A feasibility analysis and dynamic optimization method for intercropping in harbors

Abstract

The present application provides a feasibility analysis and dynamic optimization method for interbreeding applied to harbors, comprising: according to harbor climate characteristic data, using a machine learning algorithm to obtain a combination of species suitable for breeding under different climatic conditions, and forming a climate-breeding species adaptability matrix; comprehensively considering water quality parameters and climatic conditions, using an optimization algorithm, determining the optimal breeding species combination plan under the current harbor environment, so as to achieve a balance between breeding feasibility and output; using an ecological model simulation unit to virtually repair the impacted breeding areas, and obtain key control points and regulation parameters for restoring the ecological balance of breeding, so as to guide the implementation of actual restoration work; within the breeding area, obtaining gradient data of each key ecological position, and judging the ecological health status of different areas by analyzing the efficiency of material circulation and energy flow in the gradient data.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a feasibility analysis and dynamic optimization method for interbreeding applied to harbors. Background Art

[0002] During the interbreeding process in harbors, the gradient change of the ecosystem has a crucial impact on the breeding efficiency and yield. However, there is currently a lack of systematic understanding of the interaction mechanism between gradient change and key point recovery. In the actual breeding process, there are often many technical difficulties, among which the restoration priority between different key points is difficult to determine. There is an intricate interaction between the various key points in the ecosystem, such as water quality, bottom sediment, and biological populations. When disturbed by the outside world, there is no consensus on which key points should be restored first to maximize the ecological balance. Secondly, the law of gradient change in the recovery process of key points is still unclear. The gradient change rate and amplitude of different key points vary greatly during the recovery process. Some key points may recover quickly, while others may take years. How to master these gradient change laws is crucial to formulating scientific recovery strategies. Thirdly, the gradient changes in different breeding areas vary greatly. Due to the differences in natural conditions such as harbor topography and hydrology, there are often significant differences in the material circulation and energy flow processes in different breeding areas. This leads to the fact that the recovery effect of the same key point in different areas may be very different. Moreover, the mechanism of the influence of external interference factors on gradient changes is still unclear. The harbor ecosystem is constantly affected by external forces such as tides, wind and waves, and human activities, which will interfere with gradient changes to varying degrees. In summary, in the process of harbor interbreeding, it is urgent to strengthen the study of the law of gradient changes and the interaction mechanism between them and key point restoration, which is of great significance for maintaining the ecological balance of the harbor, improving breeding efficiency, and ensuring breeding production. Summary of the invention

[0003] The present invention provides a feasibility analysis and dynamic optimization method for intercropping applied to harbors, which mainly includes:

[0004] By collecting and analyzing historical water quality data of the harbor, we determined the water quality parameters that affect the feasibility of interbreeding, including temperature, salinity and dissolved oxygen, and established a correlation model between water quality parameters and the adaptability of aquaculture species;

[0005] Based on the harbor climate characteristic data, a machine learning algorithm is used to obtain the species combination suitable for breeding under different climatic conditions, forming a climate-breeding species adaptability matrix;

[0006] Comprehensively consider water quality parameters and climate conditions, and use optimization algorithms to determine the best aquaculture species mix in the current harbor environment to achieve a balance between aquaculture feasibility and yield;

[0007] When the aquaculture area is hit by a shock, including a storm, the impact on the aquaculture environment can be determined by real-time monitoring of sediment changes, and corresponding recovery strategies can be initiated based on preset thresholds;

[0008] Using ecological model simulation units, we conduct virtual restoration of the impacted aquaculture areas, and obtain key control points and regulatory parameters for restoring the ecological balance of aquaculture to guide the actual restoration work.

[0009] Through dynamic monitoring of the number of breeding populations, the speed and degree of population recovery can be judged. When the number of breeding populations reaches a stable threshold, it is determined that the ecological balance of the breeding area has been restored and it has entered the stage of normalized management.

[0010] Obtain gradient data of key ecological locations within the breeding area, and judge the ecological health status of different areas by analyzing the efficiency of material circulation and energy flow in the gradient data;

[0011] Based on the results of gradient analysis, network analysis methods were used to reveal the interaction relationships and influencing mechanisms among key ecological positions, and the contribution of each key ecological position to the stability of the ecosystem was calculated. The ecological positions were ranked based on their contribution, the restoration priority of the damaged harbor ecological areas was determined, and corresponding restoration strategies were formulated to promote the balance and stability of the harbor aquaculture ecosystem by regulating key gradient parameters.

[0012] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0013] The present invention discloses a feasibility analysis and dynamic optimization method for interbreeding in harbors to achieve the balance, stability and recovery of the interbreeding aquaculture ecosystem in harbors, including determining key water quality parameters that affect the adaptability of aquaculture species, determining species suitable for aquaculture under different climatic conditions, optimal aquaculture species matching, environmental impact assessment after aquaculture areas are impacted, rapid recovery of ecological balance, real-time monitoring of aquaculture populations, and determination of the ecological health status within aquaculture areas. The refined management and rapid response mechanism for the interbreeding aquaculture ecosystem in harbors is achieved; it not only improves aquaculture output and feasibility, but also enhances the system's ability to recover after natural impacts, ensuring the long-term health and stability of the aquaculture ecological environment, which is of great significance for sustainable fishery development. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a flow chart of a feasibility analysis and dynamic optimization method of interbreeding applied to harbors.

[0015] Figure 2 It is a schematic diagram of a feasibility analysis and dynamic optimization method of interbreeding applied to harbors according to the present invention.

[0016] Figure 3 It is another schematic diagram of the feasibility analysis and dynamic optimization method of inter-breeding applied to harbors according to the present invention. DETAILED DESCRIPTION

[0017] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0018] like Figure 1-3 In this embodiment, a feasibility analysis and dynamic optimization method for intercropping applied to harbors may specifically include:

[0019] Step S101, by collecting and analyzing the historical water quality data of the harbor, determine the water quality parameters that affect the feasibility of interbreeding, the water quality parameters include temperature, salinity and dissolved oxygen, and establish a correlation model between water quality parameters and the adaptability of aquaculture species.

[0020] By collecting and analyzing the historical water quality data of the harbor, the key water quality parameters that affect the feasibility of interbreeding are obtained, including temperature, salinity, and dissolved oxygen, and a correlation model between water quality parameters and the adaptability of aquaculture species is established. According to the established correlation model, the adaptability of the current harbor water quality parameters and aquaculture species is judged, and the species available for aquaculture are determined. The time series analysis method is used to obtain the historical trend of harbor water quality parameters and predict water quality changes in the future. By comparing the current water quality parameters with the predicted water quality parameters, the suitability of the aquaculture site is judged, and combined with the adaptability of the aquaculture species, the feasibility of interbreeding in the harbor is analyzed and determined. If interbreeding in the harbor is judged to be feasible, the growth and survival of the aquaculture species under different water quality conditions are obtained through simulation experimental methods, and the aquaculture plan is optimized. If interbreeding in the harbor is judged to be unfeasible, measures need to be taken to improve water quality, including regulating temperature, salinity, dissolved oxygen, and re-evaluating the feasibility. Based on the feasibility analysis results of interbreeding in the harbor, the key factors affecting the feasibility of interbreeding in the harbor are obtained.

[0021] Specifically, by collecting and analyzing the historical water quality data of the harbor, we can obtain the changes in key water quality parameters such as water temperature, salinity and dissolved oxygen in the past 10 years. Taking water temperature as an example, by analyzing its time series data, it can be found that the water temperature in the harbor shows an obvious seasonal change pattern. The water temperature in summer is usually 25-28 degrees Celsius, while the water temperature in winter drops to 15-18 degrees Celsius. At the same time, the correlation model between water temperature and the growth adaptability of aquaculture species can be established through regression analysis and other methods, for example: Y = 0.8X + 12, where Y represents the growth rate of a certain aquaculture species and X represents the water temperature. The model shows that for every 1 degree Celsius increase in water temperature, the growth rate of the species will increase by 0.8 percentage points. Similarly, the correlation model between other water quality parameters such as salinity and dissolved oxygen and the adaptability of aquaculture species can also be established. With these correlation models, it is possible to determine the species that are more suitable for aquaculture based on the actual water quality conditions of the current harbor. For example, if the current water temperature of the harbor is 22 degrees Celsius, according to the aforementioned association model, under this water temperature condition, the growth rate of a certain farmed fish is about 22*0.8+12=28%. Combined with the adaptability analysis of other water quality parameters, we can comprehensively judge which fish species are suitable for farming in the harbor. At the same time, we can also use time series analysis and other methods to predict the changing trend of harbor water quality parameters in the future. Taking water temperature as an example, assuming that the harbor water temperature will gradually increase from the current 22 degrees Celsius to 25 degrees Celsius in the next three months. Then according to the association model, the growth rate of this type of fish will increase from 28% to 28+(25-22)*0.8=30.4%. By comparing the current water quality conditions with future predictions, the feasibility of aquaculture in the harbor can be further judged. If it is judged that interbreeding in the harbor is feasible, the growth and survival of a certain farmed species under different water quality conditions can also be obtained through simulation experiments and other methods. Assuming that the water temperature is 25 degrees Celsius, the salinity is 30 grams per liter, and the dissolved oxygen is 6 milligrams per liter, the average daily weight gain of this type of fish is 0.8%, and the survival rate is 95%. Based on this, the breeding plan can be optimized, such as adjusting the stocking density, adding dissolved oxygen enhancers, and other measures to improve the breeding effect. If it is judged that inter-harbor breeding is not feasible, measures need to be taken to improve the water quality. If the harbor water temperature is found to be too high, it is possible to consider building an artificial lake near the breeding area and using the mixture of seawater and fresh water to adjust the water temperature; if the dissolved oxygen is low, aerators and other equipment can be used to increase the dissolved oxygen content of the water body. After optimizing the water quality through these measures, the feasibility of harbor breeding can be re-evaluated. Through in-depth analysis of the historical water quality data of the harbor, a correlation model between water quality parameters and the adaptability of breeding species is established. Combined with the current water quality status and the prediction of future change trends, the feasibility of inter-harbor breeding can be comprehensively evaluated, and an optimized breeding plan can be formulated accordingly.

[0022] Step S102, based on the harbor climate characteristic data, a machine learning algorithm is used to obtain a combination of species suitable for aquaculture under different climatic conditions to form a climate-aquaculture species adaptability matrix.

[0023] According to the acquired harbor climate characteristic data, which include temperature, rainfall, and sunshine duration, the principal component analysis method is used to extract the features of the data and obtain the key parameters that can represent the climate characteristics. The support vector machine or neural network supervised learning algorithm is used to construct the association model between climate parameters and the adaptability of aquaculture species. In the training process of the association model between climate parameters and the adaptability of aquaculture species, the climate parameters are input and the corresponding aquaculture species adaptability score is output. The genetic algorithm or particle swarm optimization algorithm method is used to optimize and solve the trained association model to obtain the optimal aquaculture species combination under different climatic conditions. The optimization solution results are organized into a climate-aquaculture species adaptability matrix, and combined with actual project needs, the main species suitable for aquaculture and their combinations under the current harbor climate conditions are determined. A climate change monitoring mechanism is established, and the climate-aquaculture adaptability matrix is ​​regularly updated to cope with future climate change.

