An Antarctic krill yield analysis system and method based on multi-source big data

Abstract

The present invention discloses a system and method for analyzing Antarctic krill production based on multi-source big data, which relates to the technical field of marine fisheries. The system includes the following components: Data acquisition and management module: It collects data on ocean currents, marine environment, marine food chain, and ecosystem structure in the Antarctic waters through satellite remote sensing, ocean monitoring stations, and scientific research survey vessels, and stores them in a distributed database after preprocessing. By integrating multi-source big data from satellite remote sensing, ocean monitoring stations, scientific research survey vessels, etc., and comprehensively considering the impacts of various complex factors such as ocean current changes, marine environmental parameters, dynamic balance of the food chain, and structural functions of the ecosystem on Antarctic krill production, and using hydrodynamic models and numerical simulation technologies, combined with high-precision ocean current simulation results, it can more accurately predict the fluctuations in krill production under different ocean current scenarios, providing a scientific and forward-looking decision-making basis for the fishery production department.

Description

Technical Field

[0001] The present invention relates to the technical field of marine fishery, and particularly to an Antarctic krill yield analysis system and method based on multi-source big data. Background Art

[0002] As a key species in the Antarctic ecosystem, Antarctic krill is not only an important part of the Antarctic marine ecosystem but also an important source of global fishery resources. The environment in the Antarctic waters is complex and changeable, and the changes in ocean currents have a significant impact on the distribution, foraging, migration, and survival of krill. In addition, as a basic link in the food chain, the dynamic changes of krill play a crucial role in the balance of the entire Antarctic marine ecosystem. Therefore, the accurate prediction of Antarctic krill yield is of great significance for the sustainable utilization of fishery resources and ecological protection.

[0003] Traditional methods for predicting krill yield and studying ecosystem mostly rely on single data source or simple mathematical models. These methods cannot comprehensively and accurately reflect the complex changes in the marine ecosystem and the comprehensive effects of ocean currents on the food chain. Due to the complexity and variability of the Antarctic waters environment, a single data source often fails to capture all key information, resulting in poor accuracy and reliability of the prediction results. At the same time, simple models cannot fully consider the interaction relationships between organisms and the dynamic impacts of ocean currents on the food chain, making the understanding of the dynamic balance of the ecosystem have great limitations. Therefore, traditional prediction and analysis methods have obvious deficiencies in dealing with Antarctic krill yield prediction and ecosystem research.

[0004] In view of the above problems, it is necessary to optimize the existing Antarctic krill yield analysis system. By using hydrodynamic models and numerical simulation techniques, high-precision simulation of ocean currents in the sea area is carried out, and a dynamic balance model of the Antarctic marine food chain with krill as the core is constructed to achieve high-precision prediction of Antarctic krill yield. Therefore, it is of great significance to develop an Antarctic krill yield analysis system and method based on multi-source big data that can comprehensively achieve the above characteristics. Summary of the Invention

[0005] The object of the present invention is to make up for the deficiencies of the prior art and provide an Antarctic krill yield analysis system and method based on multi-source big data. It can integrate data from various channels such as satellite remote sensing, ocean monitoring stations, and scientific research survey vessels, use advanced hydrodynamic models and numerical simulation techniques to accurately simulate the ocean currents in the Antarctic sea area, and construct a dynamic balance model of the Antarctic marine food chain with krill as the core. By deeply analyzing the impact of ocean current changes on the krill ecosystem and the interaction relationships among various organisms in the food chain, the present invention can achieve high-precision prediction of krill yield and reveal the impact mechanism of ocean currents on the dynamic balance of the food chain. This comprehensive analysis method and system not only provide scientific and forward-looking guidance for fishery production, but also provide strong theoretical support for the protection of the Antarctic ecosystem.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an Antarctic krill yield analysis system based on multi-source big data, the system includes the following components:

[0007] Data collection and management module: Collect data on ocean currents, marine environment, marine food chain and ecosystem structure in the Antarctic sea area through satellite remote sensing, ocean monitoring stations and scientific research survey vessels, and store them in a distributed database after preprocessing;

