Weather forecast data generation method and device and terminal equipment

Abstract

The invention provides a weather forecast data generation method and device and terminal equipment, and is suitable for the technical field of data processing, and the method comprises the steps: calculating the dispersion information and average information of initial weather forecast data corresponding to weather forecast mode information, initial weather forecast data dispersion information and initial weather forecast data average value information are obtained; screening the initial weather forecast data according to the dispersion information of the initial weather forecast data and the average information of the initial weather forecast data to generate intermediate weather forecast data; and generating target weather forecast data according to the intermediate weather forecast data. According to the method, the difference of each weather forecast mode can be reflected, and the weather forecast data closer to the real situation can be screened out, so that the accuracy and effectiveness of weather forecast are improved.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to methods, devices and terminal equipment for generating meteorological forecast data. Background Technology

[0002] In the field of numerical weather prediction, the forecast results of a single sample or model are uncertain due to initial errors and model errors. Therefore, the industry generally adopts a multi-sample, multi-model ensemble approach to improve forecast accuracy and reliability.

[0003] Currently, existing technologies mainly generate meteorological data through various multi-model ensemble averaging techniques such as simple ensemble averaging, bias-free ensemble averaging, and super ensemble averaging. These techniques essentially perform model correction by assigning fixed weights to different models.

[0004] In existing technologies, assigning fixed weights to different models cannot be adjusted based on the forecast results of the current starting time of the real-time rolling forecast. As a result, it cannot effectively reflect the differences in forecasting skill among different models / samples in the current forecast, leading to extremely limited room for improvement in the accuracy and effectiveness of weather forecasts. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus and terminal device for generating meteorological forecast data, which aims to solve the problem that the existing technology cannot effectively reflect the differences in forecasting skills of different models in the current forecast, resulting in low accuracy and insufficient effectiveness of meteorological forecasts.

[0006] The first aspect of this application provides a method for generating weather forecast data, including: Acquire multiple initial weather forecast data corresponding to multiple weather forecast models; The dispersion information and average value information of multiple initial weather forecast data corresponding to the weather forecast model information are calculated to obtain the dispersion information and average value information of multiple initial weather forecast data; the dispersion information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence; the average value information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence. Based on the dispersion information and the average value information of the initial weather forecast data, the initial weather forecast data are filtered to generate multiple intermediate weather forecast data. Target weather forecast data is generated based on multiple intermediate weather forecast data.

[0007] A second aspect of this application provides a weather forecast data generation apparatus, comprising: The initial weather forecast data acquisition module is used to acquire multiple initial weather forecast data corresponding to multiple weather forecast model information; The dispersion and average value calculation module is used to calculate the dispersion and average value information of multiple initial weather forecast data corresponding to the weather forecast model information, thereby obtaining the dispersion information and average value information of multiple initial weather forecast data; the dispersion information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence; the average value information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence. The intermediate weather forecast data generation module is used to filter and process multiple initial weather forecast data based on the dispersion information and the average value information of multiple initial weather forecast data to generate multiple intermediate weather forecast data. The target weather forecast data generation module is used to generate target weather forecast data based on multiple intermediate weather forecast data.

[0008] A third aspect of this application provides a terminal device, which includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the weather forecast data generation method described in the first aspect above.

[0009] A fourth aspect of this application provides a computer-readable storage medium, comprising: storing a computer program, wherein when executed by a processor, the computer program implements the steps of the weather forecast data generation method described in the first aspect above.

[0010] The beneficial effects of this application embodiment compared with the prior art are as follows: This application utilizes the negative correlation between single-model multi-sample dispersion and model average forecast skill to dynamically screen high-skill intermediate weather forecast data that match historical statistical patterns before acquiring real observation data. By comparing dispersion, the sample set is further optimized so that the target weather forecast data can reflect the model / sample skill differences at the current reporting time in real time, thereby improving the accuracy and reliability of ensemble average forecast skill. Moreover, it can be updated continuously with the real-time reporting time to improve the accuracy and effectiveness of weather forecasts. Attached Figure Description

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0012] Figure 1 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 2 of this application; Figure 3 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 3 of this application; Figure 4 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 4 of this application; Figure 5 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 5 of this application; Figure 6 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment Six of this application; Figure 7 This is a schematic diagram illustrating the implementation process of the meteorological forecast data generation method provided in Embodiment 7 of this application; Figure 8 This is a schematic diagram of the structure of the weather forecast data generation device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the terminal device provided in the embodiments of this application. Detailed Implementation

[0013] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0014] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0015] Figure 1 A flowchart illustrating the implementation of the meteorological forecast data generation method provided in Embodiment 1 of this application is shown, and is described in detail below: Step S101: Obtain multiple initial weather forecast data corresponding to multiple weather forecast model information.

