Extreme air temperature forecasting method and device and storage medium

Abstract

The invention relates to the technical field of air temperature forecasting, in particular to an extreme air temperature forecasting method and device and a storage medium. The method comprises the following steps: acquiring historical meteorological observation data within a preset historical time period in a preset territorial range; according to the historical meteorological observation data, determining a time sequence of a typical spatial mode in a preset territorial range; determining a key circulation factor according to the circulation factor and the time sequence corresponding to the circulation factor; determining predicted circulation factor data according to the weather forecast data; determining an extreme air temperature predicted value in a preset prediction time period according to the predicted circulation factor data; constructing an air temperature distance flat field in a preset territorial range according to the extreme air temperature predicted value; determining extreme temperature forecast in the preset prediction time period according to the weather forecast data in the preset prediction time period; and updating the extreme air temperature forecast through the air temperature distance flat field, and determining the updated extreme air temperature forecast as a target extreme air temperature forecast within the preset prediction time period in the preset territorial range.

Description

Technical Field

[0001] The present application relates to the technical field of temperature forecasting, and in particular to a method, device and storage medium for extreme temperature forecasting. Background Art

[0002] In recent years, driven by global warming, extreme temperature events have become more frequent and stronger. Summer temperatures can cause a surge in air conditioning power load and equipment overload, while also leading to drought disasters. On the one hand, this can significantly reduce the supply of hydropower, causing power supply shortages; on the other hand, continued droughts can cause wildfires, seriously threatening the safety of power transmission equipment and further exacerbating the power supply shortage.

[0003] In terms of temperature forecasting, the meteorological department can use regional numerical models to carry out medium- and short-term refined forecasts within 2 weeks, but its forecast time is relatively short. The monthly and seasonal scale forecasting methods based on global models or statistical dynamic models can only predict temperature anomalies and changing trends, and cannot accurately predict temperature extremes. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and storage medium for extreme temperature forecasting that accurately forecasts temperature extremes.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for extreme temperature forecasting, the method comprising:

[0006] Obtaining historical meteorological observation data within a preset historical time period within a preset geographical area, wherein the meteorological observation data includes a variety of circulation factors, daily maximum temperature, and daily minimum temperature;

[0007] Determine the time series of typical spatial modes within a preset geographical area based on historical meteorological observation data;

[0008] For each circulation factor, the key circulation factor is determined according to the circulation factor and the time series corresponding to the circulation factor;

[0009] Determining predicted circulation factor data of key circulation factors within a preset prediction time period based on weather forecast data within a preset prediction time period;

[0010] Determine the predicted value of extreme temperature within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period;

[0011] Construct a temperature anomaly field within a preset geographical range based on the extreme temperature forecast values ​​within a preset forecast period;

[0012] Determine the extreme temperature forecast within the preset prediction time period according to the weather forecast data within the preset prediction time period;

[0013] The extreme temperature forecast is updated through the temperature anomaly field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

[0014] In an embodiment of the present application, the extreme temperature prediction values ​​include a maximum temperature prediction value and a minimum temperature prediction value, and constructing a temperature deviation field within a preset geographical range based on the extreme temperature prediction values ​​within a preset prediction time period includes: determining multiple historical time intervals within a preset historical time period corresponding to the preset prediction time period, wherein the interval duration between the historical time interval and the prediction time period is an integer multiple of the preset duration; determining the average maximum temperature and the average minimum temperature within the preset geographical range based on the historical meteorological observation data of each historical time interval; and constructing a temperature deviation field within the preset geographical range based on a first difference between the maximum temperature prediction value and the average maximum temperature within the preset prediction time period, and a second difference between the minimum temperature prediction value and the average minimum temperature within the prediction time period.

[0015] In an embodiment of the present application, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for a preset geographical range within a preset prediction time period, including: determining the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast; determining the sum of the minimum temperature forecast within the preset prediction time period and the second difference as the target minimum temperature forecast.

[0016] In an embodiment of the present application, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the extreme temperature forecast value for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period; for each day within the preset prediction time period, determining the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the day; for each day within the prediction time period, determining the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day.

[0017] In an embodiment of the present application, the method also includes: before determining the extreme temperature prediction value within a preset prediction time period based on the predicted circulation factor data within a preset prediction time period, determining the key circulation factor observation value within the preset historical time period and the daily maximum temperature observation value and the daily minimum temperature observation value of the date corresponding to the key circulation factor observation value based on historical meteorological observation data; using a first preset proportion of key factor observation values ​​as training input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the first preset proportion of key factor observation values ​​as training output values ​​to train the temperature prediction model; when the training accuracy of the temperature prediction model reaches the preset accuracy, using a second preset proportion of key factor observation values ​​as test input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the second preset proportion of key factor observation values ​​as test output values ​​to test the temperature prediction model; when the test accuracy of the temperature prediction model reaches the preset accuracy, determining that the training of the temperature prediction model is completed.

[0018] In an embodiment of the present application, determining the extreme temperature prediction value within a preset prediction time period based on the prediction circulation factor data within the preset prediction time period includes: inputting the prediction circulation factor data within the preset prediction time period into a trained temperature prediction model, and outputting the extreme temperature prediction value corresponding to the prediction circulation factor within the prediction time period through the trained temperature prediction model.

[0019] In an embodiment of the present application, determining a time series of typical spatial modes within a preset geographical scope based on historical meteorological observation data includes: determining the highest temperature and the lowest temperature within each preset historical time range within a preset historical time period based on the historical meteorological observation data; performing empirical orthogonal function decomposition on the highest temperature and the lowest temperature within multiple preset historical time ranges to obtain a time series of typical spatial modes within the preset geographical scope.

[0020] In an embodiment of the present application, for each circulation factor, determining the key circulation factor based on the circulation factor and the time series corresponding to the circulation factor includes: for each circulation factor, determining the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor; and determining the circulation factor whose correlation coefficient is greater than a preset value as the key circulation factor.

[0021] A second aspect of the present application provides a device for extreme temperature forecasting, comprising:

[0022] A data acquisition module is used to acquire historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a variety of circulation factors, daily maximum temperature and daily minimum temperature;

[0023] A time series determination module is used to determine the time series of typical spatial modes within a preset geographical range based on historical meteorological observation data;

[0024] A key circulation factor determination module, for determining the key circulation factor for each circulation factor according to the circulation factor and a time series corresponding to the circulation factor;

[0025] A data prediction module, used to determine predicted circulation factor data of key circulation factors within a preset prediction time period based on weather forecast data within a preset prediction time period; and also used to determine predicted extreme temperature values ​​within a preset prediction time period based on predicted circulation factor data within a preset prediction time period;

[0026] A temperature anomaly field construction module is used to construct a temperature anomaly field within a preset geographical range based on the extreme temperature forecast values ​​within a preset forecast time period;

[0027] The extreme temperature forecast module is used to determine the extreme temperature forecast within a preset prediction time period based on the weather forecast data within the preset prediction time period; it is also used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

[0028] In an embodiment of the present application, the extreme temperature prediction values ​​include a maximum temperature prediction value and a minimum temperature prediction value, and the temperature deviation field construction module is used to construct a temperature deviation field within a preset geographical range according to the extreme temperature prediction values ​​within a preset prediction time period, including: determining multiple historical time intervals within a preset historical time period corresponding to a preset prediction time period, wherein the interval duration between the historical time interval and the prediction time period is an integer multiple of the preset duration; determining the average maximum temperature and the average minimum temperature within the preset geographical range according to the historical meteorological observation data of each historical time interval; constructing a temperature deviation field within the preset geographical range according to a first difference between the maximum temperature prediction value and the average maximum temperature within the preset prediction time period, and a second difference between the minimum temperature prediction value and the average minimum temperature within the prediction time period.

[0029] In an embodiment of the present application, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module is used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for a preset geographical range within a preset prediction time period. The forecast includes: determining the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast; determining the sum of the minimum temperature forecast within the preset prediction time period and the second difference as the target minimum temperature forecast.

[0030] In an embodiment of the present application, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module is used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the extreme temperature forecast value for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period; for each day within the preset prediction time period, determining the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the day; for each day within the prediction time period, determining the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day.

[0031] In an embodiment of the present application, the device also includes: a model training module, which is used to determine the key circulation factor observation values ​​within the preset historical time period and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​of the dates corresponding to the key circulation factor observation values ​​according to historical meteorological observation data before determining the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period; use the key factor observation values ​​of a first preset proportion as training input values, and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​corresponding to the key factor observation values ​​of the first preset proportion as training output values ​​to train the temperature prediction model; when the training accuracy of the temperature prediction model reaches the preset accuracy, use the key factor observation values ​​of a second preset proportion as test input values, and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​corresponding to the key factor observation values ​​of the second preset proportion as test output values ​​to test the temperature prediction model; when the test accuracy of the temperature prediction model reaches the preset accuracy, it is determined that the training of the temperature prediction model is completed.

[0032] In an embodiment of the present application, a data prediction module is used to determine the extreme temperature prediction value within a preset prediction time period based on the prediction circulation factor data within the preset prediction time period, including: inputting the prediction circulation factor data within the preset prediction time period into a trained temperature prediction model, and outputting the extreme temperature prediction value corresponding to the prediction circulation factor within the prediction time period through the trained temperature prediction model.

[0033] In an embodiment of the present application, a time series determination module is used to determine the time series of typical spatial modes within a preset geographical scope based on historical meteorological observation data, including: determining the maximum temperature and the minimum temperature within each preset historical time range within a preset historical time period based on historical meteorological observation data; performing empirical orthogonal function decomposition on the maximum temperature and the minimum temperature within multiple preset historical time ranges to obtain a time series of typical spatial modes within a preset geographical scope.

[0034] In an embodiment of the present application, a key circulation factor determination module is used to determine the key circulation factor for each circulation factor based on the circulation factor and the time series corresponding to the circulation factor, including: determining the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor for each circulation factor; and determining the circulation factor whose correlation coefficient is greater than a preset value as the key circulation factor.

[0035] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute a method for extreme temperature forecasting according to any one of the above-mentioned embodiments.

[0036] Through the above technical scheme, the circulation factors are optimized, the key circulation factors are selected, the extreme temperatures are predicted through the key circulation factors, and the temperature deviation field is established. Then, the extreme temperatures predicted by ordinary weather forecast data are adjusted through the temperature deviation field, thereby improving the forecast accuracy of extreme temperatures.

[0037] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0039] Figure 1 A schematic diagram of a process flow of a method for extreme temperature forecasting according to an embodiment of the present application is shown;

[0040] Figure 2 The structure block diagram of an extreme temperature forecasting device according to an embodiment of the present application is schematically shown;

[0041] Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme 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. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0043] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0044] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0045] Figure 1 The flowchart of a method for extreme temperature forecasting according to an embodiment of the present application is schematically shown. Figure 1 As shown, an embodiment of the present application provides a method for extreme temperature forecasting, which may include the following steps.

