Aquaculture capacity prediction method and system based on multi-source data

Abstract

The invention discloses an aquaculture capacity prediction method and system based on multi-source data, and relates to the technical field of aquaculture management. An aquaculture capacity prediction system based on multi-source data comprises a data acquisition module, a capacity prediction module, a density adjustment analysis module, a typhoon correction module, an elastic capacity generation module and a space mapping module. According to the method, the typhoon influence correction model is constructed, and the basic capacity is dynamically corrected by using the capacity correction weight, so that automatic adjustment of the prediction capacity in the typhoon season is realized, and the robustness of a prediction result facing extreme meteorological conditions is enhanced; on the basis of recommended capacity, a historical disaster damage data fitting model and risk preference setting, three capacity strategy intervals of conservative, neutral and aggressive are generated, hierarchical selection is provided for breeding decisions of different risk bearing capacities, and decision elasticity and risk control capacity are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of aquaculture management, and in particular to an aquaculture capacity prediction method and system based on multi-source data. Background Art

[0002] With the development of coastal aquaculture in my country, multi-species polyculture has become a mainstream aquaculture model to improve aquaculture efficiency and enhance ecological stability. Traditional aquaculture capacity prediction methods, often based on empirical thresholds, single-factor estimates, or single-species models, fail to fully reflect the dynamic impacts of resource competition, interspecies relationships, and environmental changes on aquaculture capacity in complex ecosystems.

[0003] Especially in multi-age, mixed-breeding scenarios, different aquaculture species and their lifecycle characteristics vary significantly, with varying occupancy and response capacities for spatial resources, water nutrients, and ecological loads. Simple linear models or average methods are unlikely to meet practical management needs. Furthermore, many current capacity forecasting methods fail to account for natural disaster risks, particularly extreme weather events like typhoons. This often leads to distorted forecasts during typhoon season, increasing decision-making risks.

[0004] Some existing research has attempted to incorporate ecological models for capacity simulation, but most focus on long-term ecological balance or resource assessment, lacking adaptability to actual aquaculture plans. Furthermore, most approaches lack deep integration with real-time environmental data or disaster forecasting data. Furthermore, current aquaculture capacity assessment results lack spatial representation, making it difficult to support differentiated management strategies based on regional distribution. Summary of the Invention

[0005] The present invention proposes an aquaculture capacity prediction method and system based on ecosystem modeling, integrating multi-source data input, possessing real-time disaster correction capabilities, and outputting visual adjustment suggestions, in order to enhance the intelligence level of aquaculture capacity management and risk response capabilities.

[0006] A method for predicting aquaculture capacity based on multi-source data, comprising: Collect multi-source polyculture data of the target aquaculture sea area, including sea area environmental data and polyculture plan data; the polyculture plan data includes information on the aquaculture species to be polycultured and their estimated breeding age groups; Input multi-source polyculture data into a polyculture capacity prediction model established based on ecosystem modeling methods to perform capacity prediction calculations and output the basic capacity of each aquaculture species in the target aquaculture area at the estimated breeding age stage, as well as the estimated capacity for the next breeding age stage; Calculate the difference between the basic capacity and estimated capacity of aquaculture species and output the stocking density adjustment strategy; Obtain real-time or forecast typhoon season meteorological data and input it into a typhoon impact correction model built based on historical typhoon meteorological data. The typhoon impact correction model obtains capacity correction weight coefficients based on the capacity response relationship of each aquaculture species under different typhoon intensities, paths, and frequencies, and dynamically corrects the basic capacity to obtain the recommended capacity for the typhoon season; Based on the recommended capacity, combined with the economic loss estimation results of historical disaster loss data and the preset risk preference strategy, the capacity elasticity range for the typhoon season is constructed. The capacity elasticity range includes conservative strategy capacity, neutral strategy capacity and aggressive strategy capacity; The basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and the elastic range of each capacity are mapped to the regional sea area raster layer to form a spatial aquaculture capacity distribution map.

[0007] As a preferred technical solution of the present invention, the polyculture capacity prediction model includes functional group units, ecological process units and spatial environment units constructed based on the ecosystem modeling method, which comprehensively perform capacity prediction calculations; the functional group units are used to simulate the physiological characteristics and resource requirements of various aquaculture species at different breeding ages, the ecological process units are used to describe the feeding, growth, excretion and resource competition processes among breeding species, and the spatial environment units are used to express the spatial grid structure, hydrodynamic background and environmental factor distribution characteristics of the target sea area.

