Antarctic krill fishery change prediction method based on ocean circulation-sea ice-species distribution coupling model

Abstract

The invention discloses an euphausia superba fishery change prediction method based on an ocean circulation-sea ice-species distribution coupling model, and relates to the technical field of ocean science. Euphausia superba fishery historical observation data, satellite remote sensing data and reanalysis data are collected, euphausia superba resources and environmental data are integrated, and the euphausia superba fishery change prediction method based on the ocean circulation-sea ice-species distribution coupling model is obtained. Constructing a polar region resource environment database covering total elements of physics-biology-environment; and based on an FVCOM model, constructing an ocean circulation-sea ice coupling model of a surrounding sea area of the peninsula of the south pole, and simulating and verifying physical environment characteristics of a target sea area. By constructing the ocean circulation-sea ice-species distribution coupling model, integrating multi-source data and analyzing a cooperative driving mechanism of a multi-scale physical process to euphausia superba resource change, compared with a traditional method, the change of an euphausia superba fishery can be simulated and predicted more accurately, and the method has the advantages of being high in practicability and the like. And the problem of inaccurate prediction caused by limited space-time coverage rate of observation data is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of marine science and technology, and particularly relates to a method for predicting the change of Antarctic krill fishing grounds based on a coupled model of ocean circulation - sea ice - species distribution. Background Art

[0002] Antarctic krill is a key primary consumer in the Antarctic ecosystem and plays a crucial role in maintaining the balance of the marine ecosystem. Its abundant biomass makes it an important fishery resource with great economic value. With the increasing tension of global fishery resources, Antarctic krill, as a sustainable fishery resource, has received more and more attention.

[0003] Traditional research on the change of Antarctic krill fishing grounds often focuses on a single scale, making it difficult to comprehensively analyze the synergistic driving mechanism of multi-scale physical processes on the change of krill resources. Moreover, the coverage rate of observational data in space and time is limited, making it difficult to meet the requirements of high-precision prediction, resulting in inaccurate prediction results. Therefore, how to construct a coupled model of ocean circulation - sea ice - species distribution, reveal the formation mechanism of Antarctic krill fishing grounds, and improve the accuracy and precision of fishing ground change prediction is the problem to be solved by the present invention. For this purpose, a method for predicting the change of Antarctic krill fishing grounds based on a coupled model of ocean circulation - sea ice - species distribution is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for predicting the change of Antarctic krill fishing grounds based on a coupled model of ocean circulation - sea ice - species distribution to solve the problems mentioned in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is: A method for predicting the change of Antarctic krill fishing grounds based on a coupled model of ocean circulation - sea ice - species distribution, comprising the following steps: S1. Collect historical observational data of Antarctic krill fisheries, satellite remote sensing data and reanalysis data, integrate Antarctic krill resources and environmental data, and construct a polar resource and environment database covering all elements of physics - biology - environment; S2. Based on the FVCOM model, construct a high-resolution ocean circulation - sea ice coupled model for the waters around the Antarctic Peninsula, and simulate and verify the physical environmental characteristics of the target waters; S3. Simulate and analyze the spatio-temporal variation laws of physical processes including large-scale circulation, meso-scale and small-scale eddies, local ocean currents and sea ice in the target waters, analyze the synergistic effects of physical processes at different scales and their impacts on krill distribution, and quantify the energy transfer paths between different scales; S4. Integrate the acoustic data collected by krill fishing boats, combine the target strength model and the body length - body weight distribution of krill, conduct acoustic assessment of krill resources, and obtain the spatio-temporal distribution characteristics of resource density; S5. Using the deep learning method of three-dimensional convolutional neural network (3DCNN), combining the acoustic assessment results and environmental data, constructing a species distribution model of Antarctic krill, and mining the spatio-temporal correlation between the two; S6. Combining the environmental data simulated in real time by the ocean circulation-sea ice coupled model and the quasi-real-time krill acoustic data, as model inputs, inputting them into the species distribution model of Antarctic krill, analyzing and predicting the spatio-temporal distribution of krill density in the waters around the fishing hotspots, and revealing the formation mechanism of fishing grounds.

[0006] A further improvement of the technical solution of the present invention lies in: The specific steps of S1 include: Collect the historical observation data of Antarctic krill fisheries in the target sea area, including hydrographic sections, krill biological parameters and resource acoustic data, and sort out the marine survey data carried out by domestic scientific research teams in the waters around the Antarctic Peninsula; Obtain the satellite remote sensing data of the waters around the Antarctic Peninsula, and collect the global climate reanalysis data, covering the reanalysis data such as ocean currents, salinity, and wind fields. Preprocess the collected historical observation data of Antarctic krill fisheries, satellite remote sensing data and reanalysis data, and then classify the collected data according to the data source and type, and establish a detailed data list; Based on time and space, integrate the preprocessed historical observation data of fisheries, satellite remote sensing data and reanalysis data, establish data association rules, associate the biological information covering the distribution and quantity of Antarctic krill with the marine environmental information, construct an associated data set covering all physical-biological-environmental elements, based on the integrated associated data set, build the framework of the polar resource and environment database, store the preprocessed data into the database according to the designed database framework, form a polar resource and environment database covering all physical-biological-environmental elements, and establish a data dictionary and a metadata management system to describe and label the data in detail.

[0007] A further improvement of the technical solution of the present invention lies in: The specific steps of S2 include: Collect the basic geographical information of the waters around the Antarctic Peninsula, including data such as coastline and water depth, construct a high-resolution computational grid to ensure that the grid can finely depict the complex terrain of this sea area. At the same time, obtain the initial field data of the ocean and sea ice, including temperature, salinity, sea ice concentration, etc. Then, according to the research requirements and the actual marine environmental characteristics, select the FVCOM model as the basic framework, set the physical parameters of the FVCOM model including the turbulence closure scheme, sea ice thermodynamics and dynamics parameters, determine the model calculation area, and configure the open boundary conditions, terrain data and meteorological forcing data; Within the FVCOM framework, an ice module (UG-CICE) and a Lagrangian particle tracking module are embedded to conduct a coupled multi-scale numerical simulation of ocean circulation - sea ice - Lagrangian particle tracking. Through data assimilation technology, in-situ surveys, historical data, and satellite remote sensing data are incorporated into the model to optimize the model parameterization scheme, and then a complete ocean circulation - sea ice coupled model is constructed to ensure smooth data interaction and collaborative operation among modules; Run the constructed ocean circulation - sea ice coupled model to simulate the three-dimensional temperature, salinity, ocean currents, and sea ice dynamic distribution at high spatio-temporal resolution in the target sea area. During the model operation, monitor the running state of the model in real time, and pay attention to the spatio-temporal characteristics of large-scale physical processes such as the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the ocean front, as well as the variation laws of meso-scale physical processes such as the internal vortices in the krill fishing ground, local ocean currents, key temperature-salinity fronts, and water mass structures; Utilize the measured data of the Global Drifter Program, the ARGO Global Ocean Observation Network, and the NOAA National Buoy Data Center, combined with the resource distribution data in the historical literature of krill, to verify the reliability of the model. Compare the simulation results with the measured data, including tidal levels, temperature, salinity, ocean currents, and sea ice coverage, evaluate the simulation accuracy of the model, and adjust the model parameters including adjusting the grid resolution, optimizing the open boundary conditions, and improving the sea ice parameterization scheme according to the verification results to optimize the model performance. Then analyze the verified simulation results to extract the ocean circulation characteristics and the physical environmental characteristics of sea ice in the waters around the Antarctic Peninsula. Among them, the ocean circulation characteristics in the waters around the Antarctic Peninsula include large-scale circulation structures and meso-scale physical processes, and the physical environmental characteristics of sea ice include the sea ice distribution range, sea ice thickness, and sea ice movement. The large-scale circulation structures cover the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the ocean front, and the meso-scale physical processes cover the internal vortices in the krill fishing ground, local ocean currents, key temperature-salinity fronts, and water mass structures.