[0016] In this embodiment, weather forecast model information refers to dynamical models, such as the European Centre for Medium-Range Weather Forecasts (ECMWF) model and the China Meteorological Administration (CMA) model, which are used to calculate input weather data and output weather forecast results. It is understood that different weather forecast models use different dynamical models for calculation. Even with the same input data, the weather forecast results obtained from different weather forecast models may differ, and the calculated weather forecast data will correspond to their respective weather forecast models. Multiple initial weather forecast data corresponding to multiple weather forecast models refer to the weather forecast data calculated by different dynamical models. Each dynamical model outputs multiple weather forecast data, and all the weather forecast data output by all dynamical models are used as the initial weather forecast data.

[0017] Step S102: Calculate the dispersion information and average value information of multiple initial weather forecast data corresponding to the weather forecast model information, and obtain the dispersion information and average value information of multiple initial weather forecast data; the dispersion information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence; the average value information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence.

[0018] In this embodiment, forecast skill scores can be calculated based on observational reanalysis data and multi-model historical return data for each weather forecast model at each reporting time, using multiple initial weather forecast data. The dispersion information of the initial weather forecast data for each model is the standard deviation of the forecast skills of all samples for that model; the standard deviation characterizes the degree of dispersion between samples. The mean information of the initial weather forecast data is the arithmetic mean of the forecast skills of all samples, and both correspond one-to-one with the weather forecast model information. For example, a model has m samples of weather forecast data; its dispersion is the standard deviation of the m sample skills, and its mean is the mean of the m sample skills.

[0019] Step S103: Based on the dispersion information and the average value information of the initial weather forecast data, the initial weather forecast data are filtered to generate multiple intermediate weather forecast data.

[0020] In this embodiment, the correlation between the dispersion and average values ​​of initial weather forecast data for each model in historical report data can be analyzed. It is found that the two are negatively correlated, i.e., the linear regression coefficient is negative. Therefore, for the current reporting time, each initial weather forecast data is treated as an "observed" value, and the hypothetical forecast skill of other samples is calculated. This yields the hypothetical dispersion and hypothetical average value for each model. The linear regression coefficient between these two values ​​is then calculated. If the linear regression coefficient is less than 0, the sample is determined to conform to the historical negative correlation pattern and is selected as intermediate weather forecast data. It is understandable that the greater the dispersion, the lower the accuracy of the weather forecast data under that model.

[0021] Step S104: Generate target weather forecast data based on the multiple intermediate weather forecast data.

[0022] In this embodiment, the current weather forecast dataset and the previous weather forecast dataset can be separated from the intermediate weather forecast data. Then, the intermediate weather forecast data can be removed from the initial weather forecast data to obtain the remaining forecast data. The inter-sample dispersion and inter-model dispersion of the current weather forecast dataset are calculated, as are the inter-sample dispersion and inter-model dispersion of the remaining forecast data. If the inter-sample dispersion of the current weather forecast dataset is less than the inter-sample dispersion of the remaining forecast data, and the inter-model dispersion is less than the inter-model dispersion of the remaining forecast data, then the average value of the intermediate weather forecast data can be used as the target weather forecast data. Otherwise, the average value of the remaining forecast data is selected as the target weather forecast data.

[0023] The meteorological forecast data generation method provided in this application utilizes the negative correlation between single-model multi-sample dispersion and model average forecast skill. Before acquiring real observation data, it dynamically selects high-skill intermediate meteorological forecast data that matches historical statistical patterns. By comparing dispersion, it further optimizes the sample set, enabling the target meteorological forecast data to reflect the model / sample skill differences at the current forecast time in real time. This improves the accuracy and reliability of ensemble average forecast skill and allows for rolling updates with the real-time forecast time, thereby enhancing the accuracy and effectiveness of meteorological forecasts.

[0024] Figure 2 The flowchart illustrating the implementation of the meteorological forecast data generation method provided in Embodiment 2 of this application is shown. The difference between this method and Embodiment 1 is that step S103 specifically includes: Step S201: Perform linear fitting processing on the dispersion information and the average value information of the multiple initial weather forecast data to obtain the linear regression coefficient information of the multiple initial weather forecast data.

[0025] In this embodiment, the initial weather forecast data dispersion information and average value information corresponding to each weather forecast model information in the historical return data can be fitted and calculated using a linear regression algorithm to obtain the linear regression coefficient corresponding to each model. This coefficient is used to characterize the degree of correlation between dispersion and average value, forming the initial weather forecast data linear regression coefficient information, which corresponds one-to-one with each weather forecast model information.

[0026] Step S202: Determine whether the linear regression coefficient information of the initial weather forecast data is negative; if yes, proceed to step S203; if no, skip the weather forecast model information corresponding to the linear regression coefficient information of the initial weather forecast data.

[0027] In this embodiment, based on historical statistical patterns, when the linear regression coefficient between the dispersion information and the average information of the initial weather forecast data of a certain model is negative, it indicates that the model conforms to the negative correlation relationship of "the greater the dispersion, the lower the average forecast skill", and has the basis for screening high-skill samples; if the linear regression coefficient information of the initial weather forecast data is non-negative, then the model does not currently meet the historical correlation characteristics and is not included in the screening range.

[0028] Step S203: Based on the meteorological forecast model information corresponding to the linear regression coefficient information of the initial meteorological forecast data, obtain multiple filtered intermediate meteorological forecast model information.

[0029] In this embodiment, weather forecast model information with negative linear regression coefficients is marked as intermediate weather forecast model information that meets the screening criteria, forming a set of models to be further processed, so that the corresponding initial weather forecast data can be extracted based on the models in the set.

[0030] Step S204: Generate multiple intermediate weather forecast data based on the initial weather forecast data corresponding to the multiple filtered intermediate weather forecast model information.

[0031] In this embodiment, the initial weather forecast data corresponding to each model is extracted from the filtered intermediate weather forecast model information. These data are used as intermediate weather forecast data to provide a high-skill sample basis for the subsequent generation of target weather forecast data.

[0032] The meteorological forecast data generation method provided in this application provides a method for accurately selecting intermediate meteorological forecast model information that conforms to the negative correlation law and the intermediate meteorological forecast data corresponding to the intermediate meteorological forecast model information by linearly fitting and coefficient discrimination of the dispersion information and average information of the initial meteorological forecast data. This further enhances the dynamic identification capability of high-skill samples and ensures the consistency between intermediate meteorological forecast data and historical statistical laws. As a result, when generating target meteorological forecast data, it can more effectively improve the accuracy and reliability of ensemble average forecast skills and adapt to the needs of real-time rolling updates of meteorological forecasts.

[0033] Figure 3 The flowchart illustrating the implementation of the meteorological forecast data generation method provided in Embodiment 3 of this application is shown. The difference between this method and Embodiment 1 is that step S104 specifically includes: Step S301: Extract time information from multiple intermediate weather forecast data to obtain multiple historical intermediate weather forecast data and multiple current intermediate weather forecast data.

[0034] In this embodiment, time attribute information can be separated from intermediate weather forecast data. Intermediate weather forecast data belonging to the previous reporting time can be marked as historical intermediate weather forecast data, and intermediate weather forecast data belonging to the current reporting time can be marked as current intermediate weather forecast data, thereby realizing the classification and organization of data from different time periods.

[0035] Step S302: Calculate the correlation characterization values ​​of multiple intermediate weather forecast historical data and multiple intermediate weather forecast current data to obtain intermediate weather forecast data correlation information.

[0036] In this embodiment, the correlation coefficient between the current data of the intermediate weather forecast at the current reporting time and the ensemble average of the historical data of the intermediate weather forecast at the previous time within the same forecast period can be calculated. This correlation coefficient can be used as a correlation characterization value to form the correlation information of the intermediate weather forecast data, which is used to measure the consistency of the forecast results between different time periods.

[0037] Step S303: Determine whether the correlation information of the intermediate weather forecast data is greater than the preset correlation threshold of the intermediate weather forecast data; if yes, proceed to step S304; if no, proceed to step S305.

[0038] In this embodiment, the preset correlation threshold for intermediate weather forecast data can be set manually. The calculated correlation information of the intermediate weather forecast data can be compared with the preset correlation threshold. If the correlation information is greater than the threshold, it indicates that the forecast effect of the current intermediate weather forecast data is similar to that of the previous forecast, and they have continuity. If the correlation information is less than the threshold, it indicates that the forecast results of the previous and subsequent forecasts differ significantly, and further processing is required.

[0039] Step S304: Calculate the average value of the current intermediate weather forecast data to generate target weather forecast data.

[0040] In this embodiment, when the correlation information meets the conditions, the arithmetic average of the current intermediate weather forecast data is directly calculated, and the average value is output as the target weather forecast data. Since the obtained target weather forecast data is highly consistent with the historical forecast results, the forecasting technique can be considered reliable.

[0041] Step S305: Generate target weather forecast data based on the multiple initial weather forecast data and intermediate weather forecast data.

[0042] In this embodiment, when the correlation does not meet the conditions, the inter-sample dispersion and inter-model dispersion of the intermediate weather forecast data at the current reporting time can be calculated. At the same time, the corresponding dispersion of the remaining forecast data after removing the intermediate weather forecast data from the initial weather forecast data can be calculated. If the dispersion characteristics of the intermediate weather forecast data are better, that is, the inter-sample dispersion is small and the inter-model dispersion is small, then the average value of the intermediate weather forecast data is used as the target weather forecast data; otherwise, the average value of the remaining forecast data is selected as the target weather forecast data to ensure the accuracy of the final result.

[0043] The meteorological forecast data generation method provided in this application extracts the time information of intermediate meteorological forecast data and calculates the correlation between the time intervals before and after the time intervals. It then combines the dispersion comparison to make the generation decision of the target meteorological forecast data, further enhancing the dynamic adaptability to real-time forecast data. While ensuring the continuity of forecasts, it optimizes the sample set according to the time interval differences, improves the ability of the target meteorological forecast data to represent the differences in the current starting time pattern / sample skill, and thus more accurately improves the reliability of the ensemble average forecast skill, adapting to the needs of complex and ever-changing meteorological forecast scenarios.

[0044] Figure 4 The flowchart illustrating the meteorological forecast data generation method provided in Embodiment 4 of this application is shown. The difference between this method and Embodiment 3 above is that step S305 specifically includes: Step S401: Obtain the dispersion information of the intermediate weather forecast model based on multiple intermediate weather forecast data.

[0045] In this embodiment, the set average of the forecast skills of each model can be calculated based on the weather forecast model information to which each sample in the intermediate weather forecast data belongs, and then the standard deviation of the forecast skills among these models can be obtained. This standard deviation is used as the dispersion information of the intermediate weather forecast models to characterize the degree of dispersion among the models to which the intermediate weather forecast data belongs.

[0046] Step S402: Based on the multiple initial weather forecast data and intermediate weather forecast data, obtain the dispersion information of the remaining weather forecast model.

[0047] In this embodiment, intermediate weather forecast data can be removed from the initial weather forecast data to obtain the remaining forecast data. Based on the weather forecast model information to which each sample in the remaining forecast data belongs, the set average of the forecast skills of each model is calculated, and then the standard deviation of the forecast skills among these models is obtained to form the dispersion information of the remaining weather forecast models, which is used to characterize the degree of dispersion among the models to which the remaining forecast data belongs.

[0048] Step S403: Generate target weather forecast data based on the dispersion information of the intermediate weather forecast model, the dispersion information of the remaining weather forecast model, and the remaining weather forecast data.

[0049] In this embodiment, the dispersion information of intermediate weather forecast models can be compared with that of the remaining weather forecast models. If the dispersion information of the intermediate weather forecast models is less than that of the remaining weather forecast models, it indicates that the dispersion between the models to which the intermediate weather forecast data belongs is smaller and the forecasting skills are more concentrated. In this case, the average value of the intermediate weather forecast data is used as the target weather forecast data. If the dispersion information of the intermediate weather forecast models is not less than that of the remaining weather forecast models, the average value of the remaining weather forecast data is used as the target weather forecast data. The reliability of the target weather forecast data is ensured by comparing the model dispersion information.

[0050] The meteorological forecast data generation method provided in this application focuses on comparing the model dispersion of intermediate meteorological forecast data and remaining forecast data to accurately determine the model dispersion characteristics of the high-skill sample set. When the correlation between forecasts at different times is insufficient, the method optimizes sample selection through quantitative analysis of model dispersion, thereby improving the ability of the target meteorological forecast data to represent differences in model skill. This enhances the accuracy and dynamic adaptability of ensemble average forecast skill, improves the accuracy and effectiveness of meteorological forecasts, and better adapts to the real-time update needs of complex meteorological forecast scenarios.

[0051] Figure 5The flowchart illustrating the implementation of the meteorological forecast data generation method provided in Embodiment 5 of this application is shown. The difference between this method and Embodiment 4 above is that step S401 specifically includes: Step S501: Extract model information from multiple intermediate weather forecast data to obtain multiple intermediate weather forecast data model information.

[0052] In this embodiment, the weather forecast model information corresponding to each data point can be extracted from the intermediate weather forecast data, and the dynamic model to which each intermediate weather forecast data belongs, such as ECMWF, CMA, etc., can be identified, forming intermediate weather forecast data model information that corresponds one-to-one with the intermediate weather forecast data, providing a basis for subsequent model-based classification processing.

[0053] Step S502: Based on the information of multiple intermediate weather forecast data models, classify and process the multiple intermediate weather forecast data to obtain intermediate weather forecast data corresponding to multiple weather models.

[0054] In this embodiment, the intermediate weather forecast data can be grouped and classified according to the weather forecast model to which it belongs, so that each weather model corresponds to a group of intermediate weather forecast data. For example, the intermediate weather forecast data belonging to the ECMWF model can be grouped into one group, and the data belonging to the CMA model can be grouped into another group, thereby realizing the classification and organization of data by model dimension.

[0055] Step S503: Calculate the dispersion of intermediate weather forecast data corresponding to multiple weather models to obtain intermediate weather forecast model dispersion information.

[0056] In this embodiment, the set average of the forecast skills of the intermediate weather forecast data corresponding to each weather model can be calculated, and the standard deviation of the forecast skills between models can be calculated based on the average value of each model. This can be used as the dispersion information of the intermediate weather forecast models, which quantitatively characterizes the degree of dispersion between the models to which the intermediate weather forecast data belongs, and provides a basis for the generation of subsequent target weather forecast data.

[0057] The meteorological forecast data generation method provided in this application can accurately characterize the discrete features of intermediate meteorological forecast data in the model dimension by extracting model information, classifying and calculating the dispersion of intermediate meteorological forecast data. This improves the reliability and robustness of judging the model consistency of high-skill sample sets, enhances the scientific nature of target meteorological forecast data generation, and improves the dynamic adaptability and accuracy of ensemble average forecast skills, so as to better meet the real-time optimization needs of complex meteorological forecast scenarios.

[0058] Figure 6The flowchart illustrating the meteorological forecast data generation method provided in Embodiment Six of this application is shown. The difference between this method and Embodiment Four is that step S402 specifically includes: Step S601: Based on the multiple initial weather forecast data and intermediate weather forecast data, multiple remaining weather forecast data are obtained.

[0059] In this embodiment, the intermediate weather forecast data that has been screened out can be removed from the initial weather forecast data. The remaining weather forecast data is the residual weather forecast data. These data were not included in the screening range of intermediate weather forecast data and their model dispersion characteristics need to be further analyzed.

[0060] Step S602: Extract model information from multiple remaining weather forecast data to obtain multiple remaining weather forecast data model information.

[0061] In this embodiment, the weather forecast model information corresponding to each data point can be extracted from the remaining weather forecast data, the dynamic model to which each remaining weather forecast data belongs can be identified, and the remaining weather forecast data model information corresponding one-to-one with the remaining weather forecast data can be formed, providing a basis for subsequent model-based classification processing.

[0062] Step S603: Based on the information of multiple remaining weather forecast data models, classify and process the multiple remaining weather forecast data to obtain the remaining weather forecast data corresponding to multiple weather models.

[0063] In this embodiment, the remaining weather forecast data can be grouped and classified according to the weather forecast model to which it belongs, so that each weather model corresponds to a group of remaining weather forecast data. For example, the remaining weather forecast data belonging to the ECMWF model can be grouped into one group, and the data belonging to the CMA model can be grouped into another group, thereby realizing the classification and organization of the remaining data according to the model dimension.

[0064] Step S604: Calculate the dispersion of the remaining weather forecast data corresponding to the multiple weather models to obtain the dispersion information of the remaining weather forecast models.

[0065] In this embodiment, the set average of the forecast skills of the remaining weather forecast data corresponding to each weather model can be calculated, and the standard deviation of the forecast skills between models can be calculated based on the average of each model. This can be used as the dispersion information of the remaining weather forecast models, quantitatively characterizing the degree of dispersion between the models to which the remaining weather forecast data belongs, and providing data support for subsequent comparison with the dispersion information of intermediate weather forecast models.

[0066] The meteorological forecast data generation method provided in this application extracts, classifies, and calculates the dispersion of the remaining meteorological forecast data by model information extraction, classification, and dispersion calculation. This accurately characterizes the discrete features of the remaining meteorological forecast data in the model dimension. By comparing the model dispersion with that of intermediate meteorological forecast data, the method accurately judges the model consistency of the high-skill sample set, enhances the scientific nature of the target meteorological forecast data generation, and improves the dynamic adaptability and accuracy of the ensemble average forecast skill, so as to better meet the real-time optimization needs of complex meteorological forecast scenarios.

[0067] Figure 7 The flowchart illustrating the implementation of the meteorological forecast data generation method provided in Embodiment Seven of this application is shown. The difference between this method and Embodiment Four above is that step S403 specifically includes: Step S701: Determine whether the dispersion information of the intermediate weather forecast model is greater than the dispersion information of the remaining weather forecast model; if yes, proceed to step S702; if no, proceed to step S704.

[0068] In this embodiment, by comparing the numerical values ​​of the dispersion information of intermediate weather forecast models with those of the remaining weather forecast models, it is determined whether the dispersion among the models to which the intermediate weather forecast data belongs is higher than that of the remaining forecast data. If the dispersion information of the intermediate weather forecast models is larger, it indicates that the forecast skill differences among the models in the intermediate weather forecast data are more significant, and there may be interference from low-skill models; if the dispersion information of the intermediate weather forecast models is smaller, it indicates that the model consistency of the intermediate weather forecast data is better.

[0069] Step S702: Extract the current time information of multiple remaining weather forecast data to obtain multiple remaining weather forecast current time data.

[0070] In this embodiment, data belonging to the current forecast time can be filtered from the remaining weather forecast data, and historical data from the previous time can be removed to obtain the remaining weather forecast data for the current time. This ensures that the remaining data used in the calculation matches the current forecast time and avoids the time mixing affecting the accuracy of the results.

[0071] Step S703: Calculate the average value of the current time data of the multiple remaining weather forecasts to generate target weather forecast data.

[0072] In this embodiment, when the dispersion information of the intermediate weather forecast model is greater than that of the remaining weather forecast model, it indicates that the dispersion between models in the remaining weather forecast data is smaller and the forecast skills are more concentrated. At this time, the arithmetic mean of the current time data of the remaining weather forecast is performed, and the average value is used as the target weather forecast data to improve the forecast reliability by utilizing the feature of better model consistency in the remaining data.

[0073] Step S704: Calculate the average value of the current intermediate weather forecast data to generate target weather forecast data.

[0074] In this embodiment, when the dispersion information of the intermediate weather forecast model is not greater than that of the remaining weather forecast model, it indicates that the inter-model dispersion of the intermediate weather forecast data is smaller and the forecast skill is more concentrated. The arithmetic mean of the current intermediate weather forecast data is directly calculated and the average value is used as the target weather forecast data to ensure that the model consistency characteristics of the high-skill sample set are fully utilized.

[0075] The meteorological forecast data generation method provided in this application achieves accurate screening and utilization of high-skill sample sets by quantitatively comparing the pattern dispersion of intermediate meteorological forecast data and remaining forecast data, avoiding interference of low-skill models on ensemble averaging results, ensuring that the advantages of high-skill models are reflected, thereby further improving the accuracy and dynamic adaptability of ensemble averaging forecast skills, and better meeting the real-time optimization needs of complex meteorological forecast scenarios.

[0076] Corresponding to the method in the above embodiments, Figure 8 A structural block diagram of a weather forecast data generation device provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown. Figure 8 The meteorological forecast data generation device in the example can be the execution subject of the meteorological forecast data generation method provided in the aforementioned embodiment 1.

[0077] Reference Figure 8 The weather forecast data generation device includes: The initial weather forecast data acquisition module 810 is used to acquire multiple initial weather forecast data corresponding to multiple weather forecast model information; The dispersion and average value calculation module 820 is used to calculate the dispersion information and average value information of multiple initial weather forecast data corresponding to the weather forecast model information, thereby obtaining the dispersion information and average value information of multiple initial weather forecast data; the dispersion information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence; the average value information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence. The intermediate weather forecast data generation module 830 is used to filter and process multiple initial weather forecast data based on the dispersion information and the average value information of multiple initial weather forecast data to generate multiple intermediate weather forecast data. The target weather forecast data generation module 840 is used to generate target weather forecast data based on multiple intermediate weather forecast data.

[0078] The process by which each module in the meteorological forecast data generation device provided in this application implements its respective function can be found in the foregoing. Figure 1 The description of Embodiment 1 shown will not be repeated here.

[0079] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0080] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0081] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0082] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0083] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first," "second," etc., are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. For example, a first table may be named a second table, and similarly, a second table may be named a first table, without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0084] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0085] The weather forecast data generation method provided in this application embodiment can be applied to terminal devices such as mobile phones, tablets, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). This application embodiment does not impose any restrictions on the specific type of terminal device.

[0086] For example, the terminal device may be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a set-top box (STB), customer premises equipment (CPE), and / or other devices used for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved Public Land Mobile Network (PLMN) networks.

[0087] As an example and not a limitation, when the terminal device is a wearable device, the term "wearable device" can also refer to any device that utilizes wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices worn directly on the body or integrated into a user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large sizes, and the ability to perform complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those focused on a specific application function that require interaction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0088] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 (Only one is shown in the image) A memory 91 stores a computer program 92 that can run on the processor 90. When the processor 90 executes the computer program 92, it implements the steps in the various weather forecast data generation method embodiments described above, for example... Figure 1 Steps S101 to S104 are shown. Alternatively, when the processor 90 executes the computer program 92, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 8 The functions of modules 810 to 840 are shown.

[0089] The terminal device 9 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will understand that... Figure 9 This is merely an example of terminal device 9 and does not constitute a limitation on terminal device 9. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmission devices, network access devices, buses, etc.

[0090] The processor 90 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0091] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device 9. Furthermore, the memory 91 may include both internal and external storage units of the terminal device 9. The memory 91 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 91 can also be used to temporarily store data that has been sent or will be sent.

[0092] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0093] This application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, it causes the terminal device to implement the steps in any of the above method embodiments.

[0094] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0095] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0096] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0097] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0098] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for generating weather forecast data, characterized in that, include: Acquire multiple initial weather forecast data corresponding to multiple weather forecast models; Calculate the dispersion information and average value information of multiple initial weather forecast data corresponding to the weather forecast model information to obtain the dispersion information and average value information of multiple initial weather forecast data; The initial weather forecast data dispersion information and the weather forecast model information are in one-to-one correspondence; the initial weather forecast data average value information and the weather forecast model information are in one-to-one correspondence. Based on the dispersion information and the average value information of the initial weather forecast data, the initial weather forecast data are filtered to generate multiple intermediate weather forecast data. Target weather forecast data is generated based on multiple intermediate weather forecast data.

2. The meteorological forecast data generation method as described in claim 1, characterized in that, The step of filtering and processing multiple initial weather forecast data based on the dispersion information and average value information of multiple initial weather forecast data to generate multiple intermediate weather forecast data specifically includes: Linear fitting is performed on the dispersion information and the average value information of the initial weather forecast data to obtain the linear regression coefficient information of the initial weather forecast data. When the linear regression coefficient information of the initial weather forecast data is negative, multiple filtered intermediate weather forecast model information are obtained based on the weather forecast model information corresponding to the linear regression coefficient information of the initial weather forecast data. Multiple intermediate weather forecast data are generated based on the initial weather forecast data corresponding to the multiple filtered intermediate weather forecast model information.

3. The meteorological forecast data generation method as described in claim 1, characterized in that, The step of generating target weather forecast data based on multiple intermediate weather forecast data specifically includes: Time information is extracted from multiple intermediate weather forecast data to obtain multiple historical intermediate weather forecast data and multiple current intermediate weather forecast data. Calculate the correlation characterization values ​​of multiple historical intermediate weather forecast data and multiple current intermediate weather forecast data to obtain intermediate weather forecast data correlation information; Determine whether the correlation information of the intermediate weather forecast data is greater than a preset correlation threshold for intermediate weather forecast data; If so, calculate the average value of the current intermediate weather forecast data to generate the target weather forecast data; If not, then target weather forecast data is generated based on the multiple initial weather forecast data and intermediate weather forecast data.

4. The meteorological forecast data generation method as described in claim 3, characterized in that, The step of generating target weather forecast data based on multiple initial weather forecast data and intermediate weather forecast data specifically includes: Based on multiple intermediate weather forecast data, the dispersion information of the intermediate weather forecast model is obtained; Based on multiple initial weather forecast data and intermediate weather forecast data, the dispersion information of the remaining weather forecast model is obtained; Target weather forecast data is generated based on the dispersion information of the intermediate weather forecast model, the dispersion information of the remaining weather forecast model, and the remaining weather forecast data.

5. The meteorological forecast data generation method as described in claim 4, characterized in that, The step of obtaining the dispersion information of the intermediate weather forecast model based on multiple intermediate weather forecast data specifically includes: Model information is extracted from multiple intermediate weather forecast data to obtain multiple intermediate weather forecast data model information; Based on the information of multiple intermediate weather forecast data models, the multiple intermediate weather forecast data are classified and processed to obtain intermediate weather forecast data corresponding to multiple weather models. The dispersion of intermediate weather forecast data corresponding to multiple weather models is calculated to obtain the dispersion information of intermediate weather forecast models.

6. The meteorological forecast data generation method as described in claim 4, characterized in that, The step of obtaining the dispersion information of the remaining weather forecast model based on multiple initial weather forecast data and intermediate weather forecast data specifically includes: Based on the initial weather forecast data and intermediate weather forecast data, multiple remaining weather forecast data are obtained; Model information is extracted from multiple remaining weather forecast data to obtain multiple remaining weather forecast data model information; Based on the information of multiple remaining weather forecast data models, the multiple remaining weather forecast data are classified and processed to obtain the remaining weather forecast data corresponding to multiple weather models; The dispersion of the remaining weather forecast data corresponding to multiple weather models is calculated to obtain the dispersion information of the remaining weather forecast models.

7. The meteorological forecast data generation method as described in claim 4, characterized in that, The step of generating target weather forecast data based on the dispersion information of the intermediate weather forecast model, the dispersion information of the remaining weather forecast model, and the remaining weather forecast data specifically includes: Determine whether the dispersion information of the intermediate weather forecast model is greater than the dispersion information of the remaining weather forecast model; If so, extract the current time information of multiple remaining weather forecast data to obtain multiple remaining weather forecast current time data; Calculate the average value of the current time data of multiple remaining weather forecasts to generate target weather forecast data; If not, the average value of the current intermediate weather forecast data is calculated to generate the target weather forecast data.

8. A weather forecast data generation device, characterized in that, include: The initial weather forecast data acquisition module is used to acquire multiple initial weather forecast data corresponding to multiple weather forecast model information; The dispersion and average value calculation module is used to calculate the dispersion and average value information of multiple initial weather forecast data corresponding to the weather forecast model information, thereby obtaining the dispersion information and average value information of multiple initial weather forecast data; the dispersion information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence; the average value information of the initial weather forecast data and the weather forecast model information are in one-to-one correspondence. The intermediate weather forecast data generation module is used to filter and process multiple initial weather forecast data based on the dispersion information and the average value information of multiple initial weather forecast data to generate multiple intermediate weather forecast data. The target weather forecast data generation module is used to generate target weather forecast data based on multiple intermediate weather forecast data.

9. A terminal device, characterized in that, The terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images