Automatic matching evaluation method and system based on meteorological prediction and live data

Abstract

The invention relates to the technical field of weather forecast element forecast, in particular to an automatic matching evaluation method and system based on weather forecast and live data, and the collection and integration of weather data, the processing and interpolation of the weather data and the generation of a data set are the basis of automatic matching and evaluation. In the process, the prediction precision of the meteorological elements can be effectively analyzed by setting indexes of the evaluation model; according to the method, the matching and evaluation work of WRF prediction meteorological elements and live data is automatically realized by utilizing computer deployment of a Shell script and a Python language, so that the labor cost is reduced, the development of a meteorological large model is promoted, reliable information support is provided for all walks of life, and the method has important practical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological forecast element forecasting, and in particular to an automatic matching evaluation method and system based on meteorological forecast and actual data. Background Art

[0002] The automated matching evaluation of meteorological forecasts and actual data is an important task in modern meteorological science, which aims to improve the accuracy and reliability of meteorological forecast models. By automatically comparing and analyzing forecast data with actual observation data, the sources of errors and performance advantages and disadvantages in the forecast model can be identified. This evaluation method can not only quantitatively analyze forecast errors and then optimize and correct forecast models, but also provide key support for many fields such as agriculture, aviation, navigation, energy management and emergency response. Accurate meteorological forecasts are crucial for decision-making and planning in these fields. For example, farmers need accurate rainfall forecasts to arrange agricultural activities, airlines need reliable weather forecasts to plan routes, and governments and emergency departments rely on accurate meteorological information to formulate disaster response measures. Automated matching evaluation can quickly provide forecast accuracy information, enabling decision makers to make scientific and reasonable decisions based on the latest evaluation results, optimize resource allocation, and reduce losses and risks. Therefore, the automated matching evaluation of meteorological forecasts and actual data not only promotes the development and improvement of meteorological models, but also provides reliable information support for all walks of life, and has important practical application value. Summary of the invention

[0003] In view of the above problems existing in the prior art, the present invention is proposed.

[0004] Therefore, the technical problem to be solved by the present invention is: to overcome the shortcomings of the prior art and provide an automated matching and evaluation technical method based on meteorological forecasts and actual data, which not only promotes the development and improvement of meteorological models, but also provides reliable information support for all walks of life and has important practical application value.

[0005] To solve the above technical problems, the present invention provides the following technical solution, an automated matching and evaluation method based on meteorological forecasts and actual data, comprising: collecting meteorological data to obtain primary data; processing the primary data to obtain secondary data; using an evaluation model to perform matching and evaluation on the secondary data; and setting indicators of the evaluation model.

[0006] As a preferred solution of the automatic matching evaluation method based on meteorological forecast and actual data described in the present invention, the collection of meteorological data includes systematic collection of meteorological data and effective integration of the data.

[0007] As a preferred solution of the automatic matching evaluation method based on meteorological forecast and actual data described in the present invention, the processing of primary data includes systematically processing the primary data to obtain secondary data.

[0008] As a preferred solution of the automated matching and evaluation method based on meteorological forecasts and actual data described in the present invention, the matching and evaluation of the secondary data includes systematically comparing and analyzing the meteorological data through a programmed method to evaluate the accuracy and reliability of the data.

[0009] As a preferred solution of the automatic matching evaluation method based on meteorological forecast and actual data described in the present invention, the indicators for setting the evaluation model include formulating quantitative standards and parameters to measure and evaluate the performance of the model during the meteorological data evaluation process.

[0010] As a preferred solution of the automatic matching evaluation method based on meteorological forecast and actual data described in the present invention, wherein: the primary data includes actual meteorological data and forecast data of the primary model;

[0011] The processing of the primary data also includes interpolation processing of the primary data, that is, processing the primary data by using an interpolation technique.

[0012] As a preferred solution of the automatic matching evaluation method based on meteorological forecast and actual data described in the present invention, wherein: the secondary data, a set consisting of meteorological observation data points and forecast data points, i.e., a data set, specifically includes actual observation data and primary model forecast data in the primary data.

[0013] Another object of the present invention is to provide an automated matching and evaluation system based on meteorological forecasts and actual data to improve the efficiency and accuracy of meteorological data processing, thereby providing more reliable support and reference for the optimization of meteorological forecast models; this system will realize real-time matching and evaluation of data, helping related industries to make more scientific decisions.