[0008] As a preferred technical solution of the present invention, the comprehensive capacity prediction calculation includes: Input the information of each aquaculture species and its estimated breeding age in the collected polyculture plan data into the functional group unit, and establish a set of individual functional group parameters corresponding to each species and age; Input the marine environmental data into the spatial environment unit to generate a spatial gridded environmental background field of the target aquaculture sea area, including the spatial distribution data of water temperature, salinity, flow velocity and nutrient concentration; The outputs of the functional group unit and the spatial environment unit serve as the inputs of the ecological process unit. The ecological process unit dynamically simulates the feeding, growth, metabolism, excretion and interaction processes of each functional group under the background field, and outputs the basic capacity value of each functional group under the estimated breeding age period. Based on the simulation output results of the current age group, the ecological process unit deduces the biomass change trend towards the next breeding age group, and outputs the estimated capacity value corresponding to the next breeding age group in combination with the growth rate of resource demand per unit weight during the growth of the age group.

[0009] As a preferred technical solution of the present invention, the output breeding density adjustment strategy includes: Based on the difference between the basic capacity of each aquaculture species in the estimated breeding age group and the estimated capacity of its next breeding age group, the capacity change rate per unit area or unit grid is calculated; the capacity change rate is compared with the preset density adjustment threshold to determine whether a breeding density adjustment operation needs to be performed; when the capacity change rate exceeds the threshold, an adjustment strategy including diluting the breeding density or staged fishing is generated in combination with the age growth cycle of each breeding species and the capacity status of the local spatial environment. The adjustment strategy includes the time node for strategy implementation, the target density range and the recommended operation area.

[0010] As a preferred technical solution of the present invention, the typhoon impact correction model includes a typhoon event feature extraction unit, an aquaculture species response parameter unit and a capacity correction calculation unit; the typhoon event feature extraction unit is used to match event features according to typhoon season data; the aquaculture species response parameter unit is used to construct the capacity impact response relationship of different aquaculture species and their aquaculture age groups under different typhoon event characteristics through historical typhoon season data, and form a corresponding correction weight library; the capacity correction calculation unit is used to obtain the capacity correction weight coefficient and calculate the recommended capacity of the basic capacity in the typhoon season.

[0011] As a preferred technical solution of the present invention, the recommended capacity for calculating the basic capacity during the typhoon season includes: The real-time or forecast typhoon season meteorological data is input into the typhoon event feature extraction unit to obtain the parameter characteristics of the intensity, path, landing frequency, duration and landing location of the current typhoon event, and match the corresponding event characteristics; the event characteristics are used as the search conditions to match the corresponding capacity correction weight coefficient in the correction weight library; the capacity correction weight coefficient and the basic capacity of each aquaculture species are weighted and corrected according to the species and age group to obtain the recommended capacity of the basic capacity under the current typhoon season conditions; the calculation of the recommended capacity takes into account the regional environmental carrying limit and the synergistic relationship between the species. When the total capacity exceeds the regional ecological carrying limit, proportional compression is performed based on the capacity adjustment priority of each species.

[0012] As a preferred technical solution of the present invention, the capacity elasticity interval for constructing the typhoon season includes: The recommended capacity of each aquaculture species during the typhoon season is used as the benchmark capacity value; a fitting model is constructed between the capacity change and economic loss of each species based on historical typhoon disaster loss data to obtain the loss change trend corresponding to capacity decline or exceeding the limit; a risk preference level is set, and each level corresponds to a capacity adjustment range and an acceptable economic loss interval; based on the fitting model and the risk preference level, the capacity floating interval corresponding to each species during the typhoon season is calculated to form a capacity elasticity interval.

[0013] An aquaculture capacity prediction system based on multi-source data, comprising: Data acquisition module: used to collect multi-source polyculture data in target aquaculture areas; Capacity prediction module: used to input multi-source polyculture data into the polyculture capacity prediction model and output the basic capacity and estimated capacity of each aquaculture species; Density adjustment analysis module: used to generate breeding density adjustment suggestions based on the difference between basic capacity and estimated capacity; Typhoon correction module: used to obtain real-time or forecast typhoon season meteorological data, and dynamically correct the basic capacity through the typhoon impact correction model to output the recommended capacity for the typhoon season; Elastic capacity generation module: used to construct the capacity elasticity range during the typhoon season based on the recommended capacity; The spatial mapping module is used to map the basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and the elastic range of each capacity to the regional sea area raster layer, forming a spatial aquaculture capacity distribution map.

[0014] The present invention has the following advantages: The present invention constructs a polyculture capacity prediction model based on the ecosystem modeling method, combines marine environmental data with polyculture plan data, and outputs the capacity prediction results of each cultured species in the current age group and the next age group, thereby improving the accuracy and adaptability of capacity assessment in polyculture scenarios.

[0015] The present invention supports the joint output of the basic capacity of the current age group and the predicted capacity of the next age group for each aquaculture species, making the adjustment of aquaculture density more forward-looking and facilitating the timely formulation of fishing opportunities or regulatory strategies; it automatically generates aquaculture density adjustment strategies based on the difference between the current and next age group capacities, including density dilution or phased fishing recommendations, and improves the operability of the plan through directional output of spatial environmental conditions.

