Spatial-temporal resolution self-adaptive adjustment marine environment forecasting method and related device
The marine environment forecasting method, which employs multi-mode collaborative optimization and dynamic resolution adjustment, addresses the issues of insufficient resolution and low computational efficiency in existing technologies, achieving higher accuracy and more efficient marine environment forecasting.
Patent Information
- Application Number
- CN202511731019.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-24
- Publication Date
- 2026-02-03
AI Technical Summary
Existing marine environmental forecasting models suffer from problems such as insufficient resolution, low computational efficiency, and simplification of physical processes when dealing with complex and ever-changing marine systems, making it difficult to achieve comprehensive forecasting capabilities. In particular, it is difficult to balance accuracy and efficiency in multi-process coupled scenarios.
A spatiotemporal resolution adaptive adjustment method is adopted. Through multi-mode collaborative optimization and weight allocation, combined with atmospheric model, wave model and tidal current model, the spatiotemporal resolution is dynamically adjusted. By using collaborative optimization algorithm and spatial interpolation technology, a smooth transition between different resolution regions is achieved.
It improves the accuracy and computational efficiency of marine environmental forecasts, with wind speed forecast accuracy increased by 30% and computational efficiency in calm sea areas increased by 45%. It also reduces forecast errors and boundary jump problems, resulting in an overall forecast accuracy increase of 27% and computational resource utilization rate increase of 50%.
Smart Images
Figure CN121457738A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of marine environmental forecasting technology, and relates to a method and related apparatus for adaptive adjustment of marine environmental forecasting with spatiotemporal resolution. Background Technology
[0002] Single-model marine environmental forecasting systems are facing increasingly significant limitations when dealing with complex and ever-changing ocean systems. These limitations are particularly pronounced in regions with significant ocean-atmosphere coupling—such as the typhoon-prone Northwest Pacific, the monsoon-dominated Indian Ocean, and marginal seas influenced by polar climates. In these regions, the dynamic changes in elements such as ocean surface temperature, air-sea flux, and wave energy spectrum are not only directly affected by atmospheric forcing but also form complex feedback mechanisms through nonlinear processes such as internal ocean circulation and topographic friction, making it difficult for a single physical model to fully characterize its multi-scale coupling features.
[0003] From the perspective of model principles, current mainstream ocean forecasting models can be mainly divided into three categories: The first category is numerical models based on the original equations, which simulate ocean dynamic processes by discretizing the Navier-Stokes equations. They have advantages in large-scale circulation simulations, but lack resolution for small- and medium-scale processes (such as fronts and eddies). The second category is wave-induced current models, which focus on the interaction between waves and ocean currents and can accurately capture the turbulent mixing effects caused by wave breaking, but lack coupling with atmospheric boundary layer processes. The third category is data assimilation models, which optimize the model's initial field by fusing observational data, which can significantly improve forecast accuracy, but their performance is highly dependent on the spatiotemporal coverage of the observational data. This functional differentiation among models means that a single model may perform well in specific scenarios, but it is difficult to form a comprehensive forecasting capability.
[0004] Specifically, the differences in performance among different models in simulating key elements are particularly evident. Taking wind field simulation as an example, the WRF (Weather Research and Forecasting) model can achieve high-resolution wind field forecasts of 1-3 kilometers through nested grid technology, and the error in simulating wind speed gradients in typhoon eyewall areas can be controlled within 5%. However, its ocean boundary layer parameterization scheme still has systematic biases in characterizing sea surface roughness. In contrast, wave models (such as WAVEWATCH III), which use third-generation spectral wave models, can accurately simulate wave growth, attenuation, and refraction processes, with an error of less than 0.5 meters in deep-water wave height forecasts. However, its ability to simulate nearshore wave breaking and coastal current generation is relatively weak. Tidal current forecasting relies more on two-dimensional / three-dimensional tidal current models (such as ADCIRC), which can finely characterize tidal current movements under complex terrains such as estuaries and bays through unstructured grid technology. However, its handling of the coupling effect between wind-driven currents and density-driven currents still needs improvement.
[0005] This specialized nature of single models presents a dilemma in integrated marine environmental forecasting: pursuing high accuracy requires sacrificing computational efficiency (e.g., increasing the resolution of global models to 1 / 12° increases the time required for a single forecast by eight times); emphasizing timeliness necessitates simplifying physical processes (e.g., ignoring the feedback of wave radiation stress on ocean currents). More seriously, the evolution of marine hazards (such as storm surges and red tides) often involves the coupling of multiple processes—wind, waves, currents, temperature, and salinity—which single models cannot capture across scales. For example, during Typhoon "Hwah" in 2021, storm surge in the Yangtze River estuary was not only directly driven by the typhoon's wind field but also closely related to topographic changes caused by nearshore sediment transport accumulated from previous waves. Such multi-process coupling effects can only be accurately characterized through multi-model integrated forecasting. Summary of the Invention
[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and related apparatus for adaptive adjustment of spatiotemporal resolution in marine environmental forecasting. This method and apparatus can integrate the advantages of multiple models and achieve higher accuracy marine environmental forecasting through collaborative optimization and weight allocation.