[0008] A further improvement of the technical solution of the present invention lies in that: the S3 specifically includes: Run the constructed high-resolution ocean circulation - sea ice coupled model to simulate the three-dimensional temperature, salinity, ocean currents, and sea ice dynamic distribution in the target sea area, analyze the physical processes in the target sea area, focus on large-scale circulation structures such as the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the ocean front, as well as the variation characteristics of meso-scale vortices, local ocean currents, key temperature-salinity fronts, and water mass structures inside the krill fishing ground, and record the dynamic change data of each physical process in time and space, including three-dimensional velocity fields, temperature, salinity, and sea ice data; Analyze the simulation results, extract the spatio-temporal variation laws of large-scale circulation, meso-scale vortices, local ocean currents, and sea ice, and analyze the interaction between physical processes at different scales; Screen the ecological habit data of Antarctic krill from the historical observation data of Antarctic krill fishery in the target sea area, analyze the influence of physical processes at different scales on the distribution of krill, establish a quantitative relationship model between physical processes and krill distribution, and evaluate the relative importance of each physical process to krill distribution; Use the energy flux spectrum analysis method to quantify the energy transfer path between physical processes at different scales, analyze the energy cascade process from large-scale circulation to small- and medium-scale physical processes, as well as the distribution and dissipation characteristics of energy in physical processes at different scales. Through energy transfer analysis, further understand the cooperative mechanism of physical processes.

[0009] A further improvement of the technical solution of the present invention lies in that: the specific process of quantifying the energy transfer path between physical processes at different scales includes: Obtain the three-dimensional velocity field, temperature, salinity and sea ice data output by the high-resolution ocean circulation-sea ice coupling model, and preprocess the simulated data, including data format unification, missing value processing, outlier removal, etc., and convert the time series data into a format suitable for energy spectrum analysis; Use Fourier transform to perform spectral analysis on the preprocessed data, calculate the energy spectra of each physical process at different frequencies, analyze the obtained energy spectra, identify the energy peaks and valleys at different scales, determine the main energy transfer paths between different scales, and preliminarily judge the energy cascade characteristics from large-scale circulation to small- and medium-scale physical processes, as well as the distribution of energy in physical processes at different scales; Further quantify the specific path and efficiency of energy transfer from large scales to small and medium scales, calculate the energy transfer flux between different scales, and then analyze the distribution and dissipation characteristics of energy in physical processes at different scales, calculate the energy content of physical processes at each scale, determine the relative importance of energy at different scales, and at the same time, analyze the dissipation of energy at each scale, and identify the main regions and processes of energy dissipation; Combined with the quantified energy transfer path, distribution and dissipation characteristics, analyze the cooperative mechanism between physical processes, clarify the role of each physical process in maintaining the stability and productivity of the krill fishing ground, and summarize the results of energy flux spectrum analysis, and write an analysis report, including the description of the energy transfer path between different scales, the summary of energy distribution and dissipation characteristics, and the elaboration of the cooperative mechanism of physical processes.

[0010] A further improvement of the technical solution of the present invention lies in that: the specific content of S4 includes: Collect cross-sectional acoustic data through the acoustic equipment carried on krill fishing vessels, combine with the environmental parameter data synchronously recorded by expendable bathythermographs, use Echoview software to eliminate noise from the original cross-sectional acoustic data and environmental parameter data, adopt the dynamic signal-to-noise ratio threshold method to remove background noise, and distinguish krill from other plankton by the frequency difference method. After optimizing the resampling interval, ensure that the data amplitude change conforms to the acoustic scattering characteristics to generate a clean acoustic echogram; Based on the Demer-Martin target strength model, combine with the krill body length-target strength relationship, convert the acoustic scattering value to krill density through echo integration technology, use the multi-frequency difference method to invert the krill body length distribution, combine with the on-site trawl sampling data to verify the model accuracy, and establish the body length-body weight power function relationship; Input the cross-sectional acoustic data into the target strength model, combine with the krill body length-body weight distribution information, conduct target recognition and classification on the cross-sectional acoustic data, distinguish krill from other marine organisms or non-biological targets, perform spatial grid processing on the cross-sectional acoustic data, and calculate the krill density in each grid unit according to the acoustic signals and target strengths in different regions to obtain the distribution characteristics of krill resource density in different times and spaces and generate the spatio-temporal distribution map of krill resource density.

[0011] A further improvement of the technical solution of the present invention lies in: the generation process of the spatio-temporal distribution map of krill resource density is as follows: Import the collected cross-sectional acoustic data into the target strength model, and at the same time incorporate the krill body length-body weight distribution information. Use the target strength model to analyze the characteristics of acoustic signals, and based on the differences in acoustic responses of different biological or non-biological targets, complete target recognition and classification, distinguish krill from other marine organisms or non-biological targets, and use the target strength model to calculate the target strength corresponding to each acoustic signal in combination with the acoustic signal characteristics, and then estimate the target size and biomass; Based on the target strength and biomass data calculated by the target strength model, conduct a preliminary estimate of krill resource density, comprehensively consider the covered area of acoustic data and sampling interval, and combine with the biological characteristics of krill to convert the target biomass into krill resource density per unit area; Perform spatial grid processing on the cross-sectional acoustic data, divide grid units according to the size and accuracy requirements of the research area, integrate the acoustic signals and target strength data in each grid unit, and calculate the krill density in each grid unit in combination with the estimated krill resource density information; Based on the cross-sectional acoustic data collected at different times and the corresponding spatial grid processing results, analyze the variation law of krill resource density in time and space. By comparing the data at different time points, determine the dynamic change of krill resource density over time. Combining the data of different spatial grid units, explore the spatial distribution differences of krill resource density. Use geographic information system to visualize the analysis results and generate a spatio-temporal distribution map of krill resource density, intuitively showing the distribution characteristics of krill resources at different times and in different spaces.