[0016] The present invention constructs a typhoon impact correction model and uses capacity correction weights to dynamically correct the basic capacity, thereby realizing automatic adjustment of the typhoon season forecast capacity and enhancing the robustness of the forecast results in the face of extreme meteorological conditions. Based on the recommended capacity, historical disaster loss data fitting model and risk preference settings, three capacity strategy intervals, conservative, neutral and aggressive, are generated, providing graded choices for breeding decisions with different risk tolerances, thereby improving decision-making flexibility and risk control capabilities.

[0017] The present invention maps basic capacity, recommended capacity and elastic capacity to a sea area grid layer to form a spatial aquaculture capacity distribution map, supports the formulation of strategies based on regional differences, and realizes the visualization and platform application of aquaculture capacity prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only schematic diagrams of the present invention. Those skilled in the art can also derive other drawings based on the provided drawings without inventive effort. Figure 1 This is a structural diagram of an aquaculture capacity prediction system based on multi-source data adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Example 1, a method for predicting aquaculture capacity based on multi-source data, comprising the following steps: Step S1: Collect multi-source polyculture data of the target aquaculture sea area, including sea area environmental data and polyculture plan data; the polyculture plan data includes polycultured aquaculture species and their estimated breeding age information; Marine environmental data: used to express the hydrological, physical, and chemical ecological background of the target aquaculture area, and for use in the spatial environment and ecological process modeling in the capacity prediction model (forming a rasterized environmental background field of the target sea area), including at least the following tables:

[0021] It also includes: hydrodynamic structure data (such as tidal currents, wave propagation direction, wind speed and direction, etc.) obtained through remote sensing data platforms or local ocean forecasting systems, which is used to analyze the permeability and material exchange characteristics of the sea area; spatial environmental factors, including the coordinate boundaries of the aquaculture sea area, topographic features (whether it is near the coast / bay mouth / open area), bottom sediment type (silt, reef, etc.), and other geographical background information; Polyculture plan data (taking the "large yellow croaker + mussel + kelp" combination as an example): refers to the mixed species culture structure plan set for the target aquaculture area, providing the core information required by the model, including species types, initial parameters, and spatial locations, such as: Polyculture species combination: large yellow croaker, mussels and kelp; Stocking density: Large yellow croaker - 5 per square meter; Mussels - 20 per cage; Kelp - 10 kg per rope; Estimated breeding age: Yellow croaker - early fattening stage (6th month); Mussels - middle stage; Kelp - adult stage; The ratio of polyculture structure is: yellow croaker: mussel: kelp = 2:2:1; Spatial distribution and numbering: Cages are numbered F1 to F30 and are located in the sea area between N26°10' and N26°12'. The numbering coordinates match the GIS layer. Source and update method: exported from the breeding management system, or entered by on-site inspection personnel through the mobile terminal.

[0022] This type of multi-species combination is used in nearshore cage ecological polyculture. Kelp absorbs nutrients to reduce the risk of eutrophication, while mussels filter particulate matter to purify water quality. At the same time, they complement each other with large yellow croaker and are typical.

[0023] The aforementioned marine environmental data and polyculture plan data are input in a unified data format (JSON or structured tables) to form a complete multi-source input dataset for the polyculture capacity prediction model in the next step. Parameter fields are automatically connected to the model input interface to achieve seamless data flow.

[0024] Step S2: Input the multi-source polyculture data into a polyculture capacity prediction model established based on the ecosystem modeling method to perform capacity prediction calculations and output the basic capacity of each aquaculture species in the target aquaculture sea area at the estimated breeding age stage and the estimated capacity of the next breeding age stage; Ecosystem modeling is a method based on ecological dynamics theory that uses structured models to quantitatively represent the nutrient uptake, growth metabolism, interspecies interactions, and environmental feedback mechanisms of multiple species in aquaculture systems. This modeling method typically adopts a modular structure and has the following characteristics: Taking functional groups as the basic simulation unit, individuals with similar ecological behaviors are aggregated to simplify the computational complexity; Emphasize the biological-environmental coupling relationship and reflect the regulatory effect of biological behavior on ecological capacity through two-way dynamic coupling with environmental factors; Supports data input for multiple age groups, multiple species, and multiple spatial grid points, making it suitable for complex scenarios such as high-density polyculture and three-dimensional space utilization; Common modeling framework packages such as EwE, Farm-AEM, and AquaFarm have good ecological process simulation and visualization capabilities.

[0025] In this embodiment, the ecosystem modeling method is used to construct a polyculture capacity prediction model, which is broken down into three parts: functional group unit, ecological process unit and spatial environment unit, and capacity prediction simulation is carried out in a coordinated manner.

