Intelligent intermittent fishing operation management method and system based on lamplight purse seine trapping

Abstract

The invention discloses an intelligent intermittent fishing operation management method and system based on lamplight purse seine trapping. A fish behavior spatio-temporal evolution graph is constructed by acquiring fish resource survey data of a fishing destination of a target fishing boat and fish dynamic response data after arrangement of a lamplight purse seine, future gathering tropism change of a fish school is predicted, and the actual trapping abundance and the expected trapping abundance of the lamplight purse seine are determined according to the future gathering tropism change. When the actual trapping abundance is lower than the expected trapping abundance, in combination with water body environment data and fingerling space-time distribution sequence data, identifying multi-source environment interference factors such as natural enemy interference factors and water body environment interference factors, monitoring each interference factor in real time, evaluating interference intensity change, and constructing an interference intensity change curve; and generating an intermittent fishing operation strategy of the target fishing boat. According to the invention, intelligent regulation and control of fishing operation can be realized, the trapping efficiency is improved, invalid fishing is reduced, and the application value is good.

Description

Technical Field

[0001] This invention relates to the field of fishery fishing technology, and in particular to an intelligent intermittent fishing operation management method and system based on light-based seine net trapping. Background Technology

[0002] Light-guided purse seine fishing is a highly efficient fishing method widely used in marine fisheries. It attracts fish at night by using artificial light sources to induce their phototaxis, and then uses a purse seine structure to encircle and capture schools of fish. It has advantages such as high fishing efficiency and applicability to a wide range of fish species, and has been widely used in the fishing of mid-to-upper-level fish.

[0003] However, existing light-based purse seine fishing operations mainly rely on fishermen's experience or simple, fixed operating procedures. On the one hand, the aggregation behavior of fish schools during light-attracting exhibits significant spatiotemporal dynamics, influenced by various factors such as the fish's own behavioral patterns, migration paths, and changes in light parameters. Traditional methods struggle to accurately determine the optimal attraction time and fishing window, easily leading to low attraction efficiency or deviated fishing timing. On the other hand, the aquatic environment of the fishing area is complex and variable. Changes in environmental parameters such as current velocity, temperature, salinity, dissolved oxygen, and turbidity, as well as the presence of predatory fish, can significantly interfere with the stability of fish aggregation and the attraction effect. Existing technologies typically lack comprehensive identification, quantitative assessment, and dynamic response mechanisms for these multi-source interference factors.

[0004] Therefore, there is an urgent need for an intelligent fishing management method and system that can integrate the spatiotemporal evolution analysis of fish behavior and the perception and prediction results of multi-source environmental disturbance factors, so as to realize the dynamic control and intermittent optimization management of the attraction and fishing process in light-based purse seine fishing operations, thereby improving fishing efficiency, reducing environmental disturbance impact, and promoting the sustainable use of fishery resources. Summary of the Invention

[0005] To address at least one of the aforementioned technical problems, this invention proposes an intelligent intermittent fishing operation management method and system based on light-based netting.

[0006] The first aspect of this invention provides a method for managing intelligent intermittent fishing operations based on light-based netting, comprising: Acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination. Construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. Based on the spatiotemporal evolution map, predict the fish population aggregation trend changes in the future time period, and determine the actual and expected fish attraction abundance of the light-filled enclosure based on the aggregation trend changes and fish resource survey data. When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up are obtained. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, are determined when the actual attraction abundance is less than the expected attraction abundance. The multi-source environmental interference factors are monitored in real time to obtain the data change information of each interference factor. The interference intensity change is evaluated based on the data change information of each interference factor, and an interference intensity change curve is constructed. Based on the interference intensity variation curve, an intermittent fishing operation strategy for the target fishing vessel is constructed.

[0007] In this scheme, the acquisition of fish resource survey data at the target fishing vessel's fishing destination and fish dynamic response data within a preset time period after the target fishing vessel deploys its light-filled purse seine at the fishing destination, and the construction of a spatiotemporal evolution map of fish behavior based on the fish dynamic response data, specifically involves: Obtain fish resource survey data of the target fishing vessel's fishing destination, including fish species composition and density distribution data of the target sea area; The dynamic response data of fish within a preset time period after the deployment of the light-filled seine net at the target fishing destination by underwater acoustic detection equipment is obtained. The dynamic response data of fish includes three-dimensional spatial position sequence data of fish schools within a preset range of the seine net area, individual movement speed data, and population density change data. Based on the three-dimensional spatial location sequence data, a spatial distribution point cloud of fish population within a preset range is constructed for each equally divided time slice. The spatial distribution point cloud is then subjected to spatial interpolation processing to generate a fish population density distribution raster map for each time slice. An optical flow method is introduced to calculate the motion vector field between the fish density distribution raster maps of adjacent time slices, and the overall movement direction, movement speed and migration trajectory of the aggregation center of the fish are extracted based on the motion vector field. Based on the extracted overall movement direction, movement speed and migration trajectory of the gathering center of the fish, an initial spatiotemporal network is constructed in the spatial geographic coordinate system, with the gathering center location corresponding to each time slice as a node and the actual migration path between nodes in adjacent time slices as directed edges. The overall movement direction and movement speed are respectively used as the direction vector and weight attribute of the directed edge, and node attributes are generated by combining the residence time of the gathering center at each node, forming a spatiotemporal evolution map of fish behavior that includes the dynamic migration of the fish gathering center and changes in path direction and speed.

