Meteorological data calibration method, device and equipment and meteorological station

Abstract

The invention discloses a meteorological data calibration method, device and equipment and a meteorological station, and relates to the field of meteorological calibration. The method comprises the following steps: acquiring meteorological time sequence data of a standard meteorological station and an uncalibrated meteorological station at the same observation point in different regions; the standard meteorological station is a meteorological station with corrected meteorological data; extracting time features of the meteorological time sequence data of the uncalibrated meteorological station; forming a meteorological data set by taking the meteorological time sequence data of the uncalibrated meteorological station and the extracted time features as input data and the meteorological time sequence data of the standard meteorological station as labels; training a neural network model by adopting the meteorological data set to obtain a meteorological data calibration model; and inputting the meteorological time sequence data of the to-be-calibrated meteorological station and the extracted time features into the meteorological data calibration model, and outputting the calibrated meteorological time sequence data of the to-be-calibrated meteorological station. According to the method, the meteorological data calibration complexity can be simplified, and universality is achieved.

Description

Technical Field

[0001] The present application relates to the field of meteorological calibration, and in particular to a meteorological data calibration method, device, equipment and meteorological station. Background Art

[0002] Weather stations are used to monitor meteorological and environmental data in real time. The data of traditional multi-factor weather stations are affected by many factors, including their structure, material, and sensor accuracy. On the one hand, the ventilation of the structure, the thermal insulation performance of the material, and the thermal conductivity have a great influence on the accuracy of temperature and humidity. On the other hand, the drift and deviation accuracy of the sensor will also affect the accuracy and stability of the data. Therefore, it is usually necessary to calibrate the meteorological data.

[0003] Traditional weather station data calibration involves a series of complex calibration tasks and lacks versatility. First, sensor calibration needs to be considered, covering zero point and span calibration to ensure that the sensor output is consistent with the standard value. The second is environmental calibration, considering the impact of environmental factors such as temperature, humidity, and air pressure on the data, and establishing a calibration model to eliminate these errors. Compare standard reference data to verify and correct weather station data. Finally, a calibration curve or model needs to be established to help calibrate future data more accurately. Different weather station structures and materials require different calibration schemes. Summary of the invention

[0004] The purpose of this application is to provide a meteorological data calibration method, device, equipment and meteorological station, which can simplify the complexity of meteorological data calibration and have universality.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a meteorological data calibration method, comprising: obtaining meteorological time series data of standard meteorological stations and uncalibrated meteorological stations in different regions at the same observation point; the standard meteorological station is a meteorological station with calibrated meteorological data; extracting the time features of the meteorological time series data of the uncalibrated meteorological station; using the meteorological time series data of the uncalibrated meteorological station and the extracted time features as input data, and the meteorological time series data of the standard meteorological station as a label to form a meteorological data set; using the meteorological data set to train a neural network model to obtain a meteorological data calibration model; inputting the meteorological time series data of the meteorological station to be calibrated and the extracted time features into the meteorological data calibration model, and outputting the calibrated meteorological time series data of the meteorological station to be calibrated.

[0007] In a second aspect, the present application provides a meteorological data calibration device, including: a data collection module, a feature extraction module, a data set construction module, a training module and an application module.

[0008] A data collection module is used to obtain meteorological time series data of standard meteorological stations and uncalibrated meteorological stations in different regions at the same observation point; the standard meteorological station is a meteorological station with calibrated meteorological data; a feature extraction module is used to extract the time features of the meteorological time series data of the uncalibrated meteorological station; a data set construction module is used to use the meteorological time series data of the uncalibrated meteorological station and the extracted time features as input data, and the meteorological time series data of the standard meteorological station as a label to construct a meteorological data set; a training module is used to use the meteorological data set to train a neural network model to obtain a meteorological data calibration model; an application module is used to input the meteorological time series data of the meteorological station to be calibrated and the extracted time features into the meteorological data calibration model, and output the calibrated meteorological time series data of the meteorological station to be calibrated.

[0009] In a third aspect, the present application provides a weather station, which uses the above-mentioned meteorological data calibration method to calibrate meteorological time series data.

[0010] In a fourth aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the meteorological data calibration methods described above.

[0011] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0012] The present application provides a meteorological data calibration method, device, equipment and meteorological station. Through the training and application of a meteorological data calibration model, which is a machine training model, the calibration of the meteorological time series data of the meteorological station can be achieved, which simplifies the calibration complexity and is applicable to different meteorological station structures and materials, and has universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0014] Figure 1 This is a flow chart of a meteorological data calibration method in one embodiment of the present application;

[0015] Figure 2 A schematic diagram of the structure of a neural network model provided in one embodiment of the present application;

[0016] Figure 3 A schematic diagram of the linear regression result of hidden layer layer1 provided in an embodiment of the present application;

[0017] Figure 4 A schematic diagram of a flow chart of the application of a meteorological data calibration model provided in another embodiment of the present application;

[0018] Figure 5 A schematic diagram of the principle of a meteorological data calibration method provided in one embodiment of the present application;

[0019] Figure 6 A schematic diagram of temperature data before calibration using meteorological data provided by an embodiment of the present application;

[0020] Figure 7 A schematic diagram of temperature data calibrated using a meteorological data calibration method provided by another embodiment of the present application;

[0021] Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] In an exemplary embodiment, Figure 1 As shown, the present application provides a meteorological data calibration method, including the following steps 101 to 105. Among them:

[0025] Step 101: Acquire meteorological time series data of standard meteorological stations and uncalibrated meteorological stations at the same observation point in different regions; the standard meteorological station is a meteorological station with calibrated meteorological data.

[0026] Step 102: extracting the time characteristics of the meteorological time series data of the uncalibrated meteorological station.

[0027] Step 103: The meteorological time series data of the uncalibrated meteorological station and the extracted time features are used as input data, and the meteorological time series data of the standard meteorological station is used as a label to form a meteorological data set.

[0028] Step 104: using the meteorological data set to train a neural network model to obtain a meteorological data calibration model;

[0029] Step 105: input the meteorological time series data of the meteorological station to be calibrated and the extracted time features into the meteorological data calibration model, and output the calibrated meteorological time series data of the meteorological station to be calibrated.

[0030] By implementing the above-mentioned steps 101 to 105, the present application aims to realize the calibration of multi-factor weather stations by training and predicting the data set of the whole season through the machine training model, simplify the calibration complexity through data, and have a universal calibration solution.

[0031] In another exemplary embodiment of the present application, since the standard data released by the meteorological department are all revised data, directly using the released data as sample data cannot reflect the real meteorological standard station data. And the sample data in different regions have relatively large differences at different times, and there are differences even in the same city due to different terrains. Considering the calibration cost and convenience, the calibrated equipment is generally deployed in a unified location, and the meteorological data obtained cannot reflect the spatiotemporal data deployed in the future. It is necessary to provide a data training solution to solve the differentiation problem. Therefore, in order to solve the selection of standard reference values ​​and the spatiotemporal problem of training data, the above step 101 meteorological time series data collection method is: considering the easy accessibility and accuracy of the data, the uncalibrated equipment and the standard equipment are placed in the same venue (same observation point) to obtain data samples, and the meteorological data of the observation points in each area are used as reference data.

[0032] The meteorological time series data may be one or more of temperature, humidity, wind speed, etc. When the meteorological time series data is multiple of temperature, humidity, wind speed, etc., the standard meteorological station, the uncalibrated meteorological station, and the calibrated meteorological station are multi-factor meteorological stations. Therefore, the method of the present application can realize the calibration of a multi-factor meteorological station.

[0033] In another exemplary embodiment of the present application, in order to ensure the integrity and consistency of the data, before the above step 102, the method can also preprocess the meteorological time series data of the uncalibrated meteorological station; the preprocessing includes: data cleaning, removal of outliers and missing value processing, etc.

[0034] In another exemplary embodiment of the present application, step 102 extracts time features from the meteorological time series data of the uncalibrated meteorological station, and the time features include: year, month, day, hour and minute. In addition to extracting time features, location, season, etc., and other factors that may affect meteorological data can also be further extracted.

[0035] In another exemplary embodiment of the present application, the neural network model in step 104 may be a time series autoregressive moving average model, or other neural network models.

[0036] In another exemplary embodiment of the present application, the neural network model in step 104 includes: an input layer, multiple hidden layers and an output layer; the multiple hidden layers are connected in sequence, the input ends of the multiple hidden layers connected in sequence are connected to the input layer, and the output ends of the multiple hidden layers connected in sequence are connected to the output layer. Figure 2 It is shown that the neural network model includes only two hidden layers: a first hidden layer (Layer1) and a second hidden layer (Layer2).

[0037] The input data of the input layer is X includes 6 types of data. The superscript of X element is the data amount and the subscript is the data type. -Year, -moon, -day, -Hour, -point, -Collect value.

[0038] The weights of the first and second hidden layers are The data output by the output layer is

[0039] The purpose of training the neural network model is to map the input meteorological data to the output layer by learning the patterns and correlations of meteorological data.

[0040] In another exemplary embodiment of the present application, the process of training the neural network model in step 104 can be replaced by steps 201 to 203:

[0041] Step 201: Divide the meteorological data set into a training set, a test set and a validation set.

[0042] Step 202: Using the training set and the validation set, the neural network model is trained by back propagation algorithm and gradient descent method.

[0043] Step 203: using the test set to evaluate the calibration effect of the trained neural network model, and determining the neural network model that passes the evaluation as the meteorological data calibration model.

[0044] Compare the data differences and accuracy before and after calibration, and use statistical indicators and visualization methods to evaluate the calibration effect.

[0045] When training a neural network model, the training process for the two hidden layers is:

[0046] 1. Linear regression is used to obtain the hidden layer layer1, as shown in Table 1.

[0047] Table 1 Hidden layer layer1 linear regression

[0048]

[0049] 2. Gradient descent and ascent are performed to obtain the hidden layer layer2, as shown in Table 2.

[0050] Table 2 Gradient descent and ascent optimization of hidden layer layer2

[0051]

[0052] In another exemplary embodiment of the present application, Figure 4 The flow chart of the meteorological data calibration model application is shown. Figure 4 In the above step 105, the meteorological time series data of the meteorological station to be calibrated is the collected data, the extraction of time features is the front-end program data processing, and the meteorological data calibration model is the back-end model. The meteorological time series data of the meteorological station to be calibrated, that is, the calibration data, can be obtained by using the back-end model.

[0053] Figure 5 The schematic diagram of the meteorological data calibration method of the present application is shown. The meteorological data calibration method is roughly divided into three stages: data acquisition and processing stage, model training stage and model application stage. In the data acquisition and processing stage, data collection, data preprocessing and feature extraction are performed in sequence, and the model training stage includes a neural network model, data calibration and data evaluation.

[0054] The feasibility and effectiveness of the meteorological data calibration method of the present application are verified by actual cases below: A large amount of meteorological data is collected and calibrated using a neural network model. Figure 6 The temperature data before calibration using the meteorological data of this application is shown. Figure 7 The temperature data after calibration using the meteorological data calibration method of the present application is shown. Figure 6 and Figure 7 The horizontal axis represents the sampling point, and the vertical axis represents the temperature. Figure 6 Raw in the table indicates the temperature data before calibration, and standard indicates the standard temperature data. Figure 7 The calibration in the figure represents the calibrated temperature data. Experimental results show that the meteorological data calibration method of the present application can significantly improve the accuracy and reliability of meteorological data.

[0055] This application can improve the accuracy and reliability of meteorological data through advanced machine learning technology. This method has broad application prospects and can be used in meteorological forecasting, climate research and related fields, providing an effective tool for meteorological and climatological research.

[0056] The advantages of this method are as follows:

[0057] 1. The neural network model has high flexibility and adaptability and can handle complex nonlinear relationships.

[0058] 2. Automatically learn the patterns and correlations of meteorological data through machine learning technology, improving the accuracy and effectiveness of calibration.

[0059] 3. The calibrated meteorological data can be applied to meteorological forecasting, climate research and other related fields to provide more accurate and reliable data support.

[0060] 4. This solution can also be used for data calibration of environmental sensors and is universal.

[0061] Based on the same inventive concept, the embodiment of the present application also provides a meteorological data calibration device for implementing the meteorological data calibration method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more meteorological data calibration device embodiments provided below can refer to the limitations of the meteorological data calibration method above, and will not be repeated here.

[0062] In an exemplary embodiment, the present application provides a meteorological data calibration device including: a data collection module, a feature extraction module, a data set construction module, a training module and an application module.

[0063] The data collection module is used to obtain meteorological time series data of standard meteorological stations and uncalibrated meteorological stations at the same observation point in different regions; the standard meteorological station is a meteorological station with calibrated meteorological data.

[0064] The feature extraction module is used to extract the time features of the meteorological time series data of the uncalibrated meteorological station.

[0065] The data set construction module is used to take the meteorological time series data of the uncalibrated meteorological station and the extracted time features as input data, and the meteorological time series data of the standard meteorological station as labels to construct a meteorological data set.

[0066] The training module is used to train the neural network model using the meteorological data set to obtain a meteorological data calibration model.

[0067] The application module is used to input the meteorological time series data of the meteorological station to be calibrated and the extracted time characteristics into the meteorological data calibration model, and output the calibrated meteorological time series data of the meteorological station to be calibrated.

[0068] As an optional implementation, the meteorological data calibration device further includes: a data preprocessing module. The data preprocessing module performs preprocessing operations such as cleaning, outlier processing and missing value processing on the collected meteorological time series data.

[0069] Based on the same inventive concept, an embodiment of the present application also provides a weather station, which uses the above-mentioned meteorological data calibration method to calibrate meteorological time series data.

[0070] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store meteorological time series data calibrated by the meteorological station to be calibrated. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a meteorological data calibration method is implemented.

[0071] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0072] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0073] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0074] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0075] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0076] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0077] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A meteorological data calibration method, characterized in that: include: Obtain meteorological time series data from standard meteorological stations and uncalibrated meteorological stations at the same observation point in different regions; The standard weather station is a weather station with calibrated weather data; Extracting temporal characteristics of meteorological time series data from uncalibrated weather stations; The meteorological time series data of the uncalibrated meteorological station and the extracted time features are used as input data, and the meteorological time series data of the standard meteorological station is used as a label to form a meteorological dataset; Using the meteorological data set to train a neural network model to obtain a meteorological data calibration model; The meteorological time series data of the meteorological station to be calibrated and the extracted time characteristics are input into the meteorological data calibration model, and the meteorological time series data calibrated by the meteorological station to be calibrated is output.

2. The meteorological data calibration method according to claim 1, characterized in that: Extract the temporal characteristics of the meteorological time series data of the uncalibrated weather station, which also includes: The meteorological time series data of the uncalibrated meteorological station are preprocessed; the preprocessing includes: data cleaning, removal of outliers and missing value processing.

3. The meteorological data calibration method according to claim 1, characterized in that: The extracted time features include: year, month, day, hour and minute.

4. The meteorological data calibration method according to claim 1, characterized in that: The neural network model includes: an input layer, multiple hidden layers and an output layer; the multiple hidden layers are connected in sequence, the input ends of the multiple hidden layers connected in sequence are connected to the input layer, and the output ends of the multiple hidden layers connected in sequence are connected to the output layer.

5. The meteorological data calibration method according to claim 1, characterized in that: The neural network model is a time series autoregressive moving average model.

6. The meteorological data calibration method according to claim 1, characterized in that: The meteorological data set is used to train a neural network model to obtain a meteorological data calibration model, which specifically includes: Dividing the meteorological data set into a training set, a test set and a validation set; Using the training set and the validation set, training the neural network model through a back propagation algorithm and a gradient descent method; The test set is used to evaluate the calibration effect of the trained neural network model, and the neural network model that passes the evaluation is determined as the meteorological data calibration model.

7. The meteorological data calibration method according to claim 1, characterized in that: The meteorological data set is used to train a neural network model to obtain a meteorological data calibration model, and then the following steps are further included: The weather station to be calibrated and the standard weather station are set in a preset area; Obtain daily meteorological time series data of the weather station to be calibrated and the standard weather station; The meteorological data calibration model is used to calibrate the daily meteorological time series data of the meteorological station to be calibrated, so as to obtain the daily calibrated meteorological time series data of the meteorological station to be calibrated; The meteorological data calibration model is optimized daily, weekly or monthly based on the meteorological time series data of the meteorological station to be calibrated and the meteorological time series data of the standard meteorological station.

8. A meteorological data calibration device, characterized in that: include: A data collection module is used to obtain meteorological time series data of standard meteorological stations and uncalibrated meteorological stations at the same observation point in different regions; The standard weather station is a weather station with calibrated weather data; A feature extraction module, used to extract the time features of the meteorological time series data of the uncalibrated meteorological station; A data set construction module is used to take the meteorological time series data of the uncalibrated meteorological station and the extracted time features as input data, and the meteorological time series data of the standard meteorological station as labels to construct a meteorological data set; A training module, used to train a neural network model using the meteorological data set to obtain a meteorological data calibration model; The application module is used to input the meteorological time series data of the meteorological station to be calibrated and the extracted time characteristics into the meteorological data calibration model, and output the calibrated meteorological time series data of the meteorological station to be calibrated.

9. A weather station, characterized in that: The meteorological station calibrates the meteorological time series data using the meteorological data calibration method described in any one of claims 1 to 7.

10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the meteorological data calibration method according to any one of claims 1 to 7.

Images