[0008] Ocean current and ecological simulation module: Construct a hydrodynamic model based on the geographical information and environmental parameters of the Antarctic sea area for ocean current simulation and real-time update, combine the marine food chain and ecological data to construct a dynamic balance model of the food chain with krill as the core, and integrate the ocean current simulation results to simulate the impact of ocean currents on the food chain and the chain reaction law under different scenarios;

[0009] Krill ecological analysis module: Integrate the ocean current and ecological simulation results and other relevant data, analyze the foraging areas and food availability of krill under the influence of ocean currents, the migration paths and distribution changes, and comprehensively consider environmental and biological factors to construct an evaluation model to analyze the adaptability and survival probability of the krill living environment;

[0010] Krill yield prediction module: Based on krill ecological analysis and biological characteristics, determine the key factors affecting krill yield and quantify them, construct a prediction model, train and optimize it using historical data, input data on different ocean current change scenarios to predict yield fluctuations and conduct uncertainty analysis;

[0011] Result visualization and application module: Develop software tools to visualize the simulation analysis results in the form of charts, maps or dynamic demonstrations, and design a user interaction interface to assist different users in making fishery production decisions, formulating fishing strategies and carrying out Antarctic ecosystem protection work.

[0012] Further, the data collection and management module collects historical and real-time ocean current data, marine environmental data, marine food chain data, and ecosystem structure and function data through satellite remote sensing, marine monitoring stations, and scientific research vessels. Among them, the historical and real-time ocean current data includes, but is not limited to, ocean current speed, direction, and temperature; the marine environmental data includes, but is not limited to, salinity, dissolved oxygen, and light; the marine food chain data includes, but is not limited to, the distribution of food sources of krill, the distribution of natural enemies, and the interaction relationships among various organisms; and the ecosystem structure and function data includes the quantity and distribution of different biological populations.

[0013] Furthermore, the ocean current and ecological simulation module constructs a hydrodynamic model based on the geographical information and environmental parameters of the Antarctic Sea area for ocean current simulation and real-time update. Its model formula is: Where, is the ocean current velocity vector, representing the ocean current speed and direction at a certain position in the Antarctic Sea area. t1 is the time, used to describe the change of ocean current speed over time. ρ is the seawater density, determined according to the temperature and salinity factors in the Antarctic Sea area. p is the seawater pressure, related to the depth and seawater density. v is the kinematic viscosity of seawater, determined by the physical properties of seawater, which affects the viscous force and energy dissipation inside the ocean current. is the gradient operator, used to calculate the change rate of physical quantities in space. is the external force term. is the newly added force term considering the influence of seabed terrain roughness, calculated by combining high-precision seabed terrain data and terrain roughness models.

[0014] Furthermore, the ocean current and ecological simulation module combines marine food chain and ecological data to construct a dynamic balance model of the food chain with krill as the core. Its model formula is: Where, N i represents the population quantity of the i-th kind of organism, including the quantity of krill and other related biological populations. t2 is the time, used to describe the change of biological population quantity over time. r i is the intrinsic growth rate of the i-th kind of organism, reflecting the growth ability of this organism in an ideal environment. K i is the environmental carrying capacity of the i-th kind of organism, depending on the ecological environment conditions where this organism is located, including food resources and habitat space. α ij is the interaction coefficient between organisms. When i≠j, α ij represents the influence of the j-th kind of organism on the i-th kind of organism. A positive number indicates a promoting effect, and a negative number indicates an inhibitory effect. γ iis the sensitivity coefficient of the i-th organism to environmental fluctuations, which is determined according to the ecological adaptability and tolerance of the organism. ΔE is the amount of environmental fluctuation, which is obtained by analyzing and calculating multi-source environmental data by comprehensively considering the changes in factors such as ocean temperature, salinity, and ocean current changes.

[0015] Furthermore, the krill ecological analysis module analyzes the foraging areas and food availability of krill, as well as the migration paths and distribution changes of krill under the influence of ocean currents by establishing a model. Specifically, it deeply integrates the simulation results output by the ocean current and ecological simulation module with the data on the marine food chain and the structural functions of the ecosystem in the data collection and management module. Based on the integrated dataset, it analyzes the distribution of food particles carried by the ocean current, determines the food availability in different regions and at different times, and at the same time analyzes the relationship between the foraging behavior of krill and the food distribution. According to the feeding habits and foraging strategies of krill, it determines the probability of krill foraging at a certain location. The probability calculation formula is: P forage = ω1·F + ω2·D + ω3·T + ω4·C, where P forage is the probability of krill foraging at a certain location, F is the food abundance at this location, which is obtained by measuring and calculating the quantity and distribution of krill food sources, D is the water flow diffusion coefficient at this location, considering the diffusion and transportation effects of ocean currents on food particles, which is obtained by analyzing and calculating the ocean current velocity, flow direction, and diffusion model, T is the temperature suitability at this location, C is the competition pressure index at this location, comprehensively considering the competition situation of other organisms for food resources, which is obtained by analyzing the quantity and distribution of biological populations competing for food with krill in this area, and ω1, ω2, ω3, ω4 are the weight coefficients of the corresponding factors, which are determined by the analytic hierarchy process or machine learning methods according to actual data and analysis purposes, and are used to adjust the relative importance of each factor in the calculation of foraging probability.

[0016] Furthermore, the krill ecological analysis module comprehensively considers environmental and biological factors to construct an evaluation model to analyze the adaptability of the krill living environment and the survival probability. Specifically, by combining the data on the flow direction and velocity of ocean currents and the distribution and behavior change data of other organisms in the food chain, through the krill migration prediction algorithm, it predicts the migration paths and distribution changes of krill, analyzes the survival challenges faced by krill during migration, and evaluates the impacts of these factors on the krill population quantity and reproductive success rate. The algorithm formula is: where E survive is the comprehensive evaluation value of the krill living environment, which is used to measure the overall suitability and survival pressure of the environment where krill are located. n is the total number of environmental and biological factors considered, including factors such as temperature, salinity, dissolved oxygen, the number of natural enemies, and food availability. w k(t) is the weight coefficient of the k-th factor at time t, which changes dynamically over time and is determined by a dynamic modeling method according to the change trend of environmental factors and the requirements and sensitivities of krill to various factors at different growth stages, E k is the evaluation value of the k-th factor, which is obtained by normalizing the actual measured value of the factor and the tolerance range of krill to the factor.

[0017] Furthermore, based on krill ecological analysis and biological characteristics, the krill yield prediction module determines and quantifies the key factors affecting krill yield, and constructs a prediction model. The prediction model is: where Y t is the predicted krill yield at time t, which is the target value predicted by the present invention. σ is the activation function used to convert the input into a value within the output range. m is the number of historical time steps considered, indicating that the influence factor data of the past m time steps are used to predict the krill yield at the current moment. β i is the weight coefficient of the influence factor X t-i at the i-th historical time step. X t-i is the factor variable affecting krill yield at time t - i, including the calculated food availability, survival environment evaluation value, and ocean current speed. S is the total number of spatial regions. The Antarctic sea area is divided into S different spatial regions to consider the differences in krill yield in different regions. L is the number of hidden layers of the recurrent neural network. θ sl is the weight coefficient of the l-th hidden layer of spatial region s . is the hidden layer state of spatial region s at time t - l, indicating the hidden layer state of spatial region s at time t - l, which captures the spatio-temporal dependence through the recurrent neural network. b is the bias term used to adjust the output of the model.

[0018] On the other hand, a method for analyzing Antarctic krill yield based on multi-source big data, the method includes the following specific steps:

[0019] Data collection and preprocessing: Collect relevant data through the data collection and management module, clean, screen, and standardize the data, remove outliers and error data, and perform storage management;

[0020] Ocean current and ecological simulation: Input the preprocessed data into the ocean current and ecological simulation module, use the hydrodynamic model and numerical simulation technology to simulate the ocean currents in the Antarctic sea area, obtain the ocean current simulation results, and at the same time construct a dynamic balance model of the Antarctic marine food chain and integrate the ocean current simulation results to simulate the impact of ocean currents on the food chain and the dynamic change process of the food chain under different conditions, and analyze the chain reaction and evolution law;

[0021] Krill ecological analysis: Combining the results of the ocean current and ecological simulation module and the relevant data in the data collection and management module, and using data analysis algorithms and models to analyze the foraging, migration, and living environment of krill;

[0022] Krill yield prediction: According to the results of krill ecological analysis, using the model established by the krill yield prediction module, inputting the simulated data under different ocean current change scenarios, predicting the fluctuations of krill yield, and conducting uncertainty analysis;

[0023] Result display and application: Through the result visualization and application module, visualizing the prediction results and the dynamic change process of the food chain, and providing them to relevant users to assist them in making fishery production decisions, formulating fishing strategies, and carrying out Antarctic ecosystem protection work.

[0024] Compared with the prior art, the Antarctic krill yield analysis system and method based on multi-source big data have the following beneficial effects:

[0025] First, by integrating multi-source big data from satellite remote sensing, ocean monitoring stations, scientific research vessels, etc., and comprehensively considering the impacts of various complex factors such as ocean current changes, ocean environmental parameters, dynamic balance of the food chain, and ecological system structure and function on the Antarctic krill yield, and using hydrodynamic models and numerical simulation techniques, combined with high-precision ocean current simulation results, the present invention can more accurately predict the fluctuations of krill yield under different ocean current scenarios, providing a scientific and forward-looking decision-making basis for the fishery production department.

[0026] Second, by constructing a dynamic balance model of the Antarctic marine food chain with krill as the core, deeply exploring the impacts of ocean current changes on each biological population in the food chain and their chain reactions, and through simulating and analyzing the interaction between ocean currents and the ecosystem under different conditions, the present invention provides comprehensive data support and theoretical basis for scientific research institutions, helps to deeply understand the complexity and dynamic balance mechanism of the Antarctic marine ecosystem, and provides a solid scientific foundation for further formulating effective ecological protection measures and maintaining the stability and diversity of the Antarctic ecosystem.

[0027] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be learned from the practice of the present invention. Brief Description of the Drawings

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0029] Figure 1 It is a schematic structural diagram of a krill yield analysis system based on multi-source big data;

[0030] Figure 2 It is a flowchart of a krill yield analysis method based on multi-source big data. Specific Embodiments

[0031] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features, and their effects of the present invention as follows.

[0032] Embodiment 1

[0033] During a certain period, there was an abnormal ocean current turning phenomenon in the Antarctic Sea area, which might have a significant impact on the living environment and yield of krill. By cooperating with multiple satellite remote sensing agencies, high-resolution ocean current data covering the entire Antarctic Sea area, including parameters such as speed and flow direction, as well as ocean surface temperature data, were obtained. At the same time, the observation frequency of the abnormal ocean current area was increased to ensure real-time mastery of the ocean current changes, and a real-time data transmission channel was established with 12 ocean monitoring stations distributed in the Antarctic Sea area. Ocean environment data such as salinity, dissolved oxygen, light intensity, and water depth were collected once an hour, and a preliminary quality inspection was carried out on the data. In addition, two scientific research survey ships were dispatched to conduct a one-week on-site investigation along the path of the abnormal ocean current and its surrounding areas. Sampling equipment such as high-precision water samplers and new types of plankton nets were used to collect samples of the marine food chain, focusing on analyzing the quantity and distribution changes of the food sources of krill (such as plankton such as diatoms and copepods), as well as the activity range and quantity changes of natural enemies (such as penguins and sharks). All the collected data were transmitted to the data center, and outliers (such as extreme data beyond the normal range) and incorrect data (such as data caused by format errors or sensor failures) were removed. According to the requirements of krill yield prediction, key data fields such as the change rate of ocean current speed and the change of food source biomass were screened out, and finally stored in a distributed database, and a detailed data index was established.

[0034] Based on the latest Antarctic Sea area geographical information data and ocean environment parameters, a high-precision hydrodynamic model is constructed Simulate the impact of abnormal ocean current changes on seawater flow. By continuously adjusting the model parameters to match the actual observed data, improve the accuracy of the simulation. Based on the collected data of the marine food chain and the structural and functional data of the ecosystem, construct a dynamic balance model of the food chain with krill as the core. Considering the impact of abnormal ocean currents on the distribution and interaction of organisms, the parameters in the model are updated and adjusted in real time to simulate the dynamic change process of the food chain under abnormal conditions.

[0035] Deeply integrate the output results of the ocean current and ecological simulation module with the data of the data collection and management module to form a comprehensive krill ecological analysis data set. Based on the integrated data set, analyze the distribution of food particles carried by ocean currents, determine the food availability in different regions and at different times, and at the same time analyze the relationship between the foraging behavior of krill and the food distribution. According to the feeding habits and foraging strategies of krill, determine the probability of krill foraging at a certain location. The probability calculation formula is: P forage = ω1·F + ω2·D + ω3·T + ω4·C. Through machine learning algorithms, determine the weights ω1 = 0.4, ω2 = 0.25, ω3 = 0.2, ω4 = 0.15. Analyze the changes in the foraging areas of krill and their food acquisition ability under the influence of abnormal ocean currents, predict the food intake of krill, and combine the ocean current simulation results and the dynamic changes of the food chain to predict the migration path and new distribution areas of krill under the influence of abnormal ocean currents, as well as the survival challenges that may be faced during the migration process, such as food shortages and threats from natural enemies. Construct a comprehensive evaluation model of the krill's living environment. According to the real-time environmental data and the ecological needs of krill, dynamically adjust the weights w k (t) of each factor, and evaluate the survival adaptability and survival probability of krill in different regions under the influence of abnormal ocean currents, providing a basis for yield prediction.

[0036] Comprehensively analyze the results of the krill ecological analysis module, determine that the key factors affecting krill yield are the change in the distribution of food sources caused by abnormal ocean currents, the change in the migration path of krill, and the deterioration of the living environment, and construct a krill yield prediction model. Through the training of historical data and current real-time data, determine the model parameters m = 5 (considering the data of the past five time steps), S = 4 (divide the Antarctic sea area into 4 spatial regions), L = 3 (the number of hidden layers of the recurrent neural network is 3 layers). Input the simulated abnormal ocean current changes and related environmental data into the prediction model, predict the changes in krill yield in different regions under abnormal conditions, and conduct uncertainty analysis to provide the confidence interval of the prediction results.

[0037] According to the prediction results, the fishing company adjusted its fishing plan, reducing the fishing volume in areas severely affected by abnormal ocean currents, and at the same time increasing the fishing operations in areas where krill may gather.

[0038] Example 2

[0039] The sea ice coverage area and distribution in the Antarctic waters change significantly in different seasons, which has an important impact on the survival and reproduction of krill. A certain marine research institution cooperates with the fishery management department and uses the system and method of the present invention to predict the impact of sea ice changes in different seasons on krill production. By collecting satellite remote sensing data for each season in the past decade, including information such as sea ice coverage area, thickness, and edge position, as well as corresponding ocean current speed, direction, and sea surface temperature data, and cooperating with 10 marine monitoring stations that have been long-term monitoring the Antarctic waters to obtain marine environmental data such as salinity, dissolved oxygen, light intensity, and water depth for each season, and organizing the data for sorting and calibration. At the same time, multiple scientific research survey ships are organized to conduct on-site surveys in different seasons, using professional equipment to collect samples of the marine food chain, and analyzing the quantity and distribution changes of krill food sources (such as ice algae, planktonic bacteria, etc.) under the influence of sea ice, as well as the seasonal activity patterns of natural enemies (such as seals, seabirds, etc.). The historical and real-time data collected are transmitted to the data center for data cleaning to remove noise data and outliers, stored in a distributed database, and a data backup and recovery mechanism is established.

[0040] Based on historical and real-time sea ice data, marine geographical information, and environmental parameters, construct a hydrodynamic model that can reflect seasonal sea ice changes Simulate the impact of sea ice changes on ocean currents and the indirect effect of ocean current changes on the krill living environment, and construct a dynamic balance model of the seasonal food chain with krill as the core Consider the impact of sea ice changes on biological habitats, food resources, and interactions among organisms, adjust the model parameters, and simulate the dynamic evolution of the food chain in different seasons.

[0041] By integrating the results of the ocean current and ecological simulation module and the data of the data collection and management module, form a complete krill ecological dataset. Based on the integrated dataset, analyze the distribution of food particles carried by ocean currents, determine the food availability in different regions and at different times, and at the same time analyze the relationship between the foraging behavior of krill and the food distribution. According to the feeding habits and foraging strategies of krill, determine the probability of krill foraging at a certain location, and its probability calculation formula is: P forage = ω1·F + ω2·D + ω3·T + ω4·C. Through statistical analysis of historical data, determine the weights ω in different seasons i, for example, in seasons with a large sea ice coverage area, increase the weight of ω1 (food abundance) because the food sources are relatively concentrated near the sea ice at this time. Analyze the foraging behavior and food acquisition of krill in different seasons, determine the changes in foraging areas, consider the impact of seasonal changes in sea ice on krill migration, such as the expansion and contraction of sea ice will change the migration routes and times of krill, predict the migration paths and distribution changes of krill in different seasons, as well as the interactions with food sources and natural enemies during migration, and construct a comprehensive assessment model of the krill's living environment Dynamically adjust the weights w k (t) of each factor according to seasonal sea ice changes and the ecological needs of krill, and evaluate the quality of the living environment and the survival probability of krill in different seasons and regions, providing a basis for yield prediction.

[0042] Based on the results of the comprehensive krill ecological analysis module, determine that the key factors affecting krill yield in different seasons are changes in sea ice coverage area, seasonal distribution of food sources, krill migration patterns, and seasonal changes in the living environment, and construct a krill yield prediction model based on seasonal changes Through the training and verification of historical yield data and seasonal environmental data, determine the values of model parameters m, S, L, etc. in different seasons. For example, in seasons with large sea ice changes, appropriately increase the value of m to consider data from more historical time steps. Input the simulated sea ice changes and related environmental data in different seasons into the prediction model, predict the changing trends of krill yields in different seasons and regions, and conduct sensitivity analysis to determine the influence degree of key factors on yield prediction.

[0043] According to the prediction results, the fishery management department formulates seasonal fishery catch quotas, appropriately increasing the catch amount in seasons and regions with high krill yields, and implementing protection measures in seasons and regions with low yields.

[0044] The above is only a preferred embodiment of the present invention, and does not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or equivalents of equivalent changes within the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An Antarctic krill yield analysis system based on multi-source big data, characterized in that, The system includes the following components: Data acquisition and management module: Collect data on ocean currents, marine environment, marine food chain, and ecosystem structure in the Antarctic waters through satellite remote sensing, ocean monitoring stations, and research vessels. After preprocessing, the data is stored in a distributed database. Ocean current and ecological simulation module: Construct a hydrodynamic model based on the geographical information and environmental parameters of the Antarctic waters for ocean current simulation and real-time update. Combine the marine food chain and ecological data to construct a dynamic balance model of the food chain with krill as the core, and integrate the ocean current simulation results to simulate the impact of ocean currents on the food chain and the chain reaction rules under different scenarios. Krill ecological analysis module: Integrate the results of ocean current and ecological simulations and other relevant data to analyze the foraging areas and food availability of krill under the influence of ocean currents, as well as their migration paths and distribution changes. Consider environmental and biological factors comprehensively to construct an evaluation model to analyze the adaptability of the krill's living environment and survival probability. Specifically, combine the data on the flow direction and speed of ocean currents, as well as the distribution and behavioral changes of other organisms in the food chain, and use the krill migration prediction algorithm to predict the migration paths and distribution changes of krill, analyze the survival challenges faced by krill during migration, and evaluate the impact of these factors on the krill population size and reproductive success rate. Its algorithm formula is: Among them, E survive is the comprehensive evaluation value of the krill's living environment, used to measure the overall suitability and survival pressure of the environment where the krill is located. n is the total number of environmental and biological factors considered, including temperature, salinity, dissolved oxygen, the number of natural enemies, and food availability factors. w k (t) is the weight coefficient of the kth factor at time t, which changes dynamically over time and is determined through dynamic modeling based on the change trend of environmental factors and the requirements and sensitivities of krill to various factors at different growth stages. E k is the evaluation value of the kth factor; Krill Yield Prediction Module: Based on krill ecological analysis and biological characteristics, identify and quantify the key factors affecting krill yield, and construct a prediction model. The prediction model is as follows: where Y t is the predicted krill yield at time t, σ is the activation function used to transform the input into values within the output range, m is the number of historical time steps considered, indicating that the krill yield at the current time is predicted using the data of influencing factors for the past m time steps, β i is the weight coefficient of the influencing factor X t-i at the i-th historical time step, X t-i is the factor variable affecting krill yield at time t - i, including the calculated food availability, survival environment assessment value, and ocean current speed. S is the total number of spatial regions. The Antarctic sea area is divided into S different spatial regions to consider the differences in krill yield in different regions. L is the number of hidden layers of the recurrent neural network, and θ sl is the weight coefficient of the l-th hidden layer in spatial region s . is the hidden layer state of spatial region s at time t - l, representing the hidden layer state of spatial region s at time t - l, capturing spatio-temporal dependencies through the recurrent neural network. b is the bias term used to adjust the output of the model. The krill yield prediction module is trained and optimized using historical data, and different ocean current change scenario data are input to predict yield fluctuations and perform uncertainty analysis; Result visualization and application module: Develop software tools to visualize the simulation analysis results in the form of charts, maps, or dynamic demonstrations, and design a user interface.

2. The Antarctic krill yield analysis system based on multi-source big data according to claim 1, wherein, The data acquisition and management module collects historical and real-time ocean current data, marine environment data, marine food chain data, and ecosystem structure data through satellite remote sensing, ocean monitoring stations, and research vessels. Among them, the historical and real-time ocean current data includes ocean current speed, direction, and temperature; the marine environment data includes salinity, dissolved oxygen, and light; the marine food chain data includes the distribution of krill's food sources, natural enemies, and the interaction relationships among various organisms; the ecosystem structure data includes the quantity and distribution of different biological populations.

3. The Antarctic krill yield analysis system based on multi-source big data according to claim 1, characterized in that, The ocean current and ecological simulation module constructs a hydrodynamic model based on the geographical information and environmental parameters of the Antarctic Sea area for ocean current simulation and real-time update. The model formula is as follows: Wherein, is the ocean current velocity vector, representing the velocity and direction of the ocean current at a certain position in the Antarctic Sea area. t1 is the time, used to describe the change of the ocean current velocity over time. ρ is the seawater density, determined according to the temperature and salinity factors in the Antarctic sea area. p is the seawater pressure, related to the depth and seawater density. v is the kinematic viscosity of the seawater, determined by the physical properties of the seawater, which affects the viscous force and energy dissipation inside the ocean current. is the gradient operator, used to calculate the change rate of physical quantities in space. is the external force term. is the newly added force term considering the influence of seabed terrain roughness, calculated by combining high-precision seabed terrain data and terrain roughness models.