[0007] To achieve the above objectives, this invention discloses a method for adaptively adjusting marine environmental forecasting based on spatiotemporal resolution, comprising: Acquire historical and real-time data for the target area; Select multiple physical modes for the target area; Calculate the rate of change of the data corresponding to each physical model; The spatiotemporal resolution of each physical model is determined based on the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution adjustment threshold. The spatiotemporal resolutions of each physical model are weighted and summed, and the result of the weighted sum is used as the spatiotemporal resolution of the target area. Marine environmental forecasts are then made based on the spatiotemporal resolution of the target area.
[0008] Furthermore, before calculating the rate of change of the data corresponding to each physical model, the method further includes: Quality control and spatial interpolation are performed on the historical and real-time data of the target area.
[0009] Furthermore, the various physical models include at least atmospheric models, wave models, and tidal current models.
[0010] Furthermore, a dynamic calibration mechanism based on the spatiotemporal resolution adjustment threshold determines the preset spatiotemporal resolution adjustment threshold.
[0011] Furthermore, before performing a weighted summation of the spatiotemporal resolutions of each physical model, the following steps are also included: The weights of each physical mode are obtained using a collaborative optimization algorithm.
[0012] Furthermore, for the boundary areas of multiple target areas, a combination of spatial interpolation and temporal smoothing is used to determine the spatiotemporal resolution of the boundary areas, and marine environmental forecasts are made based on the spatiotemporal resolution of the boundary areas.
[0013] Furthermore, marine environmental forecast data should include at least wind speed, wind direction, wave height, tides, and current speed.
[0014] This invention discloses a spatiotemporal resolution adaptive adjustment marine environment forecasting system, comprising: The acquisition module is used to acquire historical and real-time data for the target area. The selection module is used to select multiple physical modes for the target area; The calculation module is used to calculate the rate of change of the data corresponding to each physical model; The determination module is used to determine the spatiotemporal resolution of each physical model by adjusting the threshold according to the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution. The forecast module is used to perform a weighted summation of the spatiotemporal resolutions of each physical model, and use the result of the weighted summation as the spatiotemporal resolution of the target area, and perform marine environmental forecasting based on the spatiotemporal resolution of the target area.
[0015] This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the spatiotemporal resolution adaptive adjustment marine environment forecasting method.
[0016] The present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the spatiotemporal resolution adaptive adjustment marine environment forecasting method.
[0017] The present invention has the following beneficial effects: In practical operation, the spatiotemporal resolution adaptive adjustment marine environment forecasting method and related device of the present invention determines the spatiotemporal resolution of each physical model based on the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution adjustment threshold. The spatiotemporal resolutions of each physical model are weighted and summed, and the result of the weighted sum is used as the spatiotemporal resolution of the target area. Marine environment forecasting is performed based on the spatiotemporal resolution of the target area, thereby integrating the advantages of multiple models and achieving higher accuracy marine environment forecasting through collaborative optimization and weight allocation.
[0018] Furthermore, a dynamic calibration mechanism based on the spatiotemporal resolution adjustment threshold determines the preset spatiotemporal resolution adjustment threshold, achieving a precise match between resolution and sensitivity to environmental changes. Compared with the fixed resolution mode, the wind speed forecast accuracy in typhoon-affected areas is improved by 30%, and the computational efficiency in stable sea areas is improved by 45%, balancing forecast accuracy and computational cost.
[0019] Furthermore, a combination of spatial interpolation and temporal smoothing is used to determine the spatiotemporal resolution of the boundary region, and marine environmental forecasts are made based on the spatiotemporal resolution of the boundary region. This overcomes the "boundary jump" problem of traditional multi-resolution fusion. Through the connection processing of spatial interpolation and temporal smoothing, the error transition rate of forecast results in different resolution regions is reduced by 60%. In particular, the continuity of wave height forecasts is significantly improved in the boundary zone between high resolution near the coast and low resolution in the open sea. Attached Figure Description
[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system structure diagram of the present invention. Detailed Implementation
[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0024] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0025] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.
[0026] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.
[0027] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."
[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0029] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.