[0008] In this scheme, the step of predicting fish population aggregation trend changes in the future time period based on the spatiotemporal evolution map, and determining the actual and expected fish attraction abundance of the light-filled purse seine based on the aggregation trend change data and fish resource survey data, specifically involves: Based on the spatiotemporal evolution map of fish behavior, the spatial location of the fish aggregation center in each time slice is mapped to a preset gridded geospatial model, each grid is defined as a state, and the state transition sequence of the fish aggregation center between consecutive time slices within the preset time period is obtained. Based on the frequency of transitions from one state to another according to the state transition sequence, a state transition frequency matrix is ​​constructed. The state transition frequency matrix is ​​then row-normalized to obtain the state transition probability matrix of the migration pattern of the fish gathering center between grids. Using the state of the fish community center in the last time slice as the initial state, multi-step Markov prediction is performed based on the state transition probability matrix to calculate the predicted probability of the fish community center being located in each grid state in the future time period. The predicted probability is used as the fish community aggregation tendency change data. Based on the data on the trend of fish population aggregation in the future time period, grids with predicted probabilities higher than the probability threshold are extracted as key areas for future fish population aggregation. The initial fish density of the key areas is multiplied by the corresponding predicted probabilities and then accumulated to obtain the actual attraction abundance of fish for the light-filled enclosure. Based on the fish resource survey data, the initial fish density distribution of each grid area in the target sea area and the phototaxis data of each fish species in the target sea area are obtained. The current light intensity, light color parameters and water transmittance data of the light purse seine are obtained to determine the effective light coverage range. Based on the initial fish density distribution, the phototaxis data of each fish species and the effective light coverage range, the expected attraction abundance of the fish population by the light purse seine is determined.

[0009] In this scheme, when the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location of the light-filled enclosure are acquired. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental disturbance factors are determined where the actual attraction abundance is less than the expected attraction abundance. These factors include natural enemy disturbance factors and water environment disturbance factors. Specifically: When the actual attraction abundance is less than the expected attraction abundance, water environment data of the location where the light-filled enclosure is deployed is obtained. The water environment data includes flow velocity, temperature, salinity, dissolved oxygen concentration and turbidity data. Meanwhile, based on the spatiotemporal evolution map of fish behavior, spatiotemporal distribution sequence data of different fish species in a preset area around the enclosure net are extracted within a preset time period. The spatiotemporal distribution sequence data of fish species includes information on the occurrence time, spatial location and quantity changes of different fish species. Based on the spatiotemporal distribution sequence of fish species, fish species that approach the area of ​​the light-filled enclosure within a preset sub-time period are identified as potential catchable fish species. Suitable aquatic environment data for the potential catchable fish species are obtained, including flow velocity range, temperature range, salinity range, dissolved oxygen concentration threshold, and water turbidity threshold. By comparing the water environment data with the suitable aquatic environment data, the water environment interference factors that affect the fish attraction abundance at the fishing destination are determined. Data on interspecific relationships between each potential catchable fish species is obtained. Based on the interspecific relationship data, it is determined whether there is a predator-prey relationship between each fish species. If there is a predator-prey relationship, the natural enemy fish species that affect the abundance of fish schools are identified as natural enemy interference factors. The aquatic environmental interference factors and natural enemy interference factors are used to construct a multi-source environmental interference factor.

[0010] In this scheme, the real-time monitoring of the multi-source environmental interference factors, obtaining data change information for each interference factor, evaluating the interference intensity change based on the data change information for each interference factor, and constructing an interference intensity change curve are specifically as follows: The underwater environment sensor array collects real-time water environment data at the location of the lighted enclosure, and at the same time, the underwater video monitoring equipment obtains the real-time occurrence frequency and spatial distribution information of natural enemy fish species in the preset area around the enclosure. The deviation between real-time aquatic environment data and suitable aquatic environment data of potential catchable fish species is calculated. The deviation of each aquatic environment parameter is normalized. The normalized deviations are weighted and summed to obtain the real-time interference intensity value of the aquatic environment interference factor. Based on the real-time occurrence frequency and spatial distribution information of predator fish species, the occurrence frequency and average aggregation density of each predator fish species per unit time are statistically analyzed, and the real-time interference intensity value of the predator interference factor is calculated based on the occurrence frequency and average aggregation density. The overall disturbance intensity change is assessed based on the real-time disturbance intensity values ​​of water environment disturbance factors and natural enemy disturbance factors, and a disturbance intensity change curve is constructed.

[0011] In this scheme, the step of constructing an intermittent fishing operation strategy for the target fishing vessel based on the interference intensity change curve specifically includes: The real-time comprehensive interference intensity value is obtained based on the interference intensity change curve, and an interference intensity threshold is set. When the real-time comprehensive interference intensity value is less than the interference intensity threshold, the current time is marked as the effective attraction start time point, and the light-filled enclosure lights are activated to attract fish. After the fish school attraction operation, the migration trajectory and density change data of the fish school gathering center are obtained, and a gathering density threshold and a gathering stability duration threshold are set. It is then determined whether the current fish school gathering density is greater than the gathering density threshold and whether the duration reaches the gathering stability duration threshold. When the fish density exceeds the aggregation density threshold and the duration reaches the aggregation stability duration threshold, the current moment is marked as the fishing operation time point, and the fish are fished. When the real-time comprehensive interference intensity value is not less than the interference intensity threshold, the current time is marked as the pause time point, and the light-attracting operation of the light-attracting net for the fish school is paused until the real-time comprehensive interference intensity value is less than the interference intensity threshold. Then, the current time is marked as the restart time point, and the light-attracting net is restarted to carry out the fish school attraction operation. Based on the effective start time of the trapping, the fishing operation time, the time of pausing the trapping, and the time of restarting the trapping, a strategy for intermittent fishing operations of the target fishing vessel is constructed.

[0012] A second aspect of the present invention also provides an intelligent intermittent fishing operation management system based on light-based netting, the system comprising: a memory and a processor, wherein the memory includes a program for an intelligent intermittent fishing operation management method based on light-based netting, and when the processor executes the program for the intelligent intermittent fishing operation management method based on light-based netting, the following steps are implemented: Acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination. Construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. Based on the spatiotemporal evolution map, predict the fish population aggregation trend changes in the future time period, and determine the actual and expected fish attraction abundance of the light-filled enclosure based on the aggregation trend changes and fish resource survey data. When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up are obtained. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, are determined when the actual attraction abundance is less than the expected attraction abundance. The multi-source environmental interference factors are monitored in real time to obtain the data change information of each interference factor. The interference intensity change is evaluated based on the data change information of each interference factor, and an interference intensity change curve is constructed. Based on the interference intensity variation curve, an intermittent fishing operation strategy for the target fishing vessel is constructed.

[0013] This invention discloses an intelligent intermittent fishing operation management method and system based on light-based purse seine netting. By acquiring fish resource survey data of the target fishing vessel's destination and fish dynamic response data after the deployment of the light-based purse seine netting, a spatiotemporal evolution map of fish behavior is constructed to predict future fish aggregation trends, thereby determining the actual and expected attraction abundance of the light-based purse seine netting. When the actual attraction abundance is lower than the expected attraction abundance, combined with aquatic environmental data and fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, such as predator interference factors and aquatic environmental interference factors, are identified. The interference intensity of each interference factor is monitored in real time and its changes are evaluated, constructing an interference intensity change curve, and thus generating an intermittent fishing operation strategy for the target fishing vessel. This invention enables intelligent control of fishing operations, improves trapping efficiency, reduces ineffective fishing, and has significant application value. Attached Figure Description

[0014] Figure 1 A flowchart of an intelligent intermittent fishing operation management method based on light-based netting trapping according to the present invention is shown; Figure 2 The flowchart illustrating the present invention for determining multi-source environmental interference factors is shown. Figure 3 The flowchart illustrating the construction of the interference intensity variation curve according to the present invention is shown; Figure 4 A block diagram of an intelligent intermittent fishing operation management system based on light-based netting trapping according to the present invention is shown. Detailed Implementation

[0015] 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.

[0016] 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.

[0017] Figure 1 The flowchart of an intelligent intermittent fishing operation management method based on light-based netting trapping according to the present invention is shown.

[0018] like Figure 1 As shown, the first aspect of the present invention provides an intelligent intermittent fishing operation management method based on light-based netting, comprising: S102, acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination, and construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. S104, predict the fish population aggregation trend change data in the future time period based on the spatiotemporal evolution map, and determine the actual and expected attraction abundance of the fish population by the light-filled enclosure net based on the aggregation trend change data and fish resource survey data. S106, when the actual attraction abundance is less than the expected attraction abundance, acquire the water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up, and determine the multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, based on the water environment data and the fish species spatiotemporal distribution sequence data. S108, Real-time monitoring of the multi-source environmental interference factors, acquisition of data change information of each interference factor, evaluation of interference intensity change based on data change information of each interference factor, and construction of interference intensity change curve; S110, construct the intermittent fishing operation strategy for the target fishing vessel based on the interference intensity change curve.

[0019] It should be noted that by acquiring fish resource survey data from the fishing destination and combining it with dynamic response information of fish schools after the deployment of light-filled purse seines, a comprehensive model is constructed to depict the spatial distribution, movement behavior, and aggregation evolution characteristics of fish schools during the trapping process. This model realistically portrays the response patterns of fish schools to light-filled purse seines from a spatiotemporal evolution perspective. Based on this, the spatiotemporal evolution trends of fish behavior are predicted, and combined with basic fish resource data, the actual trapping effect of light-filled purse seines on fish schools at different time periods is compared and analyzed with the theoretically expected effect. When the trapping effect deviates from expectations, aquatic environmental parameters and spatiotemporal distribution information of fish species are introduced to analyze the factors affecting the stability of fish school aggregation. The system identifies and differentiates environmental disturbance factors, enabling precise location of key influencing factors such as predator interference and aquatic environmental anomalies. Furthermore, it continuously monitors and assesses the intensity changes of various disturbance factors, generating quantitative curves reflecting dynamic changes in disturbance, allowing fishing operations to perceive the changing trends of adverse external conditions in real time. Finally, based on the dynamic characteristics of disturbance intensity changes, it intelligently regulates the attraction and fishing timing of light-based purse seine nets, constructing an intermittent fishing strategy. This ensures effective fish aggregation while reducing ineffective attraction and energy waste, improving the overall efficiency and stability of fishing operations, and mitigating the impact of environmental disturbances on fishery resources.

[0020] According to an embodiment of the present invention, the step of acquiring fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled purse seine at the fishing destination, and constructing a spatiotemporal evolution map of fish behavior based on the fish dynamic response data, specifically includes: Obtain fish resource survey data of the target fishing vessel's fishing destination, including fish species composition and density distribution data of the target sea area; The dynamic response data of fish within a preset time period after the deployment of the light-filled seine net at the target fishing destination by underwater acoustic detection equipment is obtained. The dynamic response data of fish includes three-dimensional spatial position sequence data of fish schools within a preset range of the seine net area, individual movement speed data, and population density change data. Based on the three-dimensional spatial location sequence data, a spatial distribution point cloud of fish population within a preset range is constructed for each equally divided time slice. The spatial distribution point cloud is then subjected to spatial interpolation processing to generate a fish population density distribution raster map for each time slice. An optical flow method is introduced to calculate the motion vector field between the fish density distribution raster maps of adjacent time slices, and the overall movement direction, movement speed and migration trajectory of the aggregation center of the fish are extracted based on the motion vector field. Based on the extracted overall movement direction, movement speed and migration trajectory of the gathering center of the fish, an initial spatiotemporal network is constructed in the spatial geographic coordinate system, with the gathering center location corresponding to each time slice as a node and the actual migration path between nodes in adjacent time slices as directed edges. The overall movement direction and movement speed are respectively used as the direction vector and weight attribute of the directed edge, and node attributes are generated by combining the residence time of the gathering center at each node, forming a spatiotemporal evolution map of fish behavior that includes the dynamic migration of the fish gathering center and changes in path direction and speed.