4. The Antarctic krill yield analysis system based on multi-source big data according to claim 1, characterized in that The ocean current and ecological simulation module combines marine food chain and ecological data to construct a dynamic balance model of the food chain with krill as the core. The model formula is as follows: Among them, N i represents the population quantity of the i-th species, including the quantity of krill and other related biological populations. t2 is time, which is used to describe the change of biological population quantity over time. r i is the intrinsic growth rate of the i-th species, reflecting the growth ability of this species in an ideal environment. K i is the environmental carrying capacity of the i-th species, which depends on the ecological environment conditions where this species is located, including food resources and habitat space. α ij is the interaction coefficient between organisms. When i≠j, α ij represents the impact of the j-th species on the i-th species. A positive number indicates a promoting effect, and a negative number indicates an inhibitory effect. γ i is the sensitivity coefficient of the i-th species to environmental fluctuations, which is determined according to the ecological adaptability and tolerance of the organism. ΔE is the environmental fluctuation quantity, which comprehensively considers the changes of factors such as ocean temperature, salinity, and ocean current changes, and is obtained through the analysis and calculation of multi-source environmental data.

5. The Antarctic krill yield analysis system based on multi-source big data according to claim 1, characterized in that The krill ecological analysis module analyzes the foraging areas, food availability, migration paths, and distribution changes of krill under the influence of ocean currents by establishing models. Specifically, it deeply integrates the simulation results output by the ocean current and ecological simulation module with the marine food chain and ecosystem structure data in the data collection and management module. Based on the integrated dataset, it analyzes the distribution of food particles carried by ocean currents to determine the food availability in different regions and at different times. At the same time, it analyzes the relationship between the foraging behavior of krill and the food distribution. According to the feeding habits and foraging strategies of krill, it determines the probability of krill foraging at a certain location. The probability calculation formula is: P forage = ω1·F + ω2·D + ω3·T + ω4·C, where P forage is the probability of krill foraging at a certain location, F is the food abundance at this location, obtained by measuring and calculating the quantity and distribution of krill food sources, D is the water flow diffusion coefficient at this location, considering the diffusion and transportation effects of ocean currents on food particles, obtained by analyzing and calculating the ocean current velocity, direction, and diffusion model, T is the temperature suitability at this location, C is the competition pressure index at this location, comprehensively considering the competition situation of other organisms for food resources, obtained by analyzing the quantity and distribution of biological populations competing for food with krill in this area, ω1, ω2, ω3, and ω4 are the weight coefficients of the corresponding factors, determined by the analytic hierarchy process or machine learning method according to actual data and analysis purposes, and used to adjust the relative importance of each factor in the calculation of foraging probability.

6. A method for analyzing the production of Antarctic krill based on multi-source big data, which is applicable to the system for analyzing the production of Antarctic krill based on multi-source big data according to any one of claims 1-5, and is characterized in that, The method includes the following specific steps: Data acquisition and preprocessing: Collect relevant data through the data acquisition and management module, clean, filter, and standardize the data, remove outliers and error data, and perform storage management. Ocean current and ecological simulation: Input the preprocessed data into the ocean current and ecological simulation module, use the hydrodynamic model and numerical simulation technology to simulate the ocean currents in the Antarctic waters, obtain the ocean current simulation results, and at the same time construct a dynamic balance model of the Antarctic marine food chain and integrate the ocean current simulation results to simulate the impact of ocean currents on the food chain and the dynamic change process of the food chain under different conditions, and analyze the chain reaction and evolution rules. Krill ecological analysis: Combine the results of the ocean current and ecological simulation module and the relevant data in the data acquisition and management module, and use data analysis algorithms and models to analyze the foraging, migration, and living environment of krill. Krill yield prediction: According to the results of the krill ecological analysis, use the model established by the krill yield prediction module, input the simulation data under different ocean current change scenarios, predict the fluctuation of krill yield, and perform uncertainty analysis. Result display and application: Visualize and display the prediction results and the dynamic change process of the food chain through the result visualization and application module, and provide them to relevant users.

Images