Air temperature data analysis method and related equipment

Abstract

The invention discloses an air temperature data analysis method and related equipment. The method comprises the following steps: acquiring geographical environment data, time data and air temperature of an adjacent reference site of a to-be-processed site, wherein the time data is determined based on a time range of actual observation data of the to-be-processed site; training an XGBoost algorithm model based on a gradient boosting tree based on a data set constructed by the geographical environment data, the time data and the air temperature of the adjacent reference site and the actual observation data of the to-be-processed site so as to obtain an air temperature data interpolation extension model; and according to the air temperature of the adjacent reference station, estimating partial missing data of the to-be-processed station or data of an unobserved time period through the data interpolation extension model so as to complete data interpolation extension. The method can solve the problem that the interpolation precision is not high due to the fact that the real air temperature distribution cannot be accurately reflected when interpolation is carried out only based on the distance weight in a region with complex terrains or changeable climate conditions.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of meteorological analysis, and more specifically, the present invention relates to a temperature data analysis method and related equipment. Background Art

[0002] Meteorological data has important application value in climate research, environmental monitoring, agricultural production and other fields. However, due to the influence of observation environment, instrument failure, communication transmission and other reasons, some stations may have missing data. In order to fill these missing data points, one of the commonly used methods is interpolation technology. Among them, IDW (Inverse Distance Weighting) is a common interpolation method. Although the inverse distance square interpolation method can better fill the missing points of meteorological data in many cases, the inverse distance square interpolation method only considers the distance factor and does not fully consider the spatial variability of meteorological data. In areas with complex terrain or changeable climatic conditions, interpolation based only on distance weights may not accurately reflect the true temperature distribution, resulting in low interpolation accuracy. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In order to solve the problem that interpolation based only on distance weight may not accurately reflect the actual temperature distribution in areas with complex terrain or changeable climatic conditions, resulting in low interpolation accuracy, in a first aspect, the present invention proposes a temperature data analysis method, the method comprising:

[0005] Obtaining geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed;

[0006] Based on the data set constructed based on the geographic environment data, time data and temperature of the adjacent reference station and the actual observation data of the station to be processed, the XGBoost algorithm model based on the gradient boosting tree is trained to obtain a temperature data interpolation and extension model;

[0007] According to the air temperature of the adjacent reference station, the data interpolation and extension model is used to estimate some missing data or data of the unobserved period of the station to be processed to complete the data interpolation and extension.

[0008] Optionally, by calculating the site similarity index, neighboring reference sites of the site to be processed are selected from the meteorological stations with long-sequence observation data.

[0009] Optionally, the geographic environment data includes at least one of longitude, latitude, altitude, slope and aspect, and the slope and aspect are determined by interpolation based on high-precision DEM data using a neighbor interpolation algorithm.

[0010] Optionally, also include:

[0011] Obtain at least one of relative humidity, sunshine and precipitation of a reference station adjacent to the station to be processed,

[0012] The actual observation data of the site to be processed is used as the label, and the data of the neighboring reference sites is used as the input feature quantity to construct the training data set and the test data set.

[0013] Optionally, also include:

[0014] The model parameters are optimized by cross-validation method to optimize the temperature data interpolation and extension model.

[0015] Optionally, also include:

[0016] Acquire image data uploaded by a user on a network platform with a geographical location marker located near the adjacent reference site and the site to be processed;

[0017] Selecting image data with outdoor clothing information as target supplementary training data, wherein the image data is associated with shooting time;

[0018] The temperature data interpolation and extension model is optimized based on the target supplementary training data.

[0019] In a second aspect, the present invention further provides a temperature data analysis device, comprising:

[0020] An acquisition unit, used to acquire geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed;

[0021] A modeling unit, for training an XGBoost algorithm model based on a gradient boosting tree based on a data set constructed from geographic environment data, time data and temperature of the adjacent reference station and actual observation data of the station to be processed to obtain a temperature data interpolation and extension model;

[0022] The interpolation unit is used to estimate the partially missing data or the data of the unobserved period of the site to be processed according to the temperature of the adjacent reference site through the data interpolation extension model to complete the data interpolation extension.

[0023] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the temperature data analysis method of any one of the first aspects described above when executing the computer program stored in the memory.

[0024] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the temperature data analysis method of any one of the above items in the first aspect is implemented.

[0025] In summary, the temperature data analysis method proposed in this application obtains the geographical environment data, time data and temperature of the neighboring reference site of the site to be processed, and the time data is determined based on the time range of the actual observation data of the site to be processed; the XGBoost algorithm model based on the gradient boosting tree is trained based on the data set constructed based on the geographical environment data, time data and temperature of the neighboring reference site and the actual observation data of the site to be processed to obtain the temperature data interpolation extension model; according to the temperature of the neighboring reference site, the data interpolation extension model is used to estimate the partial missing data or the data of the unobserved period of the site to be processed to complete the data interpolation extension. By integrating the geographical environment, time and multiple meteorological elements, a more comprehensive and accurate temperature data interpolation is provided. The powerful nonlinear fitting ability and multi-source data processing ability of the XGBoost algorithm make it suitable for power receiving areas with different geographical environments and climatic conditions. Through fine feature engineering processing and optimized model parameters, the accuracy of temperature data interpolation is significantly improved and the interpolation error is reduced. Through model training and time range expansion, the data sequence of sites with shorter observation time can be effectively extended to meet the demand for long time series data. The robustness of the XGBoost algorithm in handling missing data and outliers ensures the stability and reliability of the interpolation results.

[0026] The temperature data analysis method of the present invention, other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0028] Figure 1 A schematic diagram of a temperature data analysis method provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the structure of a temperature data analysis device provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the structure of an electronic device for analyzing temperature data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0032] In order to solve the problem that interpolation based only on distance weights may not accurately reflect the actual temperature distribution in areas with complex terrain or changeable climate conditions, resulting in low interpolation accuracy, please refer to Figure 1 , is a flow chart of a temperature data analysis method provided in an embodiment of the present application, which may specifically include: steps S110 to S130.

[0033] S110, obtaining geographical environment data, time data and temperature of reference sites adjacent to the site to be processed, wherein the time data is determined based on a time range of actual observation data of the site to be processed.

[0034] Exemplarily, the time range for model construction is determined based on the actual observation data of the site to be processed to ensure the integrity and continuity of the data. For example, if the site A to be processed has temperature data from 2010 to 2015, the data within this time range can be selected as the basic data for model construction. By determining a reasonable time range, the time continuity and integrity of the model training data can be ensured, and the impact of inconsistent time intervals on model training can be reduced.

[0035] S120, training an XGBoost algorithm model based on a gradient boosting tree based on a data set constructed based on the geographic environment data, time data and temperature of the neighboring reference sites and the actual observation data of the site to be processed to obtain a temperature data interpolation and extension model.

[0036] It is understandable that the XGBoost algorithm can effectively integrate multiple types of data, including geographic environment data (such as longitude, latitude, altitude, slope and aspect), meteorological elements (such as temperature, relative humidity, sunshine, precipitation) and time data (month, day, hour). This multi-source data integration capability enables the algorithm to fully consider the impact of various environmental factors on temperature, thereby improving the accuracy of interpolation. Different power supply areas may have diverse geographical features, such as mountains, plains, river valleys, etc. The XGBoost algorithm can effectively model the characteristics of these different geographical environments through feature engineering and data fusion. When dealing with complex terrain, the algorithm not only considers the distance factor, but also comprehensively considers environmental variables such as slope and aspect, which improves the adaptability to complex terrain areas. As an integrated learning method, the XGBoost algorithm has strong nonlinear fitting capabilities and can capture complex patterns and nonlinear relationships in temperature changes. Whether it is an area with stable climate conditions or an area with drastic climate changes, XGBoost can provide high-precision temperature data interpolation by learning patterns in historical data. The XGBoost algorithm has high robustness in dealing with missing data and outliers. Even at some sites where data is sparse or there are outliers, the algorithm can reduce the impact of these factors on the interpolation results through its built-in processing mechanism, thereby ensuring the stability and reliability of the interpolation results. This method introduces time data (such as month, day, and hour) in the feature engineering stage, so that the algorithm can capture the temporal dynamic changes in temperature. This is especially important for power receiving areas with obvious seasonal changes or large temperature differences between day and night, and can better reflect the temporal variation characteristics of the temperature in these areas. The XGBoost algorithm has good scalability and can adjust features and parameters according to the specific needs of different regions and sites. Through continuous optimization and parameter adjustment of the model, it can ensure that the best interpolation effect can be obtained in different power receiving areas.

