CN112308281A - Temperature information prediction method and device - Google Patents
Temperature information prediction method and device Download PDFInfo
- Publication number
- CN112308281A CN112308281A CN201911098395.2A CN201911098395A CN112308281A CN 112308281 A CN112308281 A CN 112308281A CN 201911098395 A CN201911098395 A CN 201911098395A CN 112308281 A CN112308281 A CN 112308281A
- Authority
- CN
- China
- Prior art keywords
- data
- observation
- historical
- generating
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000013598 vector Substances 0.000 claims abstract description 76
- 230000004927 fusion Effects 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 13
- 230000003287 optical effect Effects 0.000 description 4
- 238000001556 precipitation Methods 0.000 description 4
- 238000013179 statistical model Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The disclosure relates to a temperature information prediction method and device. The method comprises the following steps: acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element values; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm. According to the temperature information prediction method and device, historical observation data and mode prediction data can be fused, the site data scale is expanded, and a more accurate temperature prediction result is obtained.
Description
Technical Field
The disclosure relates to the field of computer information processing, in particular to a temperature information prediction method and device.
Background
For temperature prediction, two main types of traditional statistical models and physical process models exist at present. The traditional statistical model is mainly based on historical meteorological data and relies on a traditional statistical method to establish the quantitative relation between input variables and output variables; physical process models generally require a high physical system basis and rely on a large amount of variable information to effectively represent the physical process of temperature changes through extremely complex mathematical formulas to obtain more accurate temperature predictions.
Social development and improvement of the living standard of people put higher requirements on accurate temperature prediction, and a physical process model gradually replaces a traditional statistical model by utilizing the computing power of a computer on the basis of a physical system and becomes a mainstream method for temperature prediction. Although the physical process model has better results than the traditional statistical model on the whole, the following problems still exist at present: firstly, the output grid resolution of the prediction algorithm is low, so that the prediction results of the mode prediction precision in a plurality of area ranges are unsatisfactory, namely the prediction accuracy cannot meet the specific requirements of specific activities of specific areas; secondly, the existing mode algorithm is complex, large in calculation amount and slow in forecasting speed, so that forecasting timeliness is insufficient; and thirdly, because regional economic development is unbalanced, observation stations in certain specific regions are too few, and the results cannot be corrected by fully utilizing historical data and observation data.
Therefore, a new temperature information prediction method and apparatus are needed.
The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of this, the present disclosure provides a temperature information prediction method and device, which fuse historical observation data and pattern prediction data, expand the scale of site data, and obtain a more accurate temperature prediction result.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, a temperature information prediction method is provided, which includes: acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element values; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm.
In one embodiment of the present disclosure, further comprising: acquiring historical observation data and historical mode forecast data of a plurality of meteorological sites; generating a historical observation vector based on the historical observation data; generating historical fusion data based on the historical pattern forecast data; and training a gradient boost model through the historical observation vector and historical fusion data to generate the temperature prediction model.
In one embodiment of the present disclosure, generating a historical observation vector based on historical observation data includes: generating an initial observation vector through historical observation data of a plurality of meteorological sites; clustering the initial observation vectors of the meteorological sites to generate a plurality of meteorological site sets, wherein the meteorological site sets comprise a plurality of meteorological sites; and generating the historical observation vector by historical observation data of a plurality of weather stations in the set of weather stations.
In one embodiment of the present disclosure, training a gradient boost model with the historical observation vectors and historical fusion data to generate the temperature prediction model comprises: generating training set data and test set data through the historical observation vector and the historical fusion data; training a gradient lifting model through the training set data to generate an initial temperature prediction model; and testing the initial temperature prediction model through the test set data, and generating the temperature prediction model when the conditions are met.
In one embodiment of the present disclosure, training a gradient boost model with the training set data generates an initial temperature prediction model, including: determining an objective function; substituting the training set data into the gradient lifting model; and generating the initial temperature prediction model when the gradient lifting model meets a preset objective function.
In one embodiment of the present disclosure, when the gradient boost model satisfies a preset objective function, generating the initial temperature prediction model includes: calculating a target function and a loss function by the forward propagation of the gradient lifting model; the gradient lifting model reversely propagates and updates the network weight; and calculating an objective function according to the network weight and the loss function.
In one embodiment of the present disclosure, acquiring observation data and pattern forecast data of a meteorological site comprises: carrying out missing value processing on the observation data; and/or performing outlier processing on the observed data; and/or missing value processing is carried out on the pattern forecast data.
In one embodiment of the present disclosure, generating fused data for the meteorological site based on the pattern forecast data includes: determining a fusion weight for the pattern forecast data based on a distance between a pattern forecast site that generated the pattern forecast data and the weather site; and interpolating the mode forecast data based on the fusion weight to generate the fusion data.
In one embodiment of the present disclosure, interpolating the pattern forecast data based on the fusion weight to generate the fusion data includes: distributing fusion weight for each mode forecast data; a summation calculation is performed based on each mode prediction data and its corresponding weight to generate the fused data.
In one embodiment of the present disclosure, inputting the observation vector and the fused data into a temperature prediction model to generate temperature prediction information of the meteorological site includes: inputting the observation vector and the fused data into the temperature prediction model; the temperature prediction model is used for calculating and generating temperature values under a plurality of time nodes based on the observation vector and the fusion data; and generating the temperature prediction information through the temperature values at the plurality of time nodes.
According to an aspect of the present disclosure, there is provided a temperature information prediction apparatus, including: the data module is used for acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element numerical values; the vector module is used for generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; the fusion module is used for generating fusion data of the meteorological site based on the mode forecast data; and the prediction module is used for inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm.
In one embodiment of the present disclosure, further comprising: the historical data module is used for acquiring historical observation data and historical mode forecast data of a plurality of meteorological sites; the historical vector module is used for generating a historical observation vector based on the historical observation data; the history fusion module is used for generating history fusion data based on the history mode forecast data; and the model training module is used for training a gradient lifting model through the historical observation vector and the historical fusion data to generate the temperature prediction model.
According to an aspect of the present disclosure, an electronic device is provided, the electronic device including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method as above.
According to an aspect of the disclosure, a computer-readable medium is proposed, on which a computer program is stored, which program, when being executed by a processor, carries out the method as above.
According to the temperature information prediction method and device, observation data and mode forecast data of a meteorological site are obtained; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological site, so that historical observation data and mode prediction data can be fused, the site data scale is expanded, and a more accurate temperature prediction result is obtained.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are merely some embodiments of the present disclosure, and other drawings may be derived from those drawings by those of ordinary skill in the art without inventive effort.
Fig. 1 is a system block diagram illustrating a temperature information prediction method and apparatus according to an example embodiment.
FIG. 2 is a flow chart illustrating a method of predicting temperature information in accordance with an exemplary embodiment.
FIG. 3 is a schematic diagram illustrating a method of predicting temperature information, according to an example embodiment.
FIG. 4 is a schematic diagram illustrating a method of predicting temperature information, according to an example embodiment.
FIG. 5 is a flow chart illustrating a method of predicting temperature information in accordance with an exemplary embodiment.
FIG. 6 is a schematic diagram illustrating a method of predicting temperature information, according to an example embodiment.
FIG. 7 is a flow chart illustrating a method of predicting temperature information in accordance with an exemplary embodiment.
FIG. 8 is a schematic diagram illustrating a method of predicting temperature information in accordance with an exemplary embodiment.
FIG. 9 is a schematic diagram illustrating a method of predicting temperature information, according to an example embodiment.
Fig. 10 is a block diagram illustrating a temperature information prediction apparatus according to an example embodiment.
Fig. 11 is a block diagram illustrating a temperature information prediction apparatus according to another exemplary embodiment.
FIG. 12 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below may be termed a second component without departing from the teachings of the disclosed concept. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It is to be understood by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present disclosure and are, therefore, not intended to limit the scope of the present disclosure.
The inventor of the present disclosure finds that, in the prior art, the predicted temperature data of the European middle-term Weather forecast center (EC for short) is low in the grid resolution of the forecast, and if the grid resolution is increased, the calculation amount is increased sharply, and the existing computer is difficult to support the calculation with the huge scale, so as to increase the running time of the forecast algorithm. Therefore, the forecasting error of the forecasting algorithm is large in the China area with complex terrain, especially in the southwest China area with complex terrain and multi-circle interaction.
In order to solve the problems in the prior art, the temperature information prediction method is provided for the characteristic of strong temperature prediction time sequence, observation sites are subjected to spatial clustering, EC mode output data and historical observation data are fused based on the thought, and site data scale is expanded to obtain a better temperature prediction result.
Fig. 1 is a system block diagram illustrating a temperature information prediction method and apparatus according to an example embodiment.
As shown in FIG. 1, the system architecture 10 may include weather observation devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The weather observation devices 101, 102, 103 may be used to obtain weather data, and the weather observation devices 101, 102, 103 interact with the server 105 over the network 104 to receive or transmit messages, and the like.
The meteorological observation devices 101, 102, 103 may be a collection or system of various monitoring devices having meteorological monitoring capabilities and supporting network-transmitted data, including but not limited to temperature measurement devices, wind speed measurement devices, air pressure measurement devices, and the like.
The server 105 may be a server that provides various services, such as a background management server that provides support for the weather data uploaded by the weather observation devices 101, 102, 103. The background management server may analyze the received weather data, and feed back the processing result (e.g., future weather information) to the user.
The server 105 may, for example, obtain observation data of a meteorological site and pattern forecast data, wherein the observation data includes a plurality of element values; the server 105 may generate an observation vector for the meteorological site, for example, based on the plurality of element values in the observation data and their corresponding observation times; the server 105 may generate fused data for the meteorological site, for example, based on the pattern forecast data; the server 105 may, for example, input the observation vectors and the fused data into a temperature prediction model to generate temperature prediction information for the meteorological site, wherein the temperature prediction model is generated by a gradient boosting algorithm.
The server 105 may be a single entity server, or may be composed of a plurality of servers, for example, it should be noted that the temperature information prediction method provided by the embodiment of the present disclosure may be executed by the server 105, and accordingly, the temperature information prediction apparatus may be disposed in the server 105. While the data monitoring side that provides real-time weather data for computation is typically located in the pattern prediction sites 101, 102, 103.
FIG. 2 is a flow chart illustrating a method of predicting temperature information in accordance with an exemplary embodiment. The temperature information prediction method 20 includes at least steps S202 to S208.
As shown in fig. 2, in S202, observation data of a weather station and pattern forecast data are acquired, wherein the observation data includes a plurality of element values. Observation data of a meteorological site, which may include longitude and latitude coordinates, altitude, annual average air temperature, and annual precipitation amount, may be acquired, for example, and constitute a feature vector V as element values.
In one embodiment, obtaining observation data and pattern forecast data for a meteorological site may include: carrying out missing value processing on the observation data; and/or performing outlier processing on the observed data; and/or missing value processing is carried out on the pattern forecast data.
Specifically, for example, data splitting is performed according to the forecast duration and the forecast element s; the forecast duration may be, for example, 1-7 days, so the forecast output file is divided into 7 sub-files
Missing value processing may also be performed on the observed data, for example: if the data exist before and after the missing data, linear interpolation is carried out by using the data before and after the missing data; if the number of the continuous missing data exceeds two, deleting the data record;
outlier processing may also be performed on the observed data, for example: calculating the mean (mean) and variance (std) of the observed data, classifying the data which are not in the range of (mean-2.5 std, mean +2.5 std) as abnormal values, and removing;
missing value processing may also be performed on the pattern data, for example: and calculating k mode grid points closest to each observation station, calculating the weight of the grid points by using a distance inverse weight algorithm, and finally obtaining an interpolation result.
In S204, an observation vector of the weather station is generated based on the plurality of element values in the observation data and the observation times corresponding thereto. Arranging according to the observation and forecast time and combining; the data with the same time are combined into a file.
FIG. 3 is a schematic diagram illustrating a method of predicting temperature information, according to an example embodiment. As shown in FIG. 3, the factors used in the observation data can include, for example, temperature, 10min wind speed, relative humidity, dew point temperature, etc. For time T, these elements constitute a vector.
In S206, fusion data of the weather station is generated based on the pattern forecast data. Can include the following steps: determining a fusion weight for the pattern forecast data based on a distance between a pattern forecast site that generated the pattern forecast data and the weather site; and interpolating the mode forecast data based on the fusion weight to generate the fusion data.
In one embodiment, further comprising: determining the pattern forecasting site associated with the weather site based on location information. Fig. 4 shows a positional relationship between a pattern prediction site and a meteorological site, where data in the pattern prediction site is lattice point data output according to latitude and longitude, where points at irregular positions are meteorological sites, points arranged regularly are lattice point data of pattern prediction, and in actual calculation, data of pattern prediction needs to be fused to sites.
In one embodiment, the last four pattern forecast sites of the weather site center to be predicted may be considered as the sites associated with the weather stations.
Since weather forecast is performed according to weather stations, interpolation of grid point data of patterns to observation stations is required. And (4) interpolating data of the grid points of the pattern forecasting site to the meteorological site by adopting a neighbor weight interpolation mode.
In one embodiment, weights can be given according to the distance from the site, and the weights are larger when the site is closer, so that an interpolation result is obtained to assist observation data to perform model prediction. More specifically, weather indicators such as air pressure, temperature, wind direction, relative humidity, visibility, cumulative precipitation, and precipitation value at the current time of the pattern forecast site associated with the weather site may be selected as the real-time weather data.
In S208, the observation vector and the fusion data are input into a temperature prediction model to generate temperature prediction information of the meteorological site, wherein the temperature prediction model is generated by a gradient lifting algorithm. Can include the following steps: inputting the observation vector and the fused data into the temperature prediction model; the temperature prediction model is used for calculating and generating temperature values under a plurality of time nodes based on the observation vector and the fusion data; and generating the temperature prediction information through the temperature values at the plurality of time nodes.
Specifically, temperature data for a future week may be generated, for example. The specific temperature prediction information may include a daily average temperature, a daily maximum temperature, and a daily minimum temperature, and a file corresponding to the number of days to be predicted is generated according to the date of prediction under an output folder of the temperature prediction system.
According to the temperature information prediction method disclosed by the invention, observation data and mode forecast data of a meteorological site are obtained; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological site, so that historical observation data and mode prediction data can be fused, the site data scale is expanded, and a more accurate temperature prediction result is obtained.
It should be clearly understood that this disclosure describes how to make and use particular examples, but the principles of this disclosure are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
Fig. 5 is a flow chart illustrating a method of predicting temperature information according to another exemplary embodiment. The flow shown in fig. 5 is a detailed description of the establishment of the temperature prediction model.
As shown in fig. 5, in S502, historical observation data and historical pattern forecast data of a plurality of weather stations are acquired.
In S504, a historical observation vector is generated based on the historical observation data. Can include the following steps: generating an initial observation vector through historical observation data of a plurality of meteorological sites; clustering the initial observation vectors of the meteorological sites to generate a plurality of meteorological site sets, wherein the meteorological site sets comprise a plurality of meteorological sites; and generating the historical observation vector by historical observation data of a plurality of weather stations in the set of weather stations.
In one embodiment, the specific steps of clustering the initial observation vectors of the plurality of meteorological sites to generate a plurality of meteorological site sets may be as follows:
1. acquiring historical observation data of each station, including longitude and latitude coordinates, altitude, annual average air temperature and annual precipitation, to form a feature vector V;
2. randomly selecting k initialization centers from the data according to the empirical value, and setting the maximum iteration number T;
3. calculating the vector distance d between the characteristic vector V of each station and each initialization central point;
4. classifying points nearest to the initialization center into one class according to d obtained in the third step, and repeating the steps 4 and 5;
5. iterating to the maximum iteration time T, and stopping the calculation;
6. finally, a clustered site distribution graph is obtained, and each site is classified into a category.
In one embodiment, as shown in FIG. 6, the elements required for the machine learning model are mainly composed of two broad categories, observation data elements and pattern data elements. The factors used for observing the data include temperature, 10min wind speed, relative humidity, dew point temperature and the like. For time T, these elements constitute a vector. A plurality of past time elements are combined to form a time series as a larger vector.
In one embodiment, the normalization process can be performed for all input variables, and the default normalization process is z-score normalization, while also supporting MinMax normalization.
In S506, historical fused data is generated based on the historical pattern forecast data. The temperature element of the pattern data is also used when forecasting the weather station temperature. And giving a weight according to the distance from the station, wherein the closer the distance, the larger the weight is, an interpolation result is obtained to assist the observation data to carry out model prediction. Thereafter, the observation elements and the pattern elements are integrated as an input form of the machine learning model.
In S508, a gradient boost model is trained by the historical observation vector and historical fusion data to generate the temperature prediction model. Can include the following steps: generating training set data and test set data through the historical observation vector and the historical fusion data; training a gradient lifting model through the training set data to generate an initial temperature prediction model; and testing the initial temperature prediction model through the test set data, and generating the temperature prediction model when the conditions are met.
In one embodiment, training a gradient boost model with the training set data generates an initial temperature prediction model, comprising: determining an objective function; substituting the training set data into the gradient lifting model; calculating a target function and a loss function by the forward propagation of the gradient lifting model; the gradient lifting model reversely propagates and updates the network weight; and generating the initial temperature prediction model when a preset objective function is met.
In one embodiment, model training may be performed by:
1. dividing a data set aiming at each category k, randomly selecting about 65% of data as a training set, 15% of data as a verification set and 20% of data as a test set;
2. designing an objective function: root Mean Square Error (RMSE) of model predicted values and true observed values;
3. forward propagation is carried out to calculate a target function and a loss function, and backward propagation is carried out to update the network weight;
4. and outputting and storing the model parameters according to the categories and the forecast time.
The gradient boosting model (LightGBM) is a gradient boosting framework, and a decision tree based on a learning algorithm is used. Different from other decision tree models, the LightGBM is more suitable for processing mass data due to the existence of two technologies of data parallel and feature parallel.
LightGBM has the following advantages:
1. faster training speed: with histogram-based algorithms, successive feature (attribute) values are segmented to speed training and reduce memory usage. Meanwhile, the sparse matrix is optimized correspondingly.
2. Higher accuracy: LightGBM grows trees by the leaf-wise (best-first) strategy. It will choose the leaf node with the largest loss difference to grow. When growing the same leaf node, the leaf-wise algorithm may reduce the penalty more than the level-wise algorithm. When the amount of data is small, the leaf-wise may cause an overfitting. The LightGBM may limit the depth of the tree and avoid overfitting with the maximum depth parameter.
According to the temperature information prediction method, the clustering of the sites with similar data distribution is realized, and the problem of insufficient data quantity of single observation sites can be solved.
FIG. 7 is a flow chart illustrating a method of predicting temperature information in accordance with another exemplary embodiment. FIG. 7 details the overall process of meteorological prediction model training and testing.
As shown in fig. 7, in S702, the acquired meteorological data is preprocessed.
In S704, feature selection of data is performed.
In S706, a training set is generated.
In S708, a test set is generated.
In S710, the gradient boost model is trained using the training set data.
In S712, a temperature prediction model is generated.
In S714, the temperature is predicted using the test data.
In S714, a test value of the temperature is obtained. The test values may also be compared to the actual occurring temperatures to make adjustments to the meteorological prediction model.
Based on the temperature information prediction method in the disclosure, the overall error of the temperature is greatly improved, and the error improvement of the sites in the southwest area is particularly obvious, as shown in fig. 8. For temperature forecasts of 1-7 days, more than 90% of the station RMSE is reduced by more than 10%, as shown in fig. 9.
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the above-described methods provided by the present disclosure. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.
Fig. 10 is a block diagram illustrating a temperature information prediction apparatus according to an example embodiment. As shown in fig. 10, the temperature information prediction apparatus 100 includes: a data module 1002, a vector module 1004, a fusion module 1006, and a prediction module 1008.
The data module 1002 is configured to obtain observation data and mode forecast data of a meteorological site, where the observation data includes a plurality of element values;
the vector module 1004 is configured to generate an observation vector of the meteorological site based on the plurality of element values in the observation data and observation times corresponding to the element values;
a fusion module 1006 is configured to generate fusion data of the meteorological site based on the pattern forecast data; and
the prediction module 1008 is configured to input the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological site, wherein the temperature prediction model is generated by a gradient lifting algorithm.
Fig. 11 is a block diagram illustrating a temperature information prediction apparatus according to another exemplary embodiment. As shown in fig. 11, the temperature information prediction device 110 includes: a history data module 1102, a history vector module 1104, a history fusion module 1106, and a model training module 1108.
The historical data module 1102 is used for acquiring historical observation data and historical mode forecast data of a plurality of meteorological sites;
a history vector module 1104 for generating a history observation vector based on the history observation data;
the history fusion module 1106 is used for generating history fusion data based on the history mode forecast data; and
According to the temperature information prediction device disclosed by the invention, observation data and mode forecast data of a meteorological station are obtained; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological site, so that historical observation data and mode prediction data can be fused, the site data scale is expanded, and a more accurate temperature prediction result is obtained.
FIG. 12 is a block diagram illustrating an electronic device in accordance with an example embodiment.
An electronic device 1200 according to this embodiment of the disclosure is described below with reference to fig. 12. The electronic device 1200 shown in fig. 12 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 12, the electronic device 1200 is embodied in the form of a general purpose computing device. The components of the electronic device 1200 may include, but are not limited to: at least one processing unit 1210, at least one memory unit 1220, a bus 1230 connecting the various system components including the memory unit 1220 and the processing unit 1210, a display unit 1240, and the like.
Wherein the storage unit stores program codes, which can be executed by the processing unit 1210, so that the processing unit 1210 performs the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned electronic prescription flow processing method section of this specification. For example, the processing unit 1210 may perform the steps as shown in fig. 2, 5, 7.
The storage unit 1220 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM)12201 and/or a cache memory unit 12202, and may further include a read only memory unit (ROM) 12203.
The memory unit 1220 may also include a program/utility 12204 having a set (at least one) of program modules 12205, such program modules 12205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 1200 may also communicate with one or more external devices 1200' (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1200 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 1250. Also, the electronic device 1200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 1260. The network adapter 1260 may communicate with other modules of the electronic device 1200 via the bus 1230. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. The software product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element values; generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values; generating fusion data of the meteorological site based on the pattern forecast data; and inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Exemplary embodiments of the present disclosure are specifically illustrated and described above. It is to be understood that the present disclosure is not limited to the precise arrangements, instrumentalities, or instrumentalities described herein; on the contrary, the disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (12)
1. A method for predicting temperature information, comprising:
acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element values;
generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values;
generating fusion data of the meteorological site based on the pattern forecast data; and
inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm.
2. The method of claim 1, further comprising:
acquiring historical observation data and historical mode forecast data of a plurality of meteorological sites;
generating a historical observation vector based on the historical observation data;
generating historical fusion data based on the historical pattern forecast data; and
training a gradient boost model through the historical observation vectors and historical fusion data to generate the temperature prediction model.
3. The method of claim 2, wherein generating a historical observation vector based on historical observation data comprises:
generating an initial observation vector through historical observation data of a plurality of meteorological sites;
clustering the initial observation vectors of the meteorological sites to generate a plurality of meteorological site sets, wherein the meteorological site sets comprise a plurality of meteorological sites; and
generating the historical observation vector from historical observation data for a plurality of weather sites in the set of weather sites.
4. The method of claim 2, wherein training a gradient boost model through the historical observation vectors and historical fusion data to generate the temperature prediction model comprises:
generating training set data and test set data through the historical observation vector and the historical fusion data;
training a gradient lifting model through the training set data to generate an initial temperature prediction model; and
and testing the initial temperature prediction model through the test set data, and generating the temperature prediction model when the conditions are met.
5. The method of claim 4, wherein training a gradient boost model with the training set data generates an initial temperature prediction model comprising:
determining an objective function;
substituting the training set data into the gradient lifting model;
and when the gradient lifting model meets a preset objective function, generating the initial temperature prediction model.
6. The method of claim 4, wherein generating the initial temperature prediction model when the gradient boost model satisfies a preset objective function comprises:
calculating a target function and a loss function by the forward propagation of the gradient lifting model;
the gradient lifting model reversely propagates and updates the network weight; and
and calculating an objective function according to the network weight and the loss function.
7. The method of claim 1, wherein obtaining observation data and pattern forecast data for a meteorological site comprises:
carrying out missing value processing on the observation data; and/or
Processing abnormal values of the observed data; and/or
And carrying out missing value processing on the pattern forecast data.
8. The method of claim 1, wherein generating fused data for the weather site based on the pattern forecast data comprises:
determining a fusion weight for the pattern forecast data based on a distance between a pattern forecast site that generated the pattern forecast data and the weather site; and
and carrying out interpolation processing on the mode forecast data based on the fusion weight to generate the fusion data.
9. The method of claim 8, wherein interpolating the pattern forecast data based on the fusion weights to generate the fusion data comprises:
distributing fusion weight for each mode forecast data;
a summation calculation is performed based on each mode prediction data and its corresponding weight to generate the fused data.
10. The method of claim 1, wherein inputting the observation vector and the fused data into a temperature prediction model to generate temperature prediction information for the meteorological site comprises:
inputting the observation vector and the fused data into the temperature prediction model;
the temperature prediction model is used for calculating and generating temperature values under a plurality of time nodes based on the observation vector and the fusion data; and
and generating the temperature prediction information through the temperature values at the plurality of time nodes.
11. A temperature information prediction apparatus, comprising:
the data module is used for acquiring observation data and mode forecast data of a meteorological site, wherein the observation data comprises a plurality of element numerical values;
the vector module is used for generating an observation vector of the meteorological site based on the plurality of element numerical values in the observation data and the observation time corresponding to the element numerical values;
the fusion module is used for generating fusion data of the meteorological site based on the mode forecast data; and
and the prediction module is used for inputting the observation vector and the fusion data into a temperature prediction model to generate temperature prediction information of the meteorological station, wherein the temperature prediction model is generated through a gradient lifting algorithm.
12. The apparatus of claim 11, further comprising:
the historical data module is used for acquiring historical observation data and historical mode forecast data of a plurality of meteorological sites;
the historical vector module is used for generating a historical observation vector based on the historical observation data;
the history fusion module is used for generating history fusion data based on the history mode forecast data; and
and the model training module is used for training a gradient lifting model through the historical observation vector and the historical fusion data to generate the temperature prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911098395.2A CN112308281A (en) | 2019-11-12 | 2019-11-12 | Temperature information prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911098395.2A CN112308281A (en) | 2019-11-12 | 2019-11-12 | Temperature information prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112308281A true CN112308281A (en) | 2021-02-02 |
Family
ID=74336229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911098395.2A Pending CN112308281A (en) | 2019-11-12 | 2019-11-12 | Temperature information prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308281A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075751A (en) * | 2021-03-26 | 2021-07-06 | 国网河南省电力公司电力科学研究院 | Method and system for fusing observation data in short-term forecasting |
| CN114298389A (en) * | 2021-12-22 | 2022-04-08 | 中科三清科技有限公司 | Ozone concentration forecasting method and device |
| CN114372212A (en) * | 2022-03-21 | 2022-04-19 | 国家超级计算天津中心 | Numerical weather forecasting method and device based on supercomputer |
| CN114594532A (en) * | 2022-03-09 | 2022-06-07 | 北京墨迹风云科技股份有限公司 | Method and device for predicting cold weather, electronic equipment and computer readable medium |
| CN115859222A (en) * | 2022-12-28 | 2023-03-28 | 四川省气象灾害防御技术中心 | Lightning automatic prediction method based on multi-gradient feature fusion network |
| TWI806064B (en) * | 2021-06-08 | 2023-06-21 | 遠東科技大學 | Method, computer program, and computer readable medium for controlling agricultural field environmental parameters in advance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108518804A (en) * | 2018-03-21 | 2018-09-11 | 武汉物联远科技有限公司 | A kind of machine room humiture environmental forecasting method and system |
| CN109031472A (en) * | 2017-06-09 | 2018-12-18 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device for weather prognosis |
| CN109991685A (en) * | 2019-04-03 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of precipitation prediction technique and device based on more LSTM Model Fusions |
| CN110334732A (en) * | 2019-05-20 | 2019-10-15 | 北京思路创新科技有限公司 | A kind of Urban Air Pollution Methods and device based on machine learning |
-
2019
- 2019-11-12 CN CN201911098395.2A patent/CN112308281A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109031472A (en) * | 2017-06-09 | 2018-12-18 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device for weather prognosis |
| CN108518804A (en) * | 2018-03-21 | 2018-09-11 | 武汉物联远科技有限公司 | A kind of machine room humiture environmental forecasting method and system |
| CN109991685A (en) * | 2019-04-03 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of precipitation prediction technique and device based on more LSTM Model Fusions |
| CN110334732A (en) * | 2019-05-20 | 2019-10-15 | 北京思路创新科技有限公司 | A kind of Urban Air Pollution Methods and device based on machine learning |
Non-Patent Citations (3)
| Title |
|---|
| 张明;王硕;喻慧;: "基于低空风预测模型的救援航迹修正规划方法", 西南交通大学学报, no. 06 * |
| 朱衍波;郭运韬;张军;: "基于AMDAR的航路气象模型研究", 航空电子技术, no. 02, pages 18 - 23 * |
| 谭江红;陈伟亮;王珊珊;: "一种机器学习方法在湖北定时气温预报中的应用试验", 气象科技进展, no. 05 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075751A (en) * | 2021-03-26 | 2021-07-06 | 国网河南省电力公司电力科学研究院 | Method and system for fusing observation data in short-term forecasting |
| TWI806064B (en) * | 2021-06-08 | 2023-06-21 | 遠東科技大學 | Method, computer program, and computer readable medium for controlling agricultural field environmental parameters in advance |
| CN114298389A (en) * | 2021-12-22 | 2022-04-08 | 中科三清科技有限公司 | Ozone concentration forecasting method and device |
| CN114594532A (en) * | 2022-03-09 | 2022-06-07 | 北京墨迹风云科技股份有限公司 | Method and device for predicting cold weather, electronic equipment and computer readable medium |
| CN114372212A (en) * | 2022-03-21 | 2022-04-19 | 国家超级计算天津中心 | Numerical weather forecasting method and device based on supercomputer |
| CN114372212B (en) * | 2022-03-21 | 2022-07-08 | 国家超级计算天津中心 | Numerical weather forecasting method and device based on supercomputer |
| CN115859222A (en) * | 2022-12-28 | 2023-03-28 | 四川省气象灾害防御技术中心 | Lightning automatic prediction method based on multi-gradient feature fusion network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112308281A (en) | Temperature information prediction method and device | |
| US11598900B2 (en) | Weather-driven multi-category infrastructure impact forecasting | |
| Farsi et al. | Parallel genetic algorithms for optimizing the SARIMA model for better forecasting of the NCDC weather data | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN110705115B (en) | Weather forecast method and system based on deep belief network | |
| Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
| Yahya et al. | Designing weather forecasting model using computational intelligence tools | |
| JP2016136001A (en) | Prediction device | |
| CN105528652A (en) | Method and terminal for establishing prediction model | |
| CN112613642B (en) | Emergency material demand prediction method and device, storage medium and electronic equipment | |
| Zjavka | Numerical weather prediction revisions using the locally trained differential polynomial network | |
| CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| WO2022039675A1 (en) | Method and apparatus for forecasting weather, electronic device and storage medium thereof | |
| CN116799796A (en) | Photovoltaic power generation power prediction method, device, equipment and medium | |
| Molinar et al. | Ampacity forecasting: an approach using Quantile Regression Forests | |
| Manoj et al. | FWS-DL: forecasting wind speed based on deep learning algorithms | |
| CN111105050B (en) | Fan maintenance plan generation method, device, equipment and storage medium | |
| JP2021182319A (en) | Prediction apparatus and prediction method | |
| Mohd et al. | Comparative study of rainfall prediction modeling techniques (A case study on Srinagar, J&K, India) | |
| CN116760006A (en) | Wind power prediction method, device, equipment and storage medium | |
| CN115630979A (en) | Day-ahead electricity price prediction method and device, storage medium and computer equipment | |
| CN114282657A (en) | Market data long-term prediction model training method, device, equipment and storage medium | |
| Gaudiani et al. | A computational methodology applied to optimize the performance of a river model under uncertainty conditions | |
| Chen et al. | Operational scenario definition in traffic simulation-based decision support systems: Pattern recognition using a clustering algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |