An ecological management method and system based on the interaction between seawater pond bacteria and algae
By acquiring water quality information from seawater ponds, determining the survival probability of bacteria and algae and the detection scheme, and utilizing data analysis and neural network simulation, we have achieved precise monitoring and regulation of the interaction process between bacteria and algae, solved the problem of delayed prediction of water quality changes, and improved the stability and self-purification capacity of the pond ecosystem.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SOUTH CHINA SEA FISHERIES RES INST CHINESE ACAD OF FISHERY SCI
- Filing Date
- 2026-05-06
- Publication Date
- 2026-06-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies are insufficient for real-time and accurate monitoring and regulation of the interaction between bacteria and algae in seawater ponds, resulting in delayed prediction of water quality changes, a lack of scientific basis for nutrient supplementation programs, and an inability to achieve efficient balance and stability of the bacteria-algae system.
By acquiring water quality information at different locations in the pond, the survival probability of bacteria and algae is determined, a detection plan is designed, data on the distribution and interaction of bacteria and algae are obtained, principal component analysis and long short-term memory neural networks are used for simulation and prediction, and combined with aquatic environmental data, material exchange relationships are identified, and nutrient supplementation and optimization are carried out.
It enables precise monitoring and dynamic control of the interaction between bacteria and algae in seawater ponds, improves water quality management efficiency, maintains the ecological balance of ponds, and enhances their self-purification capacity.
Smart Images
Figure CN122144900A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of marine aquaculture and environmental control technology, and in particular to an ecological management method and system based on the interaction between bacteria and algae in seawater ponds. Background Technology
[0002] As the marine aquaculture industry rapidly develops towards intensification and large-scale operations, the high-density, high-feeding production model, while significantly increasing yields, has also brought severe ecological and environmental challenges. Among these, eutrophication of aquaculture waters, drastic fluctuations in water quality indicators (such as ammonia nitrogen, nitrite, and dissolved oxygen), and frequent outbreaks of harmful algal blooms are particularly prominent. These problems not only directly affect the health and survival of farmed organisms and restrict the sustainable development of the industry, but also pose a potential threat to the nearshore marine ecosystem.
[0003] Traditional methods of managing seawater pond water quality often rely on physical filtration, chemical agents, or the application of single microbial agents. These methods are often only treating the symptoms, not the root cause, are costly, and may lead to secondary pollution or disrupt the original micro-ecological balance of the water body. Seawater ponds are complex ecosystems where bacteria and algae form a close "bacterial-algae interaction" through nutrient absorption and the exchange and utilization of metabolic products. This interaction is the core driving force of water body material cycling and energy flow, playing a crucial role in maintaining water quality stability. However, current capabilities for dynamic monitoring, quantitative analysis, and precise control of this interaction process are severely lacking. Existing technologies struggle to obtain real-time and accurate information on the spatiotemporal distribution of bacteria and algae within the pond and the dynamic changes in the flow of interacting substances. This results in delayed predictions of water quality changes, and nutrient supplementation plans are often based on experience and lack scientific basis. The targeted and timely control measures are also inadequate, failing to achieve efficient balance and stability of the bacterial-algae system.
[0004] Therefore, there is an urgent need for an intelligent ecological management method that can deeply integrate monitoring, simulation and control, accurately depict and proactively optimize the interaction process between bacteria and algae in ponds, so as to fundamentally improve the self-purification capacity and ecological stability of marine aquaculture systems and achieve environmentally friendly green aquaculture. Summary of the Invention
[0005] To address at least one of the aforementioned technical problems, this invention proposes an ecological management method and system based on the interaction between bacteria and algae in seawater ponds.
[0006] The first aspect of this invention provides an ecological management method based on the interaction between bacteria and algae in a seawater pond, comprising: Obtain water quality information at different locations in the target seawater pond, determine the survival probability of bacteria and algae based on the water quality information at different locations, determine the bacteria and algae detection scheme for the target seawater pond based on the bacteria and algae survival probability, and obtain the distribution data of bacteria and algae and the change data of bacteria and algae interaction substances in the target seawater pond based on the bacteria and algae detection scheme. Based on the material change data of the bacterial-algal interaction, the material change characteristics of the bacterial-algal interaction are determined. Based on the material change characteristics and the bacterial-algal distribution data, the material change characteristics of the bacterial-algal interaction in the target seawater pond in the future preset time period are simulated to obtain simulated material change data of the interaction. The balance state of bacterial-algal interaction is determined based on the simulated interaction material change data, and the impact of bacteria and algae on the water quality of the target seawater pond is determined based on the bacterial-algal interaction balance state. Based on the aforementioned impact, nutrients for the bacterial-algal interaction are supplemented, and the balance efficiency of the bacterial-algal interaction after the supplementation of nutrients is determined. The bacterial-algal interaction balance efficiency was optimized.
[0007] In this scheme, the steps of acquiring water quality information at different locations in the target seawater pond, determining the survival probability of bacteria and algae based on the water quality information at different locations, determining a bacteria and algae detection scheme for the target seawater pond based on the bacteria and algae survival probability, and acquiring bacteria and algae distribution data and bacteria-algae interaction substance change data of the target seawater pond based on the bacteria and algae detection scheme are as follows: Historical water quality information and historical bacterial and algal species and concentration data of different sampling points in the target seawater pond within a set historical time period are obtained to establish a mapping relationship model between water quality parameters and bacterial and algal survival status, and the weight data of the impact of different combinations of water quality parameters on the survival of various bacterial and algal species are determined based on the mapping relationship model. Obtain water quality information of the target seawater pond at different locations at the current time, input the water quality information of the target seawater pond at different locations at the current time into the mapping relationship model, and calculate the survival probability of various bacteria and algae at different locations of the target seawater pond at the current time. Based on the survival probability of bacteria and algae, the regions with a survival probability higher than a preset probability threshold are identified as bacteria and algae enrichment regions, and the regions with a survival probability lower than the preset probability threshold are identified as bacteria and algae sparse regions. Based on the spatial distribution of the bacterial and algae enrichment area and the bacterial and algae sparse area, a bacterial and algae detection scheme is determined, and bacterial and algae distribution data and bacterial and algae interaction substance change data of the target seawater pond are obtained according to the bacterial and algae detection scheme.