[0014] To solve the above technical problems, the present invention provides the following technical solutions: an automated matching and evaluation system based on meteorological forecast and actual data, comprising: a data collection module, a data processing module, a matching evaluation module, an indicator setting module and a result analysis module;

[0015] The data collection module collects meteorological data to obtain primary data;

[0016] The data processing module processes the primary data to obtain the secondary data;

[0017] The matching evaluation module uses the evaluation model to perform matching evaluation on the secondary data;

[0018] The indicator setting module sets the indicators of the evaluation model.

[0019] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the above-mentioned automatic matching evaluation method based on meteorological forecast and actual data when executing the computer program.

[0020] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the automatic matching evaluation method based on meteorological forecasts and actual data as described above are implemented.

[0021] The beneficial effects of the present invention are as follows: by using shell scripts and Python language computer deployment, the matching and evaluation of WRF predicted meteorological elements and actual data are automatically realized, which reduces a lot of manpower costs. It not only promotes the development and improvement of large meteorological models, but also provides reliable information support for all walks of life, and has important practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0023] Figure 1 A flowchart of an automated matching evaluation method based on weather forecasts and actual data provided by one embodiment of the present invention.

[0024] Figure 2 A forecast result accuracy analysis index diagram of an automated matching evaluation method based on meteorological forecasts and actual data provided by one embodiment of the present invention.

[0025] Figure 3 A schematic diagram of bilinear interpolation of an automatic matching evaluation method based on meteorological forecast and actual data provided by one embodiment of the present invention.

[0026] Figure 4 A schematic diagram of temperature factor evaluation based on an automated matching evaluation method of meteorological forecasts and actual data provided by one embodiment of the present invention.

[0027] Figure 5 A schematic diagram of wind speed factor evaluation based on an automated matching evaluation method of meteorological forecasts and actual data provided by one embodiment of the present invention.

[0028] Figure 6A schematic diagram of relative humidity factor evaluation based on an automated matching evaluation method of meteorological forecasts and actual data provided by one embodiment of the present invention.

[0029] Figure 7 A schematic diagram of precipitation factor assessment based on an automated matching assessment method of meteorological forecasts and actual data provided by one embodiment of the present invention.

[0030] Figure 8 A schematic diagram of ground pressure factor assessment based on an automated matching assessment method of meteorological forecasts and actual data provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0032] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides an automatic matching evaluation method based on meteorological forecast and actual data, including:

[0033] S1: Collect meteorological data and obtain primary data.

[0034] It should be noted that the collection of meteorological data includes the systematic collection of meteorological data and the effective integration of data, among which the first-level data includes the actual meteorological data and the forecast data of the first-level model.

[0035] Further, such as Figure 1 As shown in Section 101, collect real-time data: the real-time observation data product is produced by the real-time grid product of the National Meteorological Information Center of the China Meteorological Administration. The data is a fusion analysis product of equal longitude and latitude grids covering the assessment area. The data spatial resolution is 0.03°×0.03°, and the temporal resolution is 1 hour, including five elements: 2m temperature, 2m relative humidity, 10m wind speed, ground pressure, and precipitation. This dataset uses multi-source ground and satellite observation data, and is developed using multi-grid variational assimilation (STMAS), physical inversion, terrain correction and other technologies. The quality in China is better than similar international products, and the temporal and spatial resolution is higher. Select real-time data within the grid range.

[0036] Furthermore, Figure 1As shown in the 102 part of the figure, the prediction data of the first-level model are collected: the NCEP / GFS forecast field data with a daily data resolution of 0.25°×0.25°, a start time of 18:00 UTC, a forecast every 3 hours, and a total of 102 hours of forecast time are obtained as the initial field and lateral boundary conditions of the first-level model; the static surface data such as terrain, soil data, vegetation coverage, etc. with a resolution of 15s (about 500m) provided by the MODIS satellite are obtained; the number of grids is 600×500 and 967×535 respectively, the horizontal grid resolution is 9km and 3km respectively, and the grid center point WRF grid setting is combined with the name " CONUS” parameterization scheme: the microphysics scheme is the Thompson scheme, the cumulus parameterization scheme is the Tiedtke scheme, the long-wave and short-wave radiation schemes are both RRTMG schemes, the boundary layer and near-surface parameterization schemes are both MYJ schemes, and the pavement process scheme uses the Noah pavement process scheme to generate the WRFOUT numerical weather forecast file (including temperature, relative humidity, precipitation, air pressure, 10m wind speed, 10m wind direction, 2m dew point temperature, 10m meridional wind, 10m zonal wind, ice thickness and other meteorological elements). The original data has a time resolution of 1h, contains a variety of meteorological elements, and iso-kilometer grid data with a grid interval of 3km.

[0037] In the embodiment of the present application, the first-level data is the real-time data of the meteorology and the forecast data of the first-level model. The real-time data is generated by the real-time grid product of the National Meteorological Information Center of the China Meteorological Administration. The data covers the evaluation area, with a spatial resolution of 0.03°×0.03° and a temporal resolution of 1 hour. It includes five elements: 2m temperature, 2m relative humidity, 10m wind speed, ground pressure, and flood. It is generated by using multi-source ground, satellite and other observation data, and adopts multi-grid variational assimilation (STMAS), physical inversion, terrain correction and other technologies, with high spatiotemporal resolution and data quality; the forecast data of the first-level model comes from NCEP / GFS forecast field data with a resolution of 0.25°×0.25°, forecasts every 3 hours, a total forecast time of 102 hours, and the start time is 18:00 Universal Time; combined with the surface static data based on the MODIS satellite, including terrain, soil and vegetation coverage data with a resolution of 15 seconds, numerical weather forecasting is performed through the WRF model. The model uses two layers of grid nesting with horizontal resolutions of 9km and 3km respectively. Combined with the "CONUS" parameterization scheme, it generates WRFOUT files containing meteorological elements such as temperature, relative humidity, precipitation pressure, 10m wind speed and direction, with a time resolution of 1 hour and a grid interval of 3km.

[0038] In an optional embodiment, the primary data may also be obtained through other means, such as using mobile weather stations and drone technology for real-time data collection; the flexibility of these mobile devices allows them to move freely within a specific area and collect meteorological data, such as key elements such as temperature, humidity, wind speed and air pressure, in different geographical locations and environmental conditions;

[0039] Mobile weather stations are usually equipped with high-precision sensors and data transmission equipment, which can upload the collected data to the central database in real time to ensure the timeliness and accuracy of the data. In addition, primary data can also include other forms of environmental data, such as air quality monitoring data, ground humidity, soil temperature, and vegetation coverage. These additional data can provide more contextual information for meteorological forecasting models. For example, air quality monitoring data can help analyze the impact of pollution on the climate, and soil moisture and temperature data can provide support for agricultural decision-making, enabling farmers to better plan planting and irrigation. This integration of environmental data not only enhances the reliability of meteorological forecasts, but also provides a scientific basis for multiple fields such as agriculture, ecological protection and urban planning. Combined with drone technology, using its high-altitude perspective, more abundant meteorological data can be obtained, especially in large-scale monitoring of precipitation, wind speed changes and cloud dynamics. These dynamically collected data can not only provide more detailed spatial distribution information, but also provide important references for the verification and optimization of meteorological models, which helps to improve the accuracy of meteorological forecasts.

[0040] In an optional embodiment, the primary data may also be collected through other means, such as social media and public participation platforms. This method takes advantage of the rapid and extensive dissemination of information in today's society, encourages the public to report local weather conditions on social platforms, share weather-related photos, videos and short weather reports, and associate them with specific locations through geotags;

[0041] This real-time data from non-professionals can provide a new perspective for meteorological data, especially when extreme weather events occur, spontaneous reports from the public can quickly supplement the deficiencies in official data and enhance the ability to respond to climate change; further, combined with big data technology, these environmental data can be integrated from multiple sources to form a comprehensive meteorological database; this database can be deeply analyzed through machine learning and artificial intelligence technology to identify the correlation between different meteorological elements, helping scientists and decision makers to deeply understand the complex mechanisms of climate change; in addition, combined with satellite remote sensing technology, primary data can also be expanded to global meteorological data collection; satellites can provide large-scale meteorological observation data, including cloud cover, ocean temperature, land vegetation changes, etc., which are crucial for studying the long-term trends of climate change; combining these satellite data with ground observation data can form a more comprehensive and accurate meteorological model, providing strong data support for responding to climate change, natural disasters and other environmental issues; data collected through social media provides a diversified source of information for the input of meteorological models.

