Method and apparatus for predicting seasonal precipitation in middle- and high-latitude regions, and device and medium

Abstract

A method and apparatus for predicting seasonal precipitation in middle- and high-latitude regions, and a device and a medium. Rich historical precipitation data and a set of climate factor indices are used to perform regional division on a region to be predicted, and precipitation data of each sub-region obtained after division, together with a comprehensive climate factor index, can then be used to establish a seasonal precipitation target prediction model for predicting seasonal precipitation in middle- and high-latitude regions, thereby improving the prediction accuracy of the model, and providing a prediction reference for the planning requirements of industries such as hydropower generation.

Description

Method, device, equipment and medium for predicting seasonal precipitation in middle and high latitude regions

[0001] The present application claims priority to the Chinese patent application No. 202410896637.7, filed on July 4, 2024, and entitled "Method, device, equipment and medium for predicting seasonal precipitation in middle and high latitude regions", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of climate prediction, in particular to a method, device, equipment and medium for predicting seasonal precipitation in middle and high latitude regions. BACKGROUND

[0003] Short-term climate prediction mainly refers to the prediction of climate at the scales of month, season and year. Accurate prediction has important decision-making value for disaster prevention and reduction and industry planning. In the past 30 years, dynamic climate models have made great progress in improving the prediction of seasonal precipitation. However, the prediction skill is limited to the tropical region, and the prediction skill for regions outside the tropics, especially middle and high latitude regions, is significantly lower, which is difficult to meet the needs of disaster prevention and reduction and various industries. In addition, the research on the prediction method of seasonal precipitation in middle and high latitudes is far less than that in the tropics and subtropics, and the prediction skill of climate dynamic models is significantly lower. It is extremely difficult, costly and time-consuming to improve the prediction skill of the model, and it is still a great challenge to achieve the required accuracy of seasonal precipitation. Therefore, it is necessary to propose new technical methods to solve the existing problems.

[0004] SUMMARY

[0005] Therefore, the present application provides a method, device, equipment and medium for predicting seasonal precipitation in middle and high latitude regions to solve the problem that the prediction method of seasonal precipitation in middle and high latitudes is less and the prediction skill is significantly lower in the prior art.

[0006] In a first aspect, the present application provides a method for predicting seasonal precipitation in middle and high latitude regions, which comprises:

[0007] obtaining a historical daily precipitation data set and a set of 130 climate factor indexes; dividing the region to be predicted using the historical daily precipitation data set and the set of climate factor indexes to obtain a plurality of sub-regions; obtaining a plurality of four-season precipitation history sequences of the plurality of sub-regions in a preset time period; calculating a set of prediction factors based on the set of climate factor indexes and the plurality of four-season precipitation history sequences through a first relationship; establishing a target prediction model for seasonal precipitation in middle and high latitude regions using the set of prediction factors; and predicting the seasonal precipitation in middle and high latitude regions of the region to be predicted using the target prediction model for seasonal precipitation in middle and high latitude regions to obtain a seasonal precipitation prediction result.

[0008] The seasonal precipitation prediction method for middle and high latitude regions provided in the application can improve the prediction accuracy of the model and provide a prediction reference basis for the planning needs of the hydropower industry and the like by dividing the region to be predicted into sub-regions through rich historical precipitation data and a climate factor index set, and then establishing a seasonal precipitation target prediction model for predicting the seasonal precipitation in middle and high latitude regions by combining the precipitation data of each sub-region after the division and comprehensive climate factor indexes.

[0009] In an optional implementation, a region to be predicted is divided into a plurality of sub-regions by using a historical daily precipitation data set and a climate factor index set, including:

[0010] A first precipitation in each season of the region to be predicted within a preset time period is calculated by using the historical daily precipitation data set; a plurality of climate factor indexes of the region to be predicted within the preset time period are obtained based on the climate factor index set; a first correlation coefficient of each climate factor index and each first precipitation within the preset time period is calculated by using a first relationship; and the region to be predicted is divided into a plurality of sub-regions based on each first correlation coefficient.

[0011] The seasonal precipitation prediction method for middle and high latitude regions provided in the application can calculate the first precipitation in each season of the region to be predicted within a preset time period by using the obtained rich historical precipitation data, and can divide the region to be predicted into sub-regions according to the calculated first correlation coefficient of each climate factor index and each first precipitation, thereby realizing objective regionalization of the region to be predicted.

[0012] In an optional implementation, a prediction factor set is obtained by using a first relationship based on the climate factor index set and a plurality of four-season precipitation historical sequences, including:

[0013] A plurality of second correlation coefficients are obtained by using a first relationship based on the climate factor index set and a plurality of four-season precipitation historical sequences; a plurality of confidence level values of the plurality of second correlation coefficients are obtained; and a prediction factor set is determined in the climate factor index set based on the plurality of confidence level values.

[0014] The seasonal precipitation prediction method for middle and high latitude regions provided in the application can select a prediction factor set that meets the conditions in the climate factor index set by using the calculated confidence level values of the plurality of second correlation coefficients of the climate factor index set and the plurality of four-season precipitation historical sequences of the plurality of sub-regions after the division, thereby providing support for the subsequent model establishment with a multi-factor data set having physical meaning.

[0015] In an optional implementation, a seasonal precipitation target prediction model for middle and high latitude regions is established by using the prediction factor set, including:

[0016] obtaining a seasonal precipitation observation sequence of a to-be-predicted region in a preset time period; establishing an initial prediction model of seasonal precipitation in a middle-high latitude region by using a prediction factor set; calculating a seasonal precipitation fitting sequence of the to-be-predicted region in the preset time period by using the initial prediction model of seasonal precipitation; and verifying the initial prediction model of seasonal precipitation by using the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence until a target prediction model of seasonal precipitation in the middle-high latitude region is obtained.

[0017] The method for predicting seasonal precipitation in a middle-high latitude region provided in the application can verify the initial prediction model of seasonal precipitation by using the seasonal precipitation observation sequence of the to-be-predicted region in the preset time period and the seasonal precipitation fitting sequence of the to-be-predicted region in the preset time period calculated by using the initial prediction model of seasonal precipitation, so that the target prediction model of seasonal precipitation in the middle-high latitude region that meets the conditions can be obtained, the prediction accuracy of the model is improved, the defect that the dynamic climate model has a low prediction skill in the middle-high latitude region is made up for, and prediction reference bases are provided for planning requirements of the hydropower and other industries.

[0018] In an optional implementation, the initial prediction model of seasonal precipitation is verified by using the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence until the target prediction model of seasonal precipitation in the middle-high latitude region is obtained, and the verification includes:

[0019] The third correlation coefficient of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence is calculated by using a first relationship, the root mean square error of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence is calculated by using a second relationship, and the initial prediction model of seasonal precipitation is verified based on the third correlation coefficient and the root mean square error until the target prediction model of seasonal precipitation in the middle-high latitude region is obtained.

[0020] The method for predicting seasonal precipitation in a middle-high latitude region provided in the application can verify the initial prediction model of seasonal precipitation by calculating the correlation coefficient and the root mean square error of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence, so that the target prediction model of seasonal precipitation in the middle-high latitude region that meets the conditions can be obtained, the prediction accuracy of the model is improved, and prediction reference bases are provided for planning requirements of the hydropower and other industries.

[0021] In a second aspect, the application provides a device for predicting seasonal precipitation in a middle-high latitude region, and the device includes:

[0022] The first obtaining module is configured to obtain a historical daily precipitation data set and a climate factor index set; the division module is configured to divide a to-be-predicted region into a plurality of sub-regions by using the historical daily precipitation data set and the climate factor index set; the second obtaining module is configured to obtain a plurality of four-season precipitation history sequences of the plurality of sub-regions in a preset time period; the calculation module is configured to obtain a prediction factor set by using the climate factor index set and the plurality of four-season precipitation history sequences through a first relationship formula; the establishment module is configured to establish a seasonal precipitation target prediction model of a mid-high latitude region by using the prediction factor set; and the prediction module is configured to predict seasonal precipitation of the mid-high latitude region of the to-be-predicted region by using the seasonal precipitation target prediction model, and obtain a seasonal precipitation prediction result.

[0023] In an optional implementation, the division module comprises: a first calculation submodule configured to calculate a first precipitation of each season of the to-be-predicted region in a preset time period by using the historical daily precipitation data set; a first obtaining submodule configured to obtain a plurality of climate factor indexes of the to-be-predicted region in the preset time period based on the climate factor index set; a second calculation submodule configured to calculate a first correlation coefficient of each climate factor index and each first precipitation in the preset time period by using the first relationship formula; and a division submodule configured to divide the to-be-predicted region into a plurality of sub-regions based on each first correlation coefficient.

[0024] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, which are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the seasonal precipitation prediction method of the mid-high latitude region according to the first aspect or any one of the corresponding embodiments thereof.

[0025] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the seasonal precipitation prediction method of the mid-high latitude region according to the first aspect or any one of the corresponding embodiments thereof.

[0026] In a fifth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the seasonal precipitation prediction method of the mid-high latitude region according to the first aspect or any one of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0028] Fig. 1 is a flowchart of a seasonal precipitation prediction method in a high-middle latitude area according to an embodiment of the present application;

[0029] Fig. 2 is a flowchart of another seasonal precipitation prediction method in a high-middle latitude area according to an embodiment of the present application;

[0030] Fig. 3 is a flowchart of still another seasonal precipitation prediction method in a high-middle latitude area according to an embodiment of the present application;

[0031] Fig. 4 is a structural block diagram of a seasonal precipitation prediction device in a high-middle latitude area according to an embodiment of the present application;

[0032] Fig. 5 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0034] The embodiments of the present application provide a seasonal precipitation prediction method in a high-middle latitude area. The method divides a to-be-predicted area into regions based on abundant historical precipitation data, and establishes a seasonal precipitation target prediction model of seasonal precipitation in a high-middle latitude area to achieve and improve the accuracy of the seasonal precipitation prediction result in the high-middle latitude area.

[0035] According to the embodiments of the present application, a seasonal precipitation prediction method in a high-middle latitude area is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] A seasonal precipitation prediction method for middle and high latitude regions is provided in the embodiment, which can be used in electronic devices such as computers, mobile phones, tablet computers and the like. FIG. 1 is a flowchart of the seasonal precipitation prediction method for middle and high latitude regions according to the embodiment of the present application. As shown in FIG. 1, the flow includes the following steps:

[0037] In step S101, a historical daily precipitation data set and a climate factor index set are obtained.

[0038] Specifically, the historical daily precipitation data set can be obtained through a plurality of meteorological observation stations.

[0039] Optionally, the climate factor index set can also be obtained through the corresponding meteorological bureau.

[0040] In step S102, the historical daily precipitation data set and the climate factor index set are used to divide the region to be predicted into a plurality of sub-regions.

[0041] Specifically, in order to improve the accuracy of the seasonal precipitation prediction for middle and high latitude regions, the region to be predicted needs to be divided.

[0042] In the embodiment, the objective division of the region can be realized through the obtained rich historical daily precipitation data set.

[0043] In step S103, a plurality of seasonal precipitation history sequences of the plurality of sub-regions in a preset time period are obtained.

[0044] The preset time period represents a period of time in the past history, and the four seasons are spring (March-May), summer (June-August), autumn (September-November), and winter (December-February of the next year).

[0045] Specifically, the precipitation of each season of each sub-region in the preset time period can be obtained through the meteorological observation station.

[0046] In step S104, based on the climate factor index set and the plurality of seasonal precipitation history sequences, a prediction factor set is obtained through a first relationship.

[0047] The first relationship is used to represent the correlation between the climate factor index set and the plurality of seasonal precipitation history sequences.

[0048] Specifically, by processing the climate factor index set and the plurality of seasonal precipitation history sequences through the first relationship, the corresponding prediction factor set can be determined in the climate factor index set.

[0049] In step S105, a seasonal precipitation target prediction model for middle and high latitude regions is established using the prediction factor set.

[0050] Specifically, the seasonal precipitation target prediction model for predicting the seasonal precipitation in the middle and high latitude areas can be established by the prediction factors, thereby improving the prediction accuracy of the model and providing a prediction reference for the planning requirements of the hydropower industry and the like.

[0051] In step S106, the seasonal precipitation target prediction model is used to predict the seasonal precipitation in the middle and high latitude areas of the to-be-predicted region, and a seasonal precipitation prediction result is obtained.

[0052] Specifically, the seasonal precipitation target prediction model established can be used to predict the seasonal precipitation in the middle and high latitude areas of the to-be-predicted region.

[0053] Optionally, in the prediction, the historical daily precipitation data set and the climate factor index set of the to-be-predicted region corresponding to the time can be input into the seasonal precipitation target prediction model, and the seasonal precipitation prediction result in the middle and high latitude areas of the to-be-predicted region can be obtained.

[0054] The seasonal precipitation prediction method for the middle and high latitude areas provided in this embodiment can divide the to-be-predicted region by using rich historical precipitation data, and then can establish the seasonal precipitation target prediction model for predicting the seasonal precipitation in the middle and high latitude areas by combining the precipitation data of each sub-region after the division and comprehensive climate factor indexes, thereby improving the prediction accuracy of the model and providing a prediction reference for the planning requirements of the hydropower industry and the like.

[0055] In this embodiment, a seasonal precipitation prediction method for middle and high latitude areas is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers and the like. FIG. 2 is a flowchart of the seasonal precipitation prediction method for middle and high latitude areas according to an embodiment of the present application. As shown in FIG. 2, the flowchart includes the following steps:

[0056] In step S201, a historical daily precipitation data set and a climate factor index set are obtained. For details, refer to step S101 of the embodiment shown in FIG. 1, which will not be described here.

[0057] In step S202, the historical daily precipitation data set and the climate factor index set are used to divide the to-be-predicted region into a plurality of sub-regions.

[0058] Specifically, step S202 includes the following steps.

[0059] In step S2021, the historical daily precipitation data set is used to calculate a first precipitation in each season within a preset time period in the to-be-predicted region.

[0060] Specifically, the historical daily precipitation data set can include a plurality of daily precipitation data of a plurality of regions within a plurality of preset time periods.

[0061] Optionally, a plurality of daily precipitation data of the to-be-predicted region in a preset time period is obtained from the historical daily precipitation data set.

[0062] Optionally, the first precipitation of each season of the to-be-predicted region can be calculated from the obtained plurality of daily precipitation data of the to-be-predicted region in the preset time period.

[0063] In step S2022, a plurality of climate factor indexes of the to-be-predicted region in a preset time period is obtained based on the climate factor index set.

[0064] Specifically, the climate factor index set can include a plurality of climate factor indexes of a plurality of regions in a plurality of preset time periods.

[0065] In step S2023, a first correlation coefficient of each climate factor index and each first precipitation in the preset time period is calculated using a first relationship.

[0066] The first relationship is shown in the following relationship (1):

[0067] In the formula, r represents the correlation coefficient; x i represents the climate factor index; y i represents the precipitation sequence; represents the average value of the climate factor index; represents the average value of the precipitation sequence.

[0068] Specifically, the plurality of first precipitations calculated are combined to form a precipitation sequence, and the corresponding average precipitation is calculated.

[0069] Optionally, the average value of the obtained plurality of climate factor indexes is calculated.

[0070] Optionally, each climate factor index, precipitation sequence, average precipitation, and average climate factor index obtained are substituted into the above relationship (1) respectively, and a plurality of first correlation coefficients can be calculated.

[0071] In step S2024, the to-be-predicted region is regionally divided based on each first correlation coefficient, and a plurality of sub-regions is obtained.

[0072] Specifically, the spatial distribution map of the correlation coefficient can be drawn in combination with the plurality of first correlation coefficients calculated, and the corresponding distribution characteristics can be found.

[0073] Optionally, the to-be-predicted region is regionally divided in combination with the distribution characteristics, and a plurality of sub-regions is obtained.

[0074] In step S203, a plurality of historical sequences of seasonal precipitation in the preset time period are obtained for the plurality of sub-regions. For details, refer to step S103 of the embodiment shown in FIG. 1, which will not be repeated here.

[0075] In step S204, a set of prediction factors is obtained based on the set of climate factor indexes and the plurality of historical sequences of seasonal precipitation by using a first relationship.

[0076] Specifically, step S204 includes the following steps.

[0077] In step S2041, a plurality of second correlation coefficients are obtained based on the set of climate factor indexes and the plurality of historical sequences of seasonal precipitation by using the first relationship.

[0078] Specifically, the second correlation coefficients of the climate factor indexes and the historical sequences of seasonal precipitation for each sub-region can be calculated by using the relationship (1).

[0079] In step S2042, a plurality of confidence level values of the plurality of second correlation coefficients are obtained.

[0080] Specifically, the confidence level value of each second correlation coefficient is obtained.

[0081] In step S2043, a set of prediction factors is determined from the set of climate factor indexes based on the plurality of confidence level values.

[0082] The set of prediction factors can include a plurality of prediction factors of seasonal precipitation for each sub-region after division.

[0083] Specifically, the climate factor indexes with a confidence level value greater than 95% are selected from the set of climate factor indexes as the prediction factors.

[0084] In step S205, a target prediction model of seasonal precipitation in the mid-high latitude region is established by using the set of prediction factors. For details, refer to step S105 of the embodiment shown in FIG. 1, which will not be repeated here.

[0085] In step S206, the seasonal precipitation in the mid-high latitude region of the to-be-predicted region is predicted by using the target prediction model of seasonal precipitation, to obtain a prediction result of seasonal precipitation. For details, refer to step S106 of the embodiment shown in FIG. 1, which will not be repeated here.

[0086] The seasonal precipitation prediction method for middle and high latitude regions provided in the embodiment can calculate the first precipitation of each season of the region to be predicted within a preset time through the obtained rich historical precipitation data, and can optionally perform regional division on the region to be predicted according to the calculated each climate factor index and the first correlation coefficient of each first precipitation, so as to realize objective zoning of the region to be predicted. Optionally, the prediction factor set meeting the condition can be selected from the climate factor index set through the calculated confidence level values of the second correlation coefficients of the multiple four-season precipitation historical sequences of the multiple sub-regions after division, and then the seasonal precipitation target prediction model for predicting the seasonal precipitation of the middle and high latitude regions can be established through the prediction factor set, so as to improve the model prediction accuracy and provide a prediction reference for the planning needs of the hydropower industry and the like.

[0087] In the embodiment, a seasonal precipitation prediction method for middle and high latitude regions is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers and the like. FIG. 3 is a flowchart of the seasonal precipitation prediction method for middle and high latitude regions according to the embodiment of the present application. As shown in FIG. 3, the flowchart includes the following steps:

[0088] In step S301, a historical daily precipitation data set and a climate factor index set are obtained. For details, please refer to step S101 of the embodiment shown in FIG. 1, which will not be repeated here.

[0089] In step S302, the historical daily precipitation data set and the climate factor index set are used to divide the region to be predicted into multiple sub-regions. For details, please refer to step S202 of the embodiment shown in FIG. 2, which will not be repeated here.

[0090] In step S303, multiple four-season precipitation historical sequences of the multiple sub-regions within a preset time period are obtained. For details, please refer to step S103 of the embodiment shown in FIG. 1, which will not be repeated here.

[0091] In step S304, the prediction factor set is calculated through a first relationship based on the climate factor index set and the multiple four-season precipitation historical sequences. For details, please refer to step S204 of the embodiment shown in FIG. 2, which will not be repeated here.

[0092] In step S305, a seasonal precipitation target prediction model for middle and high latitude regions is established using the prediction factor set.

[0093] Specifically, step S305 includes:

[0094] In step S3051, a seasonal precipitation observation sequence of the region to be predicted within a preset time period is obtained.

[0095] Specifically, the seasonal precipitation observation sequence can be composed of multiple precipitation observation values of each season in a preset time period of the region to be predicted.

[0096] In step S3052, an initial seasonal precipitation prediction model of the middle and high latitude region is established by using the set of predictors.

[0097] Specifically, the initial seasonal precipitation prediction model is shown in the following relation (2):

[0098] In the formula, Y represents the fitted value of the seasonal precipitation of the region to be predicted; A CPTW represents the time of the equatorial Pacific 850 hPa zonal wind; represents the predictor; A TSA represents the tropical South Atlantic Ocean sea surface temperature index.

[0099] In step S3053, the fitted seasonal precipitation sequence of the region to be predicted in the preset time period is calculated by using the initial seasonal precipitation prediction model.

[0100] Specifically, the fitted seasonal precipitation sequence Y of the region to be predicted in the preset time period can be calculated by using the above relation (2).

[0101] In step S3054, the initial seasonal precipitation prediction model is verified by using the seasonal precipitation observation sequence and the fitted seasonal precipitation sequence, until the target seasonal precipitation prediction model of the middle and high latitude region is obtained.

[0102] Specifically, the initial seasonal precipitation prediction model established by using the above relation (2) can be verified by using the seasonal precipitation observation sequence and the fitted seasonal precipitation sequence, until the fitted seasonal precipitation sequence is closer to the seasonal precipitation observation sequence, and the corresponding target seasonal precipitation prediction model is obtained.

[0103] In some optional embodiments, the above step S3054 includes:

[0104] In step a1, a third correlation coefficient of the seasonal precipitation observation sequence and the fitted seasonal precipitation sequence is calculated by using a first relation.

[0105] In step a2, a root mean square error of the seasonal precipitation observation sequence and the fitted seasonal precipitation sequence is calculated by using a second relation.

[0106] In step a3, the initial seasonal precipitation prediction model is verified based on the third correlation coefficient and the root mean square error, until the target seasonal precipitation prediction model of the middle and high latitude region is obtained.

[0107] Specifically, the third correlation coefficient of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence can be calculated by using the above relationship (1).

[0108] Optionally, the root mean square error of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence can be calculated by using a second relationship shown in the following relationship (3):

[0109] In the formula, RMES represents the root mean square error, F(i) represents the seasonal precipitation fitting sequence, A(i) represents the seasonal precipitation observation sequence, and N represents the total number of years in the preset time period.

[0110] Optionally, the deviation between the seasonal precipitation fitting sequence and the seasonal precipitation observation sequence can be measured by the root mean square error, and when RMES = 0, it indicates that the seasonal precipitation fitting sequence and the seasonal precipitation observation sequence are completely consistent.

[0111] Optionally, the seasonal precipitation initial prediction model is verified by combining the third correlation coefficient and the root mean square error, and the corresponding seasonal precipitation target prediction model is obtained when the seasonal precipitation fitting sequence is closer to the seasonal precