A method and system for optimizing fishery enhancement control for a target water body

Abstract

The application discloses a kind of fishery propagation control optimization method and system for target water area.The method comprises the following steps: obtaining the fishery ecological change data of target water area, determining suitable propagation fish species and identifying its ecological preference;Collecting historical water layering structure data, analyzing seasonal extreme events using time series decomposition algorithm, and constructing extreme value feature dataset;Based on the dataset, generate water environment stress feature map, and develop propagation control scheme combined with fish ecological preference;Construct a propagation fish monitoring sensor network, monitor the propagation effect of fish in real time, and optimize network control according to monitoring quality information.The method can realize fine management and dynamic optimization of fish propagation process, improve the effect of fish propagation and ecological environment adaptability, and provide technical support for sustainable utilization of fishery resources.

Description

Technical Field

[0001] This invention relates to the field of fishery resource management technology, and in particular to a method and system for optimizing fishery enhancement and control in target waters. Background Technology

[0002] With increasingly serious problems such as environmental pollution, overfishing, and climate change, fishery resources in many waters around the world are facing varying degrees of decline and depletion. To achieve the sustainable use of fishery resources, fish stocking, as an important means of ecological restoration, has been widely used in many countries and regions around the world.

[0003] Traditional fishery enhancement methods rely heavily on human experience in selecting fish species and setting release locations, lacking systematic analysis and dynamic response control to changes in the aquatic ecological environment. This often results in problems such as inappropriate fish species matching, improper timing of enhancement, and failure to identify environmental stressors in a timely manner. These shortcomings not only lead to poor enhancement results but may also disturb the original ecosystem, reduce ecological restoration efficiency, and cause resource waste.

[0004] In recent years, with the development of sensor networks, remote sensing technology, big data analysis, and artificial intelligence, research on smart fisheries has gradually emerged. Although some studies have attempted to assess and regulate the aquatic environment based on ecological models and monitoring data, most methods have not yet achieved a multi-dimensional, collaborative, integrated propagation and control strategy that integrates ecological change assessment, extreme event identification, environmental stress modeling, fish species ecological matching, and monitoring feedback optimization. These methods lack systematicity and have a low level of intelligence.

[0005] Therefore, there is an urgent need for a fisheries enhancement control method and system that can integrate ecological change trend analysis, water body extreme stress identification, fish species ecological preference adaptation, intelligent monitoring and feedback control optimization, so as to achieve scientific and intelligent management of the entire process of fisheries enhancement in target waters and improve the efficiency of fishery resource restoration and ecological security. Summary of the Invention

[0006] To address at least one of the aforementioned technical problems, this invention proposes a method and system for optimizing fishery enhancement and control in target waters.

[0007] The first aspect of this invention provides a method for optimizing fisheries enhancement and control in target waters, comprising:

[0008] Acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area;

[0009] Historical water body stratification data of the target water area within a preset time period is obtained. The historical water body stratification data is analyzed based on a time series decomposition algorithm to identify seasonal extreme events in the target water area and construct a seasonal extreme event feature dataset.

[0010] A water environment stress feature map is generated based on the seasonal extreme event feature dataset, and a propagation control scheme for the target water area is determined based on the water environment stress feature map and the ecological preference information of the propagated fish species.

[0011] A sensor network for monitoring aquaculture species in a target water area is constructed. The aquaculture effect of the aquaculture species in the target water area is monitored based on the sensor network. The monitoring quality information of the sensor network is acquired in real time. The monitoring control of the sensor network is optimized based on the monitoring quality information.

[0012] In this scheme, the steps of acquiring fishery ecological change data of the target water area, determining the fish species to be propagated in the target water area based on the fishery ecological change data, and identifying the ecological preference information of the fish species to be propagated in the target water area are as follows:

[0013] Acquire fishery resource survey data of the target water area within a historical preset time period, and determine fishery ecological change data of the target water area based on the fishery resource survey data. The fishery ecological change data includes historical fish species abundance change curve data, population information, and population growth rate data.

[0014] Based on the aforementioned fishery ecological change data, the population decline degree of each fish species in the target waters was assessed, and population decline degree data for each fish species was obtained.

[0015] Obtain information on the breeding cycle and number of fish species in the target water area, and determine the population resilience of each fish species based on the breeding cycle and number of fish species and the degree of population decline.

[0016] Fish species whose population decline is greater than the first preset value and whose population recovery capacity is greater than the second preset recovery capacity are selected as the target fish species for propagation in the target waters.

[0017] Based on the fishery resource survey data, the aggregation areas of the propagated fish species in different seasons in the target waters are determined, the ecological preference zones of the propagated fish species in different seasons are determined, water body data of the ecological preference zones in different seasons are obtained, and ecological preference information is obtained. The ecological preference information includes water temperature, water pressure, water velocity, light intensity, water turbidity, food organism abundance, and dissolved oxygen concentration.

[0018] In this solution, the step of acquiring historical water body stratification data of the target water area within a preset time period, analyzing the historical water body stratification data based on a time series decomposition algorithm, identifying seasonal extreme event characteristics of the target water area, and constructing a seasonal extreme event characteristic dataset specifically involves:

[0019] The target water area is divided into sub-regions, and N three-dimensional sub-regions are constructed. Historical hydrological data of each sub-region within a preset time period are obtained. The historical hydrological data includes temperature, water pressure, and dissolved oxygen concentration data.

[0020] Based on the historical hydrological data, a time series data of historical water body layer structure is constructed according to the location information of three-dimensional sub-regions and the data acquisition time series.

[0021] The historical water body stratification time series data is decomposed on a time scale based on the empirical mode decomposition algorithm, and the intrinsic mode function components of the corresponding water body stratification data are extracted. Based on the intrinsic mode function components, the mode components containing seasonal periodic variation characteristics are identified and labeled as seasonal mode components.

[0022] Extreme point extraction and slope analysis are performed on the seasonal modal components. Based on the extreme points and slopes, the extreme value ranges of the abrupt changes in water stratification characteristics of the target water area in different seasons are identified. The abrupt changes in water stratification characteristics include sudden drops in water temperature, sudden drops in water pressure, and sudden drops in dissolved oxygen.

[0023] Based on the temporal location and magnitude changes of the extreme value intervals, a seasonal extreme value event feature dataset is constructed for the target water area in different sub-regions. The seasonal extreme value events include sudden drops in temperature, sudden changes in water pressure, and sudden drops in dissolved oxygen.

[0024] In this solution, generating a water environment stress feature map based on the seasonal extreme event feature dataset specifically involves:

[0025] Based on the seasonal extreme event feature dataset, an initial time distribution sequence for each type of seasonal extreme event is constructed. The initial time distribution sequence is processed by a sliding window to construct an event time window sample set. The event time window sample set is fitted with a probability density function based on a kernel density estimation algorithm to obtain the time distribution probability of each type of seasonal extreme event.

[0026] Based on the seasonal extreme event feature dataset, determine the spatial distribution information of each type of seasonal extreme event, aggregate the spatial distribution information according to the geographic coordinates of three-dimensional sub-regions, and use a Gaussian mixture clustering algorithm based on spatial adjacency weight to perform cluster analysis on the event spatial distribution samples, extract the spatial center and spatial diffusion characteristics of each type of seasonal extreme event in the target water area, and obtain spatial distribution feature information.

[0027] Based on the temporal distribution probability and spatial distribution characteristics, a spatiotemporal joint probability distribution model of seasonal extreme events is constructed using the Bayesian joint modeling method. The probability of various seasonal extreme events occurring in different sub-regions within a future time range is determined based on the spatiotemporal joint probability distribution model.

[0028] The target water area is mapped across the entire region based on the spatiotemporal joint probability distribution model. The probability of seasonal extreme events occurring in each sub-region is used as a weighting coefficient to construct a multi-source stress factor layer that includes events such as sudden drop in water temperature, sudden change in water pressure, and sudden drop in dissolved oxygen. The layers are then fused using a spatial weighted overlay algorithm to generate a water environment stress feature map of the target water area in different time periods and different sub-regions.

[0029] In this scheme, the step of determining the propagation control scheme for the target water area based on the aquatic environmental stress characteristic map and the ecological preference information of the propagated fish species specifically involves:

[0030] Based on the aquatic environmental stress feature map and the ecological preference information of the propagated fish species, a spatiotemporal matching analysis was performed on the occurrence probability of stress events in each sub-region of the target water area and the ecological preference parameters of the propagated fish species to generate a set of ecological stress avoidance rules.

[0031] Based on the ecological stress avoidance rule set, sub-regions in the target water area with a stress event occurrence probability lower than the stress avoidance threshold within a preset time period and meeting the ecological preference requirements of the propagated fish species are identified and marked as preferred propagation areas. At the same time, sub-regions with a stress event occurrence probability higher than the stress avoidance threshold are selected and marked as propagation avoidance areas.

[0032] Historical water carrying capacity data of the preferred breeding areas are obtained, and the maximum breeding capacity of each preferred breeding area is calculated by combining the breeding cycle and population resilience of the breeding fish species. The water carrying capacity data includes food organism abundance and dissolved oxygen cycle rate.

[0033] The stocking quantity of fish fry is determined based on the maximum carrying capacity for propagation, and the stocking time of fish fry in the preferred propagation area is determined based on the ecological stress avoidance rule set. The preferred propagation area is used as the stocking location of fish fry. Based on the stocking quantity, stocking time and stocking location of fish fry, a propagation control scheme for the target water area is constructed.

[0034] In this scheme, the construction of a monitoring sensor network for aquaculture in the target water area, the monitoring of the aquaculture effect of the aquaculture in the target water area based on the sensor network, the acquisition of monitoring quality information of the sensor network in real time, and the optimization of monitoring control of the sensor network based on the monitoring quality information are specifically as follows:

[0035] Monitoring sensors, including camera sensors, laser sensors, and hydrological monitoring sensors, are deployed in the preferred breeding area to construct a monitoring sensor network;

[0036] The activity trajectory information of the propagated fish species is acquired in real time according to the monitoring sensor network, and the dwell time of the propagated fish species within the monitoring range of each monitoring sensor in each monitoring sensor network is determined according to the activity trajectory information.

[0037] When the residence time of the propagated fish species is greater than the preset residence time threshold, initial monitoring quality information is generated based on the data transmission frequency, data integrity rate and energy consumption data uploaded by the sensor node. When the initial monitoring quality is less than the preset quality, the communication frequency and sleep cycle of the sensor are determined based on the residence time.

[0038] When the residence time of the propagated fish species is not greater than the preset residence time threshold, it is determined whether there are coverage blind spots or data transmission interruptions in the sensor nodes in the preferred propagation area. If so, the deployment simulation of the sensor nodes in the area is carried out, and the deployment density and spatial layout of the nodes are adjusted according to the simulation results until the monitoring coverage is greater than the preset coverage, and a high coverage network topology is constructed.

[0039] The sensor network is monitored and controlled and optimized based on the communication frequency and sleep cycle or network topology.

[0040] A second aspect of the present invention also provides a fisheries enhancement and control optimization system for a target water area. The system includes a memory and a processor. The memory includes a fisheries enhancement and control optimization method program for the target water area. When the processor executes the fisheries enhancement and control optimization method program for the target water area, it performs the following steps:

[0041] Acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area;

[0042] Historical water body stratification data of the target water area within a preset time period is obtained. The historical water body stratification data is analyzed based on a time series decomposition algorithm to identify seasonal extreme events in the target water area and construct a seasonal extreme event feature dataset.

[0043] A water environment stress feature map is generated based on the seasonal extreme event feature dataset. A propagation control scheme for the target water area is determined based on the water environment stress feature map and the ecological preference information of the propagated fish species.

[0044] A sensor network for monitoring aquaculture species in a target water area is constructed. The aquaculture effect of the aquaculture species in the target water area is monitored based on the sensor network. The monitoring quality information of the sensor network is acquired in real time. The monitoring control of the sensor network is optimized based on the monitoring quality information.

[0045] This invention discloses a method and system for optimizing fishery enhancement control in target waters. The method includes: acquiring fishery ecological change data of the target waters, determining suitable fish species for enhancement and identifying their ecological preferences; collecting historical water stratification data, analyzing seasonal extreme events using a time-series decomposition algorithm, and constructing an extreme value feature dataset; generating a water environment stress feature map based on this dataset, and formulating enhancement control schemes in conjunction with fish species ecological preferences; constructing a monitoring sensor network for enhanced fish species, monitoring the enhancement effect in real time, and optimizing and regulating the network based on monitoring quality information. Through this method, refined management and dynamic optimization of the fish enhancement process can be achieved, improving fishery enhancement effectiveness and ecological adaptability, and providing technical support for sustainable fishery resource utilization. Attached Figure Description

[0046] Figure 1 A flowchart of an optimization method for fisheries enhancement and control in target waters according to the present invention is shown;

[0047] Figure 2 The flowchart illustrating the generation of aquatic environmental stress feature maps according to the present invention is shown;

[0048] Figure 3 A flowchart illustrating the propagation control scheme for determining target water areas according to the present invention is shown;

[0049] Figure 4 A block diagram of a fisheries enhancement and control optimization system for target waters according to the present invention is shown. Detailed Implementation

[0050] 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.

[0051] 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.

[0052] Figure 1 A flowchart of an optimization method for fisheries enhancement and control in target waters according to the present invention is shown.

[0053] like Figure 1 As shown, the first aspect of the present invention provides a method for optimizing fishery enhancement and control in target waters, comprising:

[0054] S102, acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area;

[0055] S104, acquire historical water body stratification data of the target water area within a preset time period, analyze the historical water body stratification data based on the time series decomposition algorithm, identify seasonal extreme events of the target water area, and construct a seasonal extreme event feature dataset.

[0056] S106, Generate an aquatic environmental stress feature map based on the seasonal extreme event feature dataset, and determine the propagation control scheme for the target aquatic area based on the aquatic environmental stress feature map and the ecological preference information of the propagated fish species;

[0057] S108, Construct a monitoring sensor network for the propagated fish species in the target water area, monitor the propagation effect of the propagated fish species in the target water area based on the sensor network, acquire the monitoring quality information of the sensor network in real time, and optimize the monitoring and control of the sensor network based on the monitoring quality information.

[0058] It is important to note that acquiring and analyzing fishery ecological change data, identifying degraded fish species and their ecological preferences, and ensuring that the selected propagation fish species have recovery potential and are adapted to the aquatic environment are crucial. Secondly, based on historical water stratification data and time-series decomposition algorithms, seasonal extreme events of water temperature, water pressure, and dissolved oxygen are identified, constructing a water environment stress characteristic map to understand key environmental risks. Subsequently, the fish species' ecological preferences are matched with the environmental stress map to determine suitable propagation time, area, and stocking density, and to formulate the optimal propagation control plan. Finally, by constructing a monitoring sensor network, real-time fish activity and environmental information are acquired, and the network deployment and operating strategies are dynamically adjusted based on monitoring quality feedback to improve monitoring accuracy and efficiency, achieving closed-loop control and optimization of propagation effects, and significantly improving the efficiency of fishery resource recovery.

[0059] According to an embodiment of the present invention, the step of acquiring fishery ecological change data of a target water area, determining the fish species to be propagated in the target water area based on the fishery ecological change data, and identifying the ecological preference information of the fish species to be propagated in the target water area specifically includes:

[0060] Acquire fishery resource survey data of the target water area within a historical preset time period, and determine fishery ecological change data of the target water area based on the fishery resource survey data. The fishery ecological change data includes historical fish species abundance change curve data, population information, and population growth rate data.

[0061] Based on the aforementioned fishery ecological change data, the population decline degree of each fish species in the target waters was assessed, and population decline degree data for each fish species was obtained.

[0062] Obtain information on the breeding cycle and number of fish species in the target water area, and determine the population resilience of each fish species based on the breeding cycle and number of fish species and the degree of population decline.

[0063] Fish species whose population decline is greater than the first preset value and whose population recovery capacity is greater than the second preset recovery capacity are selected as the target fish species for propagation in the target waters.

[0064] Based on the fishery resource survey data, the aggregation areas of the propagated fish species in different seasons in the target waters are determined, the ecological preference zones of the propagated fish species in different seasons are determined, water body data of the ecological preference zones in different seasons are obtained, and ecological preference information is obtained. The ecological preference information includes water temperature, water pressure, water velocity, light intensity, water turbidity, food organism abundance, and dissolved oxygen concentration.

[0065] It should be noted that by acquiring historical fishery resource survey data of the target waters, constructing fishery ecological change data reflecting changes in fish abundance, population size, and growth rate, and then assessing the degree of population decline and resilience of each fish species, a scientific diagnosis and recovery analysis of the current state of fish resource degradation is achieved. This ensures that the selected fish species for propagation are not only ecologically vulnerable and in urgent need of intervention, but also possess good population recovery potential, thereby significantly improving the probability of effective propagation intervention and the efficiency of resource recovery. Furthermore, by analyzing the aggregation areas of target fish species in different seasons and the corresponding aquatic environmental characteristics, their ecological preference information under specific time and spatial conditions, such as water temperature, water pressure, water velocity, light intensity, water turbidity, food abundance, and dissolved oxygen concentration, can be extracted. This clarifies the most suitable environmental requirements for the survival and reproduction of propagated fish species, providing a key basis for matching the ecological needs of fish species with the adaptability of the aquatic environment in the subsequent formulation of propagation programs. This avoids propagation failure or resource waste due to environmental mismatch, thereby significantly improving the accuracy, ecological adaptability, and resource utilization efficiency of fishery propagation. The fishery resource survey data refers to data obtained through regular sampling and monitoring of fish population composition, population distribution, growth status, reproduction, and environmental conditions in aquatic waters. The ecological preference information also includes substrate type and habitat structure complexity preferences.

[0066] According to an embodiment of the present invention, the step of acquiring historical water body stratification data of the target water area within a preset time period, analyzing the historical water body stratification data based on a time series decomposition algorithm, identifying seasonal extreme event characteristics of the target water area, and constructing a seasonal extreme event characteristic dataset specifically includes:

[0067] The target water area is divided into sub-regions, and N three-dimensional sub-regions are constructed. Historical hydrological data of each sub-region within a preset time period are obtained. The historical hydrological data includes temperature, water pressure, and dissolved oxygen concentration data.

[0068] Based on the historical hydrological data, a time series data of historical water body layer structure is constructed according to the location information of three-dimensional sub-regions and the data acquisition time series.

[0069] The historical water body stratification time series data is decomposed on a time scale based on the empirical mode decomposition algorithm, and the intrinsic mode function components of the corresponding water body stratification data are extracted. Based on the intrinsic mode function components, the mode components containing seasonal periodic variation characteristics are identified and labeled as seasonal mode components.

[0070] Extreme point extraction and slope analysis are performed on the seasonal modal components. Based on the extreme points and slopes, the extreme value ranges of the abrupt changes in water stratification characteristics of the target water area in different seasons are identified. The abrupt changes in water stratification characteristics include sudden drops in water temperature, sudden drops in water pressure, and sudden drops in dissolved oxygen.

[0071] Based on the temporal location and magnitude changes of the extreme value intervals, a seasonal extreme value event feature dataset is constructed for the target water area in different sub-regions. The seasonal extreme value events include sudden drops in temperature, sudden changes in water pressure, and sudden drops in dissolved oxygen.

[0072] It should be noted that the Empirical Mode Decomposition (EMD) algorithm can effectively identify the seasonal extreme event characteristics of target water bodies because EMD has good adaptability and nonlinear non-stationary time series processing capabilities. It can decompose complex historical water body stratification time series data into several intrinsic mode function (IMF) components with different time scales. These IMF components reflect the multi-level fluctuation characteristics inherent in the original data, with certain specific components exhibiting obvious periodic variation patterns, accurately reflecting the fluctuation trends of key hydrological indicators such as water temperature, water pressure, and dissolved oxygen during seasonal transitions. By extracting extreme points and analyzing slope changes in these seasonally characteristic mode components, the occurrence time, intensity, and magnitude of seasonal extreme events such as sudden drops in water temperature, abrupt changes in water pressure, and sudden drops in dissolved oxygen concentration can be precisely located, thereby constructing a high-resolution seasonal extreme event feature dataset covering each sub-region of the target water body. The corresponding water body stratification data includes temperature stratification data, water pressure stratification data, and dissolved oxygen stratification data. The intrinsic mode function components are inherent time-scale components with local features and single oscillation modes adaptively separated from complex signals by the empirical mode decomposition algorithm. The abrupt changes in water stratification characteristics are all features whose degree of change exceeds a preset value within a preset time period, and may also include features affecting fish survival conditions such as changes in food abundance. The seasonal extreme event feature dataset includes the temporal location and amplitude changes of abrupt events such as sudden drops in water temperature, sudden changes in water pressure, and sudden drops in dissolved oxygen in each three-dimensional sub-region, extracted by the empirical mode decomposition algorithm. Seasonal extreme events may also include events affecting fish survival such as food shortage events.

[0073] Figure 2 The flowchart for generating aquatic environmental stress feature maps according to the present invention is shown.

[0074] According to an embodiment of the present invention, the step of generating aquatic environmental stress feature map based on the seasonal extreme event feature dataset specifically includes:

[0075] S202, construct an initial time distribution sequence for each type of seasonal extreme event based on the seasonal extreme event feature dataset, perform sliding window processing on the initial time distribution sequence to construct an event time window sample set, and fit the probability density function of the event time window sample set based on the kernel density estimation algorithm to obtain the time distribution probability of each type of seasonal extreme event.

[0076] S204, Based on the seasonal extreme event feature dataset, determine the spatial distribution information of each type of seasonal extreme event, aggregate the spatial distribution information according to the geographic coordinates of the three-dimensional sub-regions, and use a Gaussian mixture clustering algorithm based on spatial adjacency weight to perform cluster analysis on the event spatial distribution samples, extract the spatial center and spatial diffusion characteristics of each type of seasonal extreme event in the target water area, and obtain spatial distribution feature information.

[0077] S206, Based on the temporal distribution probability and spatial distribution characteristic information, construct a spatiotemporal joint probability distribution model of seasonal extreme events based on the Bayesian joint modeling method, and determine the probability of various seasonal extreme events occurring in different sub-regions within the future time range based on the spatiotemporal joint probability distribution model;

[0078] S208. Based on the spatiotemporal joint probability distribution model, the target water area is mapped across the entire region. The probability of occurrence of seasonal extreme events in each sub-region is used as a weighting coefficient to construct a multi-source stress factor layer that includes events such as sudden drop in water temperature, sudden change in water pressure, and sudden drop in dissolved oxygen. The layers are then fused using a spatial weighted overlay algorithm to generate a water environment stress feature map of the target water area in different time periods and different sub-regions.

[0079] It should be noted that the kernel density estimation algorithm, by smoothing the temporal data of seasonal extreme events, can estimate the probability density distribution of events without assumptions, accurately reflecting the temporal concentration trend and fluctuation characteristics of event occurrences, thus effectively determining the temporal distribution probability of each type of seasonal extreme event; the Gaussian mixture clustering algorithm based on spatial adjacency weights, by introducing spatial adjacency relationships, effectively considers the correlation and continuity of event samples in geographic space, avoiding clustering errors that rely solely on data features; this algorithm uses a Gaussian mixture model to model the probability distribution of samples, flexibly capturing the multi-peak characteristics and complex forms of event spatial distribution; through iteration... By optimizing parameters, the algorithm accurately identifies the spatial clustering center and diffusion range of events, extracts key spatial distribution features, and thus accurately depicts the spatial distribution patterns of seasonal extreme events in water bodies. The Bayesian joint modeling method can construct a spatiotemporal joint probability distribution model of seasonal extreme events because it introduces prior knowledge and the joint distribution of observed data, enabling systematic reasoning about the probability of event occurrence under uncertainty. In the modeling process, the temporal distribution probability is used as a prior condition, and the spatial distribution features are used as the input to the likelihood function. The Bayesian formula effectively integrates the two to form a unified posterior probability expression. The initial temporal distribution sequence refers to the event time sequence formed by arranging each type of seasonal extreme event in the seasonal extreme event feature dataset according to its first observed occurrence time on the historical timeline. The temporal distribution probability refers to the probability value of a certain type of seasonal extreme event occurring at a specific time point or time interval, obtained by statistically modeling the initial temporal distribution sequence, used to depict the occurrence pattern of this type of event in the time dimension. The spatiotemporal joint probability distribution model refers to a probability distribution model constructed based on Bayesian modeling methods, which jointly models the temporal distribution probability and spatial distribution characteristics of seasonal extreme events to describe the likelihood of such events occurring simultaneously within a specific time and spatial region. The aforementioned aquatic environmental stress feature map is a comprehensive map reflecting the spatiotemporal distribution patterns of seasonal extreme events, used to characterize environmental stress risk zones in target waters that affect the ecological behavior of propagated fish species.

[0080] Figure 3 A flowchart illustrating the propagation control scheme for the target water area as described in this invention is shown.

[0081] According to an embodiment of the present invention, determining the propagation control scheme for the target water area based on the aquatic environmental stress characteristic map and the ecological preference information of the propagated fish species specifically includes:

[0082] S302, Based on the aquatic environmental stress feature map and the ecological preference information of the propagated fish species, a spatiotemporal matching analysis is performed on the probability of stress events occurring in each sub-region of the target water area and the ecological preference parameters of the propagated fish species to generate a set of ecological stress avoidance rules;

[0083] S304, Based on the ecological stress avoidance rule set, identify sub-regions in the target water area where the probability of stress events occurring within a preset time period is lower than the stress avoidance threshold and meets the ecological preference requirements of the propagated fish species, and mark them as preferred propagation areas. At the same time, select sub-regions where the probability of stress events occurring is higher than the stress avoidance threshold and mark them as propagation avoidance areas.

[0084] S306, Obtain historical water carrying capacity data of the preferred breeding areas, and calculate the maximum breeding capacity of each preferred breeding area by combining the breeding cycle and population recovery of the breeding fish species. The water carrying capacity data includes food organism abundance and dissolved oxygen cycle rate.

[0085] S308, determine the stocking quantity of the fish species based on the maximum carrying capacity for propagation, determine the stocking time of the fish species in the preferred propagation area based on the ecological stress avoidance rule set, use the preferred propagation area as the stocking location of the fish species, and construct a propagation control scheme for the target water area based on the stocking quantity, stocking time, and stocking location of the fish species.

[0086] It should be noted that this technical solution enables precise coupling of the ecological environment and fish species suitability of target waters at different temporal and spatial scales, thereby formulating fishery enhancement and control schemes with high ecological adaptability and environmental risk avoidance capabilities. By performing spatiotemporal matching analysis of aquatic environmental stress characteristic maps and ecological preference information of the fish species to be enhanced, optimal enhancement areas suitable for fish growth and high-stress areas to be avoided can be accurately identified, mitigating the risk of fish stress responses or mortality caused by sudden changes in water quality. By combining data on the reproductive cycle, population resilience, and water carrying capacity of the optimal areas for enhancement, scientifically reasonable release capacity and timing can be calculated to avoid over-release leading to resource waste or local ecological imbalance, ultimately improving the survival rate of enhanced fish and the efficiency of ecological restoration. The stress events mentioned are seasonal extreme events. The ecological stress avoidance rule set refers to a set of rules constructed based on the aquatic environmental stress characteristic map and the ecological preference information of the propagated fish species to guide the selection of propagation sites and timing. This rule set includes the probability threshold of various ecological stress events (such as sudden drop in water temperature, sudden change in water pressure, and sudden drop in dissolved oxygen) in different time periods and spatial regions, the suitable survival parameter range of propagated fish species under various environmental factors (such as water temperature, dissolved oxygen, and food abundance), and the spatiotemporal matching relationship between the two. By setting the lower limit of the probability of stress events (i.e., the stress avoidance threshold) and the upper limit of the ecological adaptation parameters of fish species, unsuitable areas and time periods can be screened out, thereby forming a dynamic propagation decision-making basis oriented towards ecological security and propagation success rate.

[0087] According to an embodiment of the present invention, the construction of a target water area fish stock monitoring sensor network, the monitoring of the stock enhancement effect of the target water area fish stock based on the sensor network, the real-time acquisition of monitoring quality information of the sensor network, and the optimization of monitoring control of the sensor network based on the monitoring quality information, specifically includes:

[0088] Monitoring sensors, including camera sensors, laser sensors, and hydrological monitoring sensors, are deployed in the preferred breeding area to construct a monitoring sensor network;

[0089] The activity trajectory information of the propagated fish species is acquired in real time according to the monitoring sensor network, and the dwell time of the propagated fish species within the monitoring range of each monitoring sensor in each monitoring sensor network is determined according to the activity trajectory information.

[0090] When the residence time of the propagated fish species is greater than the preset residence time threshold, initial monitoring quality information is generated based on the data transmission frequency, data integrity rate and energy consumption data uploaded by the sensor node. When the initial monitoring quality is less than the preset quality, the communication frequency and sleep cycle of the sensor are determined based on the residence time.

[0091] It should be noted that the monitoring sensor network includes a fish tagging and identification module for acquiring fish activity data at different locations in the target water area and a hydrological monitoring module for acquiring real-time parameters of the aquatic environment. The data collected by the sensor network is transmitted to the data processing module in real time. When the residence time of the propagated fish species exceeds a preset residence time threshold, it indicates that the fish have been staying in the monitoring area for a long time. This requires the sensors to frequently collect and transmit large amounts of continuous data, which can easily lead to increased node energy consumption, increased data transmission latency, and a greater risk of data loss, thereby reducing the overall monitoring quality and network stability. By dynamically adjusting the communication frequency and sleep cycle of the sensors in conjunction with the fish residence time, effective control of node energy consumption can be achieved, improving the critical timeliness and completeness of data acquisition.

[0092] When the residence time of the propagated fish species is not greater than the preset residence time threshold, it is determined whether there are coverage blind spots or data transmission interruptions in the sensor nodes in the preferred propagation area. If so, the deployment simulation of the sensor nodes in the area is carried out, and the deployment density and spatial layout of the nodes are adjusted according to the simulation results until the monitoring coverage is greater than the preset coverage, and a high coverage network topology is constructed.

[0093] The sensor network is monitored and controlled and optimized based on the communication frequency and sleep cycle or network topology.

[0094] It should be noted that when the residence time of the propagated fish species is not greater than the preset residence time threshold, it indicates that the fish spend a relatively short time in the monitoring area. If the monitoring data is missing or discontinuous, it may not be caused by changes in fish behavior, but rather by coverage blind spots in the sensor deployment or data transmission interruptions, resulting in monitoring gaps or misjudgments. By identifying and simulating sensor deployment, and dynamically optimizing node density and spatial layout, the monitoring coverage within the area can be effectively improved, avoiding the omission of key ecological data. This leads to the construction of a high-coverage, high-reliability monitoring network topology, enhancing the overall system's data perception capabilities and monitoring accuracy.

[0095] Figure 4 A block diagram of a fisheries enhancement and control optimization system for target waters according to the present invention is shown.

[0096] A second aspect of the present invention also provides a fisheries enhancement and control optimization system 4 for a target water area. The system includes a memory 41 and a processor 42. The memory includes a fisheries enhancement and control optimization method program for the target water area. When the processor executes the fisheries enhancement and control optimization method program for the target water area, it performs the following steps:

[0097] Acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area;

[0098] Historical water body stratification data of the target water area within a preset time period is obtained. The historical water body stratification data is analyzed based on a time series decomposition algorithm to identify seasonal extreme events in the target water area and construct a seasonal extreme event feature dataset.

[0099] A water environment stress feature map is generated based on the seasonal extreme event feature dataset. A propagation control scheme for the target water area is determined based on the water environment stress feature map and the ecological preference information of the propagated fish species.

[0100] A sensor network for monitoring aquaculture species in a target water area is constructed. The aquaculture effect of the aquaculture species in the target water area is monitored based on the sensor network. The monitoring quality information of the sensor network is acquired in real time. The monitoring control of the sensor network is optimized based on the monitoring quality information.

[0101] This invention discloses a method and system for optimizing fishery enhancement control in target waters. The method includes: acquiring fishery ecological change data of the target waters, determining suitable fish species for enhancement and identifying their ecological preferences; collecting historical water stratification data, analyzing seasonal extreme events using a time-series decomposition algorithm, and constructing an extreme value feature dataset; generating a water environment stress feature map based on this dataset, and formulating enhancement control schemes in conjunction with fish species ecological preferences; constructing a monitoring sensor network for enhanced fish species, monitoring the enhancement effect in real time, and optimizing and regulating the network based on monitoring quality information. Through this method, refined management and dynamic optimization of the fish enhancement process can be achieved, improving fishery enhancement effectiveness and ecological adaptability, and providing technical support for sustainable fishery resource utilization.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0103] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0104] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0105] 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.

[0106] 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.

[0107] 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. A method for optimizing fisheries enhancement and control in target waters, characterized in that, Includes the following steps: Acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area; Historical water stratification data of the target water area within a preset time period is obtained. This historical water stratification data is then analyzed using a time series decomposition algorithm to identify seasonal extreme events in the target water area and construct a seasonal extreme event feature dataset. Specifically: Based on the empirical mode decomposition algorithm, the time series data of historical water body stratification structure are decomposed on time scale, and the intrinsic mode function components of the corresponding water body stratification structure data are extracted. Based on the intrinsic mode function components, the mode components containing seasonal periodic variation characteristics are identified and labeled as seasonal mode components. Extreme point extraction and slope analysis are performed on the seasonal modal components. Based on the extreme points and slopes, the extreme value ranges of the abrupt changes in water stratification characteristics of the target water area in different seasons are identified. The abrupt changes in water stratification characteristics include sudden drops in water temperature, sudden drops in water pressure, and sudden drops in dissolved oxygen. Based on the temporal location and magnitude changes of the extreme value intervals, a dataset of seasonal extreme value events in different sub-regions of the target water area is constructed. The seasonal extreme value events include sudden drops in temperature, sudden changes in water pressure, and sudden drops in dissolved oxygen. A water environment stress feature map is generated based on the aforementioned seasonal extreme event feature dataset, specifically as follows: Based on the temporal and spatial distribution probability and characteristics of each type of seasonal extreme event, a spatiotemporal joint probability distribution model of seasonal extreme events is constructed using the Bayesian joint modeling method. The probability of each type of seasonal extreme event occurring in different sub-regions within a future time range is determined based on the spatiotemporal joint probability distribution model. The target water area is mapped across the entire region based on the spatiotemporal joint probability distribution model. The probability of seasonal extreme events occurring in each sub-region is used as a weighting coefficient to construct a multi-source stress factor layer that includes events such as sudden drop in water temperature, sudden change in water pressure, and sudden drop in dissolved oxygen. The layers are then fused using a spatial weighted superposition algorithm to generate a water environment stress feature map of the target water area in different time periods and different sub-regions. Based on the aforementioned aquatic environmental stress characteristic map and the ecological preference information of the propagated fish species, a propagation control scheme for the target water area is determined, specifically as follows: Based on the aquatic environmental stress feature map and the ecological preference information of the propagated fish species, a spatiotemporal matching analysis was performed on the occurrence probability of stress events in each sub-region of the target water area and the ecological preference parameters of the propagated fish species to generate a set of ecological stress avoidance rules. Based on the ecological stress avoidance rule set, sub-regions in the target water area with a stress event occurrence probability lower than the stress avoidance threshold within a preset time period and meeting the ecological preference requirements of the propagated fish species are identified and marked as preferred propagation areas. At the same time, sub-regions with a stress event occurrence probability higher than the stress avoidance threshold are selected and marked as propagation avoidance areas. Historical water carrying capacity data of the preferred breeding areas are obtained, and the maximum breeding capacity of each preferred breeding area is calculated by combining the breeding cycle and population resilience of the breeding fish species. The water carrying capacity data includes food organism abundance and dissolved oxygen cycle rate. The stocking quantity of the fish species is determined based on the maximum carrying capacity for propagation, and the stocking time of the fish species in the preferred propagation area is determined based on the ecological stress avoidance rule set. The preferred propagation area is used as the stocking location of the fish species. Based on the stocking quantity, stocking time, and stocking location of the fish species, a propagation control scheme for the target water area is constructed. A sensor network for monitoring aquaculture species in a target water area is constructed. The aquaculture effect of the aquaculture species in the target water area is monitored based on the sensor network. The monitoring quality information of the sensor network is acquired in real time. The monitoring control of the sensor network is optimized based on the monitoring quality information.

2. The method for optimizing fishery enhancement and control in target waters according to claim 1, characterized in that, The process of acquiring fishery ecological change data of the target water area, determining the fish species to be propagated in the target water area based on the fishery ecological change data, and identifying the ecological preference information of the fish species to be propagated in the target water area specifically includes: Acquire fishery resource survey data of the target water area within a historical preset time period, and determine fishery ecological change data of the target water area based on the fishery resource survey data. The fishery ecological change data includes historical fish species abundance change curve data, population information, and population growth rate data. Based on the aforementioned fishery ecological change data, the population decline degree of each fish species in the target waters was assessed, and population decline degree data for each fish species was obtained. Obtain information on the breeding cycle and number of fish species in the target water area, and determine the population resilience of each fish species based on the breeding cycle and number of fish species and the degree of population decline. Fish species whose population decline is greater than the first preset value and whose population recovery capacity is greater than the second preset recovery capacity are selected as the target fish species for propagation in the target waters. Based on the fishery resource survey data, the aggregation areas of the propagated fish species in different seasons in the target waters are determined, the ecological preference zones of the propagated fish species in different seasons are determined, water body data of the ecological preference zones in different seasons are obtained, and ecological preference information is obtained. The ecological preference information includes water temperature, water pressure, water velocity, light intensity, water turbidity, food organism abundance, and dissolved oxygen concentration.

3. The method for optimizing fishery enhancement and control in target waters according to claim 1, characterized in that, The step of acquiring historical water body stratification data of the target water area within a preset time period, analyzing the historical water body stratification data based on a time series decomposition algorithm, identifying seasonal extreme event characteristics of the target water area, and constructing a seasonal extreme event characteristic dataset further includes: The target water area is divided into sub-regions, and N three-dimensional sub-regions are constructed. Historical hydrological data of each sub-region within a preset time period are obtained. The historical hydrological data includes temperature, water pressure, and dissolved oxygen concentration data. Based on the historical hydrological data, a time series data of historical water body layer structure is constructed according to the location information of three-dimensional sub-regions and the time series data acquisition.

4. The method for optimizing fishery enhancement and control in target waters according to claim 1, characterized in that, The step of generating aquatic environmental stress feature map based on the seasonal extreme event feature dataset further includes: Based on the seasonal extreme event feature dataset, an initial time distribution sequence for each type of seasonal extreme event is constructed. The initial time distribution sequence is processed by a sliding window to construct an event time window sample set. The event time window sample set is fitted with a probability density function based on a kernel density estimation algorithm to obtain the time distribution probability of each type of seasonal extreme event. Based on the seasonal extreme event feature dataset, the spatial distribution information of each type of seasonal extreme event is determined. The spatial distribution information is aggregated according to the geographical coordinates of three-dimensional sub-regions. A Gaussian mixture clustering algorithm based on spatial adjacency weight is used to perform cluster analysis on the spatial distribution samples of the events. The spatial center and spatial diffusion characteristics of each type of seasonal extreme event in the target water area are extracted to obtain spatial distribution feature information.

5. The method for optimizing fishery enhancement and control in target waters according to claim 1, characterized in that, The construction of a fish stock enhancement monitoring sensor network for the target water area involves monitoring the fish stock enhancement effect in the target water area using the sensor network, acquiring real-time monitoring quality information of the sensor network, and optimizing the monitoring and control of the sensor network based on the monitoring quality information. Specifically: Monitoring sensors, including camera sensors, laser sensors, and hydrological monitoring sensors, are deployed in the preferred breeding area to construct a monitoring sensor network; The activity trajectory information of the propagated fish species is acquired in real time according to the monitoring sensor network, and the residence time of the propagated fish species within the monitoring range of each monitoring sensor in each monitoring sensor network is determined according to the activity trajectory information. When the residence time of the propagated fish species is greater than the preset residence time threshold, initial monitoring quality information is generated based on the data transmission frequency, data integrity rate and energy consumption data uploaded by the sensor node. When the initial monitoring quality is less than the preset quality, the communication frequency and sleep cycle of the sensor are determined based on the residence time. When the residence time of the propagated fish species is not greater than the preset residence time threshold, it is determined whether there are coverage blind spots or data transmission interruptions in the sensor nodes in the preferred propagation area. If so, the deployment simulation of the sensor nodes in the area is carried out, and the deployment density and spatial layout of the nodes are adjusted according to the simulation results until the monitoring coverage is greater than the preset coverage, and a high coverage network topology is constructed. The sensor network is monitored and controlled and optimized based on the communication frequency and sleep cycle or network topology.

6. A fisheries enhancement and control optimization system for target waters, characterized in that, The fishery enhancement and control optimization system for the target water area includes a storage device and a processor. The storage device includes a fishery enhancement and control optimization method program for the target water area. When the processor executes the fishery enhancement and control optimization method program for the target water area, it performs the following steps: Acquire fishery ecological change data of the target water area, determine the fish species to be propagated in the target water area based on the fishery ecological change data, and identify the ecological preference information of the fish species to be propagated in the target water area; Historical water stratification data of the target water area within a preset time period is obtained. This historical water stratification data is then analyzed using a time series decomposition algorithm to identify seasonal extreme events in the target water area and construct a seasonal extreme event feature dataset. Specifically: Based on the empirical mode decomposition algorithm, the time series data of historical water body stratification structure are decomposed on time scale, and the intrinsic mode function components of the corresponding water body stratification structure data are extracted. Based on the intrinsic mode function components, the mode components containing seasonal periodic variation characteristics are identified and labeled as seasonal mode components. Extreme point extraction and slope analysis are performed on the seasonal modal components. Based on the extreme points and slopes, the extreme value ranges of the abrupt changes in water stratification characteristics of the target water area in different seasons are identified. The abrupt changes in water stratification characteristics include sudden drops in water temperature, sudden drops in water pressure, and sudden drops in dissolved oxygen. Based on the temporal location and magnitude changes of the extreme value intervals, a dataset of seasonal extreme value events in different sub-regions of the target water area is constructed. The seasonal extreme value events include sudden drops in temperature, sudden changes in water pressure, and sudden drops in dissolved oxygen. A water environment stress feature map is generated based on the aforementioned seasonal extreme event feature dataset, specifically as follows: Based on the temporal and spatial distribution probability and characteristics of each type of seasonal extreme event, a spatiotemporal joint probability distribution model of seasonal extreme events is constructed using the Bayesian joint modeling method. The probability of each type of seasonal extreme event occurring in different sub-regions within a future time range is determined based on the spatiotemporal joint probability distribution model. The target water area is mapped across the entire region based on the spatiotemporal joint probability distribution model. The probability of seasonal extreme events occurring in each sub-region is used as a weighting coefficient to construct a multi-source stress factor layer that includes events such as sudden drop in water temperature, sudden change in water pressure, and sudden drop in dissolved oxygen. The layers are then fused using a spatial weighted superposition algorithm to generate a water environment stress feature map of the target water area in different time periods and different sub-regions. Based on the aforementioned aquatic environmental stress characteristic map and the ecological preference information of the propagated fish species, a propagation control scheme for the target water area is determined, specifically as follows: Based on the aquatic environmental stress feature map and the ecological preference information of the propagated fish species, a spatiotemporal matching analysis was performed on the occurrence probability of stress events in each sub-region of the target water area and the ecological preference parameters of the propagated fish species to generate a set of ecological stress avoidance rules. Based on the ecological stress avoidance rule set, sub-regions in the target water area with a stress event occurrence probability lower than the stress avoidance threshold within a preset time period and meeting the ecological preference requirements of the propagated fish species are identified and marked as preferred propagation areas. At the same time, sub-regions with a stress event occurrence probability higher than the stress avoidance threshold are selected and marked as propagation avoidance areas. Historical water carrying capacity data of the preferred breeding areas are obtained, and the maximum breeding capacity of each preferred breeding area is calculated by combining the breeding cycle and population resilience of the breeding fish species. The water carrying capacity data includes food organism abundance and dissolved oxygen cycle rate. The stocking quantity of the fish species is determined based on the maximum carrying capacity for propagation, and the stocking time of the fish species in the preferred propagation area is determined based on the ecological stress avoidance rule set. The preferred propagation area is used as the stocking location of the fish species. Based on the stocking quantity, stocking time, and stocking location of the fish species, a propagation control scheme for the target water area is constructed. A sensor network for monitoring aquaculture species in a target water area is constructed. The aquaculture effect of the aquaculture species in the target water area is monitored based on the sensor network. The monitoring quality information of the sensor network is acquired in real time. The monitoring control of the sensor network is optimized based on the monitoring quality information.

Images