[0024] Specifically, we can first extract three main climate characteristic parameters by performing principal component analysis on the climate data of the harbor such as temperature, rainfall, and sunshine duration over the years: PC1 represents the temperature factor, with a value range of -2 to 2; PC2 represents the humidity factor, with a value range of -1.5 to 1.5; PC3 represents the sunshine factor, with a value range of -1 to 1. These three parameters can better summarize the climate characteristics of the harbor. Next, the support vector machine algorithm is used to establish the association model between climate parameters and the adaptability of aquaculture species. The adaptability score Y of a certain fish can be predicted by the climate parameters PC1, PC2, and PC3 through the following linear regression model: Y = 0.6PC1 + 0.4PC2 + 0.2*PC3 + ​​3. Through 10-fold cross validation, the prediction accuracy of the model on new data reached 85%, indicating that the model has strong generalization ability. With this model, we can use methods such as genetic algorithms to find the optimal aquaculture species combination under different climatic conditions. If the climate characteristics of a certain harbor are PC1=1.2, PC2=-0.8, PC3=0.6, substituting into the model, the adaptability score of fish A is 0.6*1.2+0.4*(-0.8)+0.2*0.6+3=3.52, the adaptability score of fish B is 3.54, and the adaptability score of fish C is 3.08. Through iterative optimization of genetic algorithms, it can be determined that under this climate condition, the most suitable aquaculture species combination consisting of 60% fish A, 30% fish B, and 10% fish C is the most suitable. These results are organized into a climate-aquaculture adaptability matrix to give the optimal aquaculture species combination under different climate characteristics. When the climate characteristics of the optimal aquaculture species combination PC1 = 1.2, PC2 = -0.8, PC3 = 0.6, fish A (60%), fish B (30%), fish C (10%); PC1 = 0.8, PC2 = 1.0, PC3 = -0.4, shrimp X (50%), fish Y (40%), shellfish Z (10%); PC1 = -1.5, PC2 = 0.6, PC3 = 0.9, algae A (70%), shellfish B (30%); With this matrix, we can determine the main species and their matching ratio suitable for aquaculture in the harbor according to the climate characteristics of the actual harbor. At the same time, it is necessary to establish a climate change monitoring mechanism and regularly update the matrix to cope with possible climate fluctuations in the future. If it is monitored that the climate characteristics of a certain harbor will change from PC1=1.2, PC2=-0.8, PC3=0.6 to PC1=1.5, PC2=-0.4, PC3=0.3 in the next three months, then according to the matrix information, we need to appropriately adjust the proportion of aquaculture species, reduce the proportion of fish C, and increase the release of fish B. Through continuous monitoring and dynamic optimization, we can ensure that the aquaculture plan always matches the climate conditions and improve aquaculture efficiency and benefits.

[0025] Step S103, comprehensively considering water quality parameters and climate conditions, using optimization algorithms, to determine the best aquaculture species matching plan under the current harbor environment, so as to achieve a balance between aquaculture feasibility and output.

[0026] According to the analysis results of water quality parameters and climatic conditions, the key factors affecting the feasibility and yield of harbor aquaculture are determined. A multi-objective optimization algorithm is used, with aquaculture feasibility and yield as the objective function, and water quality parameters and climatic conditions as constraints to determine the optimal aquaculture species matching scheme. The objective function includes: aquaculture feasibility index, that is, the weighted average of the adaptability scores of each aquaculture species obtained according to water quality parameters and climatic conditions; aquaculture yield index, that is, the total yield calculated according to the growth rate and stocking density of each aquaculture species. The decision variables of the multi-objective optimization algorithm include: the stocking ratio of each aquaculture species, the aquaculture species include fish, shrimp and shellfish; the stocking density of each aquaculture species. After multiple rounds of iterative optimization of the multi-objective optimization algorithm, the species matching scheme with the optimal aquaculture feasibility and yield indicators under the water quality and climate constraints is output. The species matching scheme is compared with the obtained climate-aquaculture adaptability matrix. After determining that the species matching scheme matches the current environmental conditions, the aquaculture species matching scheme is output.

[0027] Specifically, we first comprehensively analyzed the results obtained in the previous steps and determined the key factors affecting the feasibility and yield of harbor aquaculture. Taking a certain harbor as an example, the key factors include: water temperature (15-28 degrees Celsius), salinity (25-35 g / L), dissolved oxygen (4-8 mg / L), air temperature (10-30 degrees Celsius), sunshine duration (6-12 hours), etc. Next, we used a multi-objective optimization algorithm, with these factors as constraints, and aquaculture feasibility and yield as objective functions, to determine the optimal aquaculture species combination plan. Specifically, the following optimization model can be established: objective function 1 is the feasibility index of aquaculture = 0.4*fish adaptability + 0.3*shrimp adaptability + 0.3*shellfish adaptability; objective function 2 is the aquaculture yield index = 0.6*fish yield + 0.3*shrimp yield + 0.1*shellfish yield; the constraints are water temperature 15-28 degrees Celsius, salinity 25-35 g / L, dissolved oxygen 4-8 mg / L, air temperature 10-30 degrees Celsius, sunshine duration 6-12 hours, and the sum of the proportions of fish, shrimp, and shellfish is 1. The model is optimized and solved using a genetic algorithm. After multiple rounds of iterations, the optimal aquaculture species matching scheme is obtained: fish accounts for 60%, shrimp accounts for 30%, and shellfish accounts for 10%. Among them, the fish stocking density is 5,000 tails / hectare, the shrimp stocking density is 3,000 tails / hectare, and the shellfish stocking density is 20,000 / hectare. This scheme not only meets the constraints of water quality and climate, but also achieves the optimal balance under the premise of taking into account the two goals of aquaculture feasibility and yield. According to the correlation model between climate parameters and aquaculture species adaptability established in step S102, under the conditions of 25 degrees Celsius and 30 grams / liter of salinity in the harbor, the growth adaptability score of fish is 4.2, shrimp is 3.8, and shellfish is 3.5, and the comprehensive feasibility index is 4.02; at the same time, according to the stocking density and growth rate of each aquaculture species, the total output is about 12 tons / hectare. Comparing this optimization result with the climate-aquaculture adaptability matrix obtained in step S102, it is found that the current climate conditions of the harbor (PC1=1.2, PC2=-0.8, PC3=0.6) are consistent with the optimal scheme, indicating that this matching scheme can better adapt to the actual environment of the harbor. By integrating the analysis of water quality parameters and climate conditions, a multi-objective optimization algorithm is used to automatically determine the optimal aquaculture species combination, providing a scientific basis for harbor interbreeding operations under the premise of taking into account feasibility and yield indicators.

[0028] Step S104, when the aquaculture area is hit by an impact, including a storm, the impact of the impact on the aquaculture environment is determined by real-time monitoring of sediment changes, and a corresponding recovery strategy is initiated based on a preset threshold.

[0029] Sediment monitoring equipment is deployed in the aquaculture area to collect sediment data in real time, including sediment depth and particle content. Through time series analysis methods, a sediment change model under normal meteorological conditions is established to determine the normal fluctuation range of various indicators. When subjected to extreme weather events, including storms, sediment data is monitored in real time and compared with the sediment change model under normal meteorological conditions. According to the preset recovery strategy, the corresponding emergency measures are automatically initiated, including increasing water circulation. The sediment conditions in the area are continuously monitored until various indicators return to normal levels to ensure that the aquaculture environment is effectively repaired. This extreme weather event is included in big data analysis to optimize the warning threshold and emergency plan to enhance future response capabilities.

[0030] Specifically, multiple sediment monitoring devices are deployed in the aquaculture area to collect data such as sediment depth and particle content in real time. If in a certain aquaculture area, under normal meteorological conditions, the sediment depth varies between 20-30 cm, and the particle content fluctuates within the range of 10-15%, the following sediment change model can be established through time series analysis: sediment depth = 25 + 2.5sin (2πt / 30), sediment particle content

[0031] =12.5+1.5sin(2πt / 60), where t represents time (unit: day). The model describes the periodic changes of various indicators of sediments under normal conditions. When encountering extreme weather events such as storms, the sediment data in the area is monitored in real time. Assume that a certain monitoring shows that the sediment depth reaches 40 cm and the particle content rises to 20%, which significantly deviates from the normal model prediction value. Then it can be judged that the storm has caused a serious impact on the aquaculture environment. According to the preset recovery strategy, the following measures will be automatically taken: start the water circulation pump to enhance the scouring effect of the water body on the sediment and reduce the sediment concentration to normal levels; place isolation nets in key areas to block floating materials from entering the aquaculture area; increase the frequency of regular cleaning and dredging in the aquaculture area to ensure that the sediment thickness is controlled within the range of 25-30 cm. Through continuous monitoring, it was found that after 3 days of emergency treatment, the sediment depth and particle content have gradually returned to normal levels. So far, the environment in the aquaculture area has been effectively repaired. The incident was recorded in the big data system, including when the sediment depth increases by more than 50%, or the particle content increases by more than 30%, the aquaculture environment will be severely impacted; measures such as enhancing water circulation, isolating floating objects, and strengthening cleaning and dredging can restore environmental indicators to normal within 3-5 days. Based on the analysis results of this incident, the warning threshold and emergency plan were optimized, and the environmental risk management and control capabilities were further improved. For example, the sediment depth threshold can be adjusted. Given that the sediment depth increased significantly to 40 cm after the storm, 40 cm is twice the normal range, the original warning threshold, such as a sediment depth change of 20-30 cm, is obviously not enough to capture environmental anomalies in time. Therefore, the warning threshold can be raised to an increase of more than 50% in sediment depth, that is, when the sediment depth exceeds 50% of the normal upper limit of 30 cm, that is, 15 cm, the warning is triggered, ensuring that environmental changes can be detected in time at the early stage of a sharp change in sediment depth. The particle content threshold can also be adjusted. Similarly, due to the storm, the particle content increased from the normal range of 10-15% to 20%, far exceeding the normal fluctuation range. Based on this, the warning threshold can be set to a particle content increase of more than 30%, that is, when the particle content exceeds 30% of the normal upper limit of 15%, that is, 4.5%, a warning is issued to warn of possible environmental risks in advance. Emergency plan optimization can include improving the speed of emergency response, such as analyzing the time required for sediment depth and particle content to return to normal levels after a storm for 3 days, and taking countermeasures, such as starting water circulation pumps, placing isolation nets, and increasing the frequency of cleaning dredging. Based on this, the emergency plan can be optimized to clearly stipulate that the above emergency measures will be initiated immediately after the warning is triggered to ensure intervention in the shortest time and shorten the environmental recovery cycle. In this way, once similar extreme weather events are encountered in the future, environmental shocks can be automatically identified and corresponding recovery strategies can be quickly initiated to ensure the stability of the breeding area environment.

[0032] Step S105, using an ecological model simulation unit to perform virtual restoration on the impacted aquaculture area, obtain key control points and regulation parameters for restoring the aquaculture ecological balance, so as to guide the actual restoration work.

[0033] Based on the actual monitoring data of the aquaculture area, including water quality, sediment, and biomass, the ecological model is constructed as input parameters. Stella or AnyLogi c ecological simulation software is used to establish a comprehensive ecological model including hydrology, bottom sediment, and biological food chain elements. A simulation scenario including "storm impact" is set up in the comprehensive ecological model to simulate the environmental change process of the damaged aquaculture area. Through the parameter optimization algorithm, the key control points and control parameters in the comprehensive ecological model are adjusted until the simulation results are consistent with the actual monitoring data. The optimized model parameters are analyzed to determine the key factors required to restore the ecological balance of aquaculture, including water flow rate, dissolved oxygen content, and nutrient concentration. The target values ​​of key parameters and key factors are used as operational guidance suggestions in actual restoration work.

[0034] Specifically, the actual monitoring data of the aquaculture area obtained in the above steps, such as water temperature, salinity, dissolved oxygen, bottom sediment, etc., were used as input parameters to construct a comprehensive ecological model. The model includes many elements such as hydrodynamics, sediment dynamics, and aquaculture community dynamics, and can simulate the ecological changes in the aquaculture area in a relatively comprehensive manner. The hydrodynamic part uses a three-dimensional numerical model based on the shallow water equation, which can simulate hydrodynamic processes such as rising and falling tides and tidal fields; the sediment dynamics part introduces the Partheniades-Krone formula to describe the erosion and sedimentation characteristics of the bottom mud; the community dynamics uses the Lotka-Volterra equation to describe the feeding, growth, and death laws of various aquaculture organisms. By coupling these sub-models, a relatively complete ecosystem simulation platform was established. Next, simulation scenarios such as "storm impact" were set up in the model to simulate the environmental changes in the damaged aquaculture area. Assume that in a simulation, a storm causes the suspended sediment concentration in the area to increase by 50% instantly and the dissolved oxygen to decrease by 30%, which gradually recovers after a period of time, which is consistent with the actual monitoring data. To further optimize the model, parameter optimization methods such as genetic algorithms can be used to continuously adjust the key control points and control parameters in the model, such as the shear strength coefficient of the sediment and the maximum growth rate of plankton, until the simulation results are consistent with the actual monitoring data. After multiple rounds of optimization, the calibrated model parameters were obtained. Analysis of the optimized model parameters showed that: in order to restore the ecological balance of aquaculture, the shear strength of the sediment needs to be increased from the original 0.15N / m^2 to 0.20N / m^2 to enhance the anti-erosion ability of the sediment; physical, chemical, biological and other means can be used to improve the sediment structure, such as introducing sediment improvers to increase the cohesion of the sediment, planting aquatic plants or releasing benthic animals to promote the stability of sediment particles, and reasonably arranging aquaculture activities to avoid excessive disturbance of the sediment. At the same time, it is necessary to increase the maximum growth rate of plankton from the original 0.3 / day to 0.4 / day to speed up the removal rate of organic matter in the water body; optimize the species and density of aquaculture organisms, select species with fast growth and strong filter feeding ability, and reasonably adjust the stocking structure; appropriately supplement beneficial microorganisms, zooplankton and other biological resources to enhance the biological purification function of the water body; scientifically feed feed, control the input of nutrients such as nitrogen and phosphorus, and avoid excessive nutrients causing excessive growth of plankton; strengthen the maintenance and management of water circulation and aeration facilities to ensure their efficient operation; increase aeration equipment or extend the start-up time when necessary, especially in periods of high temperature, high load, low pressure, etc. that are prone to cause a decrease in dissolved oxygen; improve the natural oxygen production capacity of the water body through biological means such as planting aquatic plants and placing beneficial microorganisms; regularly monitor the dissolved oxygen status and adjust management measures in time according to the monitoring results. In addition, the dissolved oxygen concentration of the water body needs to be maintained at more than 5mg / L to ensure the normal growth of aquaculture organisms. The output of the above key parameters and their target values ​​provides operational guidance and suggestions for actual ecological restoration work.During the actual restoration process, we continuously monitor the environmental changes in the area, and feed the monitoring data back to the comprehensive ecological model, and continuously optimize the model parameters and restoration strategies to improve the accuracy and effectiveness of restoration. We regularly evaluate the actual effects of ecological restoration measures, including changes in key ecological indicators, the health status of aquaculture organisms, economic benefits, etc., to provide a basis for adjusting restoration strategies. According to the evaluation results, we timely adjust the restoration strategy, such as optimizing implementation details, adding auxiliary measures, adjusting the implementation schedule, etc., to ensure the efficiency and sustainability of ecological restoration work.

[0035] Step S106, through dynamic monitoring of the number of breeding populations, determine the speed and degree of population recovery. When the number of breeding populations reaches a stable threshold, it is determined that the ecological balance of the breeding area has been restored and enters the normalized management stage.

[0036] Deploy biological quantity monitoring equipment in the breeding area. The biological quantity monitoring equipment includes underwater cameras and sonars to regularly collect information on the number of farmed organisms. Use time series analysis methods to analyze and process the monitoring data to obtain the population change trend of each breeding species. According to the goals of ecological restoration work, set a stable threshold for the population of each breeding species. Continuously monitor changes in population size and compare them with the stable threshold to determine the speed and degree of current population recovery. If the monitoring data shows that the population size of each breeding species has stabilized within the target threshold range, it is judged that the ecological balance has been rebuilt and switched to the normalized management stage, focusing on maintaining the population size at a stable level, while optimizing the breeding density and feeding management measures. Regularly evaluate changes in population size and adjust management plans in a timely manner to ensure that the ecological balance of the breeding area is maintained in the long term.

[0037] Specifically, multiple biological monitoring devices, such as underwater cameras and sonar probes, can be deployed in the aquaculture area to regularly collect information on the number of various aquaculture organisms in the area. It was found that in a certain aquaculture area, the average density of fish was about 7,500 per hectare, the density of shrimp was 4,800 per hectare, and the density of shellfish was about 48,000 per hectare. By inputting these original monitoring data into the time series analysis model, the population change trend of each aquaculture species in the recent three months can be obtained. Taking fish as an example, its population can be fitted with the following linear regression model: Nt = 7200 + 150t, where Nt represents the number of fish on the tth day (unit: tail / hectare), and t represents time (unit: day). The model shows that under normal circumstances, the fish population increases by 150 tails / hectare every day. According to the goal of ecological restoration, the stable population targets of fish, shrimp, and shellfish are set at 8,000 tails / hectare, 5,000 tails / hectare, and 50,000 per hectare, respectively. Continuously monitor population changes and compare them with these target values. A monitoring showed that the fish density was 7,800 per hectare, which was close to the target value; the shrimp density was 4,900 per hectare, which was basically up to standard; and the shellfish density was only 45,000 per hectare, which had not yet fully recovered. Through this comparative analysis, it was judged that the ecological recovery degree of the current breeding area had not yet reached a stable state. After continuing to monitor for 3 months, it was found that the population of each species had been continuously stable within the target range, indicating that the ecological balance had been rebuilt. At this time, it automatically switched to the normalized management stage, focusing on how to maintain the population at a stable level. Appropriate measures such as adjusting the stocking density and supplementing bait can be taken to ensure that the population of each species remains near the target value. At the same time, it is also necessary to regularly evaluate the population changes, optimize the breeding management plan in a timely manner, and ensure that the ecological balance of the breeding area is maintained for a long time. By continuously monitoring the dynamics of the breeding population and combining the preset stability threshold, the timing of the reconstruction of the ecological balance can be automatically determined, and the subsequent normalized management mode can be switched.

[0038] Step S107, within the breeding area, obtain the gradient data of each key ecological position, and judge the ecological health status of different areas by analyzing the efficiency of material circulation and energy flow in the gradient data.

[0039] One or more environmental sensors are deployed inside the aquaculture area to cover key ecological locations, including the water surface, different levels of water depth, and the bottom. Environmental sensors are used to collect water temperature, dissolved oxygen, pH value, and plankton gradient data at each location in real time. The collected gradient data is input into the comprehensive ecological model to analyze the efficiency of material circulation and energy flow in the aquaculture area. The energy transfer process between organisms in the area is simulated to calculate the energy efficiency of each link. The ecological health status of different areas is judged based on the efficiency indicators of material circulation and energy flow. If the nutrient conversion rate of a certain area is lower than the nutrient conversion rate threshold or the energy transfer efficiency is lower than the energy transfer efficiency threshold, it is judged that the ecological condition of the area is poor and restoration measures need to be taken.

[0040] Specifically, multiple environmental sensors are deployed inside the aquaculture area, covering key ecological locations such as the water surface, different water depths, and the bottom. These sensors can collect gradient data such as water temperature, dissolved oxygen, pH value, and plankton at each location in real time. At the water surface, 1 meter deep, 3 meters deep, and bottom of a certain aquaculture area, the following gradient data were measured: the water surface temperature is 24.5℃, the dissolved oxygen is 24.5℃, and the pH value is 24.5℃.

[0041] 7.2mg / L, pH value 8.2, plankton density 3200 / L; water temperature 24.3℃ at a depth of 1 meter, dissolved oxygen

[0042] 6.9mg / L, pH value 8.1, plankton density 2800 / L; water temperature 24.0℃ at a depth of 3 meters, dissolved oxygen

[0043] 6.5mg / L, pH value 7.9, plankton density 2300 / L; bottom water temperature 23.8℃, dissolved oxygen 6.0mg / L, pH value 7.6, plankton density 1800 / L, these gradient data are input into our ecological model, and the material cycle process in the area is analyzed first. The nutrient conversion rate of each ecological position is calculated, the conversion rate from water surface to water layer is 75%, the conversion rate from water layer to bottom sediment is 65%, and the conversion rate from bottom sediment to organism is 60%. From the above data, it can be seen that the nutrient conversion efficiency in the bottom area is low, and there may be some ecological problems. Next, the energy flow process in the area is analyzed. The energy transfer efficiency of each link is calculated as follows: the transfer efficiency from primary producers to primary consumers is 43%, the transfer efficiency from primary consumers to secondary consumers is 38%, and the transfer efficiency from secondary consumers to top predators is 35%. These energy transfer efficiency data show that the energy flow efficiency of the entire food chain network is generally low, and the energy conversion efficiency of the ecosystem needs to be improved urgently. Comprehensively analyzing the efficiency indicators of material circulation and energy flow, it is judged that the ecological health status of the breeding area is not ideal. The nutrient conversion rate in the bottom area was lower than 60%, and the overall energy transfer efficiency did not reach the target of 40%, indicating that there were some ecological problems in the area and further restoration measures were needed.

[0044] Step S108, based on the results of gradient analysis, a network analysis method is used to reveal the interaction relationship and influence mechanism between key ecological positions, and the contribution of each key ecological position to the stability of the ecosystem is calculated; the ecological positions are sorted based on their contribution, the restoration priority of the damaged harbor ecological areas is determined, and corresponding restoration strategies are formulated to promote the balance and stability of the harbor aquaculture ecosystem by regulating key gradient parameters.

[0045] According to the results of gradient analysis, an interactive network model of the ecosystem was constructed by network analysis method. The nodes in the interactive network model represent different ecological positions, and the edges represent the interaction relationship between ecological positions. The interactive network model was run to reveal the interaction relationship between key ecological positions, analyze the impact of the interaction relationship on the stability of the ecosystem, and obtain the centrality measurement of each node. According to the centrality measurement of the node, the contribution of each key ecological position to the stability of the ecosystem was calculated, and these ecological positions were ranked. According to the contribution ranking of the ecological position, the restoration priority of the damaged harbor ecological area was determined. Aquaculture restoration strategies for harbor ecological areas with high restoration priority were formulated, and the aquaculture restoration strategies included species reintroduction, habitat reconstruction, and pollution control. By regulating key gradient parameters, which included adjusting aquaculture density and improving water quality, the restoration strategy was implemented and the response changes of key ecological positions were observed. The changes in the harbor ecosystem after the implementation of the restoration strategy were monitored, the restoration effect was evaluated, and the restoration strategy was adjusted according to the monitoring results to ensure that the harbor aquaculture ecosystem shifted to a balanced and stable state.

[0046] For example, based on the results of the gradient analysis, the researchers found that the concentration of dissolved oxygen in the water quality parameters ranged from 5 mg / L to 12 mg / L at different measuring points. This parameter was used as input for subsequent network analysis to help identify areas that may pose a threat to biodiversity due to low dissolved oxygen levels. In the constructed harbor ecosystem interaction network model, a node represents a seagrass bed, while an adjacent node may represent a fish population that feeds on seagrass; the model shows that the connection strength between the seagrass bed and the fish population is 8, indicating that the two are closely related. After running the harbor ecosystem interaction network model, it was found that the centrality measure of the seagrass bed node was 95, which means that it plays a very important role in the network and has a significant impact on the stability of the ecosystem. By comparing the centrality measures of different nodes, the researchers concluded that seagrass beds have the highest contribution, contributing 85% to the stability of the ecosystem, while others such as shellfish farming areas may contribute only 15%. Based on the contribution ranking, it was decided to prioritize the restoration of seagrass beds (85% contribution) and the secondary restoration of shellfish farming areas (15% contribution), and to allocate 70% of resources for seagrass bed restoration and 30% for shellfish farming areas. The restoration strategy for the seagrass bed area may include reintroducing native seagrass species in the 10-hectare damaged area and setting up three water quality monitoring points around it to control pollution. After the implementation of the restoration strategy, the density of shellfish farming areas was reduced from 200 to 150 per square meter by adjusting the farming density, while improving water quality and raising the dissolved oxygen level to no less than 8mg / L to support seagrass growth. One year after the implementation of the restoration strategy, monitoring data showed that the biodiversity index of the seagrass bed rose from 5 to 8, and the dissolved oxygen concentration stabilized above 9mg / L, indicating that the restoration effect was significant and the ecosystem was shifting towards a balanced state. Based on these results, the next stage of the strategy can also be adjusted, such as further expanding the seagrass planting area.