[0026] The polyculture capacity prediction model includes functional group units, ecological process units and spatial environment units constructed based on the ecosystem modeling method, and comprehensively performs capacity prediction calculations; Functional group unit: used to simulate the physiological characteristics and resource requirements of various aquaculture species at different breeding ages; Physiological characteristics include the individual growth rate, feeding capacity, excretion rate, metabolic heat flux, etc. of the species at the current age; Resource requirements include the average daily consumption of key resources such as particulate organic matter, dissolved oxygen, and nutrients; For example, in the "large yellow croaker + mussel + kelp" combination: large yellow croaker (in the early fattening stage) has the following parameters: food intake and ammonia excretion rate; mussels rely on filtering plankton particles, and their metabolic load parameters; kelp uses nutrients (nitrates and phosphates) as its main resources, and its corresponding consumption rate parameters, with photosynthesis dominating its growth process; The functional group unit organizes the above parameters into a standardized set of functional group objects as the basic unit of ecological simulation.

[0027] Ecological process unit: used to describe the feeding, growth, excretion and resource competition processes among cultured species; The input is the biological parameters output by the functional group unit and the background field data of the spatial environment unit; The population ecological dynamics model is used to dynamically simulate the following processes: the feeding efficiency and growth of each functional group under the current environment; the impact of excretions such as ammonia nitrogen produced by respiratory metabolism on the local environment; the growth inhibition, competition, and synergy of multiple populations under resource-limited conditions; and the simulation results include the ecological equilibrium capacity of each unit grid and each functional group at the current age.

[0028] Spatial environment unit: used to express the spatial grid structure, hydrodynamic background and environmental factor distribution characteristics of the target sea area; The sea area is divided into several spatial grid units (e.g., 500 m × 500 m), with each grid point bound to the following environmental information: water temperature, salinity, water flow velocity, flow direction; nitrate, phosphate, dissolved oxygen concentrations; water depth, bottom type, water exchange frequency, etc.; the environmental background field constructed by this unit (the spatial grid structure of the target sea area) will be used to constrain and drive subsequent ecological process simulations.

[0029] The comprehensive capacity forecast calculation includes: Input the information of each aquaculture species and its estimated breeding age in the collected polyculture plan data into the functional group unit, and establish a set of individual functional group parameters corresponding to each species and age; For example, the configuration of the 6-month-old group of large yellow croaker is: the feeding rate per unit body weight is 0.08 kg / kg·day, the metabolic ammonia emission is 0.015 g / kg·day, and the optimal water temperature range is 21~26℃; Each parameter comes from measured data, farming manuals, or model literature databases (such as the EcopathwithEcosim parameter set); Input the marine environmental data into the spatial environment unit to generate a spatial gridded environmental background field of the target aquaculture sea area, including the spatial distribution data of water temperature, salinity, flow velocity and nutrient concentration; A set of environmental factor vectors is established for each spatial grid, for example: grid point G_001: water temperature 23.2℃, salinity 30.5‰, NO3=0.38 mg / L; The outputs of the functional group unit and the spatial environment unit serve as the inputs of the ecological process unit. The ecological process unit dynamically simulates the feeding, growth, metabolism, excretion and interaction processes of each functional group under the background field, and outputs the basic capacity value of each functional group under the estimated breeding age period. For example, in grid G_001, the basic capacity of large yellow croaker is 150 kg, that of mussels is 80 kg, and that of kelp is 200 kg; If there are regional limitations on nutrients or dissolved oxygen, the model will automatically adjust the stocking density to maintain ecological balance.

[0030] Based on the simulation output results of the current age group, the ecological process unit deduces the biomass change trend towards the next breeding age group, and outputs the estimated capacity value corresponding to the next breeding age group in combination with the growth rate of resource demand per unit weight during the growth of the age group.

[0031] For example, when large yellow croaker transitions from 6 to 8 months of age, the food intake per unit body weight increases by 12%, and if the background nutrient level is insufficient, the capacity decreases to 130 kg; This estimate can be used to formulate aquaculture adjustment plans in advance (such as fishing, stocking optimization, etc.).

[0032] Step S3: Calculate the difference between the basic capacity and the estimated capacity of the aquaculture species and output a breeding density adjustment strategy; The output breeding density adjustment strategy includes: Based on the difference between the basic capacity of each aquaculture species in the estimated breeding age group and the estimated capacity of its next breeding age group, the capacity change rate per unit area or unit grid is calculated; the capacity change rate is compared with the preset density adjustment threshold to determine whether a breeding density adjustment operation needs to be performed; when the capacity change rate exceeds the threshold, an adjustment strategy including diluting the breeding density or staged fishing is generated in combination with the age growth cycle of each breeding species and the capacity status of the local spatial environment. The adjustment strategy includes the time node for strategy implementation, the target density range and the recommended operation area.

[0033] Density adjustment judgment mechanism: (determine whether the breeding density adjustment operation needs to be performed) The capacity change rate is the difference between the capacity of the current age segment and the capacity of the next age segment within a unit space, which is used to assess whether there is overload risk or resource redundancy; The density adjustment threshold is a system preset parameter, set based on past experience or model sensitivity analysis (±15%), and is used to define the acceptable range of capacity fluctuation; If the rate of change exceeds the positive threshold, it indicates a significant increase in biomass, which may cause resource overload and trigger a density dilution recommendation; If the rate of change < negative threshold → indicates insufficient growth or increased ecological constraints, early fishing or structural optimization may be considered.

[0034] Strategy generation process description: (Generate adjustment strategies including dilution of stocking density or staged harvesting) Input: basic capacity, estimated capacity, environmental capacity limit, age group life cycle information; Processing logic: Determine the direction and magnitude of capacity fluctuation; analyze the growth cycle and growth inflection point of the corresponding age group; check whether the environmental capacity of the corresponding space unit can accommodate the change; match the strategy according to the set strategy template; Output content: Dilution operation suggestions (such as moving boxes, reducing density); fishing time window (such as starting fishing one month in advance, removing duplicates step by step); suggestions for optimizing polyculture structure (such as postponing the stocking of seedlings in the next cycle).

[0035] Take the polyculture of "large yellow croaker + kelp" in a grid as an example:

[0036] System judgment: The growth rate of large yellow croaker exceeds the upper limit (the threshold is set at ±15%), triggering a density dilution recommendation; kelp does not exceed the lower limit, but because it is a supplementary species and is slightly deficient in nutrients, it is recommended to end the early stage of fishing or reduce subsequent stocking; The final policy output is: Grid number: G_005, adjustment type: combined; Recommendations for large yellow croaker: {reduce the density by 20%, postpone feeding for 2 weeks, and recommend fishing period: 7th to 8th week}; Kelp recommendations: {maintain current density or reduce seedling stocking ratio to 80%}; Step S4: Real-time or forecast typhoon season meteorological data is obtained and input into a typhoon impact correction model constructed based on historical typhoon meteorological data. The typhoon impact correction model obtains a capacity correction weight coefficient based on the capacity response relationship of each aquaculture species under different typhoon intensities, paths, and frequencies, and dynamically corrects the basic capacity to obtain the recommended capacity for the typhoon season; The typhoon impact correction model includes a typhoon event feature extraction unit, an aquaculture species response parameter unit and a capacity correction calculation unit. The three work together to form a complete typhoon impact correction mechanism, which is used to simulate the compression effect of typhoon disturbances on the capacity of different aquaculture species at specific age groups.

[0037] Typhoon event feature extraction unit: used to receive real-time or forecast typhoon season data provided by external meteorological systems (NOAA, regional marine meteorological service platform), parse and extract the following five key typhoon parameter characteristics: intensity level (such as tropical storm, severe tropical storm, typhoon, severe typhoon); path trajectory (latitude and longitude sequence or path number); landing frequency (number of events per unit time); duration (such as hours or days); landing location coordinates (affected area or center point landing area).

[0038] After event feature extraction, a standardized typhoon event description object will be formed and input into the downstream module for matching processing.

[0039] Aquaculture species response parameter unit: used to establish a typhoon capacity impact response model. Its main function is to fit and analyze the above-mentioned extracted event characteristics with the historical aquaculture capacity change data, thereby constructing a capacity correction weight library.

[0040] Correction weight construction process: Organize the actual loss or capacity reduction records of the target sea area during multiple typhoon events in the past; compare the event intensity and path with the capacity impact of different aquatic species and age groups; fit the capacity impact factors corresponding to different event feature combinations and species-age groups; store them as a key-value structure to form a correction weight database.

[0041] Definition of capacity correction weight coefficient: The correction coefficient is a real number in the interval [0,1], which represents the proportion of capacity retained under the influence of typhoon.

[0042] For example:

[0043] Capacity correction calculation unit: used to find the matching coefficient in the correction weight library according to the characteristics of the current typhoon event, and to correct the basic capacity of each aquaculture species.

[0044] The recommended computing capacity during the typhoon season includes: The real-time or forecast typhoon season meteorological data is input into the typhoon event feature extraction unit to obtain the parameter characteristics of the intensity, path, landing frequency, duration and landing location of the current typhoon event, and match the corresponding event characteristics; the event characteristics are used as the search conditions to match the corresponding capacity correction weight coefficient in the correction weight library; the capacity correction weight coefficient and the basic capacity of each aquaculture species are weighted and corrected according to the species and age group to obtain the recommended capacity of the basic capacity under the current typhoon season conditions; the calculation of the recommended capacity takes into account the regional environmental carrying limit and the synergistic relationship between the species. When the total capacity exceeds the regional ecological carrying limit, proportional compression is performed based on the capacity adjustment priority of each species.

[0045] Recommended capacity calculation process: Typhoon event characteristics are used as search conditions, and the correction weights provided by the response parameter unit are called; the correction weights are applied to the basic capacity of each species and age group to obtain the recommended capacity; If the total recommended capacity exceeds the ecological carrying limit of the area (such as dissolved oxygen in water, nutrient load, habitat space, etc.), the capacity compression mechanism will be activated: priority adjustment will be made based on the capacity adjustment priority of the species (preset strategy or economic value weight); all species will be proportionally compressed or partially compressed to ensure that the total capacity falls below the ecological threshold; and the final recommended capacity and compression description information will be output.

