Deep sea three-dimensional environment deduction simulation analysis system based on big data

Abstract

The invention discloses a deep sea three-dimensional environment deduction simulation analysis system based on big data, and relates to the technical field of deep sea environment simulation. The visual service desk is in communication connection with a data acquisition and integration module, a deep sea three-dimensional scene modeling module, a rendering optimization module, a deep sea environment analysis module, a marine environment deduction simulation module, a three-dimensional visual display module and a deep sea deduction typical scene roaming module, by integrating multi-source and multi-dimensional deep sea data, a highly realistic deep sea three-dimensional environment model is constructed, the change trend of the deep sea environment can be simulated in real time and the dynamic change of the deep sea environment can be reflected by using a big data processing technology, and a user can visually feel the deep sea landscape through virtual roaming, so that the user experience is improved. The efficiency and safety of deep sea resource development are remarkably improved, and the development cost and risk caused by environment uncertainty are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of deep sea environment simulation, and in particular to a deep sea three-dimensional environment deduction simulation analysis system based on big data. Background Art

[0002] As human beings' demand for deep-sea resource development increases, especially in the research of energy, mineral resources, marine life and ecosystems, in order to better understand the deep-sea environment and conduct precise deep-sea operations, the deep-sea three-dimensional environment simulation and analysis system has become an essential tool. Through this system, deep-sea environmental changes can be monitored and analyzed in real time, providing technical support for deep-sea development and scientific research.

[0003] In deep-sea 3D simulation, due to the complex details of the seabed topography and environment, it is difficult to ensure high precision and real-time performance at the same time when rendering, which can easily lead to problems such as unrealistic display effects or slow response, and then the simulation results are quite different from the actual situation. Therefore, how to improve the accuracy of deep-sea 3D environment simulation and the authenticity of the display effect to ensure the coexistence of accuracy and authenticity is a problem that needs to be solved. To this end, a deep-sea 3D environment simulation and analysis system based on big data is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a deep-sea three-dimensional environment simulation and analysis system based on big data to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A deep-sea three-dimensional environment deduction and simulation analysis system based on big data, comprising a visualization service desk, wherein the visualization service desk is communicatively connected with a data acquisition integration module, a deep-sea three-dimensional scene modeling module, a rendering optimization module, a deep-sea environment analysis module, an ocean environment deduction and simulation module, a three-dimensional visualization display module, and a deep-sea deduction typical scene roaming module, wherein electrical signals are connected between the modules; The data acquisition and integration module acquires deep-sea environment data and ship AIS data based on multiple data sources (various sensors, databases), and integrates various types of data to form a multi-dimensional deep-sea environment data set, providing a basis for subsequent analysis and deduction; The deep-sea 3D scene modeling module constructs a 3D model of the deep-sea environment including seabed topography, water bodies, organisms and equipment elements based on the data of the deep-sea environment dataset, and presents a realistic deep-sea environment through high-precision modeling; The rendering optimization module performs real-time rendering of the deep-sea environment three-dimensional model based on graphics rendering technology; The deep-sea environment analysis module further analyzes the deep-sea environment data based on a machine learning algorithm to identify changing trends in the deep-sea environment; The ocean environment simulation module dynamically simulates and predicts the future state of the deep-sea environment based on the rendering optimized three-dimensional model of the deep-sea environment and the real-time ship AIS data, combined with the deep-sea environment analysis results; The three-dimensional visualization display module is used to realize dynamic simulation of ship navigation in a virtual scene, including the display of the motion trajectory of ships and submersibles, and dynamically update environmental factors such as wave status, wind speed, and ocean currents to enhance the authenticity of the display effect; The deep-sea simulation typical scene roaming module is used to set locations for dynamic scene roaming, display simulation results and mark key locations, so as to facilitate users to quickly locate and analyze, provide a responsive roaming experience, and allow users to independently adjust the roaming speed.

[0006] A further improvement of the technical solution of the present invention is that the data acquisition and integration module specifically includes: Identify various types of data sources of deep-sea environment, including but not limited to deep-sea sensor networks, databases and ship AIS data sources, and obtain deep-sea environment data and ship AIS data from various types of data sources through corresponding interfaces and protocols; The acquired deep-sea environment data and ship AIS data are pre-processed by data cleaning, correction and standardization. In particular, missing values, outliers or duplicate data are identified and processed through data cleaning, and the data are denoised and smoothed to improve data quality. The sensor data are calibrated and standardized to ensure data consistency and accuracy, and the AIS data are converted from the original message format to a digital format that is easy to analyze and process; According to the timestamp and geographic location information, the preprocessed deep-sea environmental data and ship AIS data are matched, and data from different sources are integrated to form a deep-sea environmental dataset containing multiple dimensions. The deep-sea environmental dataset is then stored in the corresponding data warehouse for subsequent query and analysis.

[0007] A further improvement of the technical solution of the present invention is that the deep-sea three-dimensional scene modeling module specifically includes: Extract deep-sea environment data sets from the data warehouse and classify the data in the deep-sea environment data sets, including seabed topography data, water body data, biological data, and equipment data; For submarine terrain modeling, terrain data of different resolutions (global terrain data and local high-precision terrain data) are integrated to ensure the globality and local details of the terrain model. The submarine terrain is constructed using the terrain modeling tool (World Machine), and the terrain data is imported into the modeling software. The terrain mesh is generated through the height map, and then the generated terrain mesh is optimized to adjust the level of detail of the terrain. For water modeling, a physical model of the water body is constructed based on the physical properties of the water body (refractive index, reflectivity, scattering coefficient, etc.), and fluid dynamics simulation technology is used to simulate the dynamic effects of water flow, waves and ocean currents; For biological modeling, a 3D model library of marine organisms, including fish, plankton, and corals, was constructed based on biological distribution data. The biological models were created using modeling software (3ds Max), and then placed in corresponding locations to simulate their behavior patterns (swimming, foraging, reproduction, etc.). The particle swarm optimization algorithm was used to simulate the group behavior and movement trajectory of organisms. For equipment modeling, we build a 3D model library for deep-sea equipment, including scientific research vessels, submersibles, and sensors. According to the equipment location and data, we create a 3D model of the deep-sea equipment, place the equipment model at the corresponding location, and simulate its dynamic behavior (navigation, diving, data collection, etc.); Integrate the seabed terrain, water bodies, organisms and equipment elements into a unified 3D scene, ensure the spatial relationship and time synchronization between the elements, optimize the entire scene, and use LOD technology to dynamically adjust the model's level of detail to ensure good rendering performance at different viewing distances.