[0012] A further improvement of the technical solution of the present invention lies in: The S5 specifically includes: Collect and integrate the acoustic assessment data and marine environmental data of Antarctic krill from scientific research databases and marine survey vessel record systems. Match and integrate the collected acoustic assessment data and marine environmental data according to time and space coordinates to construct a unified data set, and preprocess the acoustic assessment data and marine environmental data, including data cleaning, normalization processing and format conversion, to ensure the consistency and readability of the data, and then divide the data into a training set, a validation set and a test set; Design the architecture of a three-dimensional convolutional neural network (3DCNN) model to construct a species distribution model of Antarctic krill, including multiple convolutional layers, pooling layers and fully connected layers. Select the ReLU activation function and the Adam optimizer, and set the loss function of mean square error for model training. Then use the training set to train the three-dimensional convolutional neural network model, optimize the model parameters through the backpropagation algorithm, and adjust the weights and bias values of the convolutional kernels to minimize the training loss. During the training process, use the validation set to evaluate the model performance to prevent overfitting. Adjust the hyperparameters of the model according to the loss and accuracy of the validation set, record the changes in loss and accuracy during the training process, draw a training curve, and analyze the convergence of the model; Use the test set to finally evaluate the trained species distribution model of Antarctic krill, calculate the prediction accuracy, recall rate and F1 score metrics of the model, evaluate the prediction performance of the model for the krill species distribution, and generate a prediction map of krill distribution according to the prediction results of the model, and compare it with the actual distribution map to show the prediction effect of the model; Apply the trained species distribution model of Antarctic krill to the actual assessment of Antarctic krill resources and fishing ground prediction. Input new acoustic assessment data and environmental data, output the distribution prediction results of krill, and then analyze its output results, mine the spatio-temporal correlation between the acoustic assessment results and environmental data, and show the impact of different environmental factors on krill distribution and the variation law of krill distribution over time and space through visualization technology.

[0013] A further improvement of the technical solution of the present invention lies in: The S6 specifically includes: Using an ocean circulation-sea ice coupled model, environmental data of the waters around the fishing hotspots are obtained through real-time simulation, covering temperature, salinity, sea current velocity, sea ice coverage and thickness, etc. At the same time, quasi-real-time acoustic data of krill are obtained through shipborne or buoy acoustic devices, including information such as the echo intensity and distribution depth of krill, and then the environmental data and quasi-real-time acoustic data of krill are preprocessed respectively; The preprocessed environmental data simulated by the ocean circulation-sea ice coupled model and the quasi-real-time acoustic data of krill are input into the constructed Antarctic krill species distribution model according to the time series and spatial coordinates, ensuring the integrity and accuracy of data input. Based on the input data, the Antarctic krill species distribution model makes a preliminary prediction of the krill density in the waters around the fishing hotspots and outputs the preliminary spatio-temporal distribution results of krill density to preliminarily understand the distribution trend of krill in this area; Combined with the preliminary prediction results, analyze the relationship between the environmental data and the krill density distribution, extract the distribution characteristics of krill density at different times and spaces, reveal the physical and ecological mechanisms of the formation of the fishing ground, clarify the role of key environmental factors on the distribution of krill, and identify the relationship between the high-density areas of krill and the environmental factors of ocean circulation and sea ice distribution; Visualize the prediction results of the Antarctic krill species distribution model to generate a spatio-temporal distribution map of krill density. Using geographic information system technology, combine the prediction results with the actual geographic information to generate a dynamic visualization report to show the change process of the fishing ground over time.

[0014] Due to the adoption of the above technical solutions, the technical progress achieved by the present invention compared with the prior art is: The present invention provides a method for predicting the changes in Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model. By constructing an ocean circulation-sea ice-species distribution coupled model, integrating multi-source data, and analyzing the synergistic driving mechanism of multi-scale physical processes on the changes in krill resources, it can simulate and predict the changes in Antarctic krill fishing grounds more accurately than traditional methods, and effectively solve the problem of inaccurate prediction caused by the limited spatio-temporal coverage of observational data.

[0015] The present invention provides a method for predicting the changes in Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model. By deeply analyzing the spatio-temporal variation laws of physical processes including large-scale circulation, meso-scale eddies, local sea currents and sea ice in the target sea area, as well as their impacts on the distribution of krill, quantifying the energy transfer paths between different scales, and revealing the physical and ecological mechanisms of the formation of the fishing ground, it helps to understand the formation and maintenance mechanisms of Antarctic krill fishing grounds.

[0016] The present invention provides a method for predicting the changes in Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupling model. By combining the environmental data simulated in real time by the ocean circulation-sea ice coupling model and the quasi-real-time krill acoustic data, it is possible to achieve quasi-real-time prediction of the changes in Antarctic krill fishing grounds, timely understand the dynamics of the fishing grounds, and make reasonable production decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0018] Figure 1 is a schematic diagram of the workflow of the present invention; Figure 2 is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0020] Example 1, as Figure 1 、 Figure 2 shown, the present invention provides a method for predicting the changes in Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupling model, including the following steps: S1. Collect historical observational data, satellite remote sensing data, and reanalysis data of Antarctic krill fisheries, integrate Antarctic krill resources and environmental data, and construct a polar resource and environment database covering all physical-biological-environmental elements. Collect historical observational data of Antarctic krill fisheries in the target sea area, including hydrographic sections, krill biological parameters (body length, body weight, sexual maturity, etc.), and resource acoustic data. Organize marine survey data collected by domestic scientific research teams in the waters around the Antarctic Peninsula, covering various aspects of marine physics, chemistry, and biology. At the same time, collect synchronous observational data of relevant international scientific research programs in the target sea area to obtain the investigation results of different countries on Antarctic krill resources and the environment. Obtain satellite remote sensing data of the waters around the Antarctic Peninsula, including environmental factor data such as sea surface temperature, sea surface height, sea surface wind field, chlorophyll concentration, nutrient salt distribution, and sea ice coverage. Collect global climate reanalysis data, covering reanalysis data such as ocean currents, salinity, and wind field. Preprocess the collected historical observational data, satellite remote sensing data, and reanalysis data of Antarctic krill fisheries. Among them, check the historical observational data of fisheries and domestic scientific research survey data, correct missing values and outliers, unify the data format and unit to ensure the consistency and accuracy of the data. Perform radiometric calibration on the satellite remote sensing data to convert the radiation value received by the sensor into an actual physical quantity, perform geometric correction to eliminate the geometric distortion of the image, use a cloud removal algorithm to remove the data blocked by clouds, and improve the data quality. Perform spatial interpolation on the reanalysis data to make its spatial resolution the same as that of the observational data, and perform time series matching to adjust the time interval of the reanalysis data to make its time resolution consistent with that of the observational data. Then, classify the collected data according to the data source (fishery observation, domestic scientific research survey, international scientific research program, satellite remote sensing, reanalysis data) and type (physical, chemical, biological, environmental), establish a detailed data list, and integrate the preprocessed historical observational data, satellite remote sensing data, and reanalysis data based on time and space. Establish data association rules to associate the biological information covering Antarctic krill distribution and quantity with the marine environmental information, and construct an associated dataset covering all physical-biological-environmental elements. Based on the integrated associated dataset, build the architecture of the polar resource and environment database, store the preprocessed data into the database according to the designed database architecture, form a polar resource and environment database covering all physical-biological-environmental elements, and establish a data dictionary and metadata management system to describe and annotate the data in detail to ensure the traceability and understandability of the data; S2. Based on the FVCOM model, construct a high-resolution ocean circulation-sea ice coupled model for the waters around the Antarctic Peninsula to simulate and verify the physical environmental characteristics of the target waters. Collect the basic geographical information of the waters around the Antarctic Peninsula, including data such as coastline and water depth, and construct a high-resolution computational grid to ensure that the grid can finely depict the complex terrain of this sea area. At the same time, obtain the initial field data of the ocean and sea ice, including temperature, salinity, sea ice concentration, etc. Then, according to the research needs and the actual marine environmental characteristics, select the FVCOM model as the basic framework, set the physical parameters of the FVCOM model including the turbulence closure scheme, sea ice thermodynamics and kinetics parameters, determine the model calculation area, and configure the open boundary conditions, terrain data and meteorological forcing data. Among them, select FVCOM (Unstructured Grid Finite Volume Coastal Ocean Model) as the basic model to simulate the complex waters around the Antarctic Peninsula, set the calculation area of the model to cover the main Antarctic krill fishing grounds in the southwestern Atlantic Ocean (50°W - 60°W, 60°S - 65°S), and design an unstructured triangular variable grid to densify the main fishing ground area, with the highest resolution of the order of 100 meters and about 4 km at the boundary to finely depict the sea area terrain. The open boundary is driven by tides, temperature and salinity, and circulation, and the sea surface meteorological factors (wind, evaporation, precipitation, air pressure, net heat flux and net shortwave radiation flux) are driven. The terrain data uses the bathymetry data of GEBCO 0.5´×0.5´. The open boundary tidal level is driven by the tidal model database developed by the University of Oregon. The temperature, salinity, circulation and sea ice data use the results of the HYCOM model. The meteorological forcing data uses the climate forecast system reanalysis data released by the National Centers for Environmental Prediction of the United States. Embed the sea ice module (UG-CICE) and the Lagrangian particle tracking module within the FVCOM framework to conduct multi-scale numerical simulations of ocean circulation-sea ice-Lagrangian particle tracking coupling. And through data assimilation technology, integrate the on-site surveys, historical data and satellite remote sensing data into the model to optimize the model parameterization scheme. Then construct a complete ocean circulation-sea ice coupled model to ensure smooth data interaction and collaborative operation among modules. Run the constructed ocean circulation-sea ice coupled model to simulate the three-dimensional temperature, salinity, sea current and sea ice dynamic distribution with high spatio-temporal resolution in the target waters. During the model operation process, monitor the running state of the model in real time, and pay attention to the spatio-temporal characteristics of the large-scale physical processes of the Antarctic Circumpolar Current, the Weddell Sea Circulation and the oceanic front, as well as the variation laws of the small and medium-scale physical processes of the internal vortices, local sea currents, key temperature and salinity fronts, and water mass structures in the krill fishing grounds. At the same time, use the energy flux spectrum analysis method to quantify the energy conversion between physical processes at different scales and analyze the energy cascade path to obtain the simulation results. Use the measured data of the Global Drifter Program, the ARGO Global Ocean Observation Network and the NOAA National Buoy Data Center, combined with the resource distribution data in the historical literature of krill, to verify the reliability of the model, compare the simulation results with the measured data, including tidal level, temperature, salinity, sea current and sea ice coverage, and evaluate the simulation accuracy of the model.According to the verification results, adjust the model parameters including adjusting the grid resolution, optimizing the open boundary conditions, and improving the sea ice parameterization scheme to optimize the model performance. Then analyze the verified simulation results to extract the characteristics of the ocean circulation and the physical environment of sea ice in the waters around the Antarctic Peninsula. Among them, the characteristics of the ocean circulation in the waters around the Antarctic Peninsula include large-scale circulation structures and meso- and small-scale physical processes, and the physical environment characteristics of sea ice include the sea ice distribution range, sea ice thickness, and sea ice movement. The large-scale circulation structures cover the Antarctic Circumpolar Current, the Weddell Sea circulation, and the oceanic front. The Antarctic Circumpolar Current, as an important circulation system surrounding the Antarctic continent, shows a stable flow trend in the target waters. Its flow direction and intensity have obvious seasonal and interannual variation characteristics. During the simulation period, the Circumpolar Current has a relatively fast flow velocity in some areas, playing a key role in the material transport and energy exchange in the region, mixing and transporting water masses from different sources, and affecting the temperature and salinity distribution in the surrounding waters. The Weddell Sea circulation has a unique circulation structure within the Weddell Sea, including clockwise and counterclockwise circulations. The circulation exchanges the seawater within the Weddell Sea with the surrounding waters, making the water masses in the Weddell Sea interact with those in other regions of the southwestern Atlantic Ocean. The circulation is more active at the edge of the Weddell Sea basin and in areas with complex bottom topography, forming local vortices and upwelling currents, which have an important impact on the upward transport of bottom nutrients and marine primary productivity. The oceanic front is an obvious oceanic front in the target waters. There are significant differences in the physical properties such as temperature and salinity between the water masses on both sides of the front. It is the confluence area of different water masses. The position and intensity of the front will move and change with the seasons and the ocean environment. The seawater mixing at the front is strong, resulting in enhanced vertical convection, which is beneficial to the upward replenishment of nutrients and has an important impact on the distribution and growth of marine organisms. The meso- and small-scale physical processes cover the internal vortices in the krill fishing grounds, local ocean currents, key temperature-salinity fronts, and water mass structures. The internal vortices in the krill fishing grounds, that is, the main krill fishing ground areas, have meso- and small-scale vortex structures. The vortices can change the flow direction and velocity of seawater, forming local circulation systems, mixing seawater at different levels, resulting in changes in physical properties such as temperature and salinity in local areas. At the same time, the vortices have an important impact on the distribution and aggregation of krill. Krill may aggregate in specific areas with the rotation of the vortices, forming high-density fishing grounds. Local ocean currents exist in the fishing grounds and their surrounding waters. There are various local ocean currents, and their flow direction and intensity are greatly affected by the topography and wind field. They can transport coastal nutrients into the ocean, and upwelling currents bring the seawater rich in nutrients from the bottom to the surface, promoting the improvement of marine primary productivity and providing a rich food source for marine organisms such as krill. The key temperature-salinity front exists inside and around the fishing grounds. It is the boundary between seawater of different properties. The temperature-salinity gradient at the front is large, and the seawater mixing is active, resulting in significant changes in the ocean physical and chemical environment. Marine organisms such as krill are sensitive to the temperature-salinity front and often aggregate near the front. The water mass structure is the various water masses existing in the target waters.Different water masses have different temperature, salinity, and density characteristics. The interaction and mixing processes between water masses affect the heat transfer, material cycling, and biological distribution in the ocean. Regarding the sea ice distribution range, the simulation results show that the sea ice distribution in the waters around the Antarctic Peninsula has obvious seasonal variations. In winter, the sea ice coverage reaches its maximum, extending northward to near the northern boundary of the target waters. In some areas, the sea ice thickness is relatively large. In summer, as the temperature rises, the sea ice gradually melts, and the coverage significantly shrinks, mainly concentrated in the high-latitude waters near the Antarctic Peninsula. There are significant differences in sea ice thickness in different seasons and regions. In winter, affected by low temperatures, the sea ice gradually thickens, and in some sea ice concentration areas, the thickness can reach several meters. In summer, due to the melting effect, the sea ice thickness decreases significantly, and in some areas, the sea ice even completely melts. The change in sea ice thickness not only affects the heat exchange between the ocean and the atmosphere but also has an important impact on the structure and function of the marine ecosystem. Sea ice moves under the action of ocean circulation and wind fields. In the target waters, the movement direction and speed of sea ice are affected by various factors, including the drag of ocean circulation, the driving of wind fields, and the interaction between sea ice. The movement of sea ice will lead to the redistribution of sea ice, forming the accumulation and fragmentation of sea ice. In some narrow straits and bays, the sea ice movement is more intense, which will affect the local marine ecosystem and navigation activities. S3. Simulate and analyze the spatio-temporal variation laws of the physical processes of large-scale circulation, meso- and small-scale eddies, local ocean currents, and sea ice in the target sea area, analyze the synergistic effects of physical processes at different scales and their impacts on krill distribution, quantify the energy transfer paths between different scales, run the constructed high-resolution ocean circulation-sea ice coupled model to simulate the three-dimensional temperature, salinity, ocean current, and sea ice dynamic distributions in the target sea area, analyze the physical processes in the target sea area, with a focus on large-scale circulation structures such as the Antarctic Circumpolar Current, the Weddell Sea circulation, and oceanic fronts, as well as the variation characteristics of meso- and small-scale eddies, local ocean currents, key temperature-salinity fronts, and water mass structures within the krill fishing grounds, record the dynamic change data of each physical process in time and space, including three-dimensional velocity fields, temperature, salinity, and sea ice data, analyze the simulation results, extract the spatio-temporal variation laws of large-scale circulation, meso- and small-scale eddies, local ocean currents, and sea ice, analyze the interactions between physical processes at different scales, screen the ecological habit data of krill from the historical observation data of Antarctic krill fisheries in the target sea area, analyze the impacts of physical processes at different scales on krill distribution, among which, study how large-scale circulation affects the food sources and nutrient transport of krill, how meso- and small-scale eddies and local ocean currents provide suitable habitats and aggregation sites for krill, how the distribution and movement of sea ice affect the reproduction and foraging behaviors of krill, and establish a quantitative relationship model between physical processes and krill distribution, evaluate the relative importance of each physical process to krill distribution. For large-scale impacts, use the Generalized Additive Model (GAM) to correlate the ACC intensity with the transport efficiency of krill food sources. For meso- and small-scale effects, construct a logistic regression model to analyze the relationship between eutrophic waters at the edges of eddies and krill aggregation. For the role of sea ice, use the Structural Equation Model (SEM) to quantify the impacts of sea ice melting-freshwater input on the salinity stratification of krill habitats and the stability of spawning grounds. Use the energy flux spectrum analysis method to quantify the energy transfer paths between physical processes at different scales, analyze the energy cascade process from large-scale circulation to meso- and small-scale physical processes, as well as the distribution and dissipation characteristics of energy in physical processes at different scales. Through energy transfer analysis, further understand the synergistic mechanism of physical processes; In addition, the specific process of quantifying the energy transfer paths between physical processes at different scales includes: Obtain the three-dimensional velocity field, temperature, salinity, and sea ice data output from a high-resolution ocean circulation-sea ice coupled model, and preprocess the simulated data, including unifying data formats, handling missing values, removing outliers, etc. Convert time series data into a format suitable for energy spectrum analysis, and perform spectral analysis on the preprocessed data using Fourier transform to calculate the energy spectra of various physical processes at different frequencies. Among them, for time series data, calculate its power spectral density (PSD) to understand the distribution of energy at different time scales. For spatially distributed data, calculate its spatial energy spectrum to analyze the distribution of energy at different spatial scales, and analyze the obtained energy spectra to identify the energy peaks and valleys at different scales, determine the main energy transfer paths between different scales, observe how large-scale energy transfers to medium and small scales, and the energy cascade process between different scales. By analyzing the shape and change trend of the energy spectra, preliminarily judge the energy cascade characteristics of large-scale circulation to medium and small-scale physical processes, and the energy distribution in physical processes at different scales. Further quantify the specific paths and efficiencies of energy transfer from large scales to medium and small scales, calculate the energy transfer fluxes between different scales, that is, the amount of energy passing through a unit scale per unit time. Among them, use the scale correlation of wavelet transform to calculate the energy transfer fluxes from large scales to medium and small scales, clarify the energy transfer efficiency and direction between different scales, and then analyze the distribution and dissipation characteristics of energy in physical processes at different scales. Calculate the energy content of physical processes at each scale to determine the relative importance of energy at different scales. At the same time, analyze the dissipation of energy at each scale, identify the main regions and processes of energy dissipation, and combine the quantified energy transfer paths, distribution, and dissipation characteristics to analyze the cooperative mechanism between physical processes. Among them, analyze how large-scale circulation provides energy support for medium and small-scale physical processes through energy cascade. At the same time, consider how the distribution and movement of sea ice interact with ocean circulation to affect energy transfer and distribution, reveal the cooperative mechanism between physical processes at different scales in the formation of krill fishing grounds, clarify the role of each physical process in maintaining the stability and productivity of krill fishing grounds, and summarize the results of energy flux spectrum analysis, and write an analysis report, including the description of energy transfer paths between different scales, the summary of energy distribution and dissipation characteristics, and the elaboration of the cooperative mechanism between physical processes; S4. Integrate the acoustic data collected by krill fishing boats, combine the target strength model and the krill body length-weight distribution, conduct an acoustic assessment of krill resources, and obtain the spatio-temporal distribution characteristics of resource density; S5. Use the deep learning method of three-dimensional convolutional neural network (3DCNN), combine the acoustic assessment results and environmental data, construct an Antarctic krill species distribution model, and mine the spatio-temporal correlation between the two; S6. Combine the environmental data simulated in real time by the ocean circulation-sea ice coupled model and the quasi-real-time krill acoustic data as model inputs and input them into the Antarctic krill species distribution model to analyze and predict the spatio-temporal distribution of krill density in the waters around the fishing hotspots, reveal the formation mechanism of the fishing grounds, and achieve the quasi-real-time prediction of the changes in the Antarctic krill fishing grounds.