[0030] Example 1 refer to Figure 1 The spatiotemporal resolution adaptive adjustment method for marine environment forecasting described in this invention includes the following steps: 1) Obtain historical and real-time data for the target area; The specific process of step 1) is as follows: 11) Obtain historical and real-time data of the target area from a multi-source platform. The data should include at least wind speed, wind direction, wave height, tides, and air pressure. The multi-source platform should include at least reanalysis data, satellite observation data, and regional model output. 12) Perform quality control and spatial interpolation on the historical and real-time data of the target area to ensure data consistency and spatiotemporal integrity.
[0031] 2) Multi-mode characteristic analysis; Multiple physical models for the target area are selected, such as WRF, atmospheric-ocean coupled models, and SWAN wave models. Historical data is used to verify and analyze the applicability of each model, determining its strengths in different scenarios. For example: Atmospheric models are better suited for simulating wind and pressure fields; Elliott Wave patterns are adept at predicting wave heights and cycles; The current pattern performs well in tidal and current velocity simulations.
[0032] Based on the validation results, each pattern is assigned an initial weight.
[0033] 3) Dynamic calibration of resolution adjustment threshold; A dynamic calibration mechanism for adjusting the spatiotemporal resolution threshold is established. Based on historical forecast error data of the target area, the resolution switching threshold is updated every six months. For example, in a typhoon scenario, the initial setting is "when the wind speed change rate is >5m / s, increase the spatial resolution to 1km". If historical data shows that there are still local forecast deviations under this threshold, the threshold is automatically adjusted to "when the wind speed change rate is >3m / s, increase the resolution", ensuring that the resolution adjustment matches the sensitivity of actual environmental changes.
[0034] 4) Construct a distributed collaborative system; A distributed computing architecture is built, and multiple modes are deployed to distributed nodes. The system supports parallel computing, real-time data sharing, and collaborative optimization. Through the distributed architecture, large-scale data processing and rapid model calculation are achieved, thereby improving forecast efficiency.
[0035] 5) Collaborative optimization and weight allocation; For target forecast scenarios (such as typhoons, monsoons, and severe air events), collaborative optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to fuse the outputs of various models and adjust their weights. The optimization objectives include: Improve forecast accuracy by reducing bias and mean square error; The weights are dynamically adjusted based on the importance of the forecast variables. For example, the influence weight of the wind field is increased in the typhoon scenario.
[0036] 6) Optimized resolution result transitions; For the fusion results of different resolution modes, a new stitching optimization step has been added, specifically: A combination of spatial interpolation and temporal smoothing is used to perform data transition processing on the boundary between high-resolution (e.g., 1km) and low-resolution (e.g., 5km) areas to avoid "jumps" in variables such as wind speed and wave height caused by abrupt changes in resolution. At the same time, a moving average is applied to the resolution switching points in the time dimension (e.g., switching from 1-hour resolution to 15-minute resolution) to ensure the spatiotemporal continuity of the forecast results.
[0037] 7) Fusion model generation; Weighted fusion methods (such as Bayesian model averaging and neural network fusion models) are used to integrate the results of multiple models into the final forecast result. Real-time observation data is introduced into the fusion process for correction to further improve the reliability of the forecast.
[0038] 8) Result output and verification; The generated forecasts include key variables such as wind speed, wind direction, wave height, tides, and current speed. The forecasts are validated using historical data and independent observation data, and metrics such as bias, correlation coefficient, and mean squared error are calculated to quantify the performance of the fusion model. The effectiveness of the single model and the fusion model is compared to evaluate the degree of improvement of the collaborative system.
[0039] 9) Dynamic adaptive update; An adaptive learning mechanism is introduced to continuously monitor forecast performance. When model performance declines significantly or scene characteristics change, the co-optimized parameters and fusion model are updated to ensure long-term stable operation of the system.
[0040] It should be noted that the present invention has the following characteristics: Multi-mode advantage integration: Combining the strengths of different modes and making full use of their advantages in specific variables or scenarios to improve overall forecast performance.
[0041] Distributed high-efficiency computing: Utilizing a distributed architecture to achieve large-scale data processing and efficient model computation, meeting real-time forecasting requirements.
[0042] Dynamic weight adjustment: The model's weights are optimized in real time according to different scenarios, enhancing the model's adaptability and flexibility in different scenarios.
[0043] Adaptive update capability: Through a dynamic learning mechanism, the robustness and stability of the model are ensured during long-term operation.
[0044] This invention performs exceptionally well in dealing with complex marine meteorological conditions and is applicable to multiple fields such as wind farm operation, marine disaster early warning, and shipping support, providing advanced technical means for marine environmental forecasting.
[0045] It should be noted that this invention establishes a collaborative matching rule of "scene type - resolution level - mode parameters". For example, the typhoon scene corresponds to "high resolution (1km) + WRF-SWAN coupling mode", and the stable scene corresponds to "low resolution (5km) + simplified wave mode". Compared with the random matching method, the overall forecast accuracy is improved by 27% and the utilization rate of computing resources is improved by 50%.
[0046] Example 2 refer to Figure 2 The spatiotemporal resolution adaptive adjustment marine environment forecasting system of the present invention includes: The acquisition module is used to acquire historical and real-time data for the target area. The selection module is used to select multiple physical modes for the target area; The calculation module is used to calculate the rate of change of the data corresponding to each physical model; The determination module is used to determine the spatiotemporal resolution of each physical model by adjusting the threshold according to the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution. The forecast module is used to perform a weighted summation of the spatiotemporal resolutions of each physical model, and use the result of the weighted summation as the spatiotemporal resolution of the target area, and perform marine environmental forecasting based on the spatiotemporal resolution of the target area.
[0047] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.
[0048] Example 3 A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a marine environment forecasting method with adaptive spatiotemporal resolution. For example, the steps include: acquiring historical and real-time data of a target area; selecting multiple physical models of the target area; calculating the rate of change of data corresponding to each physical model; determining the spatiotemporal resolution of each physical model based on the rate of change of data corresponding to each physical model and a preset spatiotemporal resolution adjustment threshold; performing a weighted summation of the spatiotemporal resolutions of each physical model, and using the result of the weighted summation as the spatiotemporal resolution of the target area; and performing marine environment forecasting based on the spatiotemporal resolution of the target area. The memory may include main memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry standard architecture bus, a peripheral component interconnection standard bus, an extended industry standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory stores the program; specifically, the program may include program code, which includes computer operation instructions. Memory can include main memory and non-volatile memory, and provides instructions and data to the processor.
[0049] Example 4 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the spatiotemporal resolution adaptive adjustment marine environment forecasting method. For example, the method includes: acquiring historical and real-time data of a target area; selecting multiple physical models for the target area; calculating the rate of change of data corresponding to each physical model; determining the spatiotemporal resolution of each physical model based on the rate of change of data corresponding to each physical model and a preset spatiotemporal resolution adjustment threshold; performing a weighted summation of the spatiotemporal resolutions of each physical model, and using the weighted summation result as the spatiotemporal resolution of the target area; and performing marine environment forecasting based on the spatiotemporal resolution of the target area. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.
[0050] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0051] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0054] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.
[0055] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
[0056] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.
Claims
1. A method for adaptively adjusting marine environmental forecasting based on spatiotemporal resolution, characterized in that, include: Acquire historical and real-time data for the target area; Select multiple physical modes for the target area; Calculate the rate of change of the data corresponding to each physical model; The spatiotemporal resolution of each physical model is determined based on the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution adjustment threshold. The spatiotemporal resolutions of each physical model are weighted and summed, and the result of the weighted sum is used as the spatiotemporal resolution of the target area. Marine environmental forecasts are then made based on the spatiotemporal resolution of the target area.
2. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, Before calculating the rate of change of the data corresponding to each physical model, the following steps are also included: Quality control and spatial interpolation are performed on the historical and real-time data of the target area.
3. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, The various physical models include at least atmospheric models, wave models, and tidal current models.
4. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, A dynamic calibration mechanism based on the spatiotemporal resolution adjustment threshold determines the preset spatiotemporal resolution adjustment threshold.
5. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, The process of weighted summation of the spatiotemporal resolutions of each physical model also includes: The weights of each physical mode are obtained using a collaborative optimization algorithm.
6. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, For the boundary areas of multiple target regions, a combination of spatial interpolation and temporal smoothing is used to determine the spatiotemporal resolution of the boundary areas, and marine environmental forecasts are made based on the spatiotemporal resolution of the boundary areas.
7. The method for adaptively adjusting the spatiotemporal resolution of marine environmental forecasting according to claim 1, characterized in that, Marine environmental forecast data should include at least wind speed, wind direction, wave height, tides, and current speed.
8. A marine environment forecasting system with adaptive spatiotemporal resolution, characterized in that, include: The acquisition module is used to acquire historical and real-time data for the target area. The selection module is used to select multiple physical modes for the target area; The calculation module is used to calculate the rate of change of the data corresponding to each physical model; The determination module is used to determine the spatiotemporal resolution of each physical model by adjusting the threshold according to the rate of change of the data corresponding to each physical model and the preset spatiotemporal resolution. The forecast module is used to perform a weighted summation of the spatiotemporal resolutions of each physical model, and use the result of the weighted summation as the spatiotemporal resolution of the target area, and perform marine environmental forecasting based on the spatiotemporal resolution of the target area.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the marine environment forecasting method with adaptive spatiotemporal resolution as described in any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the marine environment forecasting method with adaptive spatiotemporal resolution as described in any one of claims 1-7.