[0047] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A feasibility analysis and dynamic optimization method for interbreeding applied to harbors, characterized in that: The method comprises: By collecting and analyzing historical water quality data of the harbor, we determined the water quality parameters that affect the feasibility of interbreeding, including temperature, salinity and dissolved oxygen, and established a correlation model between water quality parameters and the adaptability of aquaculture species; Based on the harbor climate characteristic data, a machine learning algorithm is used to obtain the species combination suitable for breeding under different climatic conditions, forming a climate-breeding species adaptability matrix; Comprehensively consider water quality parameters and climate conditions, and use optimization algorithms to determine the best aquaculture species mix in the current harbor environment to achieve a balance between aquaculture feasibility and yield; When the aquaculture area is hit by a shock, including a storm, the impact on the aquaculture environment can be determined by real-time monitoring of sediment changes, and corresponding recovery strategies can be initiated based on preset thresholds; Using ecological model simulation units, we conduct virtual restoration of the impacted aquaculture areas, and obtain the key ecological positions and key gradient parameters for restoring the ecological balance of aquaculture, so as to guide the actual restoration work. Through dynamic monitoring of the number of breeding populations, the speed and degree of population recovery can be judged. When the number of breeding populations reaches the stable threshold, it is determined that the ecological balance of the breeding area has been restored and it has entered the stage of normalized management. In the breeding area, the key gradient parameters of each key ecological position are obtained, and the ecological health status of different areas is judged by analyzing the efficiency of material circulation and energy flow in the key gradient parameters; Based on the results of gradient analysis, network analysis methods were used to reveal the interaction relationships and influencing mechanisms among key ecological positions, and the contribution of each key ecological position to the stability of the ecosystem was calculated. The key ecological positions were ranked based on their contribution, the restoration priority of the damaged harbor ecological areas was determined, and corresponding restoration strategies were formulated. By regulating key gradient parameters, the balance and stability of the harbor aquaculture ecosystem could be promoted.

2. The method according to claim 1, wherein: The method collects and analyzes the historical water quality data of the harbor to determine the water quality parameters that affect the feasibility of interbreeding, including temperature, salinity and dissolved oxygen, and establishes a correlation model between water quality parameters and the adaptability of aquaculture species, including: By collecting and analyzing historical water quality data of the harbor, we can obtain water quality parameters that affect the feasibility of interbreeding, including temperature, salinity and dissolved oxygen, and establish a correlation model between water quality parameters and the adaptability of aquaculture species; Based on the established correlation model, the adaptability of the current harbor water quality parameters and aquaculture species is judged, and the species available for aquaculture are determined; Use time series analysis methods to obtain historical trends of harbor water quality parameters and predict water quality changes in the future; By comparing the current water quality parameters with the predicted water quality parameters, the suitability of the aquaculture site can be determined, and the feasibility of inter-harbor aquaculture can be analyzed and determined based on the adaptability of the aquaculture species; If interharbor culture is deemed feasible, simulation experiments will be used to obtain the growth and survival of cultured species under different water quality conditions, and to optimize the culture plan; If estuarine interbreeding is judged to be unfeasible, measures need to be taken to improve water quality, including regulation of temperature, salinity and dissolved oxygen, and the feasibility needs to be reassessed; Based on the feasibility analysis results of inter-harbor aquaculture, the key factors affecting the feasibility of inter-harbor aquaculture were obtained.

3. The method according to claim 1, wherein: According to the harbor climate characteristic data, a machine learning algorithm is used to obtain the species combination suitable for breeding under different climate conditions, forming a climate-breeding species adaptability matrix, including: Based on the acquired harbor climate characteristic data, which include temperature, rainfall and sunshine duration, the principal component analysis method is used to extract the characteristics of the data and obtain climate parameters that can represent the climate characteristics; Use support vector machine or neural network supervised learning algorithms to build association models between climate parameters and aquaculture species adaptability; In the process of training the association model between climate parameters and aquaculture species adaptability, climate parameters are input and the corresponding aquaculture species adaptability scores are output; Genetic algorithm or particle swarm optimization algorithm is used to optimize and solve the trained association model to obtain the optimal aquaculture species combination under different climatic conditions; The optimization results are organized into a climate-aquaculture species adaptability matrix, and combined with actual project needs, the main species and their combinations suitable for aquaculture under the current port climate conditions are determined; Establish a climate change monitoring mechanism and regularly update the climate-aquaculture species adaptability matrix to cope with future climate change.

4. The method according to claim 1, wherein: The above-mentioned comprehensive water quality parameters and climate conditions, using optimization algorithms, determine the best aquaculture species matching plan under the current harbor environment to achieve a balance between aquaculture feasibility and output, including: Based on the analysis of water quality parameters and climatic conditions obtained, determine the key factors affecting the feasibility and production of estuarine aquaculture; A multi-objective optimization algorithm is used to determine the optimal aquaculture species combination plan, with aquaculture feasibility and yield as the objective function, and water quality parameters and climate conditions as constraints; The objective function includes: aquaculture feasibility index, which is the weighted average of the adaptability scores of each aquaculture species obtained based on water quality parameters and climatic conditions; Aquaculture production indicators, that is, the total production calculated based on the growth rate and stocking density of each aquaculture species; The decision variables of the multi-objective optimization algorithm include: the stocking ratio of each aquaculture species, which includes fish, shrimp and shellfish; Stocking density of each cultured species; After multiple rounds of iterative optimization using a multi-objective optimization algorithm, the optimal species matching scheme with the best aquaculture feasibility and yield indicators under the constraints of water quality and climate is output; The species matching plan is compared with the obtained climate-farming species adaptability matrix. After determining that the species matching plan matches the current environmental conditions, the farming species matching plan is output.

5. The method according to claim 1, wherein: When the aquaculture area is hit by an impact, including a storm, the impact on the aquaculture environment is determined by real-time monitoring of sediment changes, and corresponding recovery strategies are initiated according to preset thresholds, including: Deploy sediment monitoring equipment in the aquaculture area to collect sediment data in real time, including sediment depth and particle content; Through time series analysis methods, a sediment variation model under normal meteorological conditions is established to determine the normal fluctuation range of various indicators; After extreme weather events, including storms, real-time monitoring of sediment data is performed and compared with sediment change models under normal meteorological conditions; According to the preset recovery strategy, the corresponding emergency measures are automatically initiated, including increasing water circulation; Continue to monitor the sediment conditions in the area until all indicators return to normal levels to ensure that the aquaculture environment is effectively restored; Incorporate this extreme weather event into big data analysis to optimize warning thresholds and emergency plans and enhance future response capabilities.

6. The method according to claim 1, wherein: The ecological model simulation unit is used to virtually repair the impacted aquaculture area, and the key ecological position and key gradient parameters for restoring the ecological balance of aquaculture are obtained to guide the actual restoration work, including: The ecological model is constructed based on the actual monitoring data of the aquaculture area, including water quality, sediment and biomass, as input parameters; Use Stella or AnyLogic ecological simulation software to build a comprehensive ecological model including hydrology, bottom sediments, and biological food chain elements; Setting up simulation scenarios including "storm impact" in the integrated ecological model to simulate the environmental changes in damaged aquaculture areas; Through the parameter optimization algorithm, the key ecological positions and key gradient parameters in the integrated ecological model are adjusted until the simulation results are consistent with the actual monitoring data; Analyze the optimized model parameters and determine the key factors needed to restore the ecological balance of aquaculture, including water flow rate, dissolved oxygen content and nutrient concentration; The target values ​​of key ecological positions, key gradient parameters and key factors are used as actionable guiding suggestions in actual restoration work.

7. The method according to claim 1, wherein: The dynamic monitoring of the breeding population is used to determine the speed and extent of population recovery. When the breeding population reaches a stable threshold, it is determined that the ecological balance of the breeding area has been restored and the normalized management stage has begun, including: Deploy biological population monitoring equipment in the aquaculture area, including underwater cameras and sonar, to regularly collect information on the number of aquaculture organisms; The monitoring data were analyzed and processed using time series analysis methods to obtain the population change trend of each breeding species; According to the goals of ecological restoration work, set a stable threshold for the population size of each aquaculture species; Continuously monitor population changes and compare them with stability thresholds to determine the speed and extent of current population recovery; If the monitoring data shows that the population of each aquaculture species has stabilized within the target threshold range, it is judged that the ecological balance has been restored and the stage of normalized management is switched to focus on maintaining the population at a stable level while optimizing the stocking density and feeding management measures; Regularly assess changes in population numbers and adjust management plans as appropriate to ensure long-term ecological balance in the breeding area.

8. The method according to claim 1, wherein: The key gradient parameters of each key ecological position are obtained within the breeding area, and the ecological health status of different areas is judged by analyzing the efficiency of material circulation and energy flow in the key gradient parameters, including: Deploy one or more environmental sensors within the aquaculture area to cover key ecological locations, including the water surface, different levels of water depth and the bottom; Environmental sensors are used to collect water temperature, dissolved oxygen, pH value and key plankton gradient parameters at each location in real time; The key gradient parameters collected were input into the comprehensive ecological model to analyze the efficiency of material circulation and energy flow in the farming area; Simulate the energy transfer process between organisms in the region and calculate the energy efficiency of each link; Judging the ecological health status of different regions based on the efficiency indicators of material circulation and energy flow; If the nutrient conversion rate of a certain area is lower than the nutrient conversion rate threshold or the energy transfer efficiency is lower than the energy transfer efficiency threshold, the ecological condition of the area is judged to be poor and restoration measures need to be taken.

9. The method according to claim 1, wherein: According to the results of gradient analysis, the network analysis method is used to reveal the interaction relationship and influence mechanism between key ecological positions, and the contribution of each key ecological position to the stability of the ecosystem is calculated; the key ecological positions are ranked based on their contribution, the restoration priority of the damaged harbor ecological areas is determined, and corresponding restoration strategies are formulated to promote the balance and stability of the harbor aquaculture ecosystem by regulating key gradient parameters, including: According to the results of gradient analysis, an interactive network model of the ecosystem was constructed through network analysis methods. In the interactive network model, nodes represent different key ecological positions, and edges represent the interaction relationship between key ecological positions. Run the interaction network model to reveal the interaction relationships between key ecological positions, analyze the impact of interaction relationships on ecosystem stability, and obtain the centrality measure of each node; According to the centrality measurement of the nodes, the contribution of each key ecological position to the stability of the ecosystem is calculated and these key ecological positions are ranked; Determine the restoration priority of damaged harbor ecological areas based on the contribution ranking of key ecological locations; Develop aquaculture restoration strategies for high priority estuarine ecological areas, including species reintroduction, habitat restoration and pollution control; By manipulating key gradient parameters, including adjusting stocking density and improving water quality, implementing restoration strategies, and observing the response changes in key ecological locations; Monitor changes in the harbor ecosystem after the implementation of the restoration strategy, evaluate the restoration effect, and adjust the restoration strategy based on the monitoring results to ensure that the harbor aquaculture ecosystem transitions to a balanced and stable state.

Images