A method, storage medium and computer program product for rapid identification of typhoon long-distance heavy rain based on an AI meteorological model

Abstract

The present invention discloses a method, a storage medium and a computer program product for rapidly identifying typhoon long-distance heavy rainfall based on an AI meteorological model, including: obtaining historical weather data and / or forecast weather data, selecting an AI weather forecast model based on deep learning technology and trained using a large amount of historical weather data, screening representative and typical precipitation cases, designing control experiments and sensitivity experiments, and removing the typhoon core vortex from the initial field. By comparing the differences in the results of the control experiment and the sensitivity experiment, and based on the analysis of the changes in the integrated water vapor divergence and precipitation, the impact of the typhoon on long-distance precipitation is quantified, and the influence range and intensity of the typhoon's long-distance heavy rainfall are identified and determined. The present invention significantly improves the accuracy of medium-term weather forecasting and extreme weather event identification, has high computational efficiency and extensive practical application value, provides a scientific basis for disaster warning and disaster reduction management, and provides a new method for meteorological scientific research and teaching.

Description

Technical Field

[0001] The present invention belongs to the technical fields of meteorological science and artificial intelligence, especially an interdisciplinary field applied to aspects such as numerical weather prediction, disaster warning and mitigation management, and the application of artificial intelligence technology in the meteorological field. Specifically, the present invention focuses on using advanced artificial intelligence models (such as deep learning, machine learning, etc.) to improve the recognition and prediction capabilities of typhoons and their long-distance precipitation effects, and proposes a method, storage medium, and computer program product for rapid identification of long-distance heavy rain caused by typhoons based on an AI meteorological model, aiming to provide new technical means for early warning of extreme weather events and disaster prevention and mitigation by optimizing calculation efficiency and prediction accuracy. Background Art

[0002] Tropical Cyclones (TCs) are one of the most destructive natural disasters, which can trigger a large amount of rainfall, floods, and landslides in affected areas. Although these extreme precipitation events are mainly concentrated in the directly affected areas of typhoons, their long-distance effects can also bring catastrophic impacts. This long-distance effect is usually referred to as "long-distance heavy rain caused by typhoons", which is often masked by the precipitation directly triggered by typhoons in research. Understanding and identifying the long-distance impact of typhoons on precipitation is an important aspect of meteorological research, and is crucial for improving the warning capabilities of meteorological disasters, disaster prevention and mitigation, and supporting effective weather decision-making processes.

[0003] Traditional Numerical Weather Prediction (NWP) models, such as the Weather Research and Forecasting Model (WRF), have been widely used to study typhoons and their related phenomena. These models help meteorologists understand the physical mechanisms of typhoons through simulations and sensitivity experiments. However, these models often require high computational costs to handle complex atmospheric dynamics and thermodynamics processes, which limits their efficiency and wide application in practical applications.

[0004] With the progress of artificial intelligence technology, innovative methods such as machine learning and deep learning technologies have been introduced into the field of weather forecasting. This transformative method provides higher prediction accuracy and computational efficiency than traditional models. Some innovative AI systems, such as Pangu-Weather (hereinafter referred to as Pangu), GraphCast, and Fengwu, have become leading models for medium-term global weather forecasting. These AI models, as open-source platforms, have promoted the cooperation and improvement of the global research community and have been adopted by multiple international forecasting centers. AI models have significant advantages in processing large amounts of data and complex pattern recognition, making their applications in weather forecasting increasingly widespread.

[0005] However, despite the excellent performance of AI models in weather forecasting, there are still doubts about whether they can accurately capture and describe complex physical processes, especially the impact of typhoons on weather patterns. Understanding the long-range effects of typhoons usually requires sensitivity experiments to fully analyze their physical mechanisms, which is computationally expensive and inefficient for traditional numerical models. Therefore, how to use advanced artificial intelligence models (such as deep learning, machine learning, etc.) to improve the recognition and prediction capabilities of tropical cyclones and their long-range precipitation effects, improve the recognition efficiency and accuracy of typhoon long-range rainstorms, and thus improve the prediction accuracy and computational efficiency of extreme precipitation events, is a technical problem that needs to be solved urgently. Summary of the invention

[0006] 1. Purpose of the invention

[0007] In order to solve at least one of the above-mentioned and other technical problems in the prior art, the present invention provides a method for quickly identifying typhoon long-distance heavy rain based on an AI meteorological model, a storage medium and a computer program product, aiming to improve the recognition accuracy and efficiency of the long-distance impact of typhoons. The method uses weather data and combines it with an AI forecast model to design control experiments and sensitivity experiments to analyze the long-distance impact of typhoons on precipitation. The sensitivity experiment removes the typhoon core vortex, thereby realizing the rapid identification of typhoon long-distance heavy rain. At the same time, by comparing the prediction results of the control experiment and the sensitivity experiment, the prediction accuracy and calculation efficiency of extreme precipitation events are significantly improved, which is of great significance to disaster warning and disaster reduction management.

[0008] (II) Technical solution

[0009] In order to achieve the purpose of the invention and solve the technical problems, the present invention adopts the following technical solutions:

[0010] The first invention object of the present invention is to provide a method for quickly identifying typhoon long-distance rainstorms based on an AI meteorological model, so as to improve the recognition accuracy and efficiency of the long-distance impact of typhoons. Specifically, the method for quickly identifying typhoon long-distance rainstorms includes at least the following steps when implemented:

[0011] SS1. Weather data acquisition

[0012] Acquire high-quality and high-temporal and high-spatial resolution historical weather data and / or forecast weather data, which covers global land and ocean areas and includes at least temperature, humidity, air pressure, wind speed, wind direction and precipitation meteorological parameters to ensure high accuracy and reliability of model initial conditions;

[0013] SS2. AI weather forecast model selection

[0014] Select an AI weather model based on deep learning technology, trained using a large amount of historical weather data, and capable of providing high-precision medium-term weather forecasts and extreme weather event identification as the forecasting model, and the selected model has the ability to process complex meteorological data and quickly generate high-precision forecasting results;

[0015] SS3. Selection of typical precipitation cases

[0016] Screen and determine representative and typical precipitation cases based on historical meteorological disaster records and historical meteorological data, and the selected typical precipitation cases should have certain characteristics of the far-field impact of typhoons, and at least provide the starting time of the typical precipitation case, precipitation location information, and typhoon location information;

[0017] SS4. Design of control and sensitivity experiments

[0018] Based on the selected AI weather forecasting model, the obtained weather data, and the selected typical precipitation cases, design a control experiment (CTRL) and a sensitivity experiment (RMTC), where:

[0019] The control experiment is based on the selected AI weather forecasting model, uses the historical weather data and / or forecast weather data corresponding to the selected typical precipitation cases as the initial field, conducts standard weather forecasting simulations, and generates benchmark prediction results;

[0020] On the basis of the control experiment, the sensitivity experiment constructs a new initial field by applying the method of removing the typhoon core vortex from the initial field, and re-conducts weather forecasting simulations based on the selected AI weather forecasting model to generate sensitivity experiment results;

[0021] SS5. Result analysis and identification of far-field typhoon heavy rain

[0022] By comparing the differences between the results of the control experiment and the sensitivity experiment, and based on the analysis of the change in the whole-layer water vapor divergence and / or precipitation change, quantitatively analyze the impact of the target typhoon on the far-field precipitation, identify and determine the far-field heavy rain impact range and intensity of the typhoon, so as to achieve the rapid identification of the far-field typhoon heavy rain.

[0023] The second object of the present invention is to provide a computer program product, including computer instructions, for executing the above-mentioned method for rapid identification of far-field typhoon heavy rain based on an AI meteorological model.

[0024] The third object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method for rapid identification of far-field typhoon heavy rain based on an AI meteorological model is realized.

[0025] (III) Technical effects

[0026] Compared with the prior art, the typhoon long-distance heavy rain rapid identification method, storage medium and computer program product based on the AI meteorological model of the present invention have the following beneficial and remarkable technical effects:

[0027] (1) The present invention adopts an AI weather forecasting model. By using advanced deep learning algorithms and a large amount of historical meteorological data for training, it can provide forecasts with higher accuracy than traditional numerical weather forecasting models. For example, the Pangu model performs particularly well in medium-term weather forecasting and extreme weather event identification, significantly improving the accuracy of weather forecasting. In addition, by using high-resolution reanalysis data and historical weather data or forecast weather data, the high accuracy and reliability of the model's initial conditions are ensured, providing a solid data foundation for the forecast results.

[0028] (2) The present invention has significant advantages in computing efficiency. Compared with traditional numerical weather forecasting models, the AI weather forecasting model can process and analyze large-scale data in a shorter time, thus providing more timely forecast results. By applying the method of removing the typhoon core vortex, the system of the present invention can effectively conduct sensitivity experiments, reduce the computational complexity, and improve the computational efficiency. This method can accurately remove the typhoon core vortex from the initial field, thereby better analyzing the long-distance influence of typhoons and enhancing the ability to identify and forecast extreme weather events.

[0029] (3) The present invention has important practical application value in disaster warning and disaster reduction management. By improving the identification accuracy and efficiency of typhoon long-distance heavy rain, it provides a scientific basis for disaster warning and disaster reduction management, helping decision-makers formulate more effective response strategies. The system uses refined analysis of the whole-layer water vapor flux and the whole-layer water vapor divergence to accurately capture the long-distance influence of typhoons, thus significantly improving the accuracy and reliability of forecasts. This is of great significance for timely warning and taking disaster prevention measures.

[0030] (4) The present invention also has broad application prospects in meteorological scientific research and teaching. Its innovative methods and refined analysis tools provide new tools and methods for meteorological research, helping to deeply understand the mechanism of the long-distance influence of typhoons and explore the influence of weather systems at different scales on precipitation. Through the comparison of control experiments and sensitivity experiments, the system can quantitatively analyze the specific influence of the typhoon core vortex on long-distance precipitation, and in combination with wavelength filtering analysis, explore the influence of weather systems at different scales on precipitation.

[0031] (5) By adopting advanced AI technology and high-resolution meteorological data, the present invention improves the accuracy and efficiency of typhoon long-distance heavy rain identification, significantly enhances the forecasting ability and computing efficiency, and has remarkable technical effects and broad application prospects in aspects such as meteorological forecasting, disaster warning and mitigation management, and meteorological scientific research and teaching. Through the above advantages and innovation points, the present invention provides strong technical support for meteorological forecasting and disaster warning, and provides a scientific solution for dealing with extreme weather events. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The figure shows a schematic diagram of the implementation process of the method for quickly identifying typhoon long-distance heavy rain based on the AI meteorological model of the present invention;

[0033] Figure 2 The figure shows a schematic diagram of the system architecture of the method for quickly identifying typhoon long-distance heavy rain based on the AI meteorological large model of the present invention;

[0034] Figure 3 The figure shows the time series of the vertically integrated water vapor flux divergence averaged over a certain region of the East Asian continent from 12:00 UTC on July 28, 2023 to 00:00 UTC on August 1, 2023 (10 4 ·g·m -2 ·s -1 ), and the figure shows the comparison results between Pangu and Pangu_RMTC. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To better understand the present invention, the content of the present invention will be further clarified below in conjunction with embodiments. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some embodiments of the present invention, rather than all embodiments. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention. The structure and technical solutions of the present invention will be further specifically described below in conjunction with the drawings, and an embodiment of the present invention is given.

[0036] The present invention aims to provide a method, a storage medium, and a computer program product for rapidly identifying typhoon-induced long-distance heavy rainfall based on an AI meteorological model, so as to improve the accuracy and efficiency of identifying the long-distance impact of typhoons. This method is based on weather data and combines an AI meteorological forecasting model. Control experiments and sensitivity experiments are designed to analyze the long-distance impact of typhoons on precipitation. The sensitivity experiment removes the typhoon's core vortex, thereby enabling the rapid identification of typhoon-induced long-distance heavy rainfall. At the same time, by comparing the prediction results of the control experiment and the sensitivity experiment, this method significantly improves the prediction accuracy and calculation efficiency of extreme precipitation events, which is of great significance for disaster warning and disaster reduction management.

[0037] As a specific example, such as Figure 1 、 2 shown, the method for rapidly identifying typhoon-induced long-distance heavy rainfall based on an AI meteorological model provided by the present invention mainly includes the following steps when implemented:

[0038] SS1. Weather data acquisition

[0039] Obtain high-quality historical weather data and / or forecast weather data with high spatio-temporal resolution. The weather data covers global land and ocean areas and includes at least meteorological parameters such as temperature, humidity, air pressure, wind speed, wind direction, and precipitation to ensure the high accuracy and reliability of the model's initial conditions.

[0040] In some preferred examples, when implementing this step, the historical weather data uses the high-resolution global meteorological data provided by the ERA5 weather dataset of the European Centre for Medium-Range Weather Forecasts (ECMWF), and the forecast weather data uses the forecast field data provided by the Integrated Forecasting System (IFS) of the European Centre for Medium-Range Weather Forecasts (ECMWF).

[0041] The ERA5 weather dataset is the fifth-generation global climate reanalysis dataset provided by the European Centre for Medium-Range Weather Forecasts (ECMWF), covering high-resolution weather data from 1979 to the present. By combining global observational data and numerical weather prediction models, it provides a long time series of global climate data, which is widely used in meteorological research, climate change analysis, and environmental monitoring. ERA5 data includes various meteorological variables such as temperature, humidity, wind speed and direction, precipitation, air pressure, etc., covering global land and ocean areas. The data resolution of ERA5 is 0.25°×0.25° (about 31 kilometers), and there are 37 pressure levels in the vertical direction, from the ground to the top of the atmosphere. ERA5 provides hourly data, which helps to analyze short-term weather changes and extreme weather events. The ERA5 dataset combines satellite observations, ground observations, and the output of weather prediction models and is generated through four-dimensional variational data assimilation (4D-Var) technology.

[0042] The Integrated Forecasting System (IFS) of ECMWF is one of the world's leading numerical weather prediction models, providing high-precision medium-range weather forecast data. The IFS forecast fields are generated through complex numerical models and observational data assimilation, producing weather forecasts for the next few days to weeks. The IFS forecast fields include various meteorological parameters such as temperature, humidity, wind speed and direction, precipitation, air pressure, etc., similar to ERA5 but focusing on future weather forecasts. The IFS data resolution can reach approximately 9 kilometers (T1279), with 137 levels vertically, from the ground to the top of the atmosphere at 0.01 hPa. The IFS forecast data usually provides hourly or three-hourly forecast outputs, with a time span ranging from several days to weeks. The IFS forecasting system combines global observational data (including satellite, radar, and ground observations), using advanced data assimilation techniques and high-performance computing platforms to generate forecasts.

[0043] SS2. Selection of AI Weather Forecast Model

[0044] Select an AI weather model based on deep learning technology, trained using a large amount of historical weather data, and capable of providing high-precision medium-range weather forecasts and identifying extreme weather events as the forecast model, and the selected model has the ability to process complex meteorological data and quickly generate high-precision forecast results.

[0045] In some preferred examples, when implementing step SS2, the AI weather forecast model selects Pangu, GraphCast, Fengwu, or other high-precision AI models with similar performance, and by combining multi-modal data inputs, including meteorological observation data, historical weather forecast data, and environmental data, to enhance the model's prediction ability and improve the recognition and forecast accuracy of complex weather events through cross-modal learning techniques. Specifically, the meteorological observation data includes but is not limited to ground observation station data, meteorological satellite remote sensing data, and radar observation data; the historical weather forecast data includes global and regional weather forecast data for the past few years; the environmental data includes key parameters such as ocean temperature, humidity, wind speed, and air pressure. Through cross-modal learning techniques, the model can extract richer feature information from multi-modal data, further improving the recognition and forecast accuracy of complex weather events. Especially in the case of the interactive influence of multiple meteorological systems, it can more accurately predict the long-distance impact of typhoons and the occurrence of rainstorm events.

[0046] SS3. Selection of Typical Precipitation Cases

[0047] Select and determine representative and typical precipitation cases based on historical meteorological disaster records and historical meteorological data. The selected typical precipitation cases should have certain characteristics of the long-distance influence of typhoons, and at least provide the starting time of the typical precipitation case, precipitation location information, and typhoon location information.

[0048] Specifically, in this step SS3, the screening criteria for typical precipitation cases include that the precipitation intensity exceeds the preset critical threshold, the precipitation duration exceeds the preset critical value, and / or the precipitation event has the characteristics caused by tropical cyclones or other extreme weather systems. By performing cluster analysis on historical meteorological disaster records and historical meteorological data, several representative typical precipitation cases are determined, providing research objects for subsequent sensitivity experiment research.

[0049] SS4. Control and Sensitivity Test Design

[0050] Based on the selected AI weather forecasting model, the obtained weather data, and the selected typical precipitation cases, design a control experiment (CTRL) and a sensitivity experiment (RMTC), where:

[0051] The control experiment is based on the selected AI weather forecasting model, using the historical weather data and / or forecast weather data corresponding to the selected typical precipitation cases as the initial field, performing standard weather forecasting simulations and generating benchmark prediction results; the sensitivity experiment, on the basis of the control experiment, constructs a new initial field by applying the method of removing the typhoon core vortex from the initial field, and re-performs weather forecasting simulations based on the selected AI weather forecasting model to generate sensitivity experiment results.

[0052] In some preferred examples, in the sensitivity experiment, the Kurihara method is used to construct a new initial field by removing the typhoon core vortex from the initial field. This method effectively separates and removes the typhoon core vortex in the initial field by applying a cylindrical filter, enabling the sensitivity experiment to better analyze the long-distance influence of typhoons, and specifically including the following sub-steps:

[0053] SS41. Determine the typhoon core position

[0054] According to the typhoon location information, and at least combining the barometric pressure and wind field meteorological data in the initial field, determine the position of the typhoon core, and locate the typhoon center by analyzing the lowest barometric pressure point and the area with the maximum wind speed;

[0055] SS42. Define the filtering area

[0056] Define a cylindrical filtering area around the typhoon core position. The radius and height dimensions of the filtering area are determined according to the actual size and influence range of the typhoon to cover the entire typhoon vortex structure;

[0057] SS43. Extract typhoon vortex

[0058] A cylindrical filter is used to calculate the average value within the filtered area, and the symmetric part of the typhoon is separated through this average value, so as to extract the typhoon vortex from the initial field;

[0059] SS44. Remove vortex structure

[0060] By replacing the vortex part within the filtered area with the average meteorological parameter value of the surrounding area, the influence of the typhoon core on the initial field is eliminated, so as to remove the extracted typhoon vortex structure from the initial field;

[0061] SS45. Construct a new initial field

[0062] Using the initial field after removing the typhoon core vortex, the initial conditions of the numerical weather prediction model are reconstructed. This new initial field is used for sensitivity experiments to analyze the long-distance influence of typhoons.

[0063] Through the above sub-steps, the typhoon core vortex in the initial field can be accurately removed, ensuring that the sensitivity experiment can more accurately analyze the influence mechanism of typhoons on long-distance heavy rain.

[0064] In a further preferred example, in the above sub-step SS44, the extracted typhoon vortex structure is removed from the initial field through the following steps:

[0065] SS441. Let the meteorological variable in the initial field be Φ( x , y , z ), the typhoon core position be ([[]] x 0 , y 0 ), and the radius of the filtered area be R , then the cylindrical filter can be expressed as:

[0066]

[0067] SS442. Calculate the typhoon vortex component of each meteorological variable (such as air pressure, wind speed, wind direction, etc.) in the initial field based on the following calculation formula:

[0068]

[0069] Among them, Φ b ( x , y , z ) represents the background field, which can usually be obtained through filter calculation:

[0070]

[0071] SS443. Subtract the vortex component calculated in the above sub-step SS442 from the original initial field to generate an initial condition without the typhoon core vortex:

[0072]

[0073] In the formula, Φ new ( x , y , z ) represents the meteorological variables in the new initial field without the typhoon core vortex, Φ( x , y , z ) are the meteorological variables in the original initial field, and Φ v ( x , y , z ) is the typhoon vortex component of each meteorological variable.

[0074] SS5. Result analysis and identification of typhoon long-distance heavy rain

[0075] By comparing the differences between the results of the control experiment and the sensitivity experiment, and based on the analysis of the change in the total-layer water vapor divergence and / or precipitation change, quantitatively analyze the impact of the target typhoon on the long-distance precipitation, identify and determine the influence range and intensity of the typhoon's long-distance heavy rain, so as to achieve the rapid identification of the typhoon's long-distance heavy rain.

[0076] In some preferred examples, the total-layer water vapor flux and the total-layer water vapor divergence are calculated in the following manner in this step, where:

[0077] (a) Calculation of the total-layer water vapor flux. The total-layer water vapor flux is used to represent the transport amount of water vapor in the atmosphere under the action of the horizontal wind field, and its calculation formula is as follows:

[0078]

[0079] Among them, q is the specific humidity, V is the horizontal wind speed, V = ( u , v ) are the east-west wind speed component and the north-south wind speed component respectively, p s 、 p t are the air pressures at the earth's surface and the top of the atmosphere respectively;

[0080] (b) Calculation of the total-layer water vapor divergence. The total-layer water vapor divergence represents the convergence or divergence of water vapor in the atmosphere and is the divergence of the water vapor flux, and its calculation formula is as follows:

[0081]

[0082] Among them, Q is the integral layer water vapor flux, Q u and Q v are the east-west component and the north-south component of the water vapor flux respectively, represents the divergence of the water vapor flux.

[0083] In step SS4, both the control experiment (CTRL) and the sensitivity experiment (RMTC) are based on the selected AI weather forecasting model, and the historical weather data and / or forecast weather data corresponding to typical precipitation cases are used as the initial fields. The control experiment uses the complete initial field data to conduct standard weather forecasting simulations to generate benchmark prediction results. On the basis of the control experiment, the sensitivity experiment applies the Kurihara method to remove the typhoon core vortex from the initial field, effectively separates and removes the typhoon core vortex in the initial field through a cylindrical filter, thereby constructing a new initial field, and re-conducts weather forecasting simulations based on this new initial field to generate sensitivity experiment results.

[0084] Using Python for plotting and using plotting libraries such as Matplotlib and Seaborn, the forecast results can be visualized. The plotting content may include, depending on the situation, the integral layer water vapor, the change of the integral layer water vapor divergence, the precipitation distribution and its evolution over time, etc., so as to more intuitively understand the far-field impact of typhoons.

[0085] Figure 3 Shows the time series of the integral layer water vapor flux divergence (10 4 ·g·m -2 ·s -1 averaged over a certain region of the East Asian continent from 12:00 UTC on July 28, 2023 to 00:00 UTC on August 1, 2023), results from Pangu and Pangu_RMTC. The figure shows the comparison results between Pangu and Pangu_RMTC, and it can be seen the change trend of the integral layer water vapor flux divergence after the removal of the typhoon core vortex. Through quantitative and visual analysis, these charts provide important reference bases for understanding the impact mechanism of far-field typhoon heavy rain.

[0086] SS6. Evaluation and verification of far-field typhoon heavy rain identification results

[0087] Compare the far-field typhoon heavy rain identification results obtained in step SS5 with the actual observed data to evaluate the accuracy and reliability of the model prediction, and optimize and adjust the parameters and algorithms of the AI weather forecasting model according to the evaluation results to improve its prediction accuracy and efficiency.

[0088] The above steps constitute a complete far-field typhoon heavy rain rapid identification system architecture based on the AI meteorological large model (as Figure 2As shown, the accuracy and efficiency of typhoon long-distance impact identification can be significantly improved through this system, thus providing strong technical support for meteorological forecasting and disaster warning.

[0089] Based on the above embodiments, the present invention improves the accuracy of medium-term weather forecasting and extreme weather event identification by using the Pangu weather large model, high-resolution ERA5 reanalysis data, and ECMWF's IFS forecast data. The system uses refined analysis of the integrated water vapor flux and integrated water vapor divergence to accurately capture the long-distance impact of typhoons, significantly improving the accuracy and reliability of the forecast. Compared with traditional numerical weather prediction models, the AI model has a significant advantage in computing efficiency and can process and analyze large-scale data more timely. The Kurihara method is applied to remove the typhoon core vortex, reducing the computational complexity and improving the computational efficiency of sensitivity experiments. Through the comparison of control experiments and sensitivity experiments, the system can quantitatively analyze the specific impact of the typhoon core vortex on long-distance precipitation and deeply understand the mechanism of the typhoon's long-distance impact. Combining wavelength filtering analysis, the impact of weather systems at different scales on precipitation is explored. This system has important application value in disaster warning and disaster reduction management, provides a scientific basis for decision-makers, and provides new tools and new methods for meteorological scientific research and teaching.

[0090] Through the above embodiments, the purpose of the present invention is fully and effectively achieved. Those skilled in the art can understand that the present invention includes but is not limited to the content described in the drawings and the above specific embodiments. Although the present invention has been described with respect to the currently considered most practical and preferred embodiments, it should be understood that the present invention is not limited to the disclosed embodiments, and any modification that does not deviate from the functional and structural principles of the present invention will be included in the scope of the claims.

Claims

1. A method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model, characterized in that: The method for quickly identifying typhoon long-distance rainstorms comprises at least the following steps when implemented: SS1. Weather data acquisition Acquire high-quality and high-temporal and high-spatial resolution historical weather data and / or forecast weather data, which covers global land and ocean areas and includes at least meteorological parameters such as temperature, humidity, air pressure, wind speed, wind direction and precipitation; SS2. AI weather forecast model selection Select an AI weather model based on deep learning technology and trained with a large amount of historical weather data, which can provide high-precision medium-term weather forecasts and identify extreme weather events as the forecast model; SS3. Selection of typical precipitation cases Based on historical meteorological disaster records and historical meteorological data, representative and typical precipitation cases are screened and determined. The selected typical precipitation cases should have certain characteristics of typhoon long-distance impact, and at least provide the starting time, precipitation location information and typhoon location information of the typical precipitation case; SS4. Control and sensitivity test design Based on the selected AI weather forecast model, the acquired weather data and the selected typical precipitation cases, control experiments and sensitivity experiments are designed, including: The control experiment is based on the selected AI weather forecast model, uses historical weather data and / or forecast weather data corresponding to the selected typical precipitation case as the initial field, performs standard weather forecast simulation and generates benchmark prediction results; The sensitivity experiment, based on the control experiment, applies the method of removing the typhoon core vortex from the initial field to construct a new initial field, and re-simulates the weather forecast based on the selected AI weather forecast model to generate sensitivity experiment results; And wherein, the typhoon core vortex is removed from the initial field to construct a new initial field, including: SS41. Determine the location of the typhoon core: Determine the location of the typhoon core based on the typhoon location information and at least the initial field pressure and wind field meteorological data, and locate the typhoon center by analyzing the lowest pressure point and the maximum wind speed area; SS42. Define filtering area: define a cylindrical filtering area around the core of the typhoon, the radius and height of the filtering area are determined according to the actual size and impact range of the typhoon to cover the entire typhoon vortex structure; SS43. Extraction of typhoon vortex: Using a cylindrical filter, the typhoon vortex is extracted from the initial field by calculating the average value within the filter area and separating the symmetrical part of the typhoon through the average value; SS44. Removal of vortex structure: The vortex part in the filter area is replaced by the average meteorological parameter value of the surrounding area to eliminate the influence of the typhoon core on the initial field, thereby removing the extracted typhoon vortex structure from the initial field; SS45. Constructing a new initial field: Using the initial field after removing the typhoon core vortex, the initial conditions of the numerical weather forecast model are reconstructed. The new initial field is used for sensitivity experiments to analyze the long-range impact of typhoons. SS5. Result analysis and identification of long-distance typhoon heavy rain By comparing the differences between the results of control experiments and sensitivity experiments, and based on the analysis of changes in water vapor divergence and / or precipitation changes in the entire layer, the impact of the target typhoon on long-distance precipitation is quantitatively analyzed, and the impact range and intensity of the typhoon's long-distance rainstorm are identified and determined, thereby achieving rapid identification of the typhoon's long-distance rainstorm.

2. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: In the above step SS1, the historical weather data adopts high-resolution global meteorological data provided by the ERA5 weather data set, and the forecast weather data adopts IFS forecast field data.

3. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: In the above step SS2, the AI ​​weather forecast model selects the Pangu, GraphCast or Fengwu forecast model, and enhances the model's prediction ability by combining multimodal data input, including meteorological observation data, historical weather forecast data and environmental data, and improves the recognition and forecasting accuracy of complex weather events through cross-modal learning technology.

4. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: In the above step SS3, the screening criteria for typical precipitation cases include precipitation intensity exceeding a preset critical threshold, precipitation duration exceeding a preset critical value, and / or the precipitation event having the characteristics of being caused by a tropical cyclone or other extreme weather system. By clustering the historical meteorological disaster records and historical meteorological data, several representative typical precipitation cases are determined to provide research objects for subsequent sensitivity experimental studies.

5. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: In the above sub-step SS44, the extracted typhoon vortex structure is removed from the initial field by: SS441. Assume that the meteorological variable in the initial field is Φ( x , y , z ), the typhoon core location is ( x 0, y 0), the radius of the filter area is R, then the cylindrical filter is expressed as: SS442. Calculate the typhoon vortex component Φ of various meteorological variables including air pressure, wind speed and wind direction in the initial field based on the following formula: v ( x , y , z ): Among them, Φ b ( x , y , z ) represents the background field and is calculated by the filter shown in the following formula: SS443. Subtract the vortex components obtained by the technique in substep SS442 from the initial field to generate initial conditions without the typhoon core vortex: In the formula, Φ new ( x , y , z ) represents the meteorological variables in the new initial field without the typhoon core vortex, Φ( x , y , z ) is the meteorological variable in the original initial field, Φ v ( x , y , z ) is the typhoon vortex component of each meteorological variable.

6. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: In the above step SS5, the whole-layer water vapor flux and the whole-layer water vapor divergence are calculated based on the following method, wherein: (a) Calculation of water vapor flux in the whole layer: The whole-layer water vapor flux is used to indicate the amount of water vapor transported in the atmosphere under the action of the horizontal wind field. The calculation formula is as follows: Where q is the specific humidity, V is the horizontal wind speed, V = (u, v), which are the east-west wind speed component and the north-south wind speed component, respectively, and p s 、p t are the air pressure at the surface and at the top of the atmosphere, respectively; (b) Calculation of water vapor dispersion in the entire layer: The whole layer water vapor divergence indicates the convergence or divergence of water vapor in the atmosphere. It is the divergence of water vapor flux and its calculation formula is as follows: Where Q is the water vapor flux of the whole layer, Q u , Q v are the east-west and north-south components of water vapor flux, Represents the divergence of water vapor flux.

7. The method for rapid identification of typhoon long-distance rainstorm based on AI meteorological model according to claim 1 is characterized in that: The method for quickly identifying typhoon long-distance rainstorms also includes: SS6. Evaluation and verification of typhoon long-distance rainstorm identification results The typhoon long-distance rainstorm identification results obtained in step SS5 are compared with the actual observation data to evaluate the accuracy and reliability of the model prediction, and the parameters and algorithms of the AI ​​weather forecast model are optimized and adjusted according to the evaluation results to improve its prediction accuracy and efficiency.

8. A computer program product, characterized in that It includes computer instructions for executing the method for quickly identifying typhoon long-distance heavy rain based on the AI ​​meteorological model as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for quickly identifying typhoon long-distance heavy rain based on the AI ​​meteorological model as described in any one of claims 1 to 7 is implemented.

Images