Micrometeorological data-based icing thickness prediction method and system

Abstract

The invention relates to the technical field of intelligent meteorological prediction and electric power system safety, in particular to an icing thickness prediction method and system based on micrometeorological data, which collects micrometeorological data such as air temperature, humidity, wind speed and the like, and performs feature extraction and model training on the data by using a time sequence analysis and machine learning algorithm to obtain an icing thickness prediction result. Meanwhile, the model is dynamically adjusted in combination with meteorological data updated in real time so as to cope with complex and changeable climate conditions; the system has higher prediction accuracy, and particularly can provide accurate prediction under extreme weather; the mechanism is updated in real time, so that the model can reflect the latest meteorological condition, the icing thickness prediction result is updated in time, and the negative influence caused by icing is reduced; the method has wide adaptability, can be used for icing prediction, flood prediction and drought monitoring; and a user interface is visual and friendly, so that professional and common users can easily understand and utilize the prediction result.

Description

Technical Field

[0001] The present invention relates to the field of intelligent meteorological forecasting and power system safety technology, and in particular to an ice thickness prediction method and system based on micro-meteorological data. Background Art

[0002] With climate change and the frequent occurrence of extreme weather events, the importance of ice thickness prediction methods has become increasingly prominent. At present, ice cover prediction mainly relies on traditional meteorological data and empirical estimation methods, which have more or less shown certain effectiveness, but still lack accuracy and reliability.

[0003] In traditional ice prediction technology, statistical models based on meteorological parameters such as temperature, humidity, and wind speed are mainly used to predict ice thickness. These models usually include linear regression analysis, neural networks, or other machine learning methods, which learn and predict future ice conditions based on historical data. In addition, some methods also try to assist predictions with satellite images and ground observation data.

[0004] Although these traditional methods are effective to a certain extent, they have several obvious flaws. First, these methods rely too much on historical data, which greatly reduces their prediction accuracy in the face of climate change and extreme weather conditions. Second, these methods usually cannot reflect environmental changes in real time, resulting in inaccurate prediction results under dynamic weather conditions. Finally, traditional models often ignore the influence of local geographical and environmental factors, which are crucial for accurate prediction of ice thickness.

[0005] The main reasons for these problems and defects are the limitations of traditional methods. They rely on fixed, historical data patterns and lack the flexibility to adapt to changing environments. At the same time, these methods fail to fully consider the impact of micro-meteorological conditions, such as local topography, vegetation cover and other factors, which are important factors affecting ice formation and thickness. In addition, existing prediction models have difficulties in dealing with nonlinear and complex meteorological phenomena, making it difficult to accurately capture and predict ice cover under extreme weather events.

[0006] In this context, it is particularly important to develop a new forecasting method that can more accurately predict ice cover thickness, especially in the face of rapidly changing meteorological conditions and extreme weather events. By combining micrometeorological data and advanced computational models, we can move towards this goal, thereby significantly improving the accuracy and reliability of ice cover forecasts. Summary of the invention

[0007] In view of the above problems existing in the prior art, the present invention is proposed.

[0008] Therefore, the present invention provides an ice thickness prediction method based on micrometeorological data. The core of the method is to utilize micrometeorological data, which include local temperature, humidity, wind speed, wind direction and other microscopic meteorological factors that may affect the icing process; in addition, the method also combines geographic information such as terrain and vegetation cover, as well as time series analysis and machine learning techniques.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions, a method for predicting ice thickness based on micrometeorological data, comprising: collecting micrometeorological data; preprocessing the collected micrometeorological data; using time series analysis and machine learning algorithms to perform feature extraction and model training on the preprocessed data, and performing model verification and adjustment; adjusting model parameters based on real-time updated meteorological data, dynamically adjusting prediction results, and presenting the predicted ice thickness results through a user interface.

[0010] As a preferred solution of the ice thickness prediction method based on micrometeorological data described in the present invention, the collection of micrometeorological data includes the use of high-precision sensors and satellite data, the sensors collect micrometeorological data including temperature, humidity, wind speed and wind direction, and the satellite data provides geographic information on terrain and vegetation coverage.

[0011] As a preferred solution of the ice thickness prediction method based on micrometeorological data described in the present invention, the preprocessing includes data cleaning and formatting operations, specifically including removing outliers, filling missing data and data standardization to improve data consistency and provide high-quality data support for subsequent analysis.

[0012] As a preferred solution of the ice thickness prediction method based on micrometeorological data described in the present invention, the feature extraction includes analyzing the data to identify the factors that have the greatest impact on the ice thickness, including identifying the main meteorological patterns and calculating the correlation of meteorological factors.

[0013] As a preferred solution of the ice thickness prediction method based on micrometeorological data described in the present invention, the model training includes using time series analysis and machine learning algorithms, including support vector machines, random forests, and deep learning, to train the processed data. During the training process, the system learns to predict the ice thickness based on the input meteorological data.

[0014] As a preferred solution of the ice thickness prediction method based on micrometeorological data described in the present invention, the model verification and adjustment includes verifying the trained model through historical data, evaluating the accuracy, and adjusting and optimizing the model based on the verification results.

[0015] As a preferred solution of the ice thickness prediction method based on micro-meteorological data described in the present invention, wherein: the model parameters are adjusted based on real-time updated meteorological data, and the prediction results are dynamically adjusted, including the system regularly receiving new meteorological data, updating the prediction model according to the real-time data, and ensuring that the model can reflect the current meteorological conditions and make accurate predictions.

[0016] Another object of the present invention is to provide an ice thickness prediction system based on micro-meteorological data, which includes a data acquisition module, a data preprocessing module, a feature extraction module and a real-time prediction module. Through the collaborative work of these modules, accurate prediction and dynamic adjustment of ice thickness can be achieved. The system can collect micro-meteorological data such as temperature, humidity, wind speed and wind direction, and use time series analysis and machine learning algorithms to extract features and train models for the data. At the same time, the model is adjusted in combination with real-time updated meteorological data to adapt to different meteorological conditions, and the prediction results are intuitively displayed through the user interface, thereby providing effective technical support for ice thickness monitoring and prevention.

[0017] As a preferred solution of the ice thickness prediction system based on micro-meteorological data described in the present invention, it includes: a data acquisition module, a data pre-processing module, a feature extraction module and a real-time prediction module;

[0018] The data acquisition module collects micro-meteorological data;

[0019] The data preprocessing module preprocesses the collected micrometeorological data;

[0020] The feature extraction module uses time series analysis and machine learning algorithms to perform feature extraction and model training on the preprocessed data, and performs model verification and adjustment;

[0021] The real-time prediction module adjusts model parameters based on real-time updated meteorological data, dynamically adjusts prediction results, and presents predicted ice thickness results through a user interface.

[0022] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and wherein when the processor executes the computer program, the processor implements the steps of any one of the methods for predicting ice thickness based on micrometeorological data.

[0023] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of any one of the methods for predicting ice thickness based on micrometeorological data are implemented.

[0024] Beneficial effects of the invention: Higher prediction accuracy: Combining micro-meteorological data with advanced data processing techniques, we expect to significantly improve the prediction accuracy of ice thickness. Especially in complex and changing climate conditions, this method can provide more accurate prediction results.

[0025] Real-time forecast updates: Thanks to the dynamic update mechanism, the forecast model will be able to reflect the latest meteorological conditions in real time, thereby updating the forecast of ice thickness in real time. This will help to take timely response measures and reduce the negative impact of ice cover.

[0026] Possibility of wide application: Due to the strong adaptability and scalability of this solution, it is expected that this technology can not only be used for the prediction of ice thickness, but also be extended to other meteorological related fields, such as flood prediction and drought monitoring, to provide solutions for more meteorological challenges.

[0027] User-friendly experience: With enhanced visualization capabilities and an intuitive user interface, it is easier for prospective users to understand and utilize forecast results, whether they are professionals or casual users.

[0028] Overall, this technical solution will bring revolutionary improvements to ice thickness prediction and other meteorological-related fields, providing more accurate and practical prediction tools to better cope with the challenges brought by meteorology. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 A schematic flow chart of a method for predicting ice thickness based on micrometeorological data provided by an embodiment of the present invention.

[0031] Figure 2 A module diagram of an ice thickness prediction system based on micrometeorological data provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0033] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an ice thickness prediction method based on micrometeorological data, comprising:

[0034] S1: Collect micrometeorological data.

[0035] It should be noted that the collection of micrometeorological data includes the use of high-precision sensors and satellite data. The sensors collect micrometeorological data including temperature, humidity, wind speed and wind direction, and the satellite data provides geographic information on terrain and vegetation cover.

[0036] Furthermore, by analyzing the micro-meteorological data of specific locations, the ice thickness in the area can be predicted more accurately, especially under complex or changing meteorological conditions. In this method, region-specific meteorological data are first collected, including but not limited to temperature (T), humidity (H), wind speed (V) and wind direction (D). These data are collected in real time through high-precision sensors and satellite data, which are crucial for predicting ice thickness. At the same time, satellite data provides a wider range of geographical and environmental information, such as terrain, vegetation cover, etc. The combination of these data enables the prediction model to take into account more influencing factors, thereby improving the accuracy of the prediction.

[0037] Furthermore, in addition to micrometeorological data, this solution can also integrate socioeconomic data, traffic flow and other information; for example, by analyzing socioeconomic data, it is possible to predict the impact and risks of icing in areas with increased economic activities; the integration of traffic flow data helps to understand and predict the potential impact of icing on the transportation system; this integration of multi-source data provides a more comprehensive perspective and supports more effective decision-making.

[0038] S2: Preprocess the collected micrometeorological data.

[0039] It should be noted that processing includes data cleaning and formatting operations, specifically removing outliers, filling missing data, and data standardization to improve data consistency and provide high-quality data support for subsequent analysis.

[0040] Furthermore, preprocessing is performed using the following formula:

[0041] P=f(T,H,V,D)

[0042] Where P represents the predicted probability of icing, and f is a function based on a machine learning algorithm that takes into account the interaction of various meteorological factors and their impact on the icing process.

[0043] S3: Use time series analysis and machine learning algorithms to extract features and train models on the preprocessed data, and perform model validation and adjustment.

[0044] It should be noted that feature extraction includes data analysis to identify the factors that have the greatest impact on ice thickness, including identifying major meteorological patterns and calculating the correlation of meteorological factors; model training includes the use of time series analysis and machine learning algorithms, including support vector machines, random forests, and deep learning, to train processed data. During the training process, the system learns to predict ice thickness based on input meteorological data; model verification and adjustment include verifying the trained model through historical data, evaluating its accuracy, and adjusting and optimizing the model based on the verification results.

[0045] Furthermore, time series analysis and machine learning algorithms are used to process and analyze large amounts of data. Time series analysis helps identify patterns and trends in the data, which is very important for understanding and predicting the ice cover process. In addition, machine learning algorithms can learn from historical data and make more accurate predictions about future situations. These algorithms include but are not limited to support vector machines (SVM), random forests, deep learning, etc. In particular, deep learning algorithms can process complex, nonlinear data patterns by simulating the processing methods of the human brain.

[0046] Furthermore, the methods and techniques of this technical solution are not limited to ice thickness prediction, but can also be extended to other meteorological-related fields, such as flood prediction, drought monitoring, etc.; for example, in flood prediction, similar data sets and models can be used to evaluate factors such as rainfall and river water levels to predict the possibility and scope of flood occurrence; this scalability enables this solution to provide solutions to a wider range of meteorological and environmental problems.

[0047] S4: Adjust model parameters based on real-time updated meteorological data, dynamically adjust prediction results, and present predicted ice thickness results through the user interface.

[0048] It should be noted that adjusting model parameters based on real-time updated meteorological data and dynamically adjusting prediction results include the system regularly receiving new meteorological data and updating the prediction model based on real-time data to ensure that the model can reflect current meteorological conditions and make accurate predictions.

[0049] Furthermore, using real-time data to update the prediction model can quickly respond to changes in meteorological conditions, thereby providing more timely predictions. This method continuously monitors changes in meteorological conditions and adjusts model parameters in real time to ensure the timeliness of prediction results. The following dynamic adjustment mechanism is used:

[0050] P new =P+αΔT+βΔH+γΔV+δΔD

[0051] Among them, ΔT, ΔH, ΔV and ΔD represent the changes in temperature, humidity, wind speed and wind direction respectively, while α, β, γ and δ are adjustment coefficients obtained by analyzing historical data;

[0052] The method can adapt to different regions and different meteorological conditions and has a wide range of applications. To achieve this, the technical solution designs a modular structure that allows rapid adjustment or replacement of certain parts of the model to adapt to different environments and needs; for example, in applications in mountainous areas and plains, the geographic information input module can be changed to adapt to the characteristics of different terrains;

[0053] Combining geographic, meteorological and environmental data provides a comprehensive prediction framework for ice cover thickness, which includes not only the above-mentioned meteorological data, but also factors such as terrain height (E) and vegetation type (Vt); these data are analyzed by the following composite model:

[0054] P total =f(P,E,V t ,……)

[0055] Among them, P total is the final prediction of ice thickness, and f is a composite function that comprehensively considers the influence of various factors on ice thickness.

[0056] Furthermore, the forecast model can be dynamically updated based on the latest meteorological data, which means that the model is not static, but can self-adjust and optimize as new data is added; this feature is particularly important because meteorological conditions are constantly changing, and a model that can adapt to these changes will be more accurate and reliable; for example, if the model detects a sudden drop in temperature in a certain area, it will adjust the relevant parameters to reflect the potential impact of this change on ice thickness. Finally, an intuitive user interface is provided so that non-professional users can easily understand and use the forecast results; the interface design includes clear charts, maps and data views, allowing users to quickly understand the forecast results and the data behind them; in addition, the interface also provides customization options, allowing users to adjust data display and analysis according to their needs; for example, users can choose to view forecast results for a specific time period, or conduct an in-depth analysis of the impact of different meteorological factors.

[0057] Specifically, considering that the climate and environmental conditions in different regions vary greatly, this solution provides the ability to customize the prediction model according to the characteristics of a specific region. This customized model takes into account the region's unique climate characteristics (such as temperature range, humidity level, wind speed distribution, etc.) and geographical environment (such as terrain, vegetation type, etc.); for example, in mountainous areas, the model will focus on the impact of terrain on climate, while in coastal areas, it will focus on the characteristics of marine climate; such customized models can provide more accurate and applicable prediction results; and, in order to make the prediction results more intuitive and easy to understand, this solution also provides advanced data visualization functions; this includes dynamic charts, interactive maps, 3D models, etc., so that users can understand data and prediction results from different angles and dimensions; for example, 3D maps can be used to show the distribution of ice thickness in different regions, or dynamic charts can be used to show the trend of ice development.

[0058] The above is a schematic scheme of the ice thickness prediction method based on micrometeorological data of this embodiment. It should be noted that the technical scheme of the system for predicting ice thickness based on micrometeorological data and the technical scheme of the above-mentioned method for predicting ice thickness based on micrometeorological data belong to the same concept. For details not described in detail in the technical scheme of the ice thickness prediction system based on micrometeorological data in this embodiment, please refer to the description of the technical scheme of the above-mentioned method for predicting ice thickness based on micrometeorological data.

[0059] The ice thickness prediction system based on micro-meteorological data in this embodiment includes: a data acquisition module, a data preprocessing module, a feature extraction module and a real-time prediction module;

[0060] The data acquisition module collects micro-meteorological data;

[0061] The data preprocessing module preprocesses the collected micrometeorological data;

[0062] The feature extraction module uses time series analysis and machine learning algorithms to perform feature extraction and model training on the preprocessed data, and performs model verification and adjustment;

[0063] The real-time prediction module adjusts model parameters based on real-time updated meteorological data, dynamically adjusts prediction results, and presents predicted ice thickness results through a user interface.

[0064] This embodiment further provides a computing device, which is applicable to the case of the ice thickness prediction method based on micrometeorological data, and includes:

[0065] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0066] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0067] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0068] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0069] Example 2 is the second example of the present invention, which provides an ice thickness prediction method based on micro-meteorological data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0070] In order to verify the effectiveness of the ice thickness prediction method based on micro-meteorological data, the experiment was conducted in a high mountain power transmission line area, which is prone to ice in winter. The experiment was divided into an experimental group and a control group for comparative testing. The experimental group used the prediction method of the present invention, and the control group used the traditional ice prediction method based on large-scale meteorological data. The experimental results are shown in Tables 1 and 2.

[0071] Table 1 Experimental group data comparison table

[0072] Collection point number Average temperature(℃) Average humidity (%) Average wind speed (m / s) Precipitation (mm) Measured ice thickness (mm) Predicted ice thickness (mm) 1 -5 85 3.2 2.5 8.3 8.1 2 -2 78 2.8 1.2 5.6 5.4 3 -8 92 4 3 12.7 12.3 4 -1 70 1.9 0.8 4.2 4 5 -6 88 3.5 2.7 9.5 9.2 6 -3 82 2.5 1.5 6.8 6.7

[0073] Table 2 Comparison of control group data

[0074] Collection point number Average temperature of the area Average humidity in the area Average wind speed in the area Regional precipitation Measured ice thickness (mm) Predicted ice thickness (mm) 1 -4 80 3 2.3 8.3 7.5 2 -3 75 2.5 1.1 5.6 4.8 3 -7 85 3.8 2.8 12.7 11 4 -2 65 1.7 0.7 4.2 3.6 5 -5 83 3.2 2.4 9.5 8.2 6 -4 78 2.3 1.3 6.8 6

[0075] It can be seen from the experimental data table that there are obvious differences between the experimental group and the control group in predicting ice thickness.

[0076] The experimental group used micro-meteorological data and clustering and classification methods for data processing and prediction. The difference between the predicted results and the measured ice thickness was small, with errors within 0.5 mm, showing a high prediction accuracy. In contrast, the prediction method of the control group was based on large-scale meteorological data and a simple linear regression model. The difference between the predicted results and the measured ice thickness was large, with an error range of 0.8 mm to 1.7 mm, and the prediction accuracy was low.

[0077] By comparing the data of the two groups, it can be seen that the experimental group is more adaptable to complex meteorological conditions. For example, under conditions of low temperature and high humidity (such as collection point 3), the experimental group can accurately predict a higher ice thickness, while the control group's prediction is significantly lower. This shows that the micrometeorological data collection and classification processing method of the experimental group can better capture the subtle features of ice formation, thereby improving the accuracy of the prediction.

[0078] In the tests at different collection points, whether it was the harsh conditions of low temperature and high humidity or the relatively mild meteorological conditions, the prediction model of the experimental group showed high stability and consistency, while the prediction results of the control group fluctuated greatly and had low reliability.

[0079] In summary, through comparative analysis of experimental data, it can be clearly seen that the present invention has significant innovation and superiority in ice thickness prediction. The micro-meteorological data processing and deep learning methods used in the experimental group are significantly better than the traditional prediction methods based on large-scale meteorological data. Especially under complex meteorological conditions, the method of the present invention can provide more accurate and reliable ice thickness prediction, effectively making up for the shortcomings of traditional technologies and providing more powerful technical support for practical applications.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The ice thickness prediction method based on micrometeorological data is characterized by: include, Collect micrometeorological data; Preprocess the collected micrometeorological data; Use time series analysis and machine learning algorithms to extract features and train models on preprocessed data, and perform model validation and adjustment; Adjust model parameters based on real-time updated meteorological data, dynamically adjust prediction results, and present predicted ice thickness results through the user interface.

2. The ice thickness prediction method based on micrometeorological data according to claim 1, characterized in that: The collection of micro-meteorological data includes the use of high-precision sensors and satellite data. The sensors collect micro-meteorological data including temperature, humidity, wind speed and wind direction, and the satellite data provides geographic information on terrain and vegetation coverage.

3. The ice thickness prediction method based on micrometeorological data according to claim 2, characterized in that: The preprocessing includes data cleaning and formatting operations, specifically including removing outliers, filling missing data and data standardization to improve data consistency and provide high-quality data support for subsequent analysis.

4. The ice thickness prediction method based on micrometeorological data according to claim 3 is characterized in that: The feature extraction includes analyzing the data to identify the factors that have the greatest impact on ice thickness, including identifying major meteorological patterns and calculating the correlation of meteorological factors.

5. The ice thickness prediction method based on micrometeorological data according to claim 4, characterized in that: The model training includes using time series analysis and machine learning algorithms, including support vector machines, random forests, and deep learning, to train the processed data. During the training process, the system learns to predict the ice thickness based on the input meteorological data.

6. The ice thickness prediction method based on micrometeorological data according to claim 5, characterized in that: The model verification and adjustment includes verifying the trained model through historical data, evaluating the accuracy, and adjusting and optimizing the model based on the verification results.

7. The ice thickness prediction method based on micrometeorological data according to claim 6, characterized in that: The adjusting of model parameters based on real-time updated meteorological data and the dynamic adjustment of prediction results include the system regularly receiving new meteorological data and updating the prediction model according to the real-time data to ensure that the model can reflect the current meteorological conditions and make accurate predictions.

8. A system based on the ice thickness prediction method based on micrometeorological data according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, data preprocessing module, feature extraction module and real-time prediction module; The data acquisition module collects micro-meteorological data; The data preprocessing module preprocesses the collected micrometeorological data; The feature extraction module uses time series analysis and machine learning algorithms to perform feature extraction and model training on the preprocessed data, and performs model verification and adjustment; The real-time prediction module adjusts model parameters based on real-time updated meteorological data, dynamically adjusts prediction results, and presents predicted ice thickness results through a user interface.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images