[0021] Example 2. As Figure 1 , Figure 2 shown, based on Example 1, the present invention provides a technical solution: Preferably, S4 specifically includes: Collect cross-section acoustic data through the acoustic equipment (Simrad EK80) carried by krill fishing boats, combine the environmental parameter data synchronously recorded by expendable bathythermographs, use Echoview software to remove noise from the original cross-section acoustic data and environmental parameter data, adopt the dynamic signal-to-noise ratio threshold method to remove background noise, and use the frequency difference method to distinguish krill from other plankton. After optimizing the resampling interval, ensure that the data amplitude change conforms to the acoustic scattering characteristics to generate a clean acoustic echo map. Based on the Demer-Martin target strength model, combine the krill body length-target strength relationship (-69.5~-40.8 dB), convert the acoustic scattering value into krill density through the echo integration technique, use the multi-frequency difference method to invert the krill body length distribution, combine the on-site trawl sampling data to verify the model accuracy, and establish the body length-body weight power function relationship. Among them, determine the dominant body length of 32~41 mm and body weight of 0.3~0.8 g from the on-site trawl sampling data, and the body length-body weight power function relationship is Log (body weight)=-1.866 + 1.2859 Log (body length). Input the cross-section acoustic data into the target strength model, combine the krill body length-body weight distribution information, perform target recognition and classification on the cross-section acoustic data, distinguish krill from other marine organisms or non-biological targets, perform spatial grid processing on the cross-section acoustic data, calculate the krill density in each grid unit according to the acoustic signals and target strengths in different regions, obtain the distribution characteristics of krill resource density in different times and spaces, and generate the spatio-temporal distribution map of krill resource density; In addition, the generation process of the spatio-temporal distribution map of krill resource density is as follows: Import the collected cross-section acoustic data into the target strength model, and at the same time integrate the krill body length-body weight distribution information. Use the target strength model to analyze the characteristics of the acoustic signals, and based on the differences in the acoustic responses of different biological or non-biological targets, complete target recognition and classification, distinguish krill from other marine organisms or non-biological targets, and use the target strength model to combine the acoustic signal characteristics to calculate the target strength corresponding to each acoustic signal, and then estimate the target size and biomass. Among them, the expression of the target strength is: , TS is the target strength, L is the body length, then based on the target strength, invert the body length of the target, and its expression is: , the expression for biomass determined based on the body length-weight power function relationship is: , based on the target strength and biomass data calculated from the target strength model, conduct a preliminary estimation of the krill resource density. Considering the acoustic data coverage area and sampling interval, and combining with the biological characteristics of krill, convert the target biomass into the krill resource density per unit area. Among them, the expression for the acoustic data coverage area is: , S is the acoustic data coverage area, is the sampling interval in the horizontal direction, is the sampling interval in the vertical direction, N is the number of sampling points, and the expression for the krill resource density per unit area is: , is the total sum of all target biomasses, D is the krill resource density per unit area. Conduct spatial grid processing on the cross-sectional acoustic data. According to the size and precision requirements of the study area, divide grid cells, integrate the acoustic signals and target strength data within each grid cell, and combine with the estimated krill resource density information to calculate the krill density within each grid cell. Among them, the expression for the krill density within each grid cell is: , is the acoustic data coverage area of the i-th grid cell, is the total sum of all target biomasses within the i-th grid cell, is the krill density within the i-th grid cell. Based on the cross-sectional acoustic data collected at different times and the corresponding spatial grid processing results, analyze the variation laws of the krill resource density in time and space. By comparing the data at different time points, determine the dynamic changes of the krill resource density over time. Combining the data of different spatial grid cells, explore the spatial distribution differences of the krill resource density. Use the geographic information system to visualize the analysis results and generate a spatio-temporal distribution map of the krill resource density to intuitively display the distribution characteristics of the krill resource at different times and in different spaces; S5 specifically includes: Collect and integrate the acoustic assessment data and marine environmental data of Antarctic krill from scientific research databases and marine survey vessel record systems. The acoustic assessment data includes information such as krill density and body length distribution, and the marine environmental data includes temperature, salinity, sea current velocity, sea ice distribution, etc. Match and integrate the collected acoustic assessment data and marine environmental data according to time and spatial coordinates to construct a unified dataset, and preprocess the acoustic assessment data and marine environmental data, including data cleaning, normalization processing, and format conversion, to ensure the consistency and readability of the data. Then divide the data into training set, validation set, and test set. Design the three-dimensional convolutional neural network (3DCNN) model architecture to construct the Antarctic krill species distribution model, including multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layers are used to extract local features in the data, the pooling layers are used to reduce the feature dimension and enhance the generalization ability of the model, and the fully connected layers are used to map the extracted features to the output categories. Select the ReLU activation function and Adam optimizer, and set the mean squared error loss function for model training. Then use the training set to train the three-dimensional convolutional neural network model, optimize the model parameters through the backpropagation algorithm, and adjust the convolutional kernel weights and bias values to minimize the training loss. During the training process, use the validation set to evaluate the model performance to prevent overfitting, adjust the hyperparameters of the model according to the loss and accuracy of the validation set, record the changes in loss and accuracy during the training process, draw the training curve, and analyze the convergence of the model. Use the test set to finally evaluate the trained Antarctic krill species distribution model, calculate the prediction accuracy, recall rate, and F1 score metrics of the model, evaluate the prediction performance of the model for the krill species distribution, and generate a predicted map of krill distribution according to the prediction results of the model, and compare it with the actual distribution map to show the prediction effect of the model. Apply the trained Antarctic krill species distribution model to the actual assessment of Antarctic krill resources and fishing ground prediction, input new acoustic assessment data and environmental data, output the predicted results of krill distribution, and then analyze its output results, mine the spatio-temporal correlation between the acoustic assessment results and environmental data, and display the impact of different environmental factors on krill distribution and the variation law of krill distribution over time and space through visualization technology; S6 specifically includes: Using an ocean circulation-sea ice coupled model, environmental data of the waters surrounding the fishing hotspots are obtained through real-time simulation, covering temperature, salinity, sea current velocity, sea ice coverage and thickness, etc. At the same time, quasi-real-time krill acoustic data, including information such as the echo intensity and distribution depth of krill, are obtained through shipborne or buoy acoustic devices. Furthermore, the environmental data and quasi-real-time krill acoustic data are respectively preprocessed to remove noise and outliers. For the quasi-real-time krill acoustic data, a preliminary conversion is carried out based on the relationship between the echo intensity and krill density. For the environmental data, spatial and temporal interpolation processing is performed to make it match the acoustic data in terms of spatio-temporal resolution. The processed data are unified in format. The environmental data simulated by the preprocessed ocean circulation-sea ice coupled model and the quasi-real-time krill acoustic data are input into the constructed Antarctic krill species distribution model according to the time series and spatial coordinates, ensuring the integrity and accuracy of data input. Based on the input data, the Antarctic krill species distribution model makes a preliminary prediction of the krill density in the waters surrounding the fishing hotspots and outputs the preliminary spatio-temporal distribution results of the krill density to preliminarily understand the distribution trend of krill in this area. Combining the preliminary prediction results, the relationship between the environmental data and the krill density distribution is analyzed, the distribution characteristics of the krill density at different times and spaces are extracted, the physical and ecological mechanisms of the formation of the fishing ground are revealed, the role of key environmental factors on the krill distribution is clarified, and the relationship between the high-density areas of krill and the environmental factors of ocean circulation and sea ice distribution is identified. The prediction results of the Antarctic krill species distribution model are visualized to generate a spatio-temporal distribution map of krill density. Using geographic information system technology, the prediction results are combined with the actual geographic information to generate a dynamic visualization report to show the change process of the fishing ground over time.

[0022] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model, characterized in that, It includes the following steps: S1. Collect historical observation data, satellite remote sensing data and reanalysis data of Antarctic krill fishery, integrate Antarctic krill resources and environmental data, and construct a polar resource and environment database covering all physical-biological-environmental elements; S2. Based on the FVCOM model, construct an ocean circulation-sea ice coupling model for the waters around the Antarctic Peninsula, and simulate and verify the physical environmental characteristics of the target waters; S3. Simulate and analyze the spatio-temporal variation laws of physical processes including large-scale circulation, meso- and small-scale eddies, local ocean currents and sea ice in the target waters, analyze the synergistic effects of physical processes at different scales and their impacts on krill distribution, and quantify the energy transfer paths between different scales; S4. Integrate the acoustic data collected by krill fishing vessels, combine the target strength model and the krill body length-weight distribution, conduct acoustic assessment of krill resources, and obtain the spatio-temporal distribution characteristics of resource density; S5. Use the deep learning method of three-dimensional convolutional neural network, combine the acoustic assessment results and environmental data, and construct a Antarctic krill species distribution model; S6. Combine the environmental data simulated in real time by the ocean circulation-sea ice coupling model and the quasi-real-time krill acoustic data, input them into the Antarctic krill species distribution model, analyze and predict the spatio-temporal distribution of krill density in the waters around the fishing hotspots, and reveal the formation mechanism of fishing grounds.

2. The method for predicting the change of Antarctic krill fishing grounds based on the ocean circulation-sea ice-species distribution coupling model according to claim 1, wherein: The specific content of S1 includes: Collect historical observation data of Antarctic krill fishery in the target waters, including hydrological sections, krill biological parameters and resource acoustic data, and sort out the marine survey data carried out in the waters around the Antarctic Peninsula; Obtain satellite remote sensing data of the waters around the Antarctic Peninsula, collect global climate reanalysis data, preprocess the collected historical observation data, satellite remote sensing data and reanalysis data of Antarctic krill fishery, and then classify the collected data according to data sources and types to establish a data list; Based on time and space, integrate the preprocessed historical observation data, satellite remote sensing data and reanalysis data of fishery, establish data association rules, associate the biological information covering Antarctic krill distribution and quantity with ocean environmental information, construct an associated data set covering all physical-biological-environmental elements, based on the integrated associated data set, build the architecture of the polar resource and environment database, and store the preprocessed data into the database according to the designed database architecture to form a polar resource and environment database covering all physical-biological-environmental elements.

3. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupling model according to claim 1, characterized in that: The specific content of S2 includes: Collect the basic geographical information of the waters around the Antarctic Peninsula, construct a high-resolution computational grid. At the same time, obtain the initial field data of the ocean and sea ice. Then, according to research requirements and actual marine environmental characteristics, select the FVCOM model as the basic framework, set the physical parameters of the FVCOM model including the turbulence closure scheme, sea ice thermodynamics and dynamics parameters, determine the model calculation area, and configure the open boundary conditions, terrain data and meteorological forcing data; Within the FVCOM framework, an ice module and a Lagrangian particle tracking module are embedded to conduct a coupled multi-scale numerical simulation of ocean circulation - sea ice - Lagrangian particle tracking. Through data assimilation technology, in-situ surveys, historical data, and satellite remote sensing data are incorporated into the model to optimize the model parameterization scheme, and then a complete ocean circulation - sea ice coupled model is constructed; Run the constructed ocean circulation - sea ice coupled model to simulate the three-dimensional temperature, salinity, ocean currents, and sea ice dynamic distribution in the target sea area. During the model operation, monitor the running state of the model in real time, and pay attention to the spatio-temporal characteristics of large-scale physical processes such as the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the oceanic frontal surface, as well as the variation laws of meso-scale physical processes such as the internal vortices in the krill fishing ground, local ocean currents, key temperature-salinity frontal surfaces, and water mass structures; Use the measured data of the Global Drifter Program, the ARGO Global Ocean Observation Network, and the NOAA National Buoy Data Center, combined with the resource distribution data in the historical literature of krill, to verify the reliability of the model. Compare the simulation results with the measured data, evaluate the simulation accuracy of the model, and adjust the model parameters including adjusting the grid resolution, optimizing the open boundary conditions, and improving the sea ice parameterization scheme according to the verification results to optimize the model performance. Then analyze the verified simulation results to extract the ocean circulation characteristics and the physical environmental characteristics of sea ice in the waters around the Antarctic Peninsula. Among them, the ocean circulation characteristics in the waters around the Antarctic Peninsula include large-scale circulation structures and meso-scale physical processes, and the physical environmental characteristics of sea ice include the sea ice distribution range, sea ice thickness, and sea ice movement. The large-scale circulation structures cover the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the oceanic frontal surface, and the meso-scale physical processes cover the internal vortices in the krill fishing ground, local ocean currents, key temperature-salinity frontal surfaces, and water mass structures.

4. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupling model according to claim 1, characterized in that: The specific content of S3 includes: Run the constructed ocean circulation - sea ice coupled model to simulate the three-dimensional temperature, salinity, ocean currents, and sea ice dynamic distribution in the target sea area, analyze the physical processes in the target sea area, focus on large-scale circulation structures such as the Antarctic Circumpolar Current, the Weddell Sea Circulation, and the oceanic frontal surface, as well as the variation characteristics of meso-scale vortices, local ocean currents, key temperature-salinity frontal surfaces, and water mass structures inside the krill fishing ground, and record the dynamic change data of each physical process in time and space, including three-dimensional velocity fields, temperature, salinity, and sea ice data; Analyze the simulation results, extract the spatio-temporal variation laws of large-scale circulation, meso-scale vortices, local ocean currents, and sea ice, and analyze the interactions between physical processes at different scales; Screen the ecological habit data of krill from the historical observation data of Antarctic krill fishery in the target sea area, analyze the influence of physical processes at different scales on the distribution of krill, and establish a quantitative relationship model between physical processes and krill distribution to evaluate the relative importance of each physical process to krill distribution; Use the energy flux spectrum analysis method to quantify the energy transfer paths between physical processes at different scales, analyze the energy cascade process from large-scale circulation to meso-scale physical processes, and the distribution and dissipation characteristics of energy in physical processes at different scales.

5. The prediction method for the change of Antarctic krill fishing grounds based on the ocean circulation-sea ice-species distribution coupling model according to claim 4, characterized in that: The specific process of quantifying the energy transfer paths between physical processes at different scales includes: Obtain the three-dimensional velocity field, temperature, salinity, and sea ice data output from a high-resolution ocean circulation-sea ice coupled model, and preprocess the simulated data; Use Fourier transform to perform spectral analysis on the preprocessed data, calculate the energy spectra of various physical processes at different frequencies, analyze the obtained energy spectra, identify the energy peaks and valleys at different scales, determine the main energy transfer paths between different scales, preliminarily judge the energy cascade characteristics from large-scale circulation to small- and medium-scale physical processes, and the distribution of energy in physical processes at different scales; Further quantify the specific paths and efficiencies of energy transfer from large scales to small and medium scales, calculate the energy transfer fluxes between different scales, and then analyze the distribution and dissipation characteristics of energy in physical processes at different scales, calculate the energy content of physical processes at each scale, and at the same time, analyze the dissipation of energy at each scale, and identify the main regions and processes of energy dissipation; Combined with the quantified energy transfer paths, distribution, and dissipation characteristics, analyze the synergistic mechanism between physical processes, clarify the roles of each physical process in maintaining the stability and productivity of the krill fishing ground, and summarize the results of the energy flux spectrum analysis, and write an analysis report, including the description of the energy transfer paths between different scales, the summary of the energy distribution and dissipation characteristics, and the elaboration of the synergistic mechanism between physical processes.

6. The method for predicting the change of Antarctic krill fishing grounds based on the ocean circulation-sea ice-species distribution coupled model according to claim 1, wherein: The specific content of S4 includes: Collect cross-section acoustic data through the acoustic equipment carried by krill fishing boats, synchronously record environmental parameter data in combination with expendable bathythermographs, use Echoview software to remove noise from the original cross-section acoustic data and environmental parameter data, and distinguish krill from other plankton by the frequency difference method. After optimizing the resampling interval, generate a clean acoustic echogram; Based on the Demer-Martin target strength model, combined with the relationship between krill body length and target strength, convert the acoustic scattering value into krill density through echo integration technology, invert the krill body length distribution using the multi-frequency difference method, and establish the power function relationship between body length and weight; Input the cross-section acoustic data into the target strength model, combined with the krill body length-weight distribution information, perform target recognition and classification on the cross-section acoustic data, distinguish krill from other marine organisms or non-biological targets, perform spatial grid processing on the cross-section acoustic data, and calculate the krill density in each grid cell according to the acoustic signals and target strengths in different regions, and obtain the distribution characteristics of krill resource density in different times and spaces, and generate the spatio-temporal distribution map of krill resource density.

7. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model according to claim 6, characterized in that: The generation process of the spatio-temporal distribution map of krill resource density is as follows: Import the collected cross-section acoustic data into the target strength model, and at the same time integrate the krill body length-weight distribution information. Use the target strength model to analyze the characteristics of the acoustic signals, and complete target recognition and classification based on the differences in acoustic responses of different biological or non-biological targets, distinguish krill from other marine organisms or non-biological targets, and use the target strength model, combined with the characteristics of acoustic signals, to calculate the target strength corresponding to each acoustic signal, and then estimate the target size and biomass; Based on the target strength and biomass data calculated from the target strength model, conduct a preliminary estimation of the krill resource density. Considering the acoustic data coverage area and sampling interval, and combining with the biological characteristics of krill, convert the target biomass into the krill resource density per unit area; Perform spatial grid processing on the cross-section acoustic data. According to the size and accuracy requirements of the study area, divide grid cells, integrate the acoustic signals and target strength data within each grid cell, and calculate the krill density within each grid cell in combination with the estimated krill resource density information; Based on the cross-section acoustic data collected at different times and the corresponding spatial grid processing results, analyze the variation patterns of the krill resource density in time and space. By comparing the data at different time points, determine the dynamic changes of the krill resource density over time. Combining the data of different spatial grid cells, explore the spatial distribution differences of the krill resource density, and visualize the analysis results using a geographic information system to generate a spatio-temporal distribution map of the krill resource density, intuitively showing the distribution characteristics of the krill resource at different times and in different spaces.

8. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model according to claim 7, characterized in that: The specific steps of S5 are as follows: Collect and integrate the acoustic assessment data and marine environmental data of Antarctic krill from scientific research databases and marine survey vessel record systems. Match and integrate the collected acoustic assessment data and marine environmental data according to time and spatial coordinates to construct a unified dataset, and preprocess the acoustic assessment data and marine environmental data, and then divide the data into training set, validation set and test set; Design the architecture of a three-dimensional convolutional neural network model to construct a species distribution model of Antarctic krill, including multiple convolutional layers, pooling layers and fully connected layers. Select the ReLU activation function and Adam optimizer, and set the loss function of mean squared error for model training. Then use the training set to train the three-dimensional convolutional neural network model, and optimize the model parameters through the backpropagation algorithm. During the training process, use the validation set to evaluate the model performance, and adjust the hyperparameters of the model according to the loss and accuracy of the validation set; Use the test set to finally evaluate the trained species distribution model of Antarctic krill, calculate the prediction accuracy, recall rate and F1 score metrics of the model, evaluate the prediction performance of the model for the species distribution of krill, and generate a predicted map of krill distribution according to the prediction results of the model, and compare it with the actual distribution map to show the prediction effect of the model; Apply the trained species distribution model of Antarctic krill to the actual assessment of Antarctic krill resources and fishery prediction. Input new acoustic assessment data and environmental data, output the predicted distribution results of krill, and then analyze its output results to explore the spatio-temporal correlation between the acoustic assessment results and environmental data.

9. A method for predicting the change of Antarctic krill fishing grounds based on an ocean circulation-sea ice-species distribution coupled model according to claim 8, characterized in that: The specific steps of S6 are as follows: Use an ocean circulation-sea ice coupled model to simulate and obtain the environmental data of the waters around the fishery hot spot in real time. At the same time, obtain quasi-real-time krill acoustic data through shipborne or buoy acoustic devices, and then preprocess the environmental data and quasi-real-time krill acoustic data respectively; The preprocessed environmental data simulated by the ocean circulation-sea ice coupled model and the quasi-real-time krill acoustic data are input into the constructed Antarctic krill species distribution model according to the time series and spatial coordinates. Based on the input data, the Antarctic krill species distribution model makes a preliminary prediction of the krill density in the waters around the fishing hotspots and outputs the preliminary spatio-temporal distribution results of the krill density to preliminarily understand the distribution trend of krill in this area; Combined with the preliminary prediction results, analyze the relationship between the environmental data and the krill density distribution, extract the distribution characteristics of the krill density at different times and spaces, reveal the physical and ecological mechanisms of the formation of the fishing ground, clarify the role of key environmental factors in the krill distribution, and identify the relationship between the high krill density areas and the environmental factors of ocean circulation and sea ice distribution; Visualize the prediction results of the Antarctic krill species distribution model to generate a spatio-temporal distribution map of the krill density. Using geographic information system technology, combine the prediction results with the actual geographic information to generate a dynamic visualization report to show the change process of the fishing ground over time.

Images