[0008] A further improvement of the technical solution of the present invention is that the rendering optimization module specifically includes: Configure Unreal Engine as the rendering engine for deep-sea 3D environment simulation analysis, initialize the rendering engine, configure basic rendering engine parameters including rendering resolution, anti-aliasing settings, and shadow quality, and then load the deep-sea 3D model and related resources (textures, materials, animations, etc.) into the rendering engine; Use Unreal Engine's face reduction tool to simplify the deep-sea 3D model, reduce the number of faces and vertices, and reduce the computational burden during rendering. In Unreal Engine, set multiple LOD levels for the model, dynamically adjust the model's level of detail according to the model's viewing distance and viewing angle, and use multi-level texture technology to automatically match the corresponding texture resolution according to the viewing distance. Configure Unreal Engine's occlusion culling system to render only objects that are within the view frustum, ignoring invisible objects to reduce unnecessary rendering calculations, and enable geometry occlusion detection to cull parts that are blocked by other objects, further reducing rendering load; Use Unreal Engine's PBR material system to optimize the reflection, refraction and scattering parameters of the material, and combine texture compression technology (DXT) to reduce the storage and transmission overhead of texture data, implement texture streaming loading, load texture data on demand, and avoid memory bottlenecks caused by loading too many textures at one time; Enable screen space global illumination, reduce computational overhead, and optimize sampling of global illumination; Use CFD technology to simulate the dynamic effects of water flow, waves and ocean currents, simplify the model to reduce the amount of calculation, use GPU acceleration technology (CUDA) to calculate the dynamic changes of water bodies in real time, and apply ray tracing technology to enhance the reflection and refraction effects of water bodies, while reducing the calculation overhead through screen space reflection (SSR) technology; Cache the animations of organisms and devices to avoid repeated calculations, use animation reuse technology to reduce the storage and transmission overhead of animation data, and use skeletal animation technology to achieve dynamic behaviors of organisms and devices, optimize bone weights and animation frame rates, and reduce the amount of calculations; Decompose rendering tasks into multiple subtasks, use multi-threading technology to assign rendering tasks to multiple CPU cores for parallel processing, use GPU to accelerate rendering, use the powerful parallel computing capabilities of GPU to increase rendering speed, and monitor rendering performance in real time, including frame rate, CPU and GPU usage, memory usage, and use performance analysis tools (NVIDIA Nsight) to locate performance bottlenecks.

[0009] A further improvement of the technical solution of the present invention is that the deep sea environment analysis module specifically includes: Extracting integrated deep-sea environmental data including seabed topography data, water body data, biological data and equipment data, standardizing the data, eliminating the dimension differences and numerical range differences between different data sources, and extracting features related to the analysis target, wherein topographic features are extracted from seabed topography data, including topographic slope, depth change rate and topographic roughness; hydrological features are extracted from water body data, including water temperature gradient, salinity change and water flow velocity field; biological features are extracted from biological data, including species density, distribution range and behavior pattern; and equipment status features are extracted from equipment data, including equipment location, movement trajectory and data collection frequency; Analyze historical deep-sea environmental data, classify the data into different categories, and annotate them. The seabed topography is divided into stable areas, erosion areas, and sedimentation areas; the water characteristics are divided into thermocline, halocline, and vortex areas; the biological distribution is divided into high-density areas, low-density areas, and migration paths; the equipment status is divided into normal operation, fault status, and data anomaly; Use historical deep-sea environmental data combined with machine learning algorithms to train machine learning models, optimize model parameters through cross-validation and other methods, and evaluate model performance to ensure the accuracy and generalization ability of the model to analyze the changing trends of deep-sea environmental data; Use the trained machine learning model to predict and analyze deep-sea environmental data and identify changing trends in the deep-sea environment, including seabed topography evolution trends, water body change trends, biological distribution and behavior trends, and equipment operation trends.

[0010] A further improvement of the technical solution of the present invention is that the calculation process of the seabed topography evolution trend is: Collecting seafloor topography data and , respectively represent the terrain depth of the i-th measurement point at time t and t-1, and determine the time interval , select the attenuation factor ; For each measurement point i, calculate its The depth change rate within the area is calculated, and an exponential decay function is applied to the depth change rate of each measuring point to smooth the sudden change of depth and reduce the impact of extreme values ​​on the trend; The adjusted depth change rate of all measurement points is summed to obtain the evolution trend of the seafloor topography in the entire area. ,like >0, indicating that the overall terrain depth increases and there is sedimentation. <0, indicating that the overall terrain depth is reduced and erosion exists; The calculation process of the water body change trend is: Collecting water parameter data and , respectively represent the values ​​of the jth water body parameter at time t and t-1, and determine the time interval , select the adjustment factor ; For each water body parameter j, calculate its The rate of change of water parameters within the water column is calculated and a nonlinear adjustment function is applied to the rate of change of each water column parameter in order to enhance significant changes and reduce the impact of minor changes; Sum the adjusted change rates of all water parameters to obtain the water change trend of the entire area ,like >0, indicating that the overall water parameters have increased, such as water temperature and salinity. <0, indicating that the overall water parameters are reduced, such as a drop in water temperature and a decrease in water flow velocity; The calculation process of the biological distribution and behavior trend is: Collecting biometric data and , respectively represent the values ​​of the kth biometric at time t and t-1, and determine the time interval , select the adjustment factor ; For each biometric feature k (from 1 to p), calculate its The rate of change of biometric features within the range is calculated, and a logarithmic function is applied to the rate of change of each biometric feature to smooth the change of biometric features and avoid the influence of extreme values ​​on the trend. Sum the adjusted change rates of all biological features to obtain the distribution and behavior trends of organisms in the entire area ,like >0, indicating an increase in overall biological characteristics, such as an increase in species density and an expansion of distribution range. <0, indicating a decrease in overall biological characteristics, such as a decrease in species density and changes in behavioral patterns; The calculation process of the equipment operation trend is: Collect device status parameter data and , respectively represent the values ​​of the lth device status parameter at time t and t-1, and determine the time interval , select the adjustment factor ; For each device state parameter l, calculate its The rate of change of the device state parameters within the device state is calculated, and the Sigmoid function is applied to the rate of change of each device state parameter to smooth the change of the device state and avoid the influence of extreme values ​​on the trend; Sum the adjusted change rates of all equipment status parameters to obtain the equipment operation trend of the entire area , >0, indicating that the overall equipment status parameters increase, such as the data collection frequency increases. <0, indicating that the overall device status parameters are reduced, such as changes in device position.

[0011] A further improvement of the technical solution of the present invention is that the marine environment simulation module specifically includes: The 3D model of the deep-sea environment generated by the rendering optimization module includes elements such as seabed topography, water bodies, organisms and equipment, ensuring the real-time and high-precision rendering of the model, providing realistic visual effects for the simulation, and access to real-time ship AIS data, including ship position, speed and heading information; Combine the analysis results of the deep-sea environment analysis module, including the evolution trend of seafloor topography, the trend of water body changes, the distribution and behavior of organisms, and the trend of equipment operation, and integrate the historical deep-sea environment data with the analysis results; Initialize the state of the deep-sea environment based on the 3D model and real-time data at the current time point, including the initial state of the seabed topography, the initial conditions of the water body, the initial distribution and behavior patterns of organisms, and the initial position and state of the equipment; Implement physical process simulation, including water body dynamics simulation, biological behavior simulation and equipment dynamics simulation. Among them, use fluid dynamics models to simulate the dynamic changes of water flow, waves and ocean currents, combine the water body change trend to predict the future water temperature, salinity and water velocity field, use behavioral models (group behavior models based on particle swarm optimization) to simulate the migration, foraging and reproduction behavior of organisms, combine the distribution and behavior trends of organisms to predict the distribution and behavior patterns of organisms in the future, use kinematics and dynamics models to simulate the movement trajectory of ships and submersibles, combine the equipment operation trend to predict the future status and potential failure points of the equipment; The time-stepping method is used to gradually update the state of the deep-sea environment, and within each time step, the state of the three-dimensional model is updated according to the simulation results of the physical process to ensure the accuracy and real-time performance of the simulation results; Based on the results of dynamic deduction, the changing trend of the deep-sea environment in the future is predicted, and the long-term evolution of the seabed topography, seasonal changes and abnormal fluctuations of water bodies, distribution and behavioral changes of organisms, and operating status of equipment are predicted. A scientific prediction report is generated, including a visual display and text description of the prediction results, providing a scientific explanation of the prediction results to help users understand the changing trends of the deep-sea environment in the future.

[0012] A further improvement of the technical solution of the present invention is that the process of updating the state of the three-dimensional model is: Define the time step, set it to 1 hour, and gradually advance the simulation time according to the set time step; In each time step, the state of the three-dimensional model is updated according to the simulation results of the physical process, and the seabed topography, water state, biological population distribution and equipment state in the three-dimensional model are updated according to the simulation results of the physical process and ecological process; The updated state is used as the initial condition for the next time step, and iterative calculations are performed. After the simulation is completed, the required result data is output, including changes in seabed topography, seasonal changes and abnormal fluctuations in water bodies, distribution and behavioral changes of organisms, and operating status of equipment. The result data is then visualized to intuitively analyze the changing trends of the deep-sea environment.

[0013] A further improvement of the technical solution of the present invention is that the three-dimensional visualization display module specifically includes: Load the deep-sea environment 3D model generated by the rendering optimization module, import the loaded 3D model into the virtual scene, set the initial state of the scene, including lighting, shadows, environmental parameters, etc., and configure the basic parameters of the rendering engine to ensure that the rendering engine can efficiently handle complex deep-sea environment scenes; Access real-time ship AIS data, including ship position, speed and heading information, synchronize AIS data to the ship and submersible models in the 3D model in real time, and use kinematic and dynamic models, combined with equipment operation trends, to simulate the movement trajectory of ships and submersibles, and dynamically display the real-time movement of ships and submersibles in the 3D scene, including navigation paths and diving trajectories. According to the results of water body dynamics simulation, dynamically update the environmental factors of wave status, wind speed and ocean currents, and render the wave, water flow and wind field effects in real time in the 3D scene to enhance the authenticity of the display effect; It provides multi-scene resource switching function, allowing users to observe the deep-sea environment from different angles, including global view, local view and specific area view. Users can switch scenes as needed and provide a user interaction interface, allowing users to switch scenes and navigate through mouse, keyboard or touch screen operations.

[0014] A further improvement of the technical solution of the present invention is that the deep-sea deduction typical scene roaming module specifically includes: According to user needs, configure the relevant parameters of the roaming module, including roaming speed, viewing angle range and scene accuracy, and read the deep-sea scene data required for deduction from the database, including seabed topography, water state and biological distribution, to ensure that the data is accurate, complete and compatible with the model; According to the location input by the user, it automatically navigates to the target location and starts dynamic roaming. During the roaming process, it dynamically updates the rendering effect of the scene according to the user's perspective and position, and provides real-time feedback on the user's operation to ensure the smoothness and real-time nature of the roaming process. At the same time, it provides a user interface to allow users to adjust the roaming speed independently. It supports multiple speed modes including fast, medium, and slow. Users can select the corresponding roaming speed according to their needs. Dynamically display the simulation results in the three-dimensional scene, use different colors, icons or animation effects to highlight key information, so that users can quickly identify it. It also provides a marking function that allows users to mark key locations in the three-dimensional scene. The marks include text annotations, icons or color highlights. At the same time, it supports users to quickly navigate to key locations through marks, and provides a query function. Users can enter the location name or mark number to locate the target location.

[0015] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: The present invention provides a deep-sea three-dimensional environment deduction simulation analysis system based on big data. By integrating multi-source and multi-dimensional deep-sea data, a highly realistic deep-sea three-dimensional environment model is constructed. The big data processing technology can be used to simulate the changing trend of the deep-sea environment in real time and reflect the dynamic changes of the deep-sea environment. Users can intuitively experience the deep-sea landscape through virtual roaming, which significantly improves the efficiency and safety of deep-sea resource development and reduces development costs and risks caused by environmental uncertainties.

[0016] The present invention provides a deep-sea three-dimensional environment deduction simulation analysis system based on big data. By dynamically deducing the changing trends of the deep-sea environment, it can predict changes in biological distribution and behavior patterns, helping researchers and managers to better understand the dynamic balance of the marine ecosystem. In addition, through the three-dimensional visualization display module, the interaction between organisms and the environment is intuitively presented, which can effectively reduce the negative impact of human activities on the marine ecosystem and promote the sustainable use of marine resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic diagram of the system function modules of the present invention; Figure 2 Schematic diagram of the workflow of the deep sea environment analysis module of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1, as Figure 1 , Figure 2 As shown, the present invention provides a deep-sea three-dimensional environment deduction simulation analysis system based on big data, including a visualization service desk, the visualization service desk is communicatively connected with a data acquisition integration module, a deep-sea three-dimensional scene modeling module, a rendering optimization module, a deep-sea environment analysis module, an ocean environment deduction simulation module, a three-dimensional visualization display module and a deep-sea deduction typical scene roaming module, wherein the modules are connected by electrical signals; The data acquisition and integration module acquires deep-sea environment data and ship AIS data based on multiple data sources (various sensors, databases), and integrates various types of data to form a multi-dimensional deep-sea environment data set, providing a basis for subsequent analysis and deduction, identifying various types of data sources of the deep-sea environment, including but not limited to deep-sea sensor networks, databases and ship AIS data sources, and acquiring deep-sea environment data and ship AIS data from various types of data sources through corresponding interfaces and protocols. Ship AIS data includes AIS base station data and satellite AIS data. AIS base station data is AIS messages sent by ships received by shore-based AIS equipment, including ship position, speed and heading information. Satellite AIS data is high-sensitivity AI carried by low-orbit satellites. The S receiver receives the ship signal and performs preprocessing operations such as data cleaning, correction and standardization on the acquired deep-sea environment data and ship AIS data. In particular, data cleaning identifies and processes missing values, outliers or duplicate data, performs denoising and smoothing on the data to improve data quality, calibrates and standardizes the sensor data to ensure data consistency and accuracy, converts the AIS data from the original message format into a digital format that is easy to analyze and process, matches the preprocessed deep-sea environment data and ship AIS data according to timestamp and geographic location information, integrates data from different sources to form a deep-sea environment data set containing multiple dimensions, and stores the deep-sea environment data set in the corresponding data warehouse for subsequent query and analysis; The deep-sea 3D scene modeling module builds a 3D model of the deep-sea environment including seabed topography, water bodies, organisms and equipment elements based on the data of the deep-sea environment dataset. Through high-precision modeling, a realistic deep-sea environment is presented. The deep-sea environment dataset is extracted from the data warehouse and the data in the deep-sea environment dataset is classified, including seabed topography data, water body data, organism data and equipment data. Among them, the seabed topography data includes global topography data, multi-beam bathymetry data, seabed geomorphology data, etc. The water body data includes water temperature, salinity, water flow speed, water quality and other data. The organism data includes the distribution, type, behavior pattern of marine organisms, etc. The equipment data includes the location and status information of scientific research vessels, submersibles, sensors and other equipment. For seabed terrain modeling, terrain data of different resolutions (global terrain data and local high-precision terrain data) are integrated to ensure the globality and local details of the terrain model. The terrain modeling tool (World Machine) constructs the seabed terrain and imports the terrain data into the modeling software. The terrain grid is generated through the height map, and then the generated terrain grid is optimized and the level of detail of the terrain is adjusted. For water body modeling, the physical model of the water body is constructed based on the physical properties of the water body (refractive index, reflectivity, scattering coefficient, etc.), and fluid dynamics simulation technology is used to simulate the dynamic effects of water flow, waves and ocean currents. For biological modeling, a three-dimensional model library of marine organisms, including fish, plankton and corals, is constructed based on biological distribution data, and modeling software (3ds Max) to create biological models, and then place the biological models in the corresponding positions to simulate their behavior patterns (swimming, foraging, reproduction, etc.). Combined with the particle swarm optimization algorithm to simulate the group behavior and movement trajectory of organisms, for equipment modeling, build a 3D model library for deep-sea equipment, including scientific research ships, submersibles and sensors, etc. According to the equipment position and data, create a 3D model of deep-sea equipment and place the equipment model in the corresponding position to simulate its dynamic behavior (navigation, diving, data collection, etc.). Integrate the seabed terrain, water body, organisms and equipment elements into a unified 3D scene to ensure the spatial relationship and time synchronization between the elements, optimize the entire scene, and use LOD technology to dynamically adjust the detail level of the model to ensure good rendering performance at different viewing distances; The rendering optimization module performs real-time rendering of the deep-sea environment 3D model based on graphics rendering technology to ensure the rendering quality. While ensuring the simulation accuracy, it improves the system's response speed and display effect to achieve a balance between accuracy and real-time performance. It configures Unreal Engine as the rendering engine for deep-sea 3D environment simulation analysis, initializes the rendering engine, configures the basic parameters of the rendering engine including rendering resolution, anti-aliasing settings, and shadow quality, and then loads the deep-sea 3D model and related resources (textures, materials, animations, etc.) into the rendering engine. It uses Unreal Engine's face reduction tool to simplify the deep-sea 3D model, reduce the number of faces and vertices, and reduce the computational burden during rendering. In Unreal Engine, it sets multiple LOD levels for the model, dynamically adjusts the model's level of detail according to the model's viewing distance and viewing angle, uses multi-level texture technology to automatically match the corresponding texture resolution according to the viewing distance, and reduces the amount of texture rendering calculations. In the case of a long distance or a small viewing angle, a low-precision model is used to reduce the rendering burden. When it is close or the viewing angle is large, it switches to a high-precision model and uses multi-level texture technology simultaneously. It configures Unreal Engine. Engine's occlusion culling system only renders objects that enter the viewing frustum, ignoring invisible objects, reducing unnecessary rendering calculations, and enabling geometric occlusion detection to cull parts blocked by other objects, further reducing rendering load. It uses Unreal Engine's PBR material system to optimize the reflection, refraction, and scattering parameters of the material to ensure the realism and consistency of the material under different lighting conditions, reduce computational complexity, and combine texture compression technology (DXT) to reduce the storage and transmission overhead of texture data, implement streaming loading of textures, load texture data on demand, and avoid memory bottlenecks caused by loading too many textures at one time. It enables screen space global illumination to reduce computational overhead, optimizes sampling of global illumination, reduces noise and calculation time, and uses screen space ambient occlusion technology to reduce the complexity of shadow calculations. It uses high-resolution shadow maps to optimize shadow maps to improve the realism and performance of shadows. It uses fluid dynamics (CFD) technology to simulate water flow, waves, and ocean currents. Dynamic effects, while reducing the amount of calculation by simplifying the model, using GPU acceleration technology (CUDA) to calculate the dynamic changes of water bodies in real time, and applying ray tracing technology to enhance the reflection and refraction effects of water bodies, while reducing computing overhead through screen space reflection (SSR) technology, caching the animations of organisms and devices to avoid repeated calculations, using animation reuse technology to reduce the storage and transmission overhead of animation data, and using skeletal animation technology to achieve dynamic behaviors of organisms and devices, optimize bone weights and animation frame rates, reduce the amount of calculation, decompose rendering tasks into multiple subtasks, use multi-threading technology to assign rendering tasks to multiple CPU cores for parallel processing, use GPU to accelerate rendering, and use the powerful parallel computing capabilities of GPU to improve rendering speed.Monitor rendering performance in real time, including frame rate, CPU and GPU usage, and memory usage, and use performance analysis tools (NVIDIA Nsight) to locate performance bottlenecks; Deep-sea environment analysis module, which further analyzes deep-sea environment data based on machine learning algorithms to identify changing trends in the deep-sea environment; The marine environment simulation module dynamically simulates and predicts the future state of the deep-sea environment based on the rendering-optimized 3D model of the deep-sea environment and real-time ship AIS data, combined with the results of deep-sea environment analysis, and provides scientific predictions of deep-sea environmental changes, thus providing decision-making support for deep-sea resource development and ecological protection. The 3D visualization display module is used to realize the dynamic simulation of ship navigation in the virtual scene, including the motion trajectory display of ships and submersibles, and dynamically update the environmental factors of wave status, wind speed, and ocean current to enhance the authenticity of the display effect. It provides a multi-scene resource switching display function to facilitate users to observe the deep-sea environment from different angles. The deep-sea simulation typical scenario roaming module is used to set locations for dynamic scene roaming, display simulation results and mark key locations to facilitate users to quickly locate and analyze, provide a responsive roaming experience, and allow users to adjust the roaming speed independently.

[0021] Embodiment 2, as Figure 1 , Figure 2 As shown, based on Example 1, the present invention provides a technical solution: preferably, the deep sea environment analysis module specifically includes: Extract integrated deep-sea environmental data including seabed topography data, water body data, biological data and equipment data, standardize the data, eliminate the dimensional differences and numerical range differences between different data sources, and extract features related to the analysis target, among which, extract topographic features from seabed topography data, including terrain slope, depth change rate and terrain roughness, extract hydrological features from water body data, including water temperature gradient, salinity change and water flow velocity field, extract biological features from biological data, including species density, distribution range and behavior pattern, extract equipment status features from equipment data, including equipment location, movement trajectory and data collection frequency, analyze historical deep-sea environmental data, divide the data into different categories, and annotate them, among which, the seabed topography is divided into stable area, erosion area and sedimentation area, the water body characteristics are divided into thermocline, halocline and vortex area, the biological distribution is divided into high-density area, low-density area and migration path, the equipment status is divided into normal operation, fault state and data anomaly, use historical deep-sea environmental data combined with machine learning Algorithms, training machine learning models, optimizing model parameters through cross-validation and other methods, and evaluating model performance to ensure the accuracy and generalization ability of the model, so as to analyze the changing trends of deep-sea environmental data. The ARIMA model can be selected to analyze the time-varying trends of water temperature, water flow velocity, etc., the K-means algorithm can be selected to identify biological distribution patterns or seabed topography features, and the neural network can be selected to predict equipment failures or biological behavior patterns. The trained machine learning model is used to predict and analyze deep-sea environmental data, and the changing trends in the deep-sea environment are identified, including the evolution trend of seabed topography, the change trend of water body, the distribution and behavior trend of organisms, and the operation trend of equipment. Among them, by analyzing the evolution trend of seabed topography, the long-term changes of seabed topography can be identified; by analyzing the change trend of water body, the seasonal changes, long-term trends and abnormal fluctuations of water body can be identified; by analyzing the distribution and behavior trend of organisms, the distribution pattern, migration path and behavior change trend of organisms can be identified; by the equipment operation trend, the operation status change and potential failure points of the equipment can be predicted; The calculation process of the seabed topography evolution trend is: Collecting seafloor topography data and , respectively represent the terrain depth of the i-th measurement point at time t and t-1, and determine the time interval , select the attenuation factor , for each measurement point i, calculate its The depth change rate within the area is calculated, and an exponential decay function is applied to the depth change rate of each measuring point to smooth the sudden change of depth and reduce the impact of extreme values ​​on the trend. The adjusted depth change rates of all measuring points are summed to obtain the evolution trend of the seafloor topography in the entire area. ,like >0, indicating that the overall terrain depth increases and sedimentation occurs. <0, indicating that the overall terrain depth is reduced and erosion exists; The expression of the evolution trend of the seabed topography is: ; In the formula, represents the evolution trend of the seafloor topography at time t, represents the terrain depth of the i-th measurement point at time t, represents the terrain depth of the i-th measurement point at time t-1, is the time interval, represents the time difference between two measurements, is the attenuation factor, which is used to adjust the sensitivity of depth changes, n is the total number of measurement points, is an exponential decay function, which is used to smooth the sudden change of depth. When , it means the terrain depth increases. When , it indicates that the terrain depth decreases; The calculation process of water body change trend is: Collecting water parameter data and , respectively represent the values ​​of the jth water body parameter at time t and t-1, and determine the time interval , select the adjustment factor , for each water body parameter j, calculate its The rate of change of water parameters in the area is calculated, and a nonlinear adjustment function is applied to the rate of change of each water parameter in order to enhance significant changes and reduce the impact of minor changes. The adjusted change rates of all water parameters are summed to obtain the water change trend of the entire area. ,like >0, indicating that the overall water parameters have increased, such as water temperature and salinity. <0, indicating that the overall water parameters are reduced, such as a drop in water temperature and a decrease in water flow velocity; Expression of water body change trend: ; In the formula, represents the changing trend of water body at time t, represents the value of the j-th water body parameter at time t, represents the value of the jth water body parameter at time t-1, is the time interval, is the adjustment factor used to control the sensitivity of the change, m is the total number of water parameters, is a nonlinear adjustment function used to enhance the significance of changes. When When , it indicates that the water parameters decrease; The calculation process of biological distribution and behavior trend is: Collecting biometric data and , respectively represent the values ​​of the kth biometric at time t and t-1, and determine the time interval , select the adjustment factor , for each biometric feature k (from 1 to p), calculate its The change rate of biometrics in the area is calculated, and a logarithmic function is applied to the change rate of each biometric to smooth the change of biometrics and avoid the influence of extreme values ​​on the trend. The adjusted change rates of all biometrics are summed to obtain the distribution and behavior trends of organisms in the entire area. ,like >0, indicating an increase in overall biological characteristics, such as an increase in species density and an expansion of distribution range. <0, indicating a decrease in overall biological characteristics, such as a decrease in species density and changes in behavioral patterns; Expressions for biological distribution and behavior trends: ; In the formula, represents the distribution and behavior trend of organisms at time t, represents the value of the kth biometric feature at time t, represents the value of the kth biometric feature at time t-1, is the time interval, is the adjustment factor used to control the sensitivity of biometric changes, p is the total number of biometrics, is a logarithmic function used to smooth the changes in biometric features. When , it means that the biometric feature increases, when When , it indicates that the biometric features are reduced; The calculation process of equipment operation trend is: Collect device status parameter data and , respectively represent the values ​​of the lth device status parameter at time t and t-1, and determine the time interval , select the adjustment factor , for each device state parameter l, calculate its The Sigmoid function is applied to the change rate of each device state parameter to smooth the change of the device state and avoid the influence of extreme values ​​on the trend. The adjusted change rates of all device state parameters are summed to obtain the equipment operation trend of the entire area. , >0, indicating that the overall equipment status parameters increase, such as the data collection frequency increases. <0, indicating that the overall device status parameters are reduced, such as changes in device position; The expression of equipment operation trend: ; In the formula, Indicates the equipment operation trend at time t, represents the value of the lth device status parameter at time t, represents the value of the lth device status parameter at time t-1, is the time interval, is the adjustment factor used to control the sensitivity of device state changes, q is the total number of device state parameters, is the Sigmoid function, which is used to smooth the change of device status. When , it indicates that the device status parameter decreases.

[0022] Embodiment 3, as Figure 1 , Figure 2 As shown, based on Embodiment 1-2, the present invention provides a technical solution: preferably, the marine environment simulation module specifically includes: The 3D model of the deep-sea environment generated by the rendering optimization module includes elements such as seabed topography, water bodies, organisms, and equipment, ensuring the real-time and high-precision rendering of the model, providing realistic visual effects for the simulation, and accessing real-time ship AIS data, including ship position, speed, and heading information, combined with the analysis results of the deep-sea environment analysis module, including the evolution trend of seabed topography, the change trend of water bodies, the distribution and behavior trend of organisms, and the operation trend of equipment, and integrating the historical deep-sea environment data with the analysis results. According to the 3D model and real-time data at the current time point, the state of the deep-sea environment is initialized, including the initial state of the seabed topography, the initial conditions of the water body, the initial conditions of the organisms, and the initial The physical process simulation is implemented, including water body dynamics simulation, biological behavior simulation and equipment dynamic simulation. The fluid dynamics model is used to simulate the dynamic changes of water flow, waves and ocean currents. The temperature, salinity and water velocity field of the water body are predicted in the future in combination with the water body change trend. The behavior model (the group behavior model based on particle swarm optimization) is used to simulate the migration, foraging and reproduction behavior of organisms. The distribution and behavior patterns of organisms are predicted in the future in combination with the distribution and behavior trends of organisms. The kinematic and dynamic models are used to simulate the motion trajectories of ships and submersibles. The future status and Potential fault points, using the time-stepping method to gradually update the state of the deep-sea environment, and in each time step, update the state of the three-dimensional model according to the simulation results of the physical process to ensure the accuracy and real-time performance of the simulation results. Based on the results of dynamic deduction, the changing trend of the deep-sea environment in the future is predicted, and the long-term evolution prediction of the seabed topography, seasonal changes and abnormal fluctuations of water bodies, distribution and behavior changes of organisms, and the operation status of equipment are predicted. A scientific prediction report is generated, including a visual display and text description of the prediction results, providing a scientific explanation of the prediction results to help users understand the changing trend of the deep-sea environment in the future. The initial state and evolution trend of the seabed topography, analyze the scouring and sedimentation effects of water flow on the seabed topography, predict the long-term change trend of the seabed topography, use fluid dynamics models to simulate seasonal changes in water bodies based on the initial conditions and change trends of water bodies, combine meteorological data and ocean observation data to predict abnormal fluctuations in water bodies, use ecological models to predict the distribution range, number and behavioral changes of biological populations based on the initial distribution and behavior patterns of organisms, as well as distribution and behavior trends, and predict the distribution and behavior changes of organisms in the future; analyze the stress conditions of equipment in deep-sea environments based on the initial position and state of equipment, as well as its operating trends, and predict its operating status and lifespan; In addition, the process of updating the 3D model status is: Define the time step, set it to 1 hour, and gradually advance the simulation time according to the set time step. In each time step, update the state of the three-dimensional model according to the simulation results of the physical process, and update the seabed topography, water state, biological population distribution and equipment state in the three-dimensional model according to the simulation results of the physical process and ecological process. Use the updated state as the initial condition of the next time step, perform iterative calculations, and output the required result data after the simulation, including changes in seabed topography, seasonal changes and abnormal fluctuations in water bodies, distribution and behavior changes of organisms, and operating status of equipment. Then visualize the result data to intuitively analyze the changing trend of the deep-sea environment. The 3D visualization display module specifically includes: Load the deep-sea environment 3D model generated by the rendering optimization module, import the loaded 3D model into the virtual scene, set the initial state of the scene, including lighting, shadows, environmental parameters, etc., and configure the basic parameters of the rendering engine to ensure that the rendering engine can efficiently handle complex deep-sea environment scenes, access real-time ship AIS data, including ship position, speed and heading information, synchronize the AIS data to the ship and submersible models in the 3D model in real time, and use kinematic and dynamic models to simulate the motion trajectory of ships and submersibles in combination with equipment operation trends. Dynamically display the real-time motion of ships and submersibles in the 3D scene, including navigation paths and diving trajectories. According to the results of water body dynamics simulation, dynamically update the environmental factors of wave status, wind speed and ocean currents, and render the wave, water flow and wind field effects in real time in the 3D scene to enhance the authenticity of the display effect. Provide multi-scene resource switching function, so that users can observe the deep-sea environment from different angles, including global view, local view and specific area view. Users can switch scenes as needed and provide a user interaction interface, allowing users to switch scenes and navigate through mouse, keyboard or touch screen operations; The deep-sea simulation typical scenario roaming module specifically includes: According to user needs, configure the relevant parameters of the roaming module, including roaming speed, viewing angle range and scene accuracy, and read the deep-sea scene data required for the deduction from the database, including seabed topography, water state and biological distribution, etc., to ensure that the data is accurate, complete and compatible with the model. According to the location entered by the user, automatically navigate to the target location and start dynamic roaming. During the roaming process, dynamically update the rendering effect of the scene according to the user's viewing angle and location, and provide real-time feedback on the user's operation to ensure the smoothness and real-time nature of the roaming process. At the same time, provide a user interface to allow users to adjust the roaming speed independently, support multiple speed modes including fast, medium and slow, and users can select the corresponding roaming speed according to their needs. Dynamically display the deduction results in the three-dimensional scene, use different colors, icons or animation effects to highlight key information, so that users can quickly identify it, and provide a marking function to allow users to mark key locations in the three-dimensional scene. The marking includes text annotations, icons or color highlights. At the same time, support users to quickly navigate to key locations through markings, provide a query function, and users can enter the location name or mark number to locate the target location.