[0037] S130, estimating some missing data or data of an unobserved period of the site to be processed through the data interpolation and extension model according to the temperature of the neighboring reference site, so as to complete the data interpolation and extension.

[0038] Exemplarily, the trained XGBoost model is used to estimate the missing data or data of the unobserved period of the processing site. For example, for some unobserved periods of the processing site A, the previously trained model is used to input the real-time data of sites B, C, and D, and the estimated temperature value of site A is output. Through the application of the model, the temperature data of the processing site can be interpolated and extended with high precision, solving the problem of missing data and improving the integrity and reliability of meteorological data.

[0039] In summary, the temperature data analysis method provided by the embodiment of the present application obtains the geographical environment data, time data and temperature of the neighboring reference site of the site to be processed, and the time data is determined based on the time range of the actual observation data of the site to be processed; the XGBoost algorithm model based on the gradient boosting tree is trained based on the geographical environment data, time data and temperature of the neighboring reference site and the data set constructed by the actual observation data of the site to be processed to obtain the temperature data interpolation extension model; according to the temperature of the neighboring reference site, the data interpolation extension model is used to estimate the data of the partially missing data or the unobserved period of the site to be processed to complete the data interpolation extension. By integrating the geographical environment, time and multiple meteorological elements, a more comprehensive and accurate temperature data interpolation is provided. The powerful nonlinear fitting ability and multi-source data processing ability of the XGBoost algorithm make it suitable for power receiving areas with different geographical environments and climatic conditions. Through fine feature engineering processing and optimized model parameters, the accuracy of temperature data interpolation is significantly improved and the interpolation error is reduced. Through model training and time range expansion, the data sequence of sites with shorter observation time can be effectively extended to meet the demand for long time series data. The robustness of the XGBoost algorithm in handling missing data and outliers ensures the stability and reliability of the interpolation results.

[0040] According to some embodiments, further comprising:

[0041] By calculating the site similarity index, neighboring reference sites of the site to be processed are selected from the meteorological stations with long-sequence observation data.

[0042] Exemplarily, a variety of geographical and meteorological characteristics (such as longitude, latitude, altitude, slope, aspect, temperature, relative humidity, etc.) are used to calculate the similarity between sites. Sites with high similarity to the site to be processed are selected from national meteorological stations with long-sequence observation data. For example, the site A to be processed is located in a mountainous area, and its similarity indicators include high altitude, large slope and aspect changes. Based on these indicators, nearby sites B, C and D with similar geographical features and climatic conditions can be selected as reference sites. Through the calculation of similarity indicators and the selection of reference sites, it can be ensured that the data of the selected reference site is closer to the actual situation of the site to be processed, thereby improving the accuracy of the interpolated data.

[0043] In some examples, the geographic environment data includes at least one of longitude, latitude, altitude, slope, and aspect, and the slope and aspect are determined by interpolation based on high-precision DEM data using a neighbor interpolation algorithm.