[0042] In the embodiment of the present application, the first-level mode is the WRF mode, i.e. the Weather Research and Forecasting mode; the WRF mode uses NCEP / GFS forecast field data as the initial field and lateral boundary conditions, with a resolution of 0.25°x0.25°, a forecast every 3 hours, a total forecast time of 102 hours, and the start time is 18:00 Universal Time. This model combines high-resolution static surface data based on the MODIS satellite, including terrain, soil and vegetation cover data with a resolution of 15 seconds (about 500 meters), and adopts a two-layer grid nesting with horizontal resolutions of 9km and 3km respectively; the WRF model uses the "CONUS" parameterization scheme, the microphysics scheme is the Thompson scheme, the cumulus parameterization scheme is the Tiedtke scheme, the long and short wave radiation scheme is the RRTMG scheme, the boundary layer and near-surface parameterization scheme is the MYJ scheme, and the ground process uses the Noah road process scheme; the WRFOUT file generated by this model contains meteorological elements such as temperature, relative humidity, precipitation, air pressure, 10m wind speed and wind direction, with a time resolution of 1 hour and a grid interval of 3km, providing refined numerical weather forecasts.

[0043] In an optional embodiment, the first-level mode can also be implemented in other ways, such as using the combined prediction of an integrated meteorological model. The integrated meteorological model can provide more accurate weather forecasts by combining the advantages of multiple meteorological forecast models. This method not only relies on the output of a single model, but also integrates the forecast results of multiple models. The forecast values ​​optimized by weighted average or other algorithms can be combined with the outputs of numerical weather prediction (NWP) models, statistical models and machine learning models to form an integrated forecast framework. In this framework, the strengths of each model are effectively utilized to form a more reliable meteorological forecast. This method is particularly effective when facing complex weather systems, and can significantly reduce forecast errors and improve the reliability and timeliness of forecasts.

[0044] In addition, by analyzing historical data, these models can also be trained for meteorological characteristics of different geographical regions and seasons to further enhance their prediction capabilities. On the other hand, the first-level model can also be implemented through real-time data assimilation technology. This method uses observational data to continuously correct and update the state of the prediction model, making the model output closer to actual weather conditions, balloon soundings, and automatic weather station data, ensuring that the model can respond more quickly to actual weather conditions. Real-time data assimilation can integrate observational data from different sources, including ground meteorological stations and satellite remote sensing of atmospheric changes, effectively improving the accuracy of short-term weather forecasts. When abnormal meteorological phenomena (such as heavy rainfall or sudden temperature changes) occur, the rapid absorption of new observational data allows the model to adjust in a short period of time, thereby providing more timely alarms and forecasts. At the same time, this method can also optimize the initial conditions of the model and reduce forecast errors caused by inaccurate initial conditions.

[0045] In an optional embodiment, the first-level model can also be implemented in other ways. For example, a regional model is used to make weather forecasts specifically for a specific geographical area. Taking into account the unique climate characteristics and terrain conditions of the area, the regional climate model can simulate the impact of complex terrain on meteorological elements and provide more detailed weather forecasts, which is of great significance in the fields of agriculture, ecological protection and urban planning. Combined with satellite remote sensing technology, the implementation of the first-level model can also be extended to global weather forecasts. Satellite remote sensing technology can provide a wide range of meteorological observation data, including cloud distribution, ocean temperature and land vegetation changes, which is crucial for long-term research on climate change. Combining satellite data with ground observation data can form a more comprehensive meteorological database and optimize the parameter settings and prediction results of the meteorological model. In addition, satellite remote sensing technology can also monitor meteorological changes in real time, providing important support for short-term weather forecasts.

[0046] Example 2, reference Figure 1-Figure 3 , is an embodiment of the present invention, which provides an automatic matching evaluation method based on meteorological forecast and actual data, including:

[0047] S2: Process the primary data to obtain the secondary data.

[0048] It should be noted that processing the first-level data includes systematically processing the first-level data to obtain the second-level data; wherein, processing the first-level data also includes interpolation processing of the first-level data, that is, processing the first-level data through interpolation technology; and the second-level data is a collection of meteorological observation data points and forecast data points, that is, a data set, which specifically includes the actual observation data in the first-level data and the first-level model forecast data.

[0049] Further, such as Figure 1 As shown in Section 103, the interpolation technology selected is bilinear interpolation processing. The bilinear interpolation processing is to cover the assessment area, with a resolution of 0.03°×0.03° and 1 hour, and is tested on equal longitude and latitude grid products including 2m temperature, 2m relative humidity, 10m wind speed, ground pressure, and precipitation.

[0050] Furthermore, Figure 3 The bilinear interpolation shown in Figure 1 represents the linear interpolation extension of the interpolation function containing two variables. The core idea of ​​this method is to perform linear interpolation in two directions respectively. Figure 3 As shown in the figure, it is a schematic diagram of bilinear interpolation. In order to obtain the value of the unknown function f at point p = (x, y), it is assumed that the known function f is at Q 11 =(x1,y1),Q 12 =(x1,y2),Q 21 =(x2,y1), and Q 22 =(x2,y2), the values ​​at four points;

[0051] First, perform linear interpolation in the direction to obtain equations (1) and (2), then perform linear interpolation in the y direction to obtain equation (3), so that the result of the function f(x, y) is obtained, as shown in equation (4);

[0052] Formulas (1)-(4) are as follows:

[0053]

[0054] S3: Use the evaluation model to perform matching evaluation on the secondary data.

[0055] It should be noted that the matching evaluation of secondary data includes systematic comparison and analysis of meteorological data through programmatic methods to evaluate the accuracy and reliability of the data.

[0056] Further, such as Figure 1As shown in part 104, the first-level pattern prediction data and the actual data set are matched in time and space, and the prediction data and the actual data are matched in real time using automated shell scripts and Python language throughout the process.

[0057] Specifically, automated Shell scripts are mainly used to automate system management tasks. Through Shell scripts, data files are called regularly to obtain real-time weather forecast data and actual data. Python scripts are used to convert and standardize the acquired data to ensure that the two are structurally compatible. Logic is implemented. Through Python programming algorithms, actual data and forecast data are matched in time and space to calculate various meteorological elements. The matching results are stored in a database or file. Shell scripts can be used to execute this process on a scheduled basis.

[0058] S4: Set the metrics for evaluating the model.

[0059] It should be noted that setting the indicators of the evaluation model includes formulating quantitative standards and parameters to measure and evaluate the performance of the model during the meteorological data evaluation process.

[0060] Further, such as Figure 1 As shown in Part 105, the 2m air temperature, 2m relative humidity, 10m wind speed, ground pressure and precipitation are tested and evaluated according to the indicators, where the precipitation TS test threshold is 0.1mm / h, all elements are in the same test range, and the test time resolution is 1 hour.

[0061] Furthermore, Figure 2 As shown, wind speed assessment index (FA): the deviation of wind speed prediction is calculated by formula, which is applicable to the scene with wind speed difference not exceeding 1m / s; precipitation assessment index (TS, ETS, ACC): used to measure the accuracy of prediction; evaluate the fairness of precipitation prediction; and show the accuracy and deviation of prediction; error analysis index (MAE, MAPE, RMSE): respectively represent the average absolute error between the predicted value and the actual value; relative error expressed as a percentage; and root mean square error, reflecting the standard degree of prediction error. Secondly, the observation equation is expressed as:

[0062] Dr=(N a +N c )*(N a +N b ) / (N a +N b +N c +N d ) (5)

[0063] Among them, Figure 2 The formula shown in the figure and formula (5), φ irepresents the difference between the ith predicted value and the observed value, represents the i-th predicted value, y i represents the i-th observation value, n represents the total number of time samples, represents the average of the observed values, N a Indicates the number of correct forecast stations (times), N b Indicates the number of empty station reports (times), N c Indicates the number of missed reporting stations (times), N d Indicates the number of correct stations (times) where both the forecast and the actual situation do not meet the threshold.

[0064] The above is a schematic scheme of an automatic matching evaluation method based on weather forecast and live data in this embodiment. It should be noted that the technical scheme of the system based on the automatic matching evaluation method of weather forecast and live data and the technical scheme of the automatic matching evaluation method based on weather forecast and live data mentioned above belong to the same concept, and the details of the technical scheme of the automatic matching evaluation system based on weather forecast and live data not described in detail in this embodiment can all be referred to the description of the technical scheme of the automatic matching evaluation method based on weather forecast and live data mentioned above.

[0065] Example 3, reference Figure 4-Figure 8 ,An embodiment of the present invention provides an automated matching evaluation method based on ,meteorological forecast and actual data. In order to verify the beneficial effects of the present ,technology, it is scientifically demonstrated through economic benefit calculation and simulation ,experiments.

[0066] The specific steps are as follows:

[0067] Step A: For the most recent icing process: from 08:00 on December 28, 2022 (Beijing Time) to 08:00 on January 4, 2022 (Beijing Time), collect the first-level model prediction data and the actual data set.