[0008] In this scheme, the determination of the algae detection scheme based on the spatial distribution of the algae-rich area and the algae-sparse area, and the acquisition of algae distribution data and algae interaction substance change data of the target seawater pond according to the algae detection scheme, specifically includes: Based on the spatial distribution of the algae-rich and algae-sparse areas, determine the algae detection sampling density and sampling frequency for each detection area, and deploy microfluidic devices in each area according to the sampling density. The volume characteristic data of the main bacterial species and algae in the target seawater pond are obtained to determine the first aperture range that can effectively intercept the target bacterial species and algae while allowing water to pass through. The screen aperture for bacterial and algae interception is selected according to the first aperture range. Based on the sieve aperture configuration, test sieves were used, and standard solutions containing target bacterial species and algae with known concentration gradients were flowed through the test sieves at different flow rates. The actual retention rate of the target bacterial species by the test sieves at different flow rates was measured and recorded, and a dataset of flow rate-retention rate correspondence was generated. Based on the velocity-retention rate correspondence dataset, the optimal velocity range corresponding to the preset retention efficiency threshold is determined by fitting analysis. The viscosity and impurity content data of the target seawater pond are obtained. Combined with the optimal velocity range, the clogging risk coefficient of the surface pores of the screen with the selected aperture is analyzed by fluid dynamics simulation under different impact times when it works in the optimal velocity range. Based on the clogging risk coefficient and the preset acceptable clogging risk threshold, the longest single impact time that can maintain the effective working time of the screen under the premise of meeting the preset interception efficiency is determined, and the optimal flow rate range and the longest single impact time are set together as the impact flow rate and impact time working parameters of the microfluidic device for intercepting bacteria and algae on the screen. Within a preset sampling period, the microfluidic device in each detection area impacts the screen with a selected bacterial and algae interception aperture according to the working parameters of the impact flow rate and impact time. The intercepted material and filtered water sample after being processed by the microfluidic device are collected. The intercepted material is subjected to bacterial isolation, culture and identification. The bacterial and algae species composition and abundance data of different sampling points are obtained to obtain the bacterial and algae distribution data of the target seawater pond. Acquire data on changes in dissolved oxygen, pH, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations in the water body within a preset sampling period, and output the changes as bacterial and algal interaction substance change data.
[0009] In this scheme, the process of determining the material change characteristics of bacterial-algal interactions based on the material change data of bacterial-algal interactions, and simulating the material change characteristics of bacterial-algal interactions in a target seawater pond over a future preset time period based on the material change characteristics and bacterial-algal distribution data, to obtain simulated interaction material change data, specifically includes: Principal component analysis was used to reduce the dimensionality of the material changes in the bacterial-algal interaction in the target seawater pond, and the core material change characteristics of the dominant bacterial-algal interaction process were extracted, including the rate of change of nitrogen and phosphorus nutrient concentrations, the daily variation of dissolved oxygen, and the slope and intercept of the metabolic product concentration change curve. The water environment data of the target seawater pond within a preset sampling period is obtained, including water temperature, light transmittance, water depth, and hydrodynamic data. The bacterial and algal distribution data, the core substance change characteristics, and the aquatic environment data are spatiotemporally aligned to construct a multidimensional feature dataset. A simulation model of material changes in bacterial-algal interactions is constructed based on a long short-term memory neural network. The model is trained by taking the multidimensional feature dataset as input and the core material change features of the next time step as output. An attention mechanism is introduced to enhance the model's sensitivity to water temperature and light transmittance in the water environment data. The current distribution data of bacteria and algae, the change characteristics of the core substances, and the predicted water environment data for a future preset time period are input into the trained simulation model. The simulation model uses its internal memory unit and attention mechanism to iteratively simulate the dynamic change sequence of the change characteristics of the core substances within the future preset time period. The dynamic change sequence was restored to simulated interaction substance change data containing the changing trends of dissolved oxygen, pH value, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations.
[0010] In this scheme, determining the bacterial-algal interaction equilibrium state based on the simulated interaction substance change data, and determining the impact of bacteria and algae on the water quality of the target seawater pond based on the bacterial-algal interaction equilibrium state, specifically involves: Based on the species composition and abundance information of each bacterial and algal species in the bacterial and algal distribution data, and combined with the changing trends of various substances in the bacterial-algal interaction substance change data, the types of substances involved in the metabolism of different bacterial and algal species and their direction of action are identified, and the correspondence between the consumption pathway of organic matter and nutrients by bacteria and the absorption of nutrients and release of metabolites by algae is established. Based on the correspondence, a correlation mapping of material supply and consumption between bacteria and algae is constructed. According to the correlation mapping, the input and output changes of various substances in the continuous time series are aligned. The pairing relationship between the substances consumed by bacteria and the substances released by algae, as well as between the substances absorbed by algae and the substances released by bacteria, is extracted to form exchange relationship data that characterizes the correspondence of material supply and consumption between bacteria and algae. The exchange relationship data is matched and analyzed with the simulated interaction material change data to determine whether the supply and consumption of various substances during the simulated interaction material change process meet the exchange relationship, and the change data of shortage and excess substances that do not meet the exchange relationship during the bacterial-algae interaction process are extracted. Based on the data on changes in scarce and abundant substances, the metabolic restriction or enrichment status of the corresponding bacterial or algal species is determined. Combined with the accumulation and reduction trends of scarce and abundant substances in the water body, the changes in dissolved oxygen, the degree of nutrient enrichment, and the residual status of metabolic products are analyzed to obtain the water quality impact data of the target seawater pond.
[0011] In this scheme, the replenishment of nutrients for the bacterial-algal interaction based on the aforementioned impact, and the determination of the balance efficiency of the bacterial-algal interaction after the replenishment of nutrients, specifically involves: Based on the water quality impact, identify the types of nutrients that are deficient in the target seawater pond, and determine the supplementation range for each deficient nutrient based on the change data of the deficient and excess substances. Acquire the bacterial and algal distribution data and hydrodynamic data of the target seawater pond, determine the spatial aggregation area of the target bacterial species and algae based on the bacterial and algal distribution data, and predict the diffusion path and diffusion rate of the nutrient placement location in the water body through particle tracking simulation in combination with the hydrodynamic data. The location for nutrient delivery is determined based on the diffusion path and diffusion rate. Nutrients are then delivered at the location, and the response characteristics of changes in bacterial-algal interaction substances after nutrient supplementation are extracted. Based on the material change response characteristics of the bacterial-algal interaction, the material exchange relationship between bacteria and algae is rematched to determine the degree of coordination between the supply and consumption of various substances, and the balance efficiency of bacterial-algal interaction after the supplementation of nutrients is determined according to the degree of coordination.
[0012] In this scheme, the optimization of bacterial-algal interactions based on the bacterial-algal interaction balance efficiency specifically includes: If the balance efficiency of the bacterial-algal interaction is lower than the preset balance efficiency, the effective absorption rate of the bacterial-algal interaction substances by the bacteria and algae for the applied nutrients is determined according to the response characteristics of the bacterial-algal interaction substances. When the effective absorption rate is lower than the preset absorption rate threshold, the concentration change data of the unused remaining nutrients in the water body are extracted, and combined with the metabolic demand rate of each bacterial species and algae in the bacterial and algal distribution data, the correlation between the nutrient consumption rate and the remaining concentration is constructed. Based on the aforementioned correlation, the consumption slope of different nutrients in the continuous time series was fitted and analyzed to determine the target supply rate range required to maintain the metabolic balance of bacteria and algae. The slow-release amount of each supplementary nutrient per unit time is determined based on the target supply rate range, and the nutrient delivery time is optimized based on the slow-release amount.
[0013] A second aspect of the present invention also provides an ecological management system based on the interaction between bacteria and algae in a seawater pond. The system includes a memory and a processor. The memory includes a program for an ecological management method based on the interaction between bacteria and algae in a seawater pond. When the program for the ecological management method based on the interaction between bacteria and algae in a seawater pond is executed by the processor, it implements the steps of the ecological management method based on the interaction between bacteria and algae in a seawater pond as described in any of the above claims.
[0014] This invention discloses an ecological management method and system based on the interaction between bacteria and algae in a seawater pond. The method includes: acquiring water quality information at different locations in a target seawater pond; determining the survival probability of bacteria and algae and the detection scheme accordingly to obtain data on the distribution of bacteria and algae and changes in the interaction substances; determining the characteristics of the changes in substances based on the change data, and simulating the changes in the interaction substances over a predetermined time period in conjunction with the distribution data; determining the balance state of the bacteria-algae interaction and its impact on water quality; supplementing the nutrients required for the interaction based on the impact, and evaluating the effectiveness of the supplemented balance; and finally optimizing the interaction based on this effectiveness. This method achieves precise monitoring, simulation prediction, and dynamic control of the bacteria-algae system in a seawater pond, helping to maintain the ecological balance of the pond and improve the efficiency of water quality management. Attached Figure Description
[0015] Figure 1 A flowchart of an ecological management method based on the interaction between bacteria and algae in a seawater pond, according to the present invention, is shown. Figure 2 The flowchart of the present invention simulates the material change characteristics of the bacterial-algal interaction in a target seawater pond. Figure 3 The flowchart of the present invention for optimizing bacterial-algal interactions based on the balance efficiency of bacterial-algal interactions is shown. Figure 4 A block diagram of an ecological management system based on the interaction between bacteria and algae in a seawater pond, according to the present invention, is shown. Detailed Implementation
[0016] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.
[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.
[0018] Figure 1 A flowchart of an ecological management method based on the interaction between bacteria and algae in a seawater pond, according to the present invention, is shown.
[0019] like Figure 1 As shown, the first aspect of the present invention provides an ecological management method based on the interaction between bacteria and algae in a seawater pond, comprising: S102, Obtain water quality information at different locations in the target seawater pond, determine the survival probability of bacteria and algae based on the water quality information at different locations, determine the bacteria and algae detection scheme for the target seawater pond based on the bacteria and algae survival probability, and obtain the distribution data of bacteria and algae and the change data of bacteria and algae interaction substances in the target seawater pond based on the bacteria and algae detection scheme. S104, determine the material change characteristics of the bacterial-algal interaction based on the material change data of the bacterial-algal interaction, and simulate the material change characteristics of the bacterial-algal interaction in the target seawater pond in the future preset time period based on the material change characteristics and the bacterial-algal distribution data to obtain simulated interaction material change data. S106, Determine the bacterial-algal interaction balance state based on the simulated interaction material change data, and determine the impact of bacteria and algae on the water quality of the target seawater pond based on the bacterial-algal interaction balance state. S108, Supplement the bacteria-algae interaction nutrients according to the aforementioned influence, and determine the bacteria-algae interaction balance efficiency after supplementing the bacteria-algae interaction nutrients. S110, optimize the bacterial-algal interaction based on the bacterial-algal interaction balance efficiency.
[0020] It should be noted that by acquiring water quality information from different locations in the pond, the survival probability of bacteria and algae is assessed, and this information guides the development of precise detection plans, thereby efficiently acquiring data on the distribution and material changes of bacteria and algae. Based on this, the core material change characteristics of bacterial-algae interactions are extracted, and combined with bacterial-algae distribution information, future water quality dynamics are simulated and predicted. By analyzing the simulation data, the balance state of bacterial-algae interactions and their actual impact on water quality can be accurately determined. Furthermore, the system can selectively supplement key nutrients based on the impact on water quality and evaluate the ecological balance effectiveness after supplementation. Finally, based on the evaluation results, the bacterial-algae interaction process is optimized and regulated, achieving full-process ecological management from intelligent diagnosis and precise prediction to proactive intervention, effectively improving the stability and self-purification capacity of seawater pond water quality.
[0021] According to an embodiment of the present invention, the steps of acquiring water quality information at different locations in a target seawater pond, determining the survival probability of bacteria and algae based on the water quality information at different locations, determining a bacteria and algae detection scheme for the target seawater pond based on the bacteria and algae survival probability, and acquiring bacteria and algae distribution data and bacteria-algae interaction substance change data of the target seawater pond based on the bacteria and algae detection scheme are as follows: Historical water quality information and historical bacterial and algal species and concentration data of different sampling points in the target seawater pond within a set historical time period are obtained to establish a mapping relationship model between water quality parameters and bacterial and algal survival status, and the weight data of the impact of different combinations of water quality parameters on the survival of various bacterial and algal species are determined based on the mapping relationship model. Obtain water quality information of the target seawater pond at different locations at the current time, input the water quality information of the target seawater pond at different locations at the current time into the mapping relationship model, and calculate the survival probability of various bacteria and algae at different locations of the target seawater pond at the current time. Based on the survival probability of bacteria and algae, the regions with a survival probability higher than a preset probability threshold are identified as bacteria and algae enrichment regions, and the regions with a survival probability lower than the preset probability threshold are identified as bacteria and algae sparse regions. Based on the spatial distribution of the bacterial and algae enrichment area and the bacterial and algae sparse area, a bacterial and algae detection scheme is determined, and bacterial and algae distribution data and bacterial and algae interaction substance change data of the target seawater pond are obtained according to the bacterial and algae detection scheme.
[0022] It should be noted that water quality parameters at different locations in a seawater pond directly affect the metabolic activity, growth rate, and population competition of bacteria and algae. Different bacteria and algae exhibit significant differences in their adaptability and sensitivity to various water quality parameters. Therefore, by performing correlation analysis on water quality information at each sampling point and corresponding bacterial and algal species and concentration data within a set historical time period, a mapping model reflecting the intrinsic relationship between water quality conditions and the survival status of bacteria and algae can be established. This allows the impact of various combinations of water quality parameters on bacterial and algal survival to be quantitatively expressed in weighted form. Based on this, by inputting the water quality information at different locations at the current moment into the mapping model, the probability of supporting the survival and reproduction of specific bacteria and algae at each location under the current water quality conditions can be calculated based on the learned parameter interaction patterns. This yields spatially differentiated bacterial and algal survival probabilities, enabling quantitative inference from water quality information to the survival status of bacteria and algae. The water quality information includes the water's pH, dissolved oxygen concentration, nitrogen and phosphorus nutrient concentration, water temperature, and pH value.
[0023] According to an embodiment of the present invention, the step of determining a bacterial and algal detection scheme based on the spatial distribution of the bacterial and algal enrichment zone and the bacterial and algal sparse zone, and obtaining bacterial and algal distribution data and bacterial and algal interaction substance change data of the target seawater pond according to the bacterial and algal detection scheme, specifically includes: Based on the spatial distribution of the algae-rich and algae-sparse areas, determine the algae detection sampling density and sampling frequency for each detection area, and deploy microfluidic devices in each area according to the sampling density. The volume characteristic data of the main bacterial species and algae in the target seawater pond are obtained to determine the first aperture range that can effectively intercept the target bacterial species and algae while allowing water to pass through. The screen aperture for bacterial and algae interception is selected according to the first aperture range. Based on the sieve aperture configuration, test sieves were used, and standard solutions containing target bacterial species and algae with known concentration gradients were flowed through the test sieves at different flow rates. The actual retention rate of the target bacterial species by the test sieves at different flow rates was measured and recorded, and a dataset of flow rate-retention rate correspondence was generated. Based on the velocity-retention rate correspondence dataset, the optimal velocity range corresponding to the preset retention efficiency threshold is determined by fitting analysis. The viscosity and impurity content data of the target seawater pond are obtained. Combined with the optimal velocity range, the clogging risk coefficient of the surface pores of the screen with the selected aperture is analyzed by fluid dynamics simulation under different impact times when it works in the optimal velocity range. Based on the clogging risk coefficient and the preset acceptable clogging risk threshold, the longest single impact time that can maintain the effective working time of the screen under the premise of meeting the preset interception efficiency is determined, and the optimal flow rate range and the longest single impact time are set together as the impact flow rate and impact time working parameters of the microfluidic device for intercepting bacteria and algae on the screen. Within a preset sampling period, the microfluidic device in each detection area impacts the screen with a selected bacterial and algae interception aperture according to the working parameters of the impact flow rate and impact time. The intercepted material and filtered water sample after being processed by the microfluidic device are collected. The intercepted material is subjected to bacterial isolation, culture and identification. The bacterial and algae species composition and abundance data of different sampling points are obtained to obtain the bacterial and algae distribution data of the target seawater pond. Acquire data on changes in dissolved oxygen, pH, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations in the water body within a preset sampling period, and output the changes as bacterial and algal interaction substance change data.
[0024] It should be noted that due to significant differences in the survival probabilities of bacteria and algae in different regions, the enriched areas contain a high density and diverse species of bacteria and algae, while the sparse areas have a limited quantity and scattered distribution. Using uniform or random sampling schemes could not only waste significant testing resources but also lead to insufficient data representativeness, failing to accurately reflect the actual distribution pattern of bacteria and algae in the pond. By determining the sampling density and frequency of each testing area based on the spatial distribution of the enriched and sparse areas, sampling is more intensive in high-density areas and moderate in low-density areas, ensuring both sufficient and efficient data collection. Simultaneously, by combining the microfluidic device with optimized screen aperture design, efficient retention of target bacteria and algae is achieved under different flow rates and impact times, ensuring that the collected samples contain the target bacteria and algae without distortion or sample loss due to screen blockage or excessive flow rate. This spatially distributed differentiated sampling strategy significantly improves the identification rate of bacteria and algae species and the accuracy of abundance determination, while reducing the incidence of duplicate testing and invalid sample collection. The microfluidic device is a low-power pumping unit that directs the pumped seawater from the pond towards a screen for the trapping of bacteria and algae. The algae studied here are microalgae, not macroalgae. Data on changes in bacterial-algal interaction materials refers to a comprehensive dataset obtained through monitoring and analysis over a specific time period, reflecting the dynamic changes in various key water quality parameters caused by metabolic activities, material exchange, and energy flow between bacterial and algal communities in a seawater pond.
[0025] Figure 2 The flowchart illustrates the simulation of material change characteristics of bacterial-algal interactions in a target seawater pond according to the present invention.
[0026] According to an embodiment of the present invention, the step of determining the material change characteristics of the bacterial-algal interaction based on the material change data of the bacterial-algal interaction, and simulating the material change characteristics of the bacterial-algal interaction in a target seawater pond over a future preset time period based on the material change characteristics and the bacterial-algal distribution data, to obtain simulated interaction material change data, specifically includes: Principal component analysis was used to reduce the dimensionality of the material changes in the bacterial-algal interaction in the target seawater pond, and the core material change characteristics of the dominant bacterial-algal interaction process were extracted, including the rate of change of nitrogen and phosphorus nutrient concentrations, the daily variation of dissolved oxygen, and the slope and intercept of the metabolic product concentration change curve. The water environment data of the target seawater pond within a preset sampling period is obtained, including water temperature, light transmittance, water depth, and hydrodynamic data. The bacterial and algal distribution data, the core substance change characteristics, and the aquatic environment data are spatiotemporally aligned to construct a multidimensional feature dataset. A simulation model of material changes in bacterial-algal interactions is constructed based on a long short-term memory neural network. The model is trained by taking the multidimensional feature dataset as input and the core material change features of the next time step as output. An attention mechanism is introduced to enhance the model's sensitivity to water temperature and light transmittance in the water environment data. The current distribution data of bacteria and algae, the change characteristics of the core substances, and the predicted water environment data for a future preset time period are input into the trained simulation model. The simulation model uses its internal memory unit and attention mechanism to iteratively simulate the dynamic change sequence of the change characteristics of the core substances within the future preset time period. The dynamic change sequence was restored to simulated interaction substance change data containing the changing trends of dissolved oxygen, pH value, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations.
[0027] It is important to note that the interaction between bacteria and algae in a pond is essentially a dynamic network of material cycling and energy flow. If there is an imbalance in the absorption, transformation, release, and utilization of nutrients and metabolic products by bacteria and algae during metabolism—for example, excessive algal consumption inhibiting bacterial growth, or excessive accumulation of bacterial metabolites inhibiting algal photosynthesis—the entire interaction system will become disordered, leading to water quality deterioration and threatening aquaculture safety. To predict and intervene in such imbalances in advance, it is necessary to predict future changes in interacting substances. By extracting core change characteristics and integrating data on bacterial and algal distribution and the environment, an attention-enhanced neural network model is used to simulate the detailed sequence of material flow changes driven by bacterial-algae interactions within a preset time period, thus obtaining simulated interacting substance change data. The simulated interacting substance change data shows whether the consumption rates of key nutrients such as nitrogen and phosphorus in the pond are matched, whether the diurnal fluctuations of dissolved oxygen will fall below the safe threshold, and whether various metabolic products (such as organic acids and toxins) will show an accumulation trend. This is equivalent to providing a detailed forecast of the "health trend" of the pond ecosystem. Based on this forecast, managers can accurately calculate the types of nutrients, timing of supplementation, and optimal amounts required to maintain or restore the balance between bacteria and algae, thereby enabling precise and proactive regulation before an imbalance actually occurs.
[0028] According to an embodiment of the present invention, the step of determining the bacterial-algal interaction equilibrium state based on the simulated interaction substance change data, and determining the impact of bacteria and algae on the water quality of the target seawater pond based on the bacterial-algal interaction equilibrium state, specifically includes: Based on the species composition and abundance information of each bacterial and algal species in the bacterial and algal distribution data, and combined with the changing trends of various substances in the bacterial-algal interaction substance change data, the types of substances involved in the metabolism of different bacterial and algal species and their direction of action are identified, and the correspondence between the consumption pathway of organic matter and nutrients by bacteria and the absorption of nutrients and release of metabolites by algae is established. Based on the correspondence, a correlation mapping of material supply and consumption between bacteria and algae is constructed. According to the correlation mapping, the input and output changes of various substances in the continuous time series are aligned. The pairing relationship between the substances consumed by bacteria and the substances released by algae, as well as between the substances absorbed by algae and the substances released by bacteria, is extracted to form exchange relationship data that characterizes the correspondence of material supply and consumption between bacteria and algae. The exchange relationship data is matched and analyzed with the simulated interaction material change data to determine whether the supply and consumption of various substances during the simulated interaction material change process meet the exchange relationship, and the change data of shortage and excess substances that do not meet the exchange relationship during the bacterial-algae interaction process are extracted. Based on the data on changes in scarce and abundant substances, the metabolic restriction or enrichment status of the corresponding bacterial or algal species is determined. Combined with the accumulation and reduction trends of scarce and abundant substances in the water body, the changes in dissolved oxygen, the degree of nutrient enrichment, and the residual status of metabolic products are analyzed to obtain the water quality impact data of the target seawater pond.
[0029] It should be noted that by establishing a specific material exchange relationship map between bacteria and algae and matching future simulated material flow data with this map, the system can automatically identify mismatched links. This means precisely identifying which key substances (such as specific nitrogen sources, phosphorus sources, or dissolved organic matter) will become limiting factors due to insufficient supply in the future, or which substances will accumulate excessively due to insufficient consumption. This is equivalent to identifying survival-blocking substances in the bacterial-algal symbiotic network at the molecular and population levels, determining the metabolic inhibition or enrichment state that specific bacterial or algal communities will face, and accurately deducing how this will specifically lead to dissolved oxygen imbalance, abnormal nutrient levels, or accumulation of harmful metabolites in the water. The direction of action refers to the clear definition of whether a specific bacterial or algal species consumes a certain substance (absorbed and utilized as a substrate or nutrient) or produces and releases it (output to the environment as a metabolic product) during its metabolic activities. These various substances are the substances produced and consumed in bacterial-algal interactions.
[0030] According to an embodiment of the present invention, the step of supplementing the bacteria-algae interaction nutrients according to the influence situation and determining the bacteria-algae interaction balance efficiency after the supplementation of bacteria-algae interaction nutrients specifically includes: Based on the water quality impact, identify the types of nutrients that are deficient in the target seawater pond, and determine the supplementation range for each deficient nutrient based on the change data of the deficient and excess substances. Acquire the bacterial and algal distribution data and hydrodynamic data of the target seawater pond, determine the spatial aggregation area of the target bacterial species and algae based on the bacterial and algal distribution data, and predict the diffusion path and diffusion rate of the nutrient placement location in the water body through particle tracking simulation in combination with the hydrodynamic data. The location for nutrient delivery is determined based on the diffusion path and diffusion rate. Nutrients are then delivered at the location, and the response characteristics of changes in bacterial-algal interaction substances after nutrient supplementation are extracted. Based on the material change response characteristics of the bacterial-algal interaction, the material exchange relationship between bacteria and algae is rematched to determine the degree of coordination between the supply and consumption of various substances, and the balance efficiency of bacterial-algal interaction after the supplementation of nutrients is determined according to the degree of coordination.
[0031] It should be noted that by precisely supplementing nutrients for bacterial-algal interactions based on water quality impacts, effective intervention can be achieved in addressing metabolically restricted or nutrient-deficient states of bacteria and algae in seawater ponds. This allows target bacterial and algal species to fully access the necessary nutrients within their spatial aggregation areas, thereby restoring and maintaining the material cycle balance during bacterial-algal interactions, improving nutrient utilization efficiency, reducing the undesirable accumulation of metabolic products, and ultimately significantly enhancing dissolved oxygen levels and water quality stability. The growth and metabolism of bacterial and algal populations in seawater pond ecosystems are highly dependent on environmental conditions and nutrient supply. Prolonged deficiency or excess of a certain nutrient can lead to deviations in bacterial and algal metabolism, causing eutrophication, excessive algal proliferation, or organic matter accumulation, thus disrupting the material exchange relationships between bacteria and algae and reducing the ecosystem's self-purification capacity. Therefore, by supplementing deficient nutrients and predicting their diffusion paths based on bacterial and algal distribution and hydrodynamic characteristics, not only can precise delivery be achieved, but the effectiveness of bacterial-algal interaction balance can also be assessed through response analysis to changes in nutrient levels after supplementation. The optimal placement of nutrients is selected based on locations that allow for high-concentration, rapid coverage and sustained action of nutrients on the target algal and bacterial aggregation areas.
[0032] Figure 3 The flowchart of the present invention for optimizing bacterial-algal interactions based on the balance efficiency of bacterial-algal interactions is shown.
[0033] According to an embodiment of the present invention, the optimization of bacterial-algal interaction based on the bacterial-algal interaction balance efficiency specifically includes: If the balance efficiency of the bacterial-algal interaction is lower than the preset balance efficiency, the effective absorption rate of the bacterial-algal interaction substances by the bacteria and algae for the applied nutrients is determined according to the response characteristics of the bacterial-algal interaction substances. When the effective absorption rate is lower than the preset absorption rate threshold, the concentration change data of the unused remaining nutrients in the water body are extracted, and combined with the metabolic demand rate of each bacterial species and algae in the bacterial and algal distribution data, the correlation between the nutrient consumption rate and the remaining concentration is constructed. Based on the aforementioned correlation, the consumption slope of different nutrients in the continuous time series was fitted and analyzed to determine the target supply rate range required to maintain the metabolic balance of bacteria and algae. The slow-release amount of each supplementary nutrient per unit time is determined based on the target supply rate range, and the nutrient delivery time is optimized based on the slow-release amount.
[0034] It should be noted that when initial nutrient supplementation fails to achieve the desired balance, analyzing the actual effective absorption rate of nutrients by the microbial and algal communities after supplementation identifies low utilization rates caused by excessive single-use additions and mismatches between supply and metabolic rhythms. Furthermore, this method delves into the dynamic relationship between the changing patterns of remaining nutrients and the metabolic needs of microorganisms and algae, precisely calculating the target supply rate that can continuously match their consumption rate. Based on this, the original single-use or extensive addition scheme is optimized into a time-controlled, precise supply strategy based on slow-release amounts per unit time. This effectively avoids nutrient waste, non-targeted transformations (such as promoting the growth of harmful algae), or secondary pollution. By achieving dynamic synchronization between nutrient supply and the metabolic needs of microorganisms and algae, it fundamentally improves the stability of microbial-algae interactions and the long-term effectiveness of ecological regulation.
[0035] Figure 4 A block diagram of an ecological management system based on the interaction between bacteria and algae in a seawater pond, according to the present invention, is shown.
[0036] A second aspect of the present invention also provides an ecological management system based on the interaction between bacteria and algae in a seawater pond. The system includes: a memory 401, a processor 402, and a communication interface 403. The memory includes a program for an ecological management method based on the interaction between bacteria and algae in a seawater pond. The communication interface is used for data connection and communication between the memory and the processor. When the program for the ecological management method based on the interaction between bacteria and algae in a seawater pond is executed by the processor, it implements the steps of the ecological management method based on the interaction between bacteria and algae in a seawater pond as described in any of the above claims.
[0037] This invention discloses an ecological management method and system based on the interaction between bacteria and algae in a seawater pond. The method includes: acquiring water quality information at different locations in a target seawater pond; determining the survival probability of bacteria and algae and the detection scheme accordingly to obtain data on the distribution of bacteria and algae and changes in the interaction substances; determining the characteristics of the changes in substances based on the change data, and simulating the changes in the interaction substances over a predetermined time period in conjunction with the distribution data; determining the balance state of the bacteria-algae interaction and its impact on water quality; supplementing the nutrients required for the interaction based on the impact, and evaluating the effectiveness of the supplemented balance; and finally optimizing the interaction based on this effectiveness. This method achieves precise monitoring, simulation prediction, and dynamic control of the bacteria-algae system in a seawater pond, helping to maintain the ecological balance of the pond and improve the efficiency of water quality management.
[0038] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0039] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.
[0040] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. An ecological management method based on the interaction between bacteria and algae in seawater ponds, characterized in that, Includes the following steps: Obtain water quality information at different locations in the target seawater pond, determine the survival probability of bacteria and algae based on the water quality information at different locations, determine the bacteria and algae detection scheme for the target seawater pond based on the bacteria and algae survival probability, and obtain the distribution data of bacteria and algae and the change data of bacteria and algae interaction substances in the target seawater pond based on the bacteria and algae detection scheme. Based on the material change data of the bacterial-algal interaction, the material change characteristics of the bacterial-algal interaction are determined. Based on the material change characteristics and the bacterial-algal distribution data, the material change characteristics of the bacterial-algal interaction in the target seawater pond in the future preset time period are simulated to obtain simulated material change data of the interaction. The balance state of bacterial-algal interaction is determined based on the simulated interaction material change data, and the impact of bacteria and algae on the water quality of the target seawater pond is determined based on the bacterial-algal interaction balance state. Based on the aforementioned impact, nutrients for the bacterial-algal interaction are supplemented, and the balance efficiency of the bacterial-algal interaction after the supplementation of nutrients is determined. The bacterial-algal interaction balance efficiency was optimized.
2. The ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 1, characterized in that, The process involves acquiring water quality information at different locations within the target seawater pond, determining the survival probability of bacteria and algae based on this information, determining a detection plan for bacteria and algae in the target seawater pond based on these survival probabilities, and acquiring data on the distribution of bacteria and algae and changes in their interaction substances based on this detection plan. Specifically, this process includes: Historical water quality information and historical bacterial and algal species and concentration data of different sampling points in the target seawater pond within a set historical time period are obtained to establish a mapping relationship model between water quality parameters and bacterial and algal survival status, and the weight data of the impact of different combinations of water quality parameters on the survival of various bacterial and algal species are determined based on the mapping relationship model. Obtain water quality information of the target seawater pond at different locations at the current time, input the water quality information of the target seawater pond at different locations at the current time into the mapping relationship model, and calculate the survival probability of various bacteria and algae at different locations of the target seawater pond at the current time. Based on the survival probability of bacteria and algae, the regions with a survival probability higher than a preset probability threshold are identified as bacteria and algae enrichment regions, and the regions with a survival probability lower than the preset probability threshold are identified as bacteria and algae sparse regions. Based on the spatial distribution of the bacterial and algae enrichment area and the bacterial and algae sparse area, a bacterial and algae detection scheme is determined, and bacterial and algae distribution data and bacterial and algae interaction substance change data of the target seawater pond are obtained according to the bacterial and algae detection scheme.
3. The ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 2, characterized in that, The method for determining the algae and bacteria detection scheme based on the spatial distribution of the algae and bacteria enrichment zone and the algae and bacteria sparse zone, and obtaining the algae and bacteria distribution data and algae interaction substance change data of the target seawater pond according to the algae and bacteria detection scheme, specifically includes: Based on the spatial distribution of the algae-rich and algae-sparse areas, determine the algae detection sampling density and sampling frequency for each detection area, and deploy microfluidic devices in each area according to the sampling density. The volume characteristic data of the main bacterial species and algae in the target seawater pond are obtained to determine the first aperture range that can effectively intercept the target bacterial species and algae while allowing water to pass through. The screen aperture for bacterial and algae interception is selected according to the first aperture range. Based on the sieve aperture configuration, test sieves were used, and standard solutions containing target bacterial species and algae with known concentration gradients were flowed through the test sieves at different flow rates. The actual retention rate of the target bacterial species by the test sieves at different flow rates was measured and recorded, and a dataset of flow rate-retention rate correspondence was generated. Based on the velocity-retention rate correspondence dataset, the optimal velocity range corresponding to the preset retention efficiency threshold is determined by fitting analysis. The viscosity and impurity content data of the target seawater pond are obtained. Combined with the optimal velocity range, the clogging risk coefficient of the surface pores of the screen with the selected aperture is analyzed by fluid dynamics simulation under different impact times when it works in the optimal velocity range. Based on the clogging risk coefficient and the preset acceptable clogging risk threshold, the longest single impact time that can maintain the effective working time of the screen under the premise of meeting the preset interception efficiency is determined, and the optimal flow rate range and the longest single impact time are set together as the impact flow rate and impact time working parameters of the microfluidic device for intercepting bacteria and algae on the screen. Within a preset sampling period, the microfluidic device in each detection area impacts the screen with a selected bacterial and algae interception aperture according to the working parameters of the impact flow rate and impact time. The intercepted material and filtered water sample after being processed by the microfluidic device are collected. The intercepted material is subjected to bacterial isolation, culture and identification. The bacterial and algae species composition and abundance data of different sampling points are obtained to obtain the bacterial and algae distribution data of the target seawater pond. Acquire data on changes in dissolved oxygen, pH, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations in the water body within a preset sampling period, and output the changes as bacterial and algal interaction substance change data.
4. The ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 1, characterized in that, The process involves determining the material change characteristics of the bacterial-algal interaction based on the material change data of the bacterial-algal interaction, and simulating the material change characteristics of the bacterial-algal interaction in a target seawater pond over a future preset time period based on the material change characteristics and bacterial-algal distribution data, to obtain simulated interaction material change data. Specifically: Principal component analysis was used to reduce the dimensionality of the material changes in the bacterial-algal interaction in the target seawater pond, and the core material change characteristics of the dominant bacterial-algal interaction process were extracted, including the rate of change of nitrogen and phosphorus nutrient concentrations, the daily variation of dissolved oxygen, and the slope and intercept of the metabolic product concentration change curve. The water environment data of the target seawater pond within a preset sampling period is obtained, including water temperature, light transmittance, water depth, and hydrodynamic data. The bacterial and algal distribution data, the core substance change characteristics, and the aquatic environment data are spatiotemporally aligned to construct a multidimensional feature dataset. A simulation model of material changes in bacterial-algal interactions is constructed based on a long short-term memory neural network. The model is trained by taking the multidimensional feature dataset as input and the core material change features of the next time step as output. An attention mechanism is introduced to enhance the model's sensitivity to water temperature and light transmittance in the water environment data. The current distribution data of bacteria and algae, the change characteristics of the core substances, and the predicted water environment data for a future preset time period are input into the trained simulation model. The simulation model uses its internal memory unit and attention mechanism to iteratively simulate the dynamic change sequence of the change characteristics of the core substances within the future preset time period. The dynamic change sequence was restored to simulated interaction substance change data containing the changing trends of dissolved oxygen, pH value, nitrogen and phosphorus nutrient concentrations, and bacterial and algal metabolite concentrations.
5. The ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 1, characterized in that, The process of determining the bacterial-algal interaction balance state based on the simulated interaction material change data, and then determining the impact of bacteria and algae on the water quality of the target seawater pond based on the bacterial-algal interaction balance state, specifically involves: Based on the species composition and abundance information of each bacterial and algal species in the bacterial and algal distribution data, and combined with the changing trends of various substances in the bacterial-algal interaction substance change data, the types of substances involved in the metabolism of different bacterial and algal species and their direction of action are identified, and the correspondence between the consumption pathway of organic matter and nutrients by bacteria and the absorption of nutrients and release of metabolites by algae is established. Based on the correspondence, a correlation mapping of material supply and consumption between bacteria and algae is constructed. According to the correlation mapping, the input and output changes of various substances in the continuous time series are aligned. The pairing relationship between the substances consumed by bacteria and the substances released by algae, as well as between the substances absorbed by algae and the substances released by bacteria, is extracted to form exchange relationship data that characterizes the correspondence of material supply and consumption between bacteria and algae. The exchange relationship data is matched and analyzed with the simulated interaction material change data to determine whether the supply and consumption of various substances during the simulated interaction material change process meet the exchange relationship, and the change data of shortage and excess substances that do not meet the exchange relationship during the bacterial-algae interaction process are extracted. Based on the data on changes in scarce and abundant substances, the metabolic restriction or enrichment status of the corresponding bacterial or algal species is determined. Combined with the accumulation and reduction trends of scarce and abundant substances in the water body, the changes in dissolved oxygen, the degree of nutrient enrichment, and the residual status of metabolic products are analyzed to obtain the water quality impact data of the target seawater pond.
6. The ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 5, characterized in that, The process of supplementing the bacteria-algae interaction nutrients according to the aforementioned influence, and determining the balance efficiency of the bacteria-algae interaction after nutrient supplementation, specifically involves: Based on the water quality impact, identify the types of nutrients that are deficient in the target seawater pond, and determine the supplementation range for each deficient nutrient based on the change data of the deficient and excess substances. Acquire the bacterial and algal distribution data and hydrodynamic data of the target seawater pond, determine the spatial aggregation area of the target bacterial species and algae based on the bacterial and algal distribution data, and predict the diffusion path and diffusion rate of the nutrient placement location in the water body through particle tracking simulation in combination with the hydrodynamic data. The location for nutrient delivery is determined based on the diffusion path and diffusion rate. Nutrients are then delivered at the location, and the response characteristics of changes in bacterial-algal interaction substances after nutrient supplementation are extracted. Based on the material change response characteristics of the bacterial-algal interaction, the material exchange relationship between bacteria and algae is rematched to determine the degree of coordination between the supply and consumption of various substances, and the balance efficiency of bacterial-algal interaction after the supplementation of nutrients is determined according to the degree of coordination.
7. An ecological management method based on the interaction between bacteria and algae in a seawater pond according to claim 1, characterized in that, The optimization of bacterial-algal interactions based on the aforementioned balance efficiency specifically involves: If the balance efficiency of the bacterial-algal interaction is lower than the preset balance efficiency, the effective absorption rate of the bacterial-algal interaction substances by the bacteria and algae for the applied nutrients is determined according to the response characteristics of the bacterial-algal interaction substances. When the effective absorption rate is lower than the preset absorption rate threshold, the concentration change data of the unused remaining nutrients in the water body are extracted, and combined with the metabolic demand rate of each bacterial species and algae in the bacterial and algal distribution data, the correlation between the nutrient consumption rate and the remaining concentration is constructed. Based on the aforementioned correlation, the consumption slope of different nutrients in the continuous time series was fitted and analyzed to determine the target supply rate range required to maintain the metabolic balance of bacteria and algae. The slow-release amount of each supplementary nutrient per unit time is determined based on the target supply rate range, and the nutrient delivery time is optimized based on the slow-release amount.
8. An ecological management system based on the interaction between bacteria and algae in a seawater pond, characterized in that, The ecological management system based on the interaction between bacteria and algae in a seawater pond includes a storage device and a processor. The storage device includes a program for an ecological management method based on the interaction between bacteria and algae in a seawater pond. When the program for the ecological management method based on the interaction between bacteria and algae in a seawater pond is executed by the processor, it implements the steps of the ecological management method based on the interaction between bacteria and algae in a seawater pond as described in any one of claims 1 to 7.