset risk thresholds, and back-calculation of the theoretically required daily light intake; optimization of sediment concentration and resuspension times based on a dynamic model of extinction coefficient to ensure that the actual daily light intake does not exceed the theoretically required daily light intake; and dynamic adjustment of parameters to achieve the target control rate by performing sediment resuspension operations using an algae control vessel.

[0057] A control system for filamentous cyanobacteria is also provided, the system being based on the aforementioned method, and its architecture is as follows: Figure 2 As shown, it includes: an unmanned surface vessel module, integrating a water quality sensor, a GPS positioning unit, and a Z-shaped cruise path planning algorithm; a data processing module, used to run machine learning models and calculate target control rates; a parameter optimization module, which generates sediment resuspension parameters based on a dynamic model of extinction coefficients; and an execution module, which implements sediment resuspension operations through the algae control vessel and provides feedback on adjustment parameters.

[0058] The details are as follows.

[0059] There is a reservoir with an area of With an average water depth of 10m and a summer water temperature of 22-28℃, it is a mesotrophic water body, with filamentous cyanobacteria as the dominant algal species.

[0060] The unmanned vessel is equipped with a multi-parameter water quality sensor, a water temperature profiler (0-10m stratified monitoring), and a solar radiation sensor. The algae control vessel is equipped with a dual-propeller disturbance device and a three-stage vibrating screening device (100-mesh fine particle screen and 20-mesh coarse particle screen).

[0061] The data processing platform is an Alibaba Cloud ECS server, which deploys the XGBoost 1.6.0 model and the dynamic hybrid layer depth calculation algorithm.

[0062] The unmanned vessel was set to cruise along a Z-shaped path, covering the central area of ​​the reservoir and five boundary grooves. The cruise speed was 1.5 m / s, and data was collected every 15 minutes for 7 consecutive days.

[0063] Based on a real-time wind speed of 3.2 m / s, Vertical gradient of water temperature and Turbulent kinetic energy dissipation rate, dynamically calculated :

[0064]

[0065] The model input includes nine water quality parameters collected over seven days (pH value). turbidity is chlorophyll is (and meteorological data).

[0066] The predicted output is algal density. Triggering risk level 1 (threshold) ).

[0067] In-situ sediment particle size includes: fine particles ( ) accounted for 38%, medium particles ( 45%, coarse particles ( 17%;

[0068] Calculate the extinction gain of the graded gradation:

[0069]

[0070] Solve for the optimal gradation index:

[0071]

[0072] Optimize the gradation adjustment to , , .

[0073] Target control rate:

[0074] ;

[0075] Theoretical illumination threshold:

[0076] ;

[0077] The gradation parameters are sourced from the laboratory as shown in Table 1.

[0078] Table 1. Sources of gradation parameters

[0079]

[0080] Initial particle size distribution: fine particles 38% optimized to 25%, medium particles 45% optimized to 55%, and coarse particles 17% optimized to 20%;

[0081] Time-weighted average extinction coefficient:

[0082] ;

[0083] Obtained from the settling experiment fitting curve, within 48 hours It dropped from 4.2 to 3.6. .

[0084] Select parameters: , Next / day, forecast .

[0085] The algae control vessel's screening device is set as follows: fine particles, 100 mesh screen, 30.5 Hz, 25% mixing ratio; medium particles, 55% mixing ratio; coarse particles, 20 mesh screen, 20.5 Hz, 20% mixing ratio. Optimized resuspension of the gradation is performed at 9:00, 13:00, and 17:00 daily, with a propeller speed of 1200 rpm.

[0086] The key parameters of the algae control cycle are compared in Table 2.

[0087] Table 2. Comparison of key parameters in the algae control cycle

[0088]

[0089] According to the experimental table, the actual... Exceeding theoretical requirements This demonstrates that gradation optimization can improve shading efficiency, achieving algae control standards earlier than the preset cycle; the light intensity at a depth of 8 m was reduced to 1.2 after gradation optimization. The method covers the bottom of the mixed layer; the proportion of coarse particles is increased to 20%, the settling rate is reduced by 37%, and the turbidity maintenance time is guaranteed; the amount of bottom sediment is reduced by 12.5%, and the resuspension frequency is reduced by 30%. The practical application effect of this method in mesotrophic reservoirs has been verified, achieving efficient inhibition of filamentous cyanobacteria and ecological safety regulation, and providing a replicable technical paradigm for the treatment of similar water bodies.

[0090] Example 2:

[0091] The mixing layer depth is a key parameter affecting the amount of light received by algal cells, and its dynamic changes directly influence the light attenuation rate and algae control efficiency. In traditional methods, the mixing layer depth is often calculated using a fixed value or empirical estimation, leading to a mismatch between the algae control parameters and the actual light intensity distribution in the water layer. Building upon the aforementioned embodiments, a dynamic mixing layer depth optimization model is added. By monitoring water temperature gradients, turbidity, and meteorological data in real time, and combining this with fluid dynamics equations, the mixing layer depth is dynamically calculated. This optimizes the vertical distribution strategy of sediment resuspending, ensuring maximum light suppression efficiency.

[0092] The unmanned vessel is equipped with multi-parameter sensors to collect data on the vertical profile of water temperature, turbidity, and surface solar radiation intensity every 15 minutes.

[0093] Calculation of mixing layer depth based on modified turbulent kinetic energy equation:

[0094]

[0095] In the formula, The depth of the mixing layer; It is the von Kármán constant; The friction speed; The turbulent kinetic energy dissipation rate; This represents the vertical gradient of water temperature.

[0096] Adjust the sediment resuspension concentration and addition depth in real time according to the mixing layer depth to ensure that the extinction coefficient meets the requirements. .

[0097] Verification shows that, while achieving an average error similar to that of the above embodiments, the dynamic model increases the algae control rate in reservoir applications to [a higher level]. The phosphorus removal efficiency was increased to 85%, and the redox potential of the sediment remained stable above +120 mV. The results show that this model significantly improved the accuracy of extinction coefficient control by dynamically adjusting the mixing layer depth. Compared with the traditional fixed-depth strategy, the model can respond in real time to changes in water temperature gradient and turbulence, optimize the vertical distribution of sediment resuspended, and ensure that the light exposure of algal cells remains below the theoretical threshold.

[0098] Example 3:

[0099] Building upon the aforementioned embodiments, and considering the issue of unstable shading effects due to the lack of control over particle size distribution in traditional resuspension operations, a sediment particle gradation optimization model to enhance extinction was added. By establishing a particle size-extinction contribution rate function, the sediment particle gradation ratio was optimized, utilizing the Mie scattering effect of fine particles and the shading effect of coarse particles to synergistically enhance light attenuation. At the same sediment concentration, gradation optimization can significantly reduce the amount of light received by algal cells.

[0100] The in-situ bottom sediment of the reservoir was screened into three grades:

[0101] Fine particles (0-10) ): quality score Unit extinction coefficient ;

[0102] Medium particles (10-50) ): quality score Unit extinction coefficient ;

[0103] Coarse particles (>50) ): quality score Unit extinction coefficient .

[0104] Establish the graded extinction gain equation:

[0105]

[0106] In the formula, To improve the extinction coefficient, quantization particle size optimization is used to enhance the extinction gain. The average extinction coefficient of ungraded sediment is preferably [value missing]. .

[0107] Define the optimal gradation index ( OCI Maximize extinction and minimize fine particle settling rate:

[0108]

[0109] The constraints are: ;

[0110] Find the optimal solution: , , .

[0111] The algae control vessel is equipped with a three-stage vibrating screening device, which dynamically adjusts the screen frequency during resuscitation.

[0112] Fine particle sieve (100 mesh): amplitude 2.0 mm, frequency 25 Hz;

[0113] Coarse particle sieve (20 mesh): amplitude 1.5 mm, frequency 15 Hz.

[0114] Based on real-time extinction coefficient feedback, the three-stage particles are mixed in proportion:

[0115] In the formula, This is the frequency adjustment amount.

[0116] The effects of optimized sediment particle size distribution on the enhanced matting model are shown in Table 3.

[0117] Table 3. Summary of the effects of optimized sediment particle size distribution on enhancing matting model

[0118]

[0119] According to the experimental table, in reservoir applications, the algae density decreased to The time was reduced from 10 days to 7 days; under the same algae control effect, the optimized gradation improved the extinction efficiency and reduced the amount of bottom sediment by 28%; the proportion of fine particles was reduced to 25%, the sediment settling time was extended by 2.1 times, and the resuspension frequency was reduced by 40%. Experimental data showed that the Mie scattering effect of fine particles and the shading effect of coarse particles formed a synergistic effect. Under the same sediment concentration, the spatial uniformity and temporal stability of the extinction coefficient were significantly enhanced, effectively suppressing the fluctuation of light received by algal cells; the optimized gradation ratio reduced the tendency of fine particles to settle rapidly, extended the duration of shading effect, and reduced the frequency of resuspension operation; in deep water, the optimized gradation combination effectively covered the main area of ​​the mixed layer in terms of light attenuation depth, overcoming the shading limitations of traditional resuspension in deep water areas.

[0120] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media containing computer-usable program code.

[0121] The present invention can provide computer program instructions to a management platform of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to produce a machine, such that the instructions executed by the management platform of the computer or other programmable data processing equipment produce means for implementing the system.

[0122] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that perform the functions of the system.

[0123] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions of the system.

Claims

1. A method for controlling filamentous cyanobacteria, characterized by, include: Real-time collection of water quality parameters and meteorological data of the reservoir; Based on machine learning models and the water quality parameters and meteorological data, the density of filamentous cyanobacteria is predicted and the risk level of algal blooms is determined. The underwater light intensity is adjusted by using a gradient light-transmitting membrane, and the target control rate is calculated based on the prediction results and a preset risk threshold, thus inferring the theoretically required daily light intake. The formula for calculating the target control rate is as follows: wherein is the target control rate; is the preset risk threshold algal density; is the predicted output algal density; The sediment concentration and resuspension times are optimized based on the dynamic model of extinction coefficient to ensure that the actual daily light intake does not exceed the theoretically required daily light intake. The target control rate is achieved by dynamically adjusting parameters through the bottom sediment resuspension operation. It also includes a step to enhance extinction by optimizing the particle size distribution of sediment. This involves optimizing the particle size distribution ratio of sediment by establishing a particle size-extinction contribution rate function, and using the Mie scattering effect of fine particles and the shading effect of coarse particles to synergistically enhance light attenuation.

2. The method according to claim 1, characterized in that: The real-time data acquisition process employs a Z-shaped path planning algorithm, covering the convex locations of the reservoir boundary. The acquisition trajectory is matched with water quality parameters in time and space via GPS positioning.

3. The method according to claim 1, characterized in that: The input variables of the machine learning model also include the mixing layer depth and meteorological conditions, and the output is the density prediction value of filamentous cyanobacteria. The model training data covers the seasonal monitoring results of the reservoir.

4. The method according to claim 1, characterized in that: It also includes a dynamic mixing layer depth optimization step, which calculates the mixing layer depth by real-time monitoring of water temperature gradient, turbidity and meteorological data, combined with fluid dynamics equations, and optimizes the vertical distribution strategy of bottom sediment resuspension.

5. A control system for filamentous cyanobacteria, characterized in that: The system is implemented based on the method described in any one of claims 1-4: The system includes: The unmanned vessel module integrates a water quality sensor, a GPS positioning unit, and a Z-shaped cruise path planning algorithm. The data processing module is used to run machine learning models and calculate the target control rate; The parameter optimization module generates sediment resuspension parameters based on a dynamic model of the extinction coefficient. The execution module performs bottom sediment resuspension operations via the algae control vessel and provides feedback on adjustment parameters.

6. The system according to claim 5, characterized in that: The execution module is linked with the meteorological data platform. It pauses the resuspension operation during continuous rainfall or a sudden drop in sunlight and verifies the control effect through historical data.

7. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by the processor to perform the method according to any one of claims 1-4.

Images