[0023] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A deep-sea three-dimensional environment simulation and analysis system based on big data, including a visualization service desk, characterized in that: The visualization service station is communicatively connected with a data acquisition integration module, a deep-sea three-dimensional scene modeling module, a rendering optimization module, a deep-sea environment analysis module, an ocean environment deduction and simulation module, a three-dimensional visualization display module, and a deep-sea deduction typical scene roaming module, wherein the modules are electrically connected with each other; The data acquisition and integration module acquires deep-sea environment data and ship AIS data based on multiple data sources, and integrates various types of data to form a multi-dimensional deep-sea environment data set; The deep-sea 3D scene modeling module constructs a deep-sea environment 3D model including seabed topography, water bodies, organisms and equipment elements based on the data of the deep-sea environment data set; The rendering optimization module performs real-time rendering of the deep-sea environment three-dimensional model based on graphics rendering technology; The deep-sea environment analysis module further analyzes the deep-sea environment data based on a machine learning algorithm to identify changing trends in the deep-sea environment; The ocean environment simulation module dynamically simulates and deduce the deep sea environment based on the rendering optimized three-dimensional model of the deep sea environment and the real-time ship AIS data, combined with the deep sea environment analysis results; The three-dimensional visualization display module is used to realize the dynamic simulation of ship navigation in a virtual scene, including the display of the movement trajectory of ships and submersibles; The deep-sea simulation typical scene roaming module is used to set locations for dynamic scene roaming, display simulation results and mark key locations.

2. The deep-sea three-dimensional environment simulation and analysis system based on big data according to claim 1 is characterized by: The data acquisition and integration module specifically includes: Identify various types of data sources of deep-sea environment, including deep-sea sensor networks, databases and ship AIS data sources, and obtain deep-sea environment data and ship AIS data from various types of data sources through corresponding interfaces and protocols; Perform pre-processing operations such as data cleaning, correction and standardization on the acquired deep-sea environment data and ship AIS data; According to the timestamp and geographic location information, the preprocessed deep-sea environmental data and ship AIS data are matched, and data from different sources are integrated to form a deep-sea environmental dataset containing multiple dimensions, which is then stored in the corresponding data warehouse.

3. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 2 is characterized by: The deep sea 3D scene modeling module specifically includes: Extract deep-sea environment data sets from the data warehouse and classify the data in the deep-sea environment data sets, including seabed topography data, water body data, biological data, and equipment data; For submarine terrain modeling, terrain data of different resolutions are merged, and submarine terrain is constructed using terrain modeling tools. The terrain data is imported into the modeling software, and terrain meshes are generated through height maps. The generated terrain meshes are then optimized and the level of detail of the terrain is adjusted. For water body modeling, a physical model of the water body is constructed based on the physical characteristics of the water body, and fluid dynamics simulation technology is used to simulate the dynamic effects of water flow, waves and ocean currents; For biological modeling, a three-dimensional model library of marine organisms, including fish, plankton and corals, is constructed based on biological distribution data. The biological models are then created using modeling software. The biological models are then placed in corresponding locations to simulate their behavior patterns. The particle swarm optimization algorithm is used to simulate the group behavior and movement trajectory of organisms. For equipment modeling, we build a 3D model library for deep-sea equipment, including research vessels, submersibles, and sensors. We create 3D models of deep-sea equipment based on equipment locations and data, place equipment models at corresponding locations, and simulate their dynamic behaviors. Integrate seabed terrain, water bodies, organisms and equipment elements into a unified 3D scene, optimize the entire scene, and use LOD technology to dynamically adjust the model's level of detail.

4. The deep-sea three-dimensional environment simulation and analysis system based on big data according to claim 3 is characterized by: The rendering optimization module specifically includes: Configure Unreal Engine as the rendering engine for deep-sea 3D environment simulation analysis, initialize the rendering engine, configure basic rendering engine parameters including rendering resolution, anti-aliasing settings, and shadow quality, and then load the deep-sea 3D model and related resources into the rendering engine; Use Unreal Engine's face reduction tool to simplify the deep-sea 3D model, reduce the number of faces and vertices, and set multiple LOD levels for the model in Unreal Engine. Dynamically adjust the model's level of detail based on the model's viewing distance and viewing angle. Use multi-level texture technology to automatically match the corresponding texture resolution based on the viewing distance. Configure Unreal Engine's occlusion culling system to render only objects that are within the view frustum, ignoring invisible objects, and enable geometry occlusion detection to cull parts that are blocked by other objects, further reducing rendering load; Use Unreal Engine's PBR material system to optimize the reflection, refraction and scattering parameters of the material, and combine texture compression technology to achieve streaming loading of textures and load texture data on demand; Enable screen space global illumination and optimize sampling of global illumination; Use fluid dynamics technology to simulate the dynamic effects of water flow, waves and ocean currents, simplify the model to reduce the amount of calculation, use GPU acceleration technology to calculate the dynamic changes of water bodies in real time, and apply ray tracing technology to enhance the reflection and refraction effects of water bodies; Cache the animations of creatures and devices, use skeletal animation technology to achieve dynamic behaviors of creatures and devices, and optimize bone weights and animation frame rates; Decompose rendering tasks into multiple subtasks, use multi-threading technology to assign rendering tasks to multiple CPU cores for parallel processing, use GPU to accelerate rendering, and monitor rendering performance in real time, including frame rate, CPU and GPU usage, memory usage, and use performance analysis tools to locate performance bottlenecks.

5. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 4 is characterized by: The deep sea environment analysis module specifically includes: Extract integrated deep-sea environmental data including seafloor topography data, water body data, biological data, and equipment data, standardize the data, and extract features related to the analysis target; Analyze historical deep-sea environmental data, classify the data into different categories, and annotate them. The seabed topography is divided into stable areas, erosion areas, and sedimentation areas; the water characteristics are divided into thermocline, halocline, and vortex areas; the biological distribution is divided into high-density areas, low-density areas, and migration paths; the equipment status is divided into normal operation, fault status, and data anomaly; Use historical deep-sea environmental data combined with machine learning algorithms to train machine learning models and evaluate model performance to analyze changing trends in deep-sea environmental data; Use the trained machine learning model to predict and analyze deep-sea environmental data and identify changing trends in the deep-sea environment, including seabed topography evolution trends, water body change trends, biological distribution and behavior trends, and equipment operation trends.

6. The deep-sea three-dimensional environment simulation and analysis system based on big data according to claim 5 is characterized by: The calculation process of the seabed topography evolution trend is: Collecting seafloor topography data and , respectively represent the terrain depth of the i-th measurement point at time t and t-1, and determine the time interval , select the attenuation factor ; For each measurement point i, calculate its The depth change rate within the range is calculated, and an exponential decay function is applied to the depth change rate at each measurement point; The adjusted depth change rate of all measurement points is summed to obtain the evolution trend of the seafloor topography in the entire area. ,like >0, indicating that the overall terrain depth increases. <0, indicating a decrease in overall terrain depth; The calculation process of the water body change trend is: Collecting water parameter data and , respectively represent the values ​​of the jth water body parameter at time t and t-1, and determine the time interval , select the adjustment factor ; For each water body parameter j, calculate its The rate of change of water parameters within the water body is calculated, and a nonlinear adjustment function is applied to the rate of change of each water body parameter; Sum the adjusted change rates of all water parameters to obtain the water change trend of the entire area ,like >0, indicating that the overall water parameters increase. <0, indicating a decrease in overall water parameters; The calculation process of the biological distribution and behavior trend is: Collecting biometric data and , respectively represent the values ​​of the kth biometric at time t and t-1, and determine the time interval , select the adjustment factor ; For each biometric feature k, calculate its The rate of change of biometric features within the range and applying a logarithmic function to the rate of change of each biometric feature; Sum the adjusted change rates of all biological features to obtain the distribution and behavior trends of organisms in the entire area ,like >0, indicating an increase in overall biometrics. <0, indicating a decrease in overall biometrics; The calculation process of the equipment operation trend is as follows: Collect device status parameter data and , respectively represent the values ​​of the lth device status parameter at time t and t-1, and determine the time interval , select the adjustment factor ; For each device state parameter l, calculate its The rate of change of the device state parameters within the device state parameter, and the Sigmoid function is applied to the rate of change of each device state parameter; Sum the adjusted change rates of all equipment status parameters to obtain the equipment operation trend of the entire area , >0, indicating that the overall equipment status parameters increase. <0, indicating that the overall device status parameters are reduced.

7. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 6 is characterized by: The marine environment simulation module specifically includes: A 3D model of the deep-sea environment generated using the rendering optimization module, including seafloor topography, water bodies, organisms, and equipment elements, and access to real-time ship AIS data, including ship position, speed, and heading information; Combine the analysis results of the deep-sea environment analysis module, including the evolution trend of seafloor topography, the trend of water body changes, the distribution and behavior of organisms, and the trend of equipment operation, and integrate the historical deep-sea environment data with the analysis results; Initialize the state of the deep-sea environment based on the 3D model and real-time data at the current time point, including the initial state of the seabed topography, the initial conditions of the water body, the initial distribution and behavior patterns of organisms, and the initial position and state of the equipment; Implement physical process simulations, including water dynamics simulations, biological behavior simulations, and equipment dynamics simulations; The state of the deep-sea environment is gradually updated using a time-stepping method, and within each time step, the state of the three-dimensional model is updated according to the simulation results of the physical process; Based on the results of dynamic deduction, the changing trend of the deep-sea environment in the future is predicted, and the long-term evolution of the seabed topography, seasonal changes and abnormal fluctuations of water bodies, distribution and behavioral changes of organisms, and operating status of equipment can be predicted. A scientific prediction report is generated, including a visual display and text description of the prediction results, providing a scientific explanation of the prediction results.

8. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 7 is characterized by: The process of updating the three-dimensional model state is as follows: Define the time step, set it to 1 hour, and gradually advance the simulation time according to the set time step; In each time step, the state of the three-dimensional model is updated according to the simulation results of the physical process, and the seabed topography, water state, biological population distribution and equipment state in the three-dimensional model are updated according to the simulation results of the physical process and ecological process; The updated state is used as the initial condition for the next time step, and iterative calculations are performed. After the simulation is completed, the required result data is output, including changes in seabed topography, seasonal changes and abnormal fluctuations in water bodies, distribution and behavioral changes of organisms, and the operating status of equipment, and the result data is then visualized.

9. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 8, characterized in that: The three-dimensional visualization display module specifically includes: Load the deep-sea environment 3D model generated by the rendering optimization module, import the loaded 3D model into the virtual scene, set the initial state of the scene, and configure the basic parameters of the rendering engine; Access real-time ship AIS data, including ship position, speed and heading information, synchronize AIS data to the ship and submersible models in the 3D model in real time, and use kinematic and dynamic models, combined with equipment operation trends, to simulate the movement trajectory of ships and submersibles, and dynamically display the real-time movement of ships and submersibles in the 3D scene, including navigation paths and diving trajectories; It provides multi-scene resource switching function, allowing users to observe the deep-sea environment from different angles, including global view, local view and specific area view.

10. The deep sea three-dimensional environment simulation and analysis system based on big data according to claim 9, characterized in that: The deep sea simulation typical scene roaming module specifically includes: According to user needs, configure the relevant parameters of the roaming module, including roaming speed, viewing angle range and scene accuracy, and read the deep-sea scene data required for deduction from the database, including seabed topography, water state and biological distribution; According to the location input by the user, it automatically navigates to the target location and starts dynamic roaming. During the roaming process, it dynamically updates the rendering effect of the scene according to the user's perspective and position, and provides real-time feedback on the user's operation. At the same time, it provides a user interface to allow the user to adjust the roaming speed independently, supporting multiple speed modes including fast, medium, and slow. The simulation results are dynamically displayed in the three-dimensional scene, and key information is highlighted using different colors, icons or animation effects. A marking function is provided, allowing users to mark key locations in the three-dimensional scene. The marks include text annotations, icons or color highlights. At the same time, users are supported to quickly navigate to key locations through marks, and a query function is provided. Users can enter the location name or mark number to locate the target location.

Images