[0046] Capacity correction weight coefficient: used to measure the proportion of actual aquaculture capacity that can be retained by organisms in each type of aquaculture unit under the influence of a typhoon, reflecting the sensitivity of typhoon disturbances; Recommended capacity: indicates the reasonable and safe aquaculture carrying capacity under the current typhoon interference assumption, which is used to generate adjustment suggestions or investment plans; Ecological carrying limit: refers to the maximum capacity of aquaculture species that can exist sustainably under current hydrological and ecological conditions, to prevent system overload or ecological degradation.

[0047] Step S5: Based on the recommended capacity, combined with the economic loss estimation results of historical disaster loss data fitting and the preset risk preference strategy, a capacity elasticity range for the typhoon season is constructed. The capacity elasticity range includes conservative strategy capacity, neutral strategy capacity, and aggressive strategy capacity; Recommended capacity: the appropriate input capacity calculated by the typhoon impact correction model; Capacity elasticity range: The upper and lower capacity fluctuation bands are formed based on the recommended capacity, loss estimates, and risk tolerance ranges. Fitting model: A model that fits historical aquaculture loss data to the degree of capacity offset as a function to quantify risk; The capacity elasticity range for constructing the typhoon season includes: The recommended capacity of each aquaculture species during the typhoon season is used as the benchmark capacity value, i.e., the corrected acceptable capacity output by the typhoon impact correction model in step S4; Based on historical typhoon damage data, a fitting model between the capacity changes of various varieties and economic losses was constructed; The historical disaster loss data include: actual aquaculture production loss during typhoons; the proportion of production reduction due to disasters; the production density when the typhoon occurred; and the post-disaster repair costs; Data sources: aquaculture enterprise ledgers, insurance claims records, and post-disaster assessment files of local marine fishery departments.

[0048] Fitting method: Based on nonlinear functions of capacity deviation and loss amount, such as piecewise linear regression, logistic regression, or loss-risk response curve, to obtain the loss trend corresponding to capacity reduction or overcapacity; Set risk appetite levels, with each level corresponding to a capacity adjustment range and acceptable economic loss range; The risk appetite strategy is set according to the investor / manager's willingness to bear losses. Typical levels include: conservative, loss tolerance <5%; neutral, tolerance 5-15%; aggressive, tolerance 15-30%; Each level will be mapped to an adjustment ratio range of the recommended capacity, such as: conservative, 85%–100% of the recommended capacity; neutral, 70%–115% of the recommended capacity; aggressive, 50%–130% of the recommended capacity; Also considered: uncertainty in typhoon forecasts; differences in risk resistance of aquaculture species; and the turning point of economic gains and losses (critical capacity).

[0049] According to the fitting model and risk preference level, the capacity floating range corresponding to each variety in the typhoon season is calculated to form the capacity elasticity range.

[0050] For each variety, the following mapping is established: ,in C 低 Indicates the conservative lower limit of the recommended capacity; C 高 Indicates the upper limit of risk compensation for recommended capacity; R Indicates the risk appetite level; L ( C ) represents the possible loss estimate in the corresponding interval, f () indicates the mapping process.

[0051] The output capacity elastic ranges are named as follows: Conservative strategy capacity: It is recommended to start production within a smaller deviation range (such as 90% of the recommended value), giving priority to protecting principal and resources; Neutral strategy capacity: Maintain the recommended capacity within a range of 10–20%, balancing stability and returns; Aggressive strategy capacity: You can exceed the recommended capacity by a certain percentage in exchange for higher returns but you will have to bear the risk of post-disaster production reduction or environmental compression.

[0052] Step S6: Map the basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and each capacity elasticity interval to the regional sea area raster layer to form a spatialized aquaculture capacity distribution map.

[0053] Definition of noun: Raster layer: Discretize the continuous sea area into grid cells, each cell contains location and attribute data; Capacity type: includes basic capacity, recommended capacity, and elastic capacity; Spatial mapping: refers to the process of tying non-spatial data (such as capacity) to specific geographic locations; Visual coding: Use colors, legends, shapes, etc. to express numerical changes and enhance the intuitive communication of information; Distribution map: Graphical display of capacity data in spatial areas, with intuitive interpretation and data support The forming of the spatialized aquaculture capacity distribution map includes: Construct a spatial grid base map of the regional sea area: the target aquaculture sea area is divided into equal-scale spatial grid units according to latitude and longitude or sea area coordinate system; Each grid cell is bound to a spatially unique identifier (GridID), which corresponds to the polyculture facility number (e.g., cage, raft); Sea bottom Figure 1 It is generally constructed by GIS systems (such as ArcGIS and QGIS), and the underlying data sources include nautical charts, remote sensing images, and sea area utilization planning maps.

[0054] Establish a mapping relationship between capacity data and spatial grids: match the basic capacity output in step S2, the recommended capacity in step S4, and the capacity elasticity interval in step S5 to the corresponding grid according to the spatial distribution coordinates of the breeding facilities; for the case of multi-species polyculture within the same grid, display the polyculture capacity status in a hierarchical manner or a composite index; If the capacity values of a grid under different strategies (conservative / neutral / aggressive) are significantly different, color gradients or symbol changes can be used for visual distinction.

[0055] Generate three types of capacity layers: the basic capacity layer, which reflects the basic biomass distribution of various species suitable for aquaculture in the current or recent marine ecosystem; the recommended capacity layer, which takes into account the capacity correction results after typhoon season disturbances and is the core basis for guiding short-term aquaculture planning; and the elastic capacity layer, which shows the range of capacity upper and lower limits based on risk preferences for dynamic decision support. Capacity value encoding and visualization: The storage format of the numerical field of each layer is: {raster ID|variety|age group|capacity type|value (kg or tail / raster)}; Visualization method: Different varieties are distinguished by legend colors; different capacity types are superimposed with layers; elastic ranges can be marked with shaded areas or error band icons.

[0056] Finally, a spatialized aquaculture capacity distribution map is formed, which realizes the visualization of capacity layout for multiple strategies, all varieties, and different age groups. It can be used in the following application scenarios: capacity allocation and adjustment of aquaculture areas; identification and early warning deployment of typhoon season risk areas; spatial decision-making on dilution or expansion strategies; and layer access to government supervision or scientific research model analysis platforms.

[0057] Example 2, a system for predicting aquaculture capacity based on multi-source data, see Figure 1 As shown, it includes the following units: A data acquisition module is used to collect multi-source polyculture data of the target aquaculture sea area, including sea area environmental data and polyculture plan data, wherein the polyculture plan data includes information on the aquaculture species to be polycultured and their estimated breeding age groups; a capacity prediction module for inputting the multi-source polyculture data into a polyculture capacity prediction model established based on an ecosystem modeling method, and outputting the basic capacity of each aquaculture species in the estimated breeding age period and the estimated capacity of the next breeding age period; Density adjustment analysis module, used to generate breeding density adjustment suggestions based on the difference between basic capacity and estimated capacity; The typhoon correction module is used to obtain real-time or forecast typhoon season meteorological data, and dynamically correct the basic capacity based on the typhoon impact correction model built based on historical typhoon data, and output the recommended capacity for the typhoon season; The elastic capacity generation module is used to generate elastic capacity intervals including conservative strategy capacity, neutral strategy capacity, and aggressive strategy capacity based on the recommended capacity, economic loss fitting model, and risk preference level; The spatial mapping module is used to map the basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and the elastic range of each capacity to the regional sea area raster layer, forming a spatial aquaculture capacity distribution map.

[0058] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting aquaculture capacity based on multi-source data, characterized in that: include: Collect multi-source polyculture data of the target aquaculture area, including marine environment data and polyculture plan data; The polyculture plan data includes information on the polycultured aquatic species and their estimated culture age groups; Input multi-source polyculture data into a polyculture capacity prediction model established based on ecosystem modeling methods to perform capacity prediction calculations and output the basic capacity of each aquaculture species in the target aquaculture area at the estimated breeding age stage, as well as the estimated capacity for the next breeding age stage; Calculate the difference between the basic capacity and estimated capacity of aquaculture species and output the stocking density adjustment strategy; Obtain real-time or forecast typhoon season meteorological data and input it into a typhoon impact correction model built based on historical typhoon meteorological data. The typhoon impact correction model obtains capacity correction weight coefficients based on the capacity response relationship of each aquaculture species under different typhoon intensities, paths, and frequencies, and dynamically corrects the basic capacity to obtain the recommended capacity for the typhoon season; Based on the recommended capacity, combined with the economic loss estimation results of historical disaster loss data and the preset risk preference strategy, the capacity elasticity range for the typhoon season is constructed. The capacity elasticity range includes conservative strategy capacity, neutral strategy capacity and aggressive strategy capacity; The basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and the elastic range of each capacity are mapped to the regional sea area raster layer to form a spatial aquaculture capacity distribution map.

2. The aquaculture capacity prediction method based on multi-source data according to claim 1, characterized in that: The polyculture capacity prediction model includes functional group units, ecological process units and spatial environment units constructed based on the ecosystem modeling method, which comprehensively perform capacity prediction calculations; the functional group units are used to simulate the physiological characteristics and resource requirements of various aquaculture species at different breeding ages; the ecological process units are used to describe the feeding, growth, excretion and resource competition processes among aquaculture species; and the spatial environment units are used to express the spatial grid structure, hydrodynamic background and environmental factor distribution characteristics of the target sea area.

3. The aquaculture capacity prediction method based on multi-source data according to claim 2, characterized in that: The comprehensive capacity forecast calculation includes: Input the information of each aquaculture species and its estimated breeding age in the collected polyculture plan data into the functional group unit, and establish a set of individual functional group parameters corresponding to each species and age; Input the marine environmental data into the spatial environment unit to generate a spatial gridded environmental background field of the target aquaculture sea area, including the spatial distribution data of water temperature, salinity, flow velocity and nutrient concentration; The outputs of the functional group unit and the spatial environment unit serve as the inputs of the ecological process unit. The ecological process unit dynamically simulates the feeding, growth, metabolism, excretion and interaction processes of each functional group under the background field, and outputs the basic capacity value of each functional group under the estimated breeding age period. Based on the simulation output results of the current age group, the ecological process unit deduces the biomass change trend towards the next breeding age group, and outputs the estimated capacity value corresponding to the next breeding age group in combination with the growth rate of resource demand per unit weight during the growth of the age group.

4. The aquaculture capacity prediction method based on multi-source data according to claim 1, characterized in that: The output breeding density adjustment strategy includes: Based on the difference between the basic capacity of each aquaculture species in the estimated breeding age group and the estimated capacity of its next breeding age group, the capacity change rate per unit area or unit grid is calculated; the capacity change rate is compared with the preset density adjustment threshold to determine whether a breeding density adjustment operation needs to be performed; when the capacity change rate exceeds the threshold, an adjustment strategy including diluting the breeding density or staged fishing is generated in combination with the age growth cycle of each breeding species and the capacity status of the local spatial environment. The adjustment strategy includes the time node for strategy implementation, the target density range and the recommended operation area.

5. The aquaculture capacity prediction method based on multi-source data according to claim 1, characterized in that: The typhoon impact correction model includes a typhoon event feature extraction unit, an aquaculture species response parameter unit and a capacity correction calculation unit; the typhoon event feature extraction unit is used to match event features according to typhoon season data; The aquaculture species response parameter unit is used to construct the capacity impact response relationship of different aquaculture species and their aquaculture age groups under different typhoon event characteristics through historical typhoon season data, and form a corresponding correction weight library; the capacity correction calculation unit is used to obtain the capacity correction weight coefficient and calculate the recommended capacity of the basic capacity in the typhoon season.

6. The aquaculture capacity prediction method based on multi-source data according to claim 5, characterized in that: The recommended computing capacity during the typhoon season includes: The real-time or forecast typhoon season meteorological data is input into the typhoon event feature extraction unit to obtain the parameter characteristics of the intensity, path, landing frequency, duration and landing location of the current typhoon event, and match the corresponding event characteristics; the event characteristics are used as the search conditions to match the corresponding capacity correction weight coefficient in the correction weight library; the capacity correction weight coefficient and the basic capacity of each aquaculture species are weighted and corrected according to the species and age group to obtain the recommended capacity of the basic capacity under the current typhoon season conditions; the calculation of the recommended capacity takes into account the regional environmental carrying limit and the synergistic relationship between the species. When the total capacity exceeds the regional ecological carrying limit, proportional compression is performed based on the capacity adjustment priority of each species.

7. The method for predicting aquaculture capacity based on multi-source data according to claim 1, characterized in that: The capacity elasticity range for constructing the typhoon season includes: The recommended capacity of each aquaculture species during the typhoon season is used as the benchmark capacity value; a fitting model is constructed between the capacity change and economic loss of each species based on historical typhoon disaster loss data to obtain the loss change trend corresponding to capacity decline or exceeding the limit; a risk preference level is set, and each level corresponds to a capacity adjustment range and an acceptable economic loss interval; based on the fitting model and the risk preference level, the capacity floating interval corresponding to each species during the typhoon season is calculated to form a capacity elasticity interval.

8. An aquaculture capacity prediction system based on multi-source data, characterized in that: The system applies the aquaculture capacity prediction method based on multi-source data according to any one of claims 1 to 7, comprising: Data acquisition module: used to collect multi-source polyculture data in target aquaculture areas; Capacity prediction module: used to input multi-source polyculture data into the polyculture capacity prediction model and output the basic capacity and estimated capacity of each aquaculture species; Density adjustment analysis module: used to generate breeding density adjustment suggestions based on the difference between basic capacity and estimated capacity; Typhoon correction module: used to obtain real-time or forecast typhoon season meteorological data, and dynamically correct the basic capacity through the typhoon impact correction model to output the recommended capacity for the typhoon season; Elastic capacity generation module: used to construct the capacity elasticity range during the typhoon season based on the recommended capacity; The spatial mapping module is used to map the basic capacity of each aquaculture species, the recommended capacity during the typhoon season, and the elastic range of each capacity to the regional sea area raster layer, forming a spatial aquaculture capacity distribution map.

Images