[0046] Step 101, obtaining historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a plurality of circulation factors, daily maximum temperature, and daily minimum temperature;

[0047] Step 102, determining a time series of a typical spatial mode within a preset geographical range according to historical meteorological observation data;

[0048] Step 103, for each circulation factor, determining a key circulation factor according to the circulation factor and a time series corresponding to the circulation factor;

[0049] Step 104, determining predicted circulation factor data of key circulation factors within a preset prediction time period according to weather forecast data within a preset prediction time period;

[0050] Step 105, determining the extreme temperature prediction value within the preset prediction time period according to the prediction circulation factor data within the preset prediction time period;

[0051] Step 106, constructing a temperature anomaly field within a preset geographical range according to the extreme temperature prediction values ​​within a preset prediction time period;

[0052] Step 107, determining the extreme temperature forecast within the preset prediction time period according to the weather forecast data within the preset prediction time period;

[0053] Step 108, updating the extreme temperature forecast through the temperature anomaly field, and determining the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

[0054] The processor can obtain historical meteorological observation data within a preset historical time period within a preset range, wherein the historical meteorological observation data includes a variety of circulation factors, daily maximum temperature and daily minimum temperature. The processor can perform empirical orthogonal function decomposition based on the historical meteorological observation data to obtain a time series of typical spatial modes within a preset geographical range. For each circulation factor in the historical meteorological observation data, the processor can determine the key circulation factor based on the circulation factor and the time series corresponding to the circulation factor. For example, the processor can determine the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor, and select the key circulation factor based on the correlation coefficient. After determining the key circulation factor, the processor can determine the predicted circulation factor data of the key circulation factor within the preset prediction time period based on the weather forecast data within the prediction time period, and then determine the extreme temperature prediction value within the preset prediction time period based on the predicted circulation factor data within the prediction time period. After the processor determines the extreme temperature prediction value within the preset prediction time period through the predicted circulation factor data, it can construct the temperature anomaly field within the preset geographical range based on the extreme temperature prediction value within the preset prediction time period. The processor can also determine the extreme temperature forecast within the preset prediction event period based on the weather forecast data within the preset prediction time period, and the processor then updates the extreme temperature forecast obtained through the weather forecast data through the established temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The embodiment of the present application optimizes the circulation factors, selects key circulation factors, predicts the extreme temperature through the key circulation factors, establishes the temperature deviation field, and then adjusts the extreme temperature predicted by the ordinary weather forecast data through the temperature deviation field, thereby improving the forecast accuracy for extreme temperature.

[0055] In one embodiment, the extreme temperature prediction values ​​include a maximum temperature prediction value and a minimum temperature prediction value, and constructing a temperature deviation field within a preset geographical range based on the extreme temperature prediction values ​​within a preset prediction time period includes: determining multiple historical time intervals within a preset historical time period corresponding to a preset prediction time period, wherein the interval duration between the historical time interval and the prediction time period is an integer multiple of the preset duration; determining the average maximum temperature and the average minimum temperature within the preset geographical range based on historical meteorological observation data of each historical time interval; and constructing a temperature deviation field within the preset geographical range based on a first difference between the maximum temperature prediction value and the average maximum temperature within the preset prediction time period, and a second difference between the minimum temperature prediction value and the average minimum temperature within the prediction time period.

[0056] The extreme temperature prediction value includes the maximum temperature prediction value and the minimum temperature prediction value. When the processor constructs the temperature deviation field within the preset geographical range according to the extreme temperature prediction value within the preset prediction time period, it can determine multiple historical time intervals corresponding to the preset prediction time period within the preset historical time period, and the interval between the historical time interval and the prediction time period is an integer multiple of the preset time length. For example, assuming that the processor sets the preset historical time period to 30 years, the preset time length is 1 year, and the preset prediction time period is the nth month of the year, the processor can determine the nth month of each year in the historical time period as the historical time interval corresponding to the preset prediction time period. After determining multiple historical time intervals, the processor can determine the daily maximum temperature and daily minimum temperature of each day in each historical time interval within the preset geographical range according to the historical meteorological observation data corresponding to each historical time interval, thereby determining the average maximum temperature and average minimum temperature within this time interval within the preset geographical range. The processor can determine a first difference between the maximum temperature prediction value of a preset geographical range within a preset prediction time period and the average maximum temperature within the preset geographical range, and a second difference between the minimum temperature prediction value of the preset geographical range within the preset prediction time period and the average minimum temperature within the preset geographical range. Based on the first difference and the second difference, the processor can construct a temperature deviation field for the maximum temperature and a temperature deviation field for the minimum temperature within the preset geographical range.

[0057] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for a preset geographical range within a preset prediction time period. The forecast includes: determining the sum of the maximum temperature forecast within the preset prediction time period and a first difference as the target maximum temperature forecast; and determining the sum of the minimum temperature forecast within the preset prediction time period and a second difference as the target minimum temperature forecast.

[0058] The extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. After the processor determines the first difference between the maximum temperature forecast value of the preset geographical range within the preset prediction time period and the average maximum temperature within the preset geographical range, and the second difference between the minimum temperature forecast value of the preset geographical range within the preset prediction time period and the average minimum temperature within the preset geographical range, the processor can update the extreme temperature forecast through the temperature deviation field. The processor can determine the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast for the preset geographical range within the preset prediction time period. Similarly, the processor can determine the sum of the minimum temperature forecast within the preset prediction time period and the second difference as the target minimum temperature forecast for the preset geographical range within the preset prediction time period. For example, the processor can set the preset prediction time period to monthly, and the above scheme can be used to achieve effective monthly prediction of extreme temperatures.

[0059] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the extreme temperature forecast value for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period; for each day within the preset prediction time period, determining the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the day; for each day within the prediction time period, determining the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day.

[0060] The extreme temperature forecast also includes a maximum temperature forecast and a minimum temperature forecast. After the processor determines a first difference between the maximum temperature forecast value of the preset geographical range within the preset prediction time period and the average maximum temperature within the preset geographical range, and a second difference between the minimum temperature forecast value of the preset geographical range within the preset prediction time period and the average minimum temperature within the preset geographical range, the processor can update the extreme temperature forecast through the temperature deviation field. The processor can determine the maximum temperature forecast and the minimum temperature forecast for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period. For each day within the preset prediction time period, the processor can determine the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the preset geographical range on the day. Similarly, for each day within the preset prediction time period, the processor can determine the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the preset geographical range on the day.

[0061] In one embodiment, the method also includes: before determining the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period, determining the key circulation factor observation value within the preset historical time period and the daily maximum temperature observation value and the daily minimum temperature observation value of the date corresponding to the key circulation factor observation value according to the historical meteorological observation data; using the key factor observation values ​​of a first preset proportion as training input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation values ​​of the first preset proportion as training output values ​​to train the temperature prediction model; when the training accuracy of the temperature prediction model reaches the preset accuracy, using the key factor observation values ​​of a second preset proportion as test input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation values ​​of the second preset proportion as test output values ​​to test the temperature prediction model; when the test accuracy of the temperature prediction model reaches the preset accuracy, determining that the training of the temperature prediction model is completed.

[0062] Before determining the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period, the processor can determine the key circulation factor observation value corresponding to the key circulation factor within the preset historical time period according to the historical meteorological observation data, and determine the daily maximum temperature observation value and the daily minimum temperature observation value of the date corresponding to the key circulation factor observation value. That is to say, for each day within the historical preset time period, the processor can determine the key circulation factor observation value, the daily maximum temperature observation value and the daily minimum temperature observation value of the day. The processor can divide the acquired key factor observation values, use the key factor observation values ​​of the first preset ratio as training input values, and use the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation value of the first preset ratio as training output values ​​to train the temperature prediction model. The temperature prediction model can be a model established by a convolutional neural network algorithm. The processor can input the key factor observation value into the temperature prediction model to output the daily maximum temperature training value and the daily minimum temperature training value through the temperature prediction model, and then compare the daily maximum temperature training value and the daily minimum temperature training value with the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the input data, and adjust the parameters of the temperature prediction model until the temperature The degree of overlap between the daily minimum temperature training value output by the prediction model and the input data and the corresponding daily maximum temperature observation value and daily minimum temperature observation value reaches a preset overlap, that is, the training accuracy of the temperature prediction model reaches a preset accuracy. At this time, the processor can use the key factor observation value of the second preset proportion as the test input value to output the daily maximum temperature test value and the daily minimum temperature test value through the temperature prediction model, and compare the output daily maximum temperature test value and the daily minimum temperature test value with the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the input key factor observation value for testing. When the test accuracy of the temperature prediction model reaches the preset accuracy, the processor can determine that the training of the temperature prediction model is completed.

[0063] In one embodiment, determining the extreme temperature prediction value within a preset prediction time period based on the prediction circulation factor data within the preset prediction time period includes: inputting the prediction circulation factor data within the preset prediction time period into a trained temperature prediction model, and outputting the extreme temperature prediction value corresponding to the prediction circulation factor within the prediction time period through the trained temperature prediction model.

[0064] When the processor determines the extreme temperature prediction value within a preset prediction time period based on the predicted circulation factor data within the preset prediction time period, the processor can input the predicted circulation factor data within the preset prediction time period into a trained temperature prediction model, and output the extreme temperature prediction value corresponding to the predicted circulation factor within the prediction time period through the trained temperature prediction model, that is, the maximum temperature prediction value and the minimum temperature prediction value corresponding to the predicted circulation factor data.

[0065] In one embodiment, determining a time series of a typical spatial mode within a preset geographical scope based on historical meteorological observation data includes: determining the highest temperature and the lowest temperature within each preset historical time range within a preset historical time period based on the historical meteorological observation data; performing empirical orthogonal function decomposition on the highest temperature and the lowest temperature within multiple preset historical time ranges to obtain a time series of a typical spatial mode within the preset geographical scope.

[0066] The processor can determine the maximum temperature and the minimum temperature within each preset historical time range within the preset historical time period based on the historical meteorological observation data. For example, the processor can reduce the preset historical time range to determine each month included in each summer and winter. The processor can determine the maximum temperature and the minimum temperature of each month in summer and winter based on the historical meteorological observation data. Based on the multiple maximum temperatures and minimum temperatures obtained, the processor can decompose them through empirical orthogonal functions to obtain a time series of typical spatial modes within a preset geographical range.

[0067] In one embodiment, for each circulation factor, determining the key circulation factor based on the circulation factor and the time series corresponding to the circulation factor includes: for each circulation factor, determining the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor; and determining the circulation factor with a correlation coefficient greater than a preset value as the key circulation factor.

[0068] The processor can select a key circulation factor from the multiple circulation factors included in the historical observation data. The processor can determine, for each circulation factor, the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor, and determine the circulation factor whose correlation coefficient is greater than a preset value set by the processor as the key circulation factor.

[0069] like Figure 2 As shown, in one embodiment, a device 200 for forecasting extreme temperature is provided, comprising:

[0070] The data acquisition module 201 is used to acquire historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a plurality of circulation factors, daily maximum temperature and daily minimum temperature;

[0071] A time series determination module 202 is used to determine a time series of a typical spatial mode within a preset geographical range according to historical meteorological observation data;

[0072] A key circulation factor determination module 203 is used to determine the key circulation factor for each circulation factor according to the circulation factor and the time series corresponding to the circulation factor;

[0073] The data prediction module 204 is used to determine the predicted circulation factor data of the key circulation factor within the preset prediction time period according to the weather forecast data within the preset prediction time period; and is also used to determine the predicted value of the extreme temperature within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period;

[0074] The temperature anomaly field construction module 205 is used to construct the temperature anomaly field within a preset geographical range according to the extreme temperature prediction value within a preset prediction time period;

[0075] The extreme temperature forecast module 206 is used to determine the extreme temperature forecast within a preset prediction time period based on the weather forecast data within the preset prediction time period; it is also used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

[0076] In one embodiment, the time series determination module 202 is used to determine the time series of typical spatial modes within a preset geographical scope based on historical meteorological observation data, including: determining the maximum temperature and the minimum temperature within each preset historical time range within a preset historical time period based on historical meteorological observation data; performing empirical orthogonal function decomposition on the maximum temperature and the minimum temperature within multiple preset historical time ranges to obtain the time series of typical spatial modes within the preset geographical scope.

[0077] In one embodiment, the key circulation factor determination module 203 is used to determine the key circulation factor for each circulation factor based on the circulation factor and the time series corresponding to the circulation factor, including: determining the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor for each circulation factor; and determining the circulation factor with a correlation coefficient greater than a preset value as the key circulation factor.

[0078] In one embodiment, the device also includes: a model training module 207, which is used to determine the key circulation factor observation values ​​within the preset historical time period and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​of the dates corresponding to the key circulation factor observation values ​​according to historical meteorological observation data before determining the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period; use the key factor observation values ​​of a first preset proportion as training input values, and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​corresponding to the key factor observation values ​​of the first preset proportion as training output values ​​to train the temperature prediction model; when the training accuracy of the temperature prediction model reaches the preset accuracy, use the key factor observation values ​​of a second preset proportion as test input values, and the daily maximum temperature observation values ​​and daily minimum temperature observation values ​​corresponding to the key factor observation values ​​of the second preset proportion as test output values ​​to test the temperature prediction model; when the test accuracy of the temperature prediction model reaches the preset accuracy, it is determined that the training of the temperature prediction model is completed.

[0079] In one embodiment, the data prediction module 204 is used to determine the extreme temperature prediction value within a preset prediction time period based on the prediction circulation factor data within the preset prediction time period, including: inputting the prediction circulation factor data within the preset prediction time period into a trained temperature prediction model, and outputting the extreme temperature prediction value corresponding to the prediction circulation factor within the prediction time period through the trained temperature prediction model.

[0080] In one embodiment, the extreme temperature prediction values ​​include the maximum temperature prediction value and the minimum temperature prediction value. The temperature deviation field construction module 205 is used to construct the temperature deviation field within the preset geographical range according to the extreme temperature prediction values ​​within the preset prediction time period, including: determining multiple historical time intervals corresponding to the preset prediction time period within the preset historical time period, wherein the interval between the historical time interval and the prediction time period is an integer multiple of the preset time length; determining the average maximum temperature and the average minimum temperature within the preset geographical range according to the historical meteorological observation data of each historical time interval; constructing the temperature deviation field within the preset geographical range according to the first difference between the maximum temperature prediction value and the average maximum temperature within the preset prediction time period, and the second difference between the minimum temperature prediction value and the average minimum temperature within the prediction time period.

[0081] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module 206 is used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast; determining the sum of the minimum temperature forecast within the preset prediction time period and the second difference as the target minimum temperature forecast.

[0082] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module 206 is used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the extreme temperature forecast value for each day within the preset prediction time period according to the weather forecast data within the preset prediction time period; for each day within the preset prediction time period, determining the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the day; for each day within the prediction time period, determining the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day.

[0083] The data acquisition module 201 can acquire historical meteorological observation data within a preset historical time period within a preset range, wherein the historical meteorological observation data include multiple circulation factors, daily maximum temperature and daily minimum temperature. The time series determination module 202 can perform empirical orthogonal function decomposition based on the historical meteorological observation data to obtain a time series of typical spatial modes within a preset geographical range. For each circulation factor in the historical meteorological observation data, the key circulation factor determination module 203 can determine the key circulation factor based on the circulation factor and the time series corresponding to the circulation factor. The key circulation factor determination module 203 can determine the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor for each circulation factor, and determine the circulation factor whose correlation coefficient is greater than the preset value set by the processor as the key circulation factor.

[0084] After the key circulation factor determination module 203 determines the key circulation factor, the model training module 207 can determine the key circulation factor observation value corresponding to the key circulation factor within the preset historical time period based on the historical meteorological observation data, and determine the daily maximum temperature observation value and the daily minimum temperature observation value of the date corresponding to the key circulation factor observation value. The model training module 207 can divide the acquired key factor observation values, use the key factor observation values ​​of a first preset ratio as training input values, and use the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation values ​​of the first preset ratio as training output values ​​to train the temperature prediction model. The temperature prediction model can be a model established by a convolutional neural network algorithm. The model training module 207 can input the key factor observation values ​​into the temperature prediction model to output the daily maximum temperature training value and the daily minimum temperature training value through the temperature prediction model, and then compare the daily maximum temperature training value and the daily minimum temperature training value with the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the input data, and adjust the parameters of the temperature prediction model until the temperature The overlap between the daily minimum temperature training value output by the prediction model and the input data and the corresponding daily maximum temperature observation value and daily minimum temperature observation value reaches the preset overlap, that is, the training accuracy of the temperature prediction model reaches the preset accuracy. At this time, the model training module 207 can use the key factor observation value of the second preset ratio as the test input value to output the daily maximum temperature test value and the daily minimum temperature test value through the temperature prediction model, and compare the output daily maximum temperature test value and the daily minimum temperature test value with the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation value input for testing. When the test accuracy of the temperature prediction model reaches the preset accuracy, the model training module 207 can determine that the training of the temperature prediction model is completed. The data prediction module 204 can determine the predicted circulation factor data of the key circulation factor in the preset prediction time period according to the weather forecast data in the prediction time period, and then input the predicted circulation factor data in the preset prediction time period into the trained temperature prediction model, and output the extreme temperature prediction value corresponding to the predicted circulation factor in the prediction time period through the trained temperature prediction model, that is, the maximum temperature prediction value and the minimum temperature prediction value corresponding to the predicted circulation factor data.

[0085] After the data prediction module 204 determines the extreme temperature prediction value within the preset prediction time period by predicting the circulation factor data, the temperature deviation field construction module 205 can construct the temperature deviation field within the preset geographical range according to the extreme temperature prediction value within the preset prediction time period. The extreme temperature prediction value includes the maximum temperature prediction value and the minimum temperature prediction value. When constructing the temperature deviation field within the preset geographical range according to the extreme temperature prediction value within the preset prediction time period, the temperature deviation field construction module 205 can determine multiple historical time intervals corresponding to the preset prediction time period within the preset historical time period, and the interval between the historical time interval and the prediction time period is an integer multiple of the preset time length. For example, assuming that the processor sets the preset historical time period to 30 years, the preset time length is 1 year, and the preset prediction time period is the nth month of a year, the processor can determine the nth month of each year in the historical time period as the historical time interval corresponding to the preset prediction time period. After determining multiple historical time intervals, the temperature deviation field construction module 205 can determine the daily maximum temperature and daily minimum temperature of each day in each historical time interval within the preset geographical range according to the historical meteorological observation data corresponding to each historical time interval, thereby determining the average maximum temperature and average minimum temperature within the preset geographical range in this time interval. The temperature deviation field construction module 205 can determine a first difference between the maximum temperature prediction value of the preset geographical range within the preset prediction time period and the average maximum temperature within the preset geographical range, and a second difference between the minimum temperature prediction value of the preset geographical range within the preset prediction time period and the average minimum temperature within the preset geographical range. According to the first difference and the second difference, the processor can construct a temperature deviation field for the maximum temperature and a temperature deviation field for the minimum temperature within the preset geographical range.

[0086] The extreme temperature forecast module 206 can also determine the extreme temperature forecast within the preset prediction event segment according to the weather forecast data within the preset prediction time period. The extreme temperature forecast includes the maximum temperature forecast and the minimum temperature forecast. After the extreme temperature forecast module 206 determines the first difference between the maximum temperature forecast value within the preset prediction time period and the average maximum temperature within the preset geographical range, and the second difference between the minimum temperature forecast value within the preset prediction time period and the average minimum temperature within the preset geographical range, the extreme temperature forecast module 206 can update the extreme temperature forecast through the temperature deviation field. The extreme temperature forecast module 206 can determine the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast within the preset prediction time period for the preset geographical range. Similarly, the extreme temperature forecast module 206 can determine the sum of the minimum temperature forecast within the preset prediction time period and the second difference as the target minimum temperature forecast within the preset prediction time period for the preset geographical range. For example, the extreme temperature forecast module 206 can set the preset prediction time period to monthly, and the above scheme can achieve effective monthly prediction of extreme temperature.

[0087] Furthermore, the extreme temperature forecast module 206 can determine the maximum temperature forecast and the minimum temperature forecast for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period. For each day within the preset prediction time period, the extreme temperature forecast module 206 can determine the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the preset geographical scope on the day. Similarly, for each day within the preset prediction time period, the extreme temperature forecast module 206 can determine the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day within the preset geographical scope.

[0088] The above technical scheme optimizes the circulation factors, selects key circulation factors, and predicts the extreme temperatures based on the key circulation factors through the key modeling between the key circulation factors and the extreme temperatures. The temperature anomaly field is then used to adjust the extreme temperatures predicted by ordinary weather forecast data, thereby improving the forecast accuracy for extreme temperatures.

[0089] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. Those skilled in the art will understand that

[0090] In one embodiment, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the method for extreme temperature forecasting according to any one of the above embodiments.

[0091] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store relevant data of the temperature. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for extreme temperature forecasting is implemented.

[0092] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the program: obtaining historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a plurality of circulation factors, a daily maximum temperature, and a daily minimum temperature; determining a time series of a typical spatial mode within a preset geographical range based on the historical meteorological observation data; determining a key circulation factor for each circulation factor based on the circulation factor and a time series corresponding to the circulation factor; determining predicted circulation factor data of the key circulation factor within a preset prediction time period based on weather forecast data within a preset prediction time period; determining an extreme temperature prediction value within a preset prediction time period based on the predicted circulation factor data within the preset prediction time period; constructing a temperature anomaly field within a preset geographical range based on the extreme temperature prediction value within the preset prediction time period; determining an extreme temperature forecast within the preset prediction time period based on the weather forecast data within the preset prediction time period; updating the extreme temperature forecast through the temperature anomaly field, and determining the updated extreme temperature forecast as a target extreme temperature forecast for the preset geographical range within the preset prediction time period.

[0093] In one embodiment, the extreme temperature prediction values ​​include a maximum temperature prediction value and a minimum temperature prediction value, and constructing a temperature deviation field within a preset geographical range based on the extreme temperature prediction values ​​within a preset prediction time period includes: determining multiple historical time intervals within a preset historical time period corresponding to a preset prediction time period, wherein the interval duration between the historical time interval and the prediction time period is an integer multiple of the preset duration; determining the average maximum temperature and the average minimum temperature within the preset geographical range based on historical meteorological observation data of each historical time interval; and constructing a temperature deviation field within the preset geographical range based on a first difference between the maximum temperature prediction value and the average maximum temperature within the preset prediction time period, and a second difference between the minimum temperature prediction value and the average minimum temperature within the prediction time period.

[0094] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for a preset geographical range within a preset prediction time period. The forecast includes: determining the sum of the maximum temperature forecast within the preset prediction time period and a first difference as the target maximum temperature forecast; and determining the sum of the minimum temperature forecast within the preset prediction time period and a second difference as the target minimum temperature forecast.

[0095] In one embodiment, the extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast is updated through the temperature deviation field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The forecast includes: determining the extreme temperature forecast value for each day within the preset prediction time period based on the weather forecast data within the preset prediction time period; for each day within the preset prediction time period, determining the sum of the maximum temperature forecast for the day and the first difference as the target maximum temperature forecast for the day; for each day within the prediction time period, determining the sum of the minimum temperature forecast for the day and the second difference as the target minimum temperature forecast for the day.

[0096] In one embodiment, the method also includes: before determining the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period, determining the key circulation factor observation value within the preset historical time period and the daily maximum temperature observation value and the daily minimum temperature observation value of the date corresponding to the key circulation factor observation value according to the historical meteorological observation data; using the key factor observation values ​​of a first preset proportion as training input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation values ​​of the first preset proportion as training output values ​​to train the temperature prediction model; when the training accuracy of the temperature prediction model reaches the preset accuracy, using the key factor observation values ​​of a second preset proportion as test input values, and the daily maximum temperature observation value and the daily minimum temperature observation value corresponding to the key factor observation values ​​of the second preset proportion as test output values ​​to test the temperature prediction model; when the test accuracy of the temperature prediction model reaches the preset accuracy, determining that the training of the temperature prediction model is completed.

[0097] In one embodiment, determining the extreme temperature prediction value within a preset prediction time period based on the prediction circulation factor data within the preset prediction time period includes: inputting the prediction circulation factor data within the preset prediction time period into a trained temperature prediction model, and outputting the extreme temperature prediction value corresponding to the prediction circulation factor within the prediction time period through the trained temperature prediction model.

[0098] In one embodiment, determining a time series of a typical spatial mode within a preset geographical scope based on historical meteorological observation data includes: determining the highest temperature and the lowest temperature within each preset historical time range within a preset historical time period based on the historical meteorological observation data; performing empirical orthogonal function decomposition on the highest temperature and the lowest temperature within multiple preset historical time ranges to obtain a time series of a typical spatial mode within the preset geographical scope.

[0099] In one embodiment, for each circulation factor, determining the key circulation factor based on the circulation factor and the time series corresponding to the circulation factor includes: for each circulation factor, determining the correlation coefficient between the circulation factor and the time series corresponding to the circulation factor; and determining the circulation factor with a correlation coefficient greater than a preset value as the key circulation factor.

[0100] 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.

[0101] 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 processor, 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.

[0102] 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.

[0103] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0108] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for extreme temperature forecasting, characterized in that: The method comprises: Acquire historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a plurality of circulation factors, daily maximum temperature, and daily minimum temperature; Determine the time series of typical spatial modes within the preset geographical range according to the historical meteorological observation data; For each circulation factor, determining a key circulation factor according to the circulation factor and a time series corresponding to the circulation factor; Determining predicted circulation factor data of key circulation factors within a preset prediction time period based on weather forecast data within a preset prediction time period; Determine the predicted value of extreme temperature within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period; Constructing a temperature anomaly field within the preset geographical range according to the extreme temperature forecast value within the preset forecast time period; Determining the extreme temperature forecast within the preset prediction time period according to the weather forecast data within the preset prediction time period; The extreme temperature forecast is updated through the temperature anomaly field, and the updated extreme temperature forecast is determined as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

2. The method for extreme temperature forecasting according to claim 1, characterized in that: The extreme temperature prediction values ​​include a maximum temperature prediction value and a minimum temperature prediction value, and constructing the temperature anomaly field within the preset geographical range according to the extreme temperature prediction values ​​within the preset prediction time period includes: Determine a plurality of historical time intervals within the preset historical time period corresponding to the preset prediction time period, wherein the interval between the historical time interval and the prediction time period is an integer multiple of the preset interval; Determine the average maximum temperature and the average minimum temperature within the preset geographical area according to the historical meteorological observation data of each historical time interval; The temperature anomaly field within the preset geographical range is constructed based on a first difference between the maximum temperature forecast value within the preset forecast time period and the average maximum temperature, and a second difference between the minimum temperature forecast value within the forecast time period and the average minimum temperature.

3. The method for extreme temperature forecasting according to claim 2, characterized in that: The extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The updating of the extreme temperature forecast by using the temperature anomaly field and determining the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period includes: Determine the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast; The sum of the minimum temperature forecast within the preset prediction time period and the second difference is determined as the target minimum temperature forecast.

4. The method for extreme temperature forecasting according to claim 2, characterized in that: The extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The updating of the extreme temperature forecast by using the temperature anomaly field and determining the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period includes: Determining the extreme temperature forecast value for each day within the preset prediction time period according to the weather forecast data within the preset prediction time period; For each day within the preset prediction time period, determining the sum of the maximum temperature forecast for that day and the first difference as the target maximum temperature forecast for that day; For each day within the forecast time period, the sum of the minimum temperature forecast for that day and the second difference is determined as the target minimum temperature forecast for that day.

5. The method for extreme temperature forecasting according to claim 1, characterized in that: The method further comprises: Before determining the extreme temperature forecast value within the preset forecast time period according to the forecast circulation factor data within the preset forecast time period, determining the key circulation factor observation value within the preset historical time period and the daily maximum temperature observation value and the daily minimum temperature observation value on the date corresponding to the key circulation factor observation value according to the historical meteorological observation data; Using a first preset ratio of key factor observation values ​​as training input values, and using a daily maximum temperature observation value and a daily minimum temperature observation value corresponding to the first preset ratio of key factor observation values ​​as training output values ​​to train the temperature prediction model; When the training accuracy of the temperature prediction model reaches a preset accuracy, the temperature prediction model is tested by using a second preset proportion of key factor observations as test input values, and the daily maximum temperature observations and daily minimum temperature observations corresponding to the second preset proportion of key factor observations as test output values; When the test accuracy of the temperature prediction model reaches the preset accuracy, it is determined that the training of the temperature prediction model is completed.

6. The method for extreme temperature forecasting according to claim 5, characterized in that: Determining the extreme temperature prediction value within the preset prediction time period according to the prediction circulation factor data within the preset prediction time period includes: The predicted circulation factor data within the preset prediction time period is input into the trained temperature prediction model, and the trained temperature prediction model outputs the extreme temperature prediction value corresponding to the predicted circulation factor within the prediction time period.

7. The method for extreme temperature forecasting according to claim 1, characterized in that: Determining the time series of typical spatial modes within the preset geographical range according to the historical meteorological observation data includes: Determine the highest temperature and the lowest temperature within each preset historical time range within the preset historical time period according to the historical meteorological observation data; The maximum and minimum temperatures within multiple preset historical time ranges are subjected to empirical orthogonal function decomposition to obtain a time series of typical spatial modes within a preset geographical range.

8. The method for extreme temperature forecasting according to claim 1, characterized in that: The determining of the key circulation factor for each circulation factor according to the circulation factor and the time series corresponding to the circulation factor comprises: For each circulation factor, determining a correlation coefficient between the circulation factor and a time series corresponding to the circulation factor; The circulation factor whose correlation coefficient is greater than a preset value is determined as the key circulation factor.

9. An extreme temperature forecasting device, characterized in that: include: A data acquisition module, used to acquire historical meteorological observation data within a preset historical time period within a preset geographical range, wherein the meteorological observation data includes a plurality of circulation factors, daily maximum temperature and daily minimum temperature; A time series determination module, used to determine the time series of the typical spatial mode within the preset geographical range according to the historical meteorological observation data; A key circulation factor determination module, used for determining the key circulation factor for each circulation factor according to the circulation factor and a time series corresponding to the circulation factor; A data prediction module, used to determine predicted circulation factor data of key circulation factors within a preset prediction time period according to weather forecast data within a preset prediction time period; and also used to determine predicted extreme temperature values ​​within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period; A temperature anomaly field construction module, used to construct a temperature anomaly field within the preset geographical range according to the extreme temperature prediction value within the preset prediction time period; The extreme temperature forecast module is used to determine the extreme temperature forecast within the preset prediction time period based on the weather forecast data within the preset prediction time period; it is also used to update the extreme temperature forecast through the temperature deviation field, and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period.

10. The device for extreme temperature forecasting according to claim 9, characterized in that: The extreme temperature prediction values ​​include the maximum temperature prediction value and the minimum temperature prediction value. The temperature anomaly field construction module is used to construct the temperature anomaly field within the preset geographical range according to the extreme temperature prediction values ​​within the preset prediction time period, and includes: Determine a plurality of historical time intervals within the preset historical time period corresponding to the preset prediction time period, wherein the interval between the historical time interval and the prediction time period is an integer multiple of the preset interval; Determine the average maximum temperature and the average minimum temperature within the preset geographical area according to the historical meteorological observation data of each historical time interval; The temperature anomaly field within the preset geographical range is constructed based on a first difference between the maximum temperature forecast value within the preset forecast time period and the average maximum temperature, and a second difference between the minimum temperature forecast value within the forecast time period and the average minimum temperature.

11. The device for extreme temperature forecasting according to claim 10, characterized in that: The extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module is used to update the extreme temperature forecast through the temperature anomaly field and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The extreme temperature forecast includes: Determine the sum of the maximum temperature forecast within the preset prediction time period and the first difference as the target maximum temperature forecast; The sum of the minimum temperature forecast within the preset prediction time period and the second difference is determined as the target minimum temperature forecast.

12. The device for extreme temperature forecasting according to claim 10, characterized in that: The extreme temperature forecast includes a maximum temperature forecast and a minimum temperature forecast. The extreme temperature forecast module is used to update the extreme temperature forecast through the temperature anomaly field and determine the updated extreme temperature forecast as the target extreme temperature forecast for the preset geographical range within the preset prediction time period. The extreme temperature forecast includes: Determining the extreme temperature forecast value for each day within the preset prediction time period according to the weather forecast data within the preset prediction time period; For each day within the preset prediction time period, determining the sum of the maximum temperature forecast for that day and the first difference as the target maximum temperature forecast for that day; For each day within the forecast time period, the sum of the minimum temperature forecast for that day and the second difference is determined as the target minimum temperature forecast for that day.

13. The device for extreme temperature forecasting according to claim 9, characterized in that: The device also includes: A model training module is used to determine the key circulation factor observation value within the preset historical time period and the daily maximum temperature observation value and the daily minimum temperature observation value on the date corresponding to the key circulation factor observation value based on historical meteorological observation data before determining the extreme temperature prediction value within the preset prediction time period based on the predicted circulation factor data within the preset prediction time period; Using a first preset ratio of key factor observation values ​​as training input values, and using a daily maximum temperature observation value and a daily minimum temperature observation value corresponding to the first preset ratio of key factor observation values ​​as training output values ​​to train the temperature prediction model; When the training accuracy of the temperature prediction model reaches a preset accuracy, the temperature prediction model is tested by using a second preset proportion of key factor observations as test input values, and the daily maximum temperature observations and daily minimum temperature observations corresponding to the second preset proportion of key factor observations as test output values; When the test accuracy of the temperature prediction model reaches the preset accuracy, it is determined that the training of the temperature prediction model is completed.

14. The device for extreme temperature forecasting according to claim 13, characterized in that: The data prediction module, which is used to determine the extreme temperature prediction value within the preset prediction time period according to the predicted circulation factor data within the preset prediction time period, includes: The predicted circulation factor data within the preset prediction time period is input into the trained temperature prediction model, and the trained temperature prediction model outputs the extreme temperature prediction value corresponding to the predicted circulation factor within the prediction time period.

15. The device for extreme temperature forecasting according to claim 9, characterized in that: The time series determination module, which is used to determine the time series of the typical spatial mode within the preset geographical range according to the historical meteorological observation data, includes: Determine the highest temperature and the lowest temperature within each preset historical time range within the preset historical time period according to the historical meteorological observation data; The maximum and minimum temperatures within multiple preset historical time ranges are subjected to empirical orthogonal function decomposition to obtain a time series of typical spatial modes within a preset geographical range.

16. The device for extreme temperature forecasting according to claim 9, characterized in that: The key circulation factor determination module is used to determine the key circulation factor for each circulation factor according to the circulation factor and the time series corresponding to the circulation factor, including: For each circulation factor, determining a correlation coefficient between the circulation factor and a time series corresponding to the circulation factor; The circulation factor whose correlation coefficient is greater than a preset value is determined as the key circulation factor.

17. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute the method for extreme temperature forecasting according to any one of claims 1 to 8.

Images