[0021] It should be noted that, based on the dynamic response information of fish schools after the deployment of the light-attracting net, the composition structure, density distribution, and spatial movement state of fish schools in the fishing area are comprehensively perceived and uniformly modeled, avoiding cognitive biases caused by relying solely on single observation data. By converting the three-dimensional spatial position sequence of the fish school into a density distribution raster under time slices, and using optical flow to characterize the motion vector relationship corresponding to the density changes of the fish school in adjacent time periods, the overall movement direction, movement speed, and migration pattern of the aggregation center of the fish school can be continuously and precisely reflected. Furthermore, the migration process of the fish school aggregation center in geographic space is abstracted into a spatiotemporal network structure with directional and weighted attributes, transforming the fish school behavior from discrete observation data into an evolutionary map with temporal correlation and spatial constraints. The preset range refers to the total water area and net area adjacent to the preset range of the net.

[0022] According to an embodiment of the present invention, the step of predicting the fish population aggregation trend change data in the future time period based on the spatiotemporal evolution map, and determining the actual and expected attraction abundance of fish populations by the light-filled purse seine net based on the aggregation trend change data and fish resource survey data, specifically includes: Based on the spatiotemporal evolution map of fish behavior, the spatial location of the fish aggregation center in each time slice is mapped to a preset gridded geospatial model, each grid is defined as a state, and the state transition sequence of the fish aggregation center between consecutive time slices within the preset time period is obtained. Based on the frequency of transitions from one state to another according to the state transition sequence, a state transition frequency matrix is ​​constructed. The state transition frequency matrix is ​​then row-normalized to obtain the state transition probability matrix of the migration pattern of the fish gathering center between grids. Using the state of the fish community center in the last time slice as the initial state, multi-step Markov prediction is performed based on the state transition probability matrix to calculate the predicted probability of the fish community center being located in each grid state in the future time period. The predicted probability is used as the fish community aggregation tendency change data. Based on the data on the trend of fish population aggregation in the future time period, grids with predicted probabilities higher than the probability threshold are extracted as key areas for future fish population aggregation. The initial fish density of the key areas is multiplied by the corresponding predicted probabilities and then accumulated to obtain the actual attraction abundance of fish for the light-filled enclosure. Based on the fish resource survey data, the initial fish density distribution of each grid area in the target sea area and the phototaxis data of each fish species in the target sea area are obtained. The current light intensity, light color parameters and water transmittance data of the light purse seine are obtained to determine the effective light coverage range. Based on the initial fish density distribution, the phototaxis data of each fish species and the effective light coverage range, the expected attraction abundance of the fish population by the light purse seine is determined.

[0023] It should be noted that the continuous spatial migration process of fish school aggregation centers is discretized into a transfer sequence between grid states. A Markov chain model is used to probabilistically model the historical transfer frequency, constructing a stochastic process model reflecting the movement patterns of fish schools. This allows for the probabilistic quantification and prediction of the spatiotemporal distribution characteristics of future fish school aggregations. Combined with the initial fish density distribution at the fishing destination, the predicted probability is transformed into an estimated value of the actual attraction abundance. This estimated value reflects the amount of fish resources that the light-enclosed net may successfully attract in the future under the currently observed fish behavior patterns. By integrating multiple static and dynamic information such as fish phototaxis, light parameters, and water transparency, the theoretically achievable attraction abundance under the current environmental configuration is calculated. This expected value represents the maximum attraction potential that the light-enclosed net should exert under ideal conditions. Attraction abundance refers to the estimated amount of fish resources that can be successfully aggregated and potentially captured through the light-enclosed net attraction method. A gridded geospatial model is a geocoding and analysis method that regularly divides a continuous geographic spatial area into a series of grid cells of the same size, defining each cell as an independent data state.

[0024] Figure 2 The flowchart illustrating the present invention for determining multi-source environmental interference factors is shown.

[0025] According to an embodiment of the present invention, when the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location of the light-filled enclosure are acquired. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental disturbance factors are determined where the actual attraction abundance is less than the expected attraction abundance. These factors include natural enemy disturbance factors and water environment disturbance factors. Specifically: When the actual attraction abundance is less than the expected attraction abundance, water environment data of the location where the light-filled enclosure is deployed is obtained. The water environment data includes flow velocity, temperature, salinity, dissolved oxygen concentration and turbidity data. Meanwhile, based on the spatiotemporal evolution map of fish behavior, spatiotemporal distribution sequence data of different fish species in a preset area around the enclosure net are extracted within a preset time period. The spatiotemporal distribution sequence data of fish species includes information on the occurrence time, spatial location and quantity changes of different fish species. Based on the spatiotemporal distribution sequence of fish species, fish species that approach the area of ​​the light-filled enclosure within a preset sub-time period are identified as potential catchable fish species. Suitable aquatic environment data for the potential catchable fish species are obtained, including flow velocity range, temperature range, salinity range, dissolved oxygen concentration threshold, and water turbidity threshold. By comparing the water environment data with the suitable aquatic environment data, the water environment interference factors that affect the fish attraction abundance at the fishing destination are determined. Data on interspecific relationships between each potential catchable fish species is obtained. Based on the interspecific relationship data, it is determined whether there is a predator-prey relationship between each fish species. If there is a predator-prey relationship, the natural enemy fish species that affect the abundance of fish schools are identified as natural enemy interference factors. The aquatic environmental interference factors and natural enemy interference factors are used to construct a multi-source environmental interference factor.

[0026] It should be noted that when the actual attraction abundance is less than the expected attraction abundance, it indicates that the trapping effect of the light-filled purse seine has not met theoretical expectations in the current fishing operation, possibly due to external interference factors such as abnormal aquatic environment or predatory fish species. By comparing real-time aquatic environmental parameters with the suitable aquatic environment range of potential catchable fish species, specific aquatic environmental elements that deviate from the suitable survival range of the target fish species are identified, thus defining these unfavorable elements as clear aquatic environmental interference factors. Using fish species spatiotemporal distribution data and a pre-set interspecific relationship knowledge base, the presence of predatory or other antagonistic relationships among fish species appearing together around the purse seine is analyzed, thereby accurately identifying predatory fish species that actually disperse or threaten the target fish population as biological predatory interference factors. These predatory fish species are those with predator status.

[0027] Figure 3 A flowchart illustrating the construction of the interference intensity variation curve according to the present invention is shown.

[0028] According to an embodiment of the present invention, the real-time monitoring of the multi-source environmental interference factors, obtaining data change information for each interference factor, evaluating the interference intensity change based on the data change information for each interference factor, and constructing an interference intensity change curve are specifically as follows: The underwater environment sensor array collects real-time water environment data at the location of the lighted enclosure, and at the same time, the underwater video monitoring equipment obtains the real-time occurrence frequency and spatial distribution information of natural enemy fish species in the preset area around the enclosure. The deviation between real-time aquatic environment data and suitable aquatic environment data of potential catchable fish species is calculated. The deviation of each aquatic environment parameter is normalized. The normalized deviations are weighted and summed to obtain the real-time interference intensity value of the aquatic environment interference factor. Based on the real-time occurrence frequency and spatial distribution information of predator fish species, the occurrence frequency and average aggregation density of each predator fish species per unit time are statistically analyzed, and the real-time interference intensity value of the predator interference factor is calculated based on the occurrence frequency and average aggregation density. The overall disturbance intensity change is assessed based on the real-time disturbance intensity values ​​of water environment disturbance factors and natural enemy disturbance factors, and a disturbance intensity change curve is constructed.

[0029] It should be noted that real-time aquatic environmental data, including key parameters such as flow velocity, temperature, salinity, dissolved oxygen concentration, and turbidity, are collected at the location of the illuminated enclosure. Simultaneously, underwater video monitoring is used to obtain information on the frequency and spatial distribution of predator fish species around the enclosure. Deviation analysis and normalization are performed between the aquatic environmental parameters and the suitable environmental conditions for potential catchable fish species. Weights are assigned to the deviations of each environmental parameter, and the real-time intensity value of the aquatic environmental disturbance factor is calculated by accumulating these deviations. Furthermore, the real-time intensity value of the predator disturbance factor is calculated based on the frequency of occurrence and average aggregation density of predator fish species per unit time. These two factors are then combined to form the overall disturbance intensity. A disturbance intensity change curve is constructed using a continuous time series, thereby dynamically depicting the changing trends of environmental and biological disturbances over time.

[0030] According to an embodiment of the present invention, the step of constructing an intermittent fishing operation strategy for the target fishing vessel based on the interference intensity variation curve specifically includes: The real-time comprehensive interference intensity value is obtained based on the interference intensity change curve, and an interference intensity threshold is set. When the real-time comprehensive interference intensity value is less than the interference intensity threshold, the current time is marked as the effective attraction start time point, and the light-filled enclosure lights are activated to attract fish. After the fish school attraction operation, the migration trajectory and density change data of the fish school gathering center are obtained, and a gathering density threshold and a gathering stability duration threshold are set. It is then determined whether the current fish school gathering density is greater than the gathering density threshold and whether the duration reaches the gathering stability duration threshold. When the fish density exceeds the aggregation density threshold and the duration reaches the aggregation stability duration threshold, the current moment is marked as the fishing operation time point, and the fish are fished. When the real-time comprehensive interference intensity value is not less than the interference intensity threshold, the current time is marked as the pause time point, and the light-attracting operation of the light-attracting net for the fish school is paused until the real-time comprehensive interference intensity value is less than the interference intensity threshold. Then, the current time is marked as the restart time point, and the light-attracting net is restarted to carry out the fish school attraction operation. Based on the effective start time of the trapping, the fishing operation time, the time of pausing the trapping, and the time of restarting the trapping, a strategy for intermittent fishing operations of the target fishing vessel is constructed.

[0031] It should be noted that by dynamically acquiring real-time comprehensive interference intensity values ​​based on interference intensity change curves, and combining these with preset interference intensity thresholds, fish school aggregation density thresholds, and aggregation stability duration thresholds, the system enables intelligent initiation, pause, and restart of the light-based purse seine's attraction operation, thereby constructing an intermittent fishing strategy for the target fishing vessel. This strategy can automatically initiate attraction operations when environmental interference is low, quickly attracting fish into the purse seine area under favorable conditions, improving fish aggregation efficiency; when the fish reach a concentrated and stable aggregation state, fishing is carried out to ensure efficient capture and reduce fish escape and ineffective operations; while when external interference intensity is high, attraction operations are paused to avoid resource waste caused by fishing in unfavorable environments. Simultaneously, real-time monitoring dynamically determines the timing for restarting attraction, allowing fishing operations to be carried out under favorable conditions. Overall, this intermittent fishing strategy achieves intelligent and dynamic control of attraction and fishing timing, significantly improving fishing efficiency and energy utilization, reducing the impact of environmental disturbances on fish schools, ensuring the sustainable use of fishery resources, and enhancing the stability and refined management level of the target fishing vessel's operations.

[0032] According to an embodiment of the present invention, it further includes: Real-time multi-layer ocean current data is obtained for the sea area where the light-filled netting is deployed. The real-time multi-layer ocean current data includes a sequence of water velocity vectors from the surface to a preset depth. By comparing the average value and standard deviation of the ocean current velocity vectors of each water layer within adjacent time windows, when the average velocity change of any water layer exceeds a preset multiple of its historical average velocity, or when the angle of change of its velocity direction exceeds a specific threshold, it is determined that a sudden change event has occurred in the current ocean current. When a sudden ocean current event is detected, fish dynamic response data within the same time period are acquired. The intensity and direction of the sudden ocean current event are coupled with the fish dynamic response data for analysis. A displacement vector highly correlated with the ocean current velocity vector is separated from the overall movement trajectory of the fish school and defined as ocean current forced displacement. At the same time, the net displacement component towards the light-filled net in the movement trajectory of the fish school is defined as active phototaxis displacement. The node migration path in the spatiotemporal evolution map of fish behavior is corrected based on the ocean current forced displacement. Specifically, the vector corresponding to the ocean current forced displacement is subtracted from the spatial vector of the original migration path to obtain the fish behavior path after eliminating the influence of ocean current forced displacement. The corrected behavior path is then used to update the direction and weight of the directed edges in the spatiotemporal evolution map. Using the updated spatiotemporal evolution map and combining the amplitude and persistence of the active phototactic displacement, the actual aggregation tendency changes of fish populations in the future time period after excluding the influence of ocean current forcing are reassessed and predicted. Based on the actual aggregation tendency changes, the actual attraction abundance of fish populations by the light-filled purse seine is recalculated.

[0033] According to an embodiment of the present invention, the step of separating a displacement vector highly correlated with the ocean current velocity vector from the overall movement trajectory of the fish school and defining this displacement vector as the ocean current-forced displacement, and defining the net displacement component of the fish school's movement trajectory toward the light-filled enclosure as the active phototactic displacement, specifically involves: A spatial reference system is established with the center of the light-filled enclosure as the origin of the coordinate system. The average position vector of the fish school gathering center is obtained in consecutive equally divided time slices to form a fish school observation displacement sequence. At the same time, the ocean current velocity vector corresponding to the water layer where the fish school is located is obtained in the same time slice to form an ocean current vector sequence. Calculate the vector correlation coefficient between the observed displacement sequence of the fish school and the ocean current vector sequence. When the vector correlation coefficient exceeds the correlation threshold, it is determined that the movement of the fish school is significantly affected by the ocean current forcing. The vector decomposition method is used to decompose the observed displacement of the fish swarm in each time slice into components parallel to the ocean current direction and components perpendicular to the ocean current direction. After superimposing the components parallel to the ocean current direction, the cumulative displacement caused by ocean current forcing is obtained by time integration, which is the ocean current forcing displacement. The residual displacement vector of the fish school is obtained by subtracting the current-forced displacement from the sum of the observed displacement sequences of the fish school. The directional component pointing to the center of the light-filled net in the residual displacement vector is extracted and accumulated to obtain the active phototaxis displacement.

[0034] It should be noted that in actual fishing operations, when unpredictable strong currents or eddies suddenly appear in the sea area, fish schools are often passively displaced by the current. If fish movement trajectories obtained from acoustic or optical monitoring are directly used to construct spatiotemporal evolution maps and predict aggregation trends, the system will misinterpret the current-driven passive drift as an active phototactic response of the fish school to light, leading to an inflated calculated actual attraction abundance. By deploying multi-layered current meters around the perimeter of the net, the system simultaneously acquires the velocity and direction sequences from the surface to the target water layer. It also identifies abrupt current changes by monitoring the rate of change of the average velocity and direction angle of each layer in adjacent time periods. Upon identifying an abrupt change, the system simultaneously acquires the spatial trajectory data of the fish school within the corresponding time period and uses vector correlation analysis to separate the current-driven displacement component, which is highly correlated with the current vector, and the active phototactic displacement component pointing towards the center of the net, from the composite displacement. Based on the separated current-forced displacements, vector corrections are performed on the migration paths in the constructed spatiotemporal evolution map of fish behavior to eliminate passive displacement interference caused by currents, thereby reconstructing the true phototactic behavior paths of fish schools. Using the corrected map and the extracted active phototactic displacement data, the true aggregation trend of fish schools after excluding the influence of currents is reassessed, and the calculation results of actual attraction abundance are updated.

[0035] Figure 4A block diagram of an intelligent intermittent fishing operation management system based on light-based netting trapping according to the present invention is shown.

[0036] A second aspect of the present invention also provides an intelligent intermittent fishing operation management system based on light-based netting, the system comprising: a memory 401, a processor 402, and a communication interface 403. The memory includes a program for an intelligent intermittent fishing operation management method based on light-based netting, and the communication interface is used for data connection and communication between the memory and the processor. When the program for an intelligent intermittent fishing operation management method based on light-based netting is executed by the processor, the following steps are implemented: Acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination. Construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. Based on the spatiotemporal evolution map, predict the fish population aggregation trend changes in the future time period, and determine the actual and expected fish attraction abundance of the light-filled enclosure based on the aggregation trend changes and fish resource survey data. When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up are obtained. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, are determined when the actual attraction abundance is less than the expected attraction abundance. The multi-source environmental interference factors are monitored in real time to obtain the data change information of each interference factor. The interference intensity change is evaluated based on the data change information of each interference factor, and an interference intensity change curve is constructed. Based on the interference intensity variation curve, an intermittent fishing operation strategy for the target fishing vessel is constructed.

[0037] This invention discloses an intelligent intermittent fishing operation management method and system based on light-based purse seine netting. By acquiring fish resource survey data of the target fishing vessel's destination and fish dynamic response data after the deployment of the light-based purse seine netting, a spatiotemporal evolution map of fish behavior is constructed to predict future fish aggregation trends, thereby determining the actual and expected attraction abundance of the light-based purse seine netting. When the actual attraction abundance is lower than the expected attraction abundance, combined with aquatic environmental data and fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, such as predator interference factors and aquatic environmental interference factors, are identified. The interference intensity of each interference factor is monitored in real time and its changes are evaluated, constructing an interference intensity change curve, and thus generating an intermittent fishing operation strategy for the target fishing vessel. This invention enables intelligent control of fishing operations, improves trapping efficiency, reduces ineffective fishing, and has significant application value.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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 management method for intelligent intermittent fishing operations based on light-based netting, characterized in that, Includes the following steps: Acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination. Construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. Based on the spatiotemporal evolution map, predict the fish population aggregation trend changes in the future time period, and determine the actual and expected fish attraction abundance of the light-filled enclosure based on the aggregation trend changes and fish resource survey data. When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up are obtained. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, are determined when the actual attraction abundance is less than the expected attraction abundance. The multi-source environmental interference factors are monitored in real time to obtain the data change information of each interference factor. The interference intensity change is evaluated based on the data change information of each interference factor, and an interference intensity change curve is constructed. Based on the interference intensity variation curve, an intermittent fishing operation strategy for the target fishing vessel is constructed.

2. The intelligent intermittent fishing operation management method based on light-based netting trapping according to claim 1, characterized in that, The process of acquiring fish resource survey data at the target fishing vessel's fishing destination and fish dynamic response data within a preset time period after the target fishing vessel deploys its light-filled purse seine at the fishing destination, and constructing a spatiotemporal evolution map of fish behavior based on the fish dynamic response data, specifically involves: Obtain fish resource survey data of the target fishing vessel's fishing destination, including fish species composition and density distribution data of the target sea area; The dynamic response data of fish within a preset time period after the deployment of the light-filled seine net at the target fishing destination by underwater acoustic detection equipment is obtained. The dynamic response data of fish includes three-dimensional spatial position sequence data of fish schools within a preset range of the seine net area, individual movement speed data, and population density change data. Based on the three-dimensional spatial location sequence data, a spatial distribution point cloud of fish population within a preset range is constructed for each equally divided time slice. The spatial distribution point cloud is then subjected to spatial interpolation processing to generate a fish population density distribution raster map for each time slice. An optical flow method is introduced to calculate the motion vector field between the fish density distribution raster maps of adjacent time slices, and the overall movement direction, movement speed and migration trajectory of the aggregation center of the fish are extracted based on the motion vector field. Based on the extracted overall movement direction, movement speed and migration trajectory of the gathering center of the fish, an initial spatiotemporal network is constructed in the spatial geographic coordinate system, with the gathering center location corresponding to each time slice as a node and the actual migration path between nodes in adjacent time slices as directed edges. The overall movement direction and movement speed are respectively used as the direction vector and weight attribute of the directed edge, and node attributes are generated by combining the residence time of the gathering center at each node, forming a spatiotemporal evolution map of fish behavior that includes the dynamic migration of the fish gathering center and changes in path direction and speed.

3. The intelligent intermittent fishing operation management method based on light-based netting trapping according to claim 1, characterized in that, The step of predicting fish population aggregation trends in the future time period based on the spatiotemporal evolution map, and determining the actual and expected fish attraction abundance of the light-filled purse seine based on the aggregation trend changes and fish resource survey data, specifically involves: Based on the spatiotemporal evolution map of fish behavior, the spatial location of the fish aggregation center in each time slice is mapped to a preset gridded geospatial model, each grid is defined as a state, and the state transition sequence of the fish aggregation center between consecutive time slices within the preset time period is obtained. Based on the frequency of transitions from one state to another according to the state transition sequence, a state transition frequency matrix is ​​constructed. The state transition frequency matrix is ​​then row-normalized to obtain the state transition probability matrix of the migration pattern of the fish gathering center between grids. Using the state of the fish community center in the last time slice as the initial state, multi-step Markov prediction is performed based on the state transition probability matrix to calculate the predicted probability of the fish community center being located in each grid state in the future time period. The predicted probability is used as the fish community aggregation tendency change data. Based on the data on the trend of fish population aggregation in the future time period, grids with predicted probabilities higher than the probability threshold are extracted as key areas for future fish population aggregation. The initial fish density of the key areas is multiplied by the corresponding predicted probabilities and then accumulated to obtain the actual attraction abundance of fish for the light-filled enclosure. Based on the fish resource survey data, the initial fish density distribution of each grid area in the target sea area and the phototaxis data of each fish species in the target sea area are obtained. The current light intensity, light color parameters and water transmittance data of the light purse seine are obtained to determine the effective light coverage range. Based on the initial fish density distribution, the phototaxis data of each fish species and the effective light coverage range, the expected attraction abundance of the fish population by the light purse seine is determined.

4. The intelligent intermittent fishing operation management method based on light-based netting trapping according to claim 1, characterized in that, When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish spatiotemporal distribution sequence data of the location where the light-filled enclosure is deployed are acquired. Based on the water environment data and the fish spatiotemporal distribution sequence data, multi-source environmental disturbance factors are determined to account for the actual attraction abundance being less than the expected attraction abundance. These factors include natural enemy disturbance factors and water environment disturbance factors. Specifically: When the actual attraction abundance is less than the expected attraction abundance, water environment data of the location where the light-filled enclosure is deployed is obtained. The water environment data includes flow velocity, temperature, salinity, dissolved oxygen concentration and turbidity data. Meanwhile, based on the spatiotemporal evolution map of fish behavior, spatiotemporal distribution sequence data of different fish species in a preset area around the enclosure net are extracted within a preset time period. The spatiotemporal distribution sequence data of fish species includes information on the occurrence time, spatial location and quantity changes of different fish species. Based on the spatiotemporal distribution sequence of fish species, fish species that approach the area of ​​the light-filled enclosure within a preset sub-time period are identified as potential catchable fish species. Suitable aquatic environment data for the potential catchable fish species are obtained, including flow velocity range, temperature range, salinity range, dissolved oxygen concentration threshold, and water turbidity threshold. By comparing the water environment data with the suitable aquatic environment data, the water environment interference factors that affect the fish attraction abundance at the fishing destination are determined. Data on interspecific relationships between each potential catchable fish species is obtained. Based on the interspecific relationship data, it is determined whether there is a predator-prey relationship between each fish species. If there is a predator-prey relationship, the natural enemy fish species that affect the abundance of fish schools are identified as natural enemy interference factors. The aquatic environmental interference factors and natural enemy interference factors are used to construct a multi-source environmental interference factor.

5. The intelligent intermittent fishing operation management method based on light-based netting trapping according to claim 1, characterized in that, The process of real-time monitoring of the multi-source environmental interference factors, acquiring data change information for each interference factor, evaluating interference intensity changes based on the data change information for each interference factor, and constructing an interference intensity change curve, specifically involves: The underwater environment sensor array collects real-time water environment data at the location of the lighted enclosure, and at the same time, the underwater video monitoring equipment obtains the real-time occurrence frequency and spatial distribution information of natural enemy fish species in the preset area around the enclosure. The deviation between real-time aquatic environment data and suitable aquatic environment data of potential catchable fish species is calculated. The deviation of each aquatic environment parameter is normalized. The normalized deviations are weighted and summed to obtain the real-time interference intensity value of the aquatic environment interference factor. Based on the real-time occurrence frequency and spatial distribution information of predator fish species, the occurrence frequency and average aggregation density of each predator fish species per unit time are statistically analyzed, and the real-time interference intensity value of the predator interference factor is calculated based on the occurrence frequency and average aggregation density. The overall disturbance intensity change is assessed based on the real-time disturbance intensity values ​​of water environment disturbance factors and natural enemy disturbance factors, and a disturbance intensity change curve is constructed.

6. The intelligent intermittent fishing operation management method based on light-based netting trapping according to claim 1, characterized in that, The intermittent fishing operation strategy for the target fishing vessel, constructed based on the interference intensity change curve, is as follows: The real-time comprehensive interference intensity value is obtained based on the interference intensity change curve, and an interference intensity threshold is set. When the real-time comprehensive interference intensity value is less than the interference intensity threshold, the current time is marked as the effective attraction start time point, and the light-filled enclosure lights are activated to attract fish. After the fish school attraction operation, the migration trajectory and density change data of the fish school gathering center are obtained, and a gathering density threshold and a gathering stability duration threshold are set. It is then determined whether the current fish school gathering density is greater than the gathering density threshold and whether the duration reaches the gathering stability duration threshold. When the fish density exceeds the aggregation density threshold and the duration reaches the aggregation stability duration threshold, the current moment is marked as the fishing operation time point, and the fish are fished. When the real-time comprehensive interference intensity value is not less than the interference intensity threshold, the current time is marked as the pause time point, and the light-attracting operation of the light-attracting net for the fish school is paused until the real-time comprehensive interference intensity value is less than the interference intensity threshold. Then, the current time is marked as the restart time point, and the light-attracting net is restarted to carry out the fish school attraction operation. Based on the effective start time of the trapping, the fishing operation time, the time of pausing the trapping, and the time of restarting the trapping, a strategy for intermittent fishing operations of the target fishing vessel is constructed.

7. A smart intermittent fishing operation management system based on light-based netting, characterized in that, The intelligent intermittent fishing operation management system based on light-based netting includes a storage unit and a processor. The storage unit includes a program for an intelligent intermittent fishing operation management method based on light-based netting. When the processor executes the program for the intelligent intermittent fishing operation management method based on light-based netting, it performs the following steps: Acquire fish resource survey data of the target fishing vessel's fishing destination and fish dynamic response data of the target fishing vessel within a preset time period after the deployment of the light-filled seine net at the fishing destination. Construct a spatiotemporal evolution map of fish behavior based on the fish dynamic response data. Based on the spatiotemporal evolution map, predict the fish population aggregation trend changes in the future time period, and determine the actual and expected fish attraction abundance of the light-filled enclosure based on the aggregation trend changes and fish resource survey data. When the actual attraction abundance is less than the expected attraction abundance, water environment data and fish species spatiotemporal distribution sequence data at the location where the light-filled enclosure is set up are obtained. Based on the water environment data and the fish species spatiotemporal distribution sequence data, multi-source environmental interference factors, including natural enemy interference factors and water environment interference factors, are determined when the actual attraction abundance is less than the expected attraction abundance. The multi-source environmental interference factors are monitored in real time to obtain the data change information of each interference factor. The interference intensity change is evaluated based on the data change information of each interference factor, and an interference intensity change curve is constructed. Based on the interference intensity variation curve, an intermittent fishing operation strategy for the target fishing vessel is constructed.

Images