[0068] Step B: Temporally and spatially match the first-level model prediction data and the actual data set, using automated shell scripts and Python language to match the prediction data and the actual data in real time.

[0069] Step C: According to the indicators, the 2m temperature, 2m relative humidity, 10m wind speed, ground pressure and precipitation are tested and evaluated, and the precipitation TS test threshold is 0.1mm / h. All elements are tested in the range of 18-29.94°N, 97.03-117.94°E, and the test time resolution is 1 hour.

[0070] Among them, the temperature factor evaluation is as follows Figure 4 As shown in Figure 2, the wind speed factor is evaluated as follows: Figure 5 As shown, the relative humidity factor is evaluated as Figure 6 As shown in Figure 2, the precipitation factor assessment is as follows: Figure 7 As shown in Figure 2, the ground pressure element is evaluated as follows: Figure 8 shown.

[0071] Therefore, this method can automatically realize the matching and evaluation of WRF predicted meteorological elements and actual data, reducing a lot of manpower costs. It not only promotes the development and improvement of large meteorological models, but also provides reliable information support for all walks of life, and has important practical application value.

[0072] Embodiment 4 is an embodiment of the present invention, which provides an automatic matching evaluation system based on meteorological forecast and real-time data, including: a data collection module, a data processing module, a matching evaluation module, an indicator setting module and a result analysis module;

[0073] The data collection module collects meteorological data to obtain primary data;

[0074] The data processing module processes the primary data to obtain the secondary data;

[0075] The matching evaluation module uses the evaluation model to perform matching evaluation on the secondary data;

[0076] The indicator setting module sets the indicators of the evaluation model.

[0077] This embodiment further provides a computing device, which is applicable to the case of an automated matching evaluation method based on meteorological forecasts and actual data, including:

[0078] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the automatic matching evaluation method based on meteorological forecast and actual data proposed in the above embodiment.

[0079] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the automatic matching evaluation method based on meteorological forecast and actual data proposed in the above embodiment is implemented.

[0080] The storage medium proposed in this embodiment and the automatic matching evaluation method based on meteorological forecast and actual data proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0081] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0082] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0083] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automated matching evaluation method based on meteorological forecast and actual data, characterized in that: include: Collect meteorological data and obtain primary data; Process the primary data to obtain the secondary data; Use the evaluation model to conduct matching evaluation on the secondary data; Set the metric to evaluate the model.

2. The automatic matching evaluation method based on weather forecast and actual data according to claim 1, characterized in that: The collecting of meteorological data includes systematically collecting meteorological data and effectively integrating the data.

3. The automatic matching evaluation method based on weather forecast and actual data according to claim 2, characterized in that: The processing of the primary data includes systematically processing the primary data to obtain secondary data.

4. The automatic matching evaluation method based on weather forecast and actual data according to claim 3, characterized in that: The matching evaluation of the secondary data includes systematically comparing and analyzing the meteorological data through a programmed method to evaluate the accuracy and reliability of the data.

5. The automatic matching evaluation method based on weather forecast and actual data according to claim 4, characterized in that: The indicators for setting the evaluation model include formulating quantitative standards and parameters to measure and evaluate the performance of the model during the meteorological data evaluation process.

6. The automatic matching evaluation method based on weather forecast and actual data according to claim 5, characterized in that: The primary data includes real-time meteorological data and forecast data of the primary model; The processing of the primary data also includes interpolation processing of the primary data, that is, processing the primary data by using an interpolation technique.

7. The automatic matching evaluation method based on weather forecast and actual data according to claim 6, characterized in that: The secondary data, a collection of meteorological observation data points and forecast data points, namely a data set, specifically includes the actual observation data and the primary model forecast data in the primary data.

8. A system for automatic matching evaluation based on weather forecast and real-time data according to any one of claims 1 to 7, characterized in that: include: Data collection module, data processing module, matching evaluation module, indicator setting module and result analysis module; The data collection module collects meteorological data to obtain primary data; The data processing module processes the primary data to obtain the secondary data; The matching evaluation module uses the evaluation model to perform matching evaluation on the secondary data; The indicator setting module sets the indicators of the evaluation model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automatic matching evaluation method based on meteorological forecast and actual data according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automatic matching evaluation method based on meteorological forecast and actual data according to any one of claims 1 to 7 are implemented.

Images