[0044] Exemplarily, DEM (Digital Elevation Model) is a raster data that digitally represents the undulation of the terrain surface. High-precision DEM data is usually stored in a regular grid form, and each unit (pixel) in the grid has a corresponding altitude value. Slope is the degree of inclination of the terrain surface relative to the horizontal plane, usually expressed in degrees or percentages. Aspect is the inclination direction of the terrain surface relative to the north direction, usually expressed in azimuth (0° for north, 90° for east, 180° for south, and 270° for west). High-precision DEM data can be used to calculate the slope and aspect of each grid cell. GIS software or special geographic information processing algorithms are usually used for calculation. High-precision DEM data can be obtained from remote sensing satellites, laser radar (LiDAR), etc., and the resolution is usually at the meter level or higher. The slope and aspect of each grid cell are calculated using a window-based algorithm. Commonly used algorithms include the Zevenbergen-Thorne method, the Horn method, etc. In practical applications, it may be necessary to apply the calculated slope and aspect values ​​to locations where there are no direct observation data. At this time, the slope and aspect of these locations can be estimated using the neighbor interpolation algorithm. For example, select several reference points with known slope and aspect around the site to be processed. Use algorithms such as IDW, Kriging, or natural neighbor interpolation to estimate the slope and aspect of the site to be processed based on the data of these reference points.

[0045] In some examples, this also includes:

[0046] Obtain at least one of relative humidity, sunshine and precipitation of a reference station adjacent to the station to be processed,

[0047] The actual observation data of the site to be processed is used as the label, and the data of the neighboring reference sites is used as the input feature quantity to construct the training data set and the test data set.

[0048] Exemplarily, in machine learning, the label is the target variable we want to predict. In the present invention, the label is the temperature data of the site to be processed, that is, the missing data point. The input feature is an independent variable used to predict the target variable. In the present invention, the input features include the geographical environment data, time data and meteorological elements of the neighboring reference sites. Assuming that the temperature data of the site A to be processed is missing for some time periods, it is necessary to use the data of the neighboring reference sites B, C, and D for interpolation. Time matching is performed on the data of the site A to be processed and the neighboring reference sites B, C, and D to ensure that the data at the same time point can correspond. For example, the temperature data of a certain day is missing, and the meteorological data of the sites B, C, and D at the same time point are matched. The data of the site A to be processed is used as a label. The data of the neighboring reference sites B, C, and D are used as input features. Specific features include: geographical environment data: longitude, latitude, altitude, slope, and slope direction of sites B, C, and D. Meteorological elements: temperature, relative humidity, sunshine, precipitation, etc. of sites B, C, and D. Time data: time features such as year, month, day, and hour. Construct a data set at multiple time points, use the known temperature data of the site A to be processed as a label, and use the multi-source data of the adjacent reference sites as input features for training. Through multi-source data fusion and time matching, the model can more accurately predict the temperature data of the site to be processed. Taking into account multiple geographical and meteorological factors, the model has strong adaptability and can be applied to power receiving areas under different environments and conditions. Through high-quality feature engineering processing, the integrity and continuity of the data are ensured, and the reliability of the interpolation results is improved.

[0049] In some examples, this also includes:

[0050] The model parameters are optimized by cross-validation method to optimize the temperature data interpolation and extension model.

[0051] In some examples, this also includes:

[0052] Acquire image data uploaded by a user on a network platform with a geographical location marker located near the adjacent reference site and the site to be processed;

[0053] Selecting image data with outdoor clothing information as target supplementary training data, wherein the image data is associated with shooting time;

[0054] The temperature data interpolation and extension model is optimized based on the target supplementary training data.

[0055] For example, since there is a huge amount of data information in social media currently, the image data uploaded by platform users covers a very wide range. Image data with geographic location tags and near the neighboring reference sites and the sites to be processed can be used. If the image data has outdoor clothing information, since the outdoor clothing information and temperature have a very high correlation, the outdoor clothing information can be used to further perform data fusion analysis through the XGBoost algorithm to provide high-precision temperature data interpolation.

[0056] See also Figure 2 , an embodiment of the temperature data analysis device in the embodiment of the present application may include:

[0057] An acquisition unit 21 is used to acquire geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed;

[0058] A modeling unit 22 is used to train an XGBoost algorithm model based on a gradient boosting tree based on a data set constructed from geographic environment data, time data and temperature of the adjacent reference station and actual observation data of the station to be processed to obtain a temperature data interpolation and extension model;

[0059] The interpolation unit 23 is used to estimate the partially missing data or the data of the unobserved period of the site to be processed according to the temperature of the adjacent reference site through the data interpolation extension model to complete the data interpolation extension.

[0060] In summary, the temperature data analysis device provided by the embodiment of the present application obtains the geographical environment data, time data and temperature of the neighboring reference site of the site to be processed, and the time data is determined based on the time range of the actual observation data of the site to be processed; the XGBoost algorithm model based on the gradient boosting tree is trained based on the geographical environment data, time data and temperature of the neighboring reference site and the data set constructed by the actual observation data of the site to be processed to obtain the temperature data interpolation extension model; according to the temperature of the neighboring reference site, the data interpolation extension model is used to estimate the partial missing data or the data of the unobserved period of the site to be processed to complete the data interpolation extension. By integrating the geographical environment, time and multiple meteorological elements, a more comprehensive and accurate temperature data interpolation is provided. The powerful nonlinear fitting ability and multi-source data processing ability of the XGBoost algorithm make it suitable for power receiving areas with different geographical environments and climatic conditions. Through fine feature engineering processing and optimized model parameters, the accuracy of temperature data interpolation is significantly improved and the interpolation error is reduced. Through model training and time range expansion, the data sequence of sites with shorter observation time can be effectively extended to meet the demand for long time series data. The robustness of the XGBoost algorithm in handling missing data and outliers ensures the stability and reliability of the interpolation results.

[0061] like Figure 3 As shown, the embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any one of the above-mentioned methods for analyzing temperature data are implemented:

[0062] Obtaining geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed;

[0063] Based on the data set constructed based on the geographic environment data, time data and temperature of the adjacent reference station and the actual observation data of the station to be processed, the XGBoost algorithm model based on the gradient boosting tree is trained to obtain a temperature data interpolation and extension model;

[0064] According to the air temperature of the adjacent reference station, the data interpolation and extension model is used to estimate some missing data or data of the unobserved period of the station to be processed to complete the data interpolation and extension.

[0065] Optionally, by calculating the site similarity index, neighboring reference sites of the site to be processed are selected from the meteorological stations with long-sequence observation data.

[0066] Optionally, the geographic environment data includes at least one of longitude, latitude, altitude, slope and aspect, and the slope and aspect are determined by interpolation based on high-precision DEM data using a neighbor interpolation algorithm.

[0067] Optionally, also include:

[0068] At least one of the relative humidity, sunshine and precipitation of the neighboring reference sites of the site to be processed is obtained, and the actual observation data of the site to be processed is used as a label, and the data of the neighboring reference sites is used as an input feature quantity to construct a training data set and a test data set.

[0069] Optionally, also include:

[0070] The model parameters are optimized by cross-validation method to optimize the temperature data interpolation and extension model.

[0071] Optionally, also include:

[0072] Acquire image data uploaded by a user on a network platform with a geographical location marker located near the adjacent reference site and the site to be processed;

[0073] Selecting image data with outdoor clothing information as target supplementary training data, wherein the image data is associated with shooting time;

[0074] The temperature data interpolation and extension model is optimized based on the target supplementary training data.

[0075] For example, since there is a huge amount of data information in social media currently, the image data uploaded by platform users covers a very wide range. Image data with geographic location tags and near the neighboring reference sites and the sites to be processed can be used. If the image data has outdoor clothing information, since the outdoor clothing information and temperature have a very high correlation, the outdoor clothing information can be used to further perform data fusion analysis through the XGBoost algorithm to provide high-precision temperature data interpolation.

[0076] Since the electronic device introduced in this embodiment is a device used to implement a temperature data analysis device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0077] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1Any implementation method in the corresponding embodiment:

[0078] Obtaining geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed;

[0079] Based on the data set constructed based on the geographic environment data, time data and temperature of the adjacent reference station and the actual observation data of the station to be processed, the XGBoost algorithm model based on the gradient boosting tree is trained to obtain a temperature data interpolation and extension model;

[0080] According to the air temperature of the adjacent reference station, the data interpolation and extension model is used to estimate some missing data or data of the unobserved period of the station to be processed to complete the data interpolation and extension.

[0081] Optionally, by calculating the site similarity index, neighboring reference sites of the site to be processed are selected from the meteorological stations with long-sequence observation data.

[0082] Optionally, the geographic environment data includes at least one of longitude, latitude, altitude, slope and aspect, and the slope and aspect are determined by interpolation based on high-precision DEM data using a neighbor interpolation algorithm.

[0083] Optionally, also include:

[0084] Obtain at least one of relative humidity, sunshine and precipitation of a reference station adjacent to the station to be processed,

[0085] The actual observation data of the site to be processed is used as the label, and the data of the neighboring reference sites is used as the input feature quantity to construct the training data set and the test data set.

[0086] Optionally, also include:

[0087] The model parameters are optimized by cross-validation method to optimize the temperature data interpolation and extension model.

[0088] Optionally, also include:

[0089] Acquire image data uploaded by a user on a network platform with a geographical location marker located near the adjacent reference site and the site to be processed;

[0090] Selecting image data with outdoor clothing information as target supplementary training data, wherein the image data is associated with shooting time;

[0091] The temperature data interpolation and extension model is optimized based on the target supplementary training data.

[0092] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0097] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1The process of temperature data analysis in the corresponding embodiment.

[0098] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0103] If the integrated unit is implemented in the form of 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, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable 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 various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0104] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for analyzing temperature data, characterized in that: include: Obtaining geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed; Based on the data set constructed based on the geographic environment data, time data and temperature of the adjacent reference station and the actual observation data of the station to be processed, the XGBoost algorithm model based on the gradient boosting tree is trained to obtain a temperature data interpolation and extension model; According to the air temperature of the adjacent reference station, the data interpolation and extension model is used to estimate some missing data or data of the unobserved period of the station to be processed to complete the data interpolation and extension.

2. The method according to claim 1, characterized in that Also includes: By calculating the site similarity index, neighboring reference sites of the site to be processed are selected from the meteorological stations with long-sequence observation data.

3. The method according to claim 1, characterized in that The geographical environment data includes at least one of longitude, latitude, altitude, slope and aspect, and the slope and aspect are determined by interpolation using a neighbor interpolation algorithm based on high-precision DEM data.

4. The method according to claim 3, characterized in that Also includes: At least one of relative humidity, sunshine and precipitation of a reference site adjacent to the site to be processed is obtained.

5. The method according to claim 4, characterized in that Also includes: The actual observation data of the site to be processed is used as the label, and the data of the neighboring reference sites is used as the input feature quantity to construct the training data set and the test data set.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: The model parameters are optimized by cross-validation method to optimize the temperature data interpolation and extension model.

7. The method according to claim 6, characterized in that Also includes: Acquire image data uploaded by a user on a network platform with a geographical location marker located near the adjacent reference site and the site to be processed; Selecting image data with outdoor clothing information as target supplementary training data, wherein the image data is associated with shooting time; The temperature data interpolation and extension model is optimized based on the target supplementary training data.

8. A temperature data analysis device, characterized in that: include: An acquisition unit, used to acquire geographical environment data, time data and temperature of a reference station adjacent to the station to be processed, wherein the time data is determined based on a time range of actual observation data of the station to be processed; A modeling unit, for training an XGBoost algorithm model based on a gradient boosting tree based on a data set constructed from geographic environment data, time data and temperature of the adjacent reference station and actual observation data of the station to be processed to obtain a temperature data interpolation and extension model; The interpolation unit is used to estimate the partially missing data or the data of the unobserved period of the site to be processed according to the temperature of the adjacent reference site through the data interpolation extension model to complete the data interpolation extension.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the temperature data analysis method as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

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 temperature data analysis method according to any one of claims 1 to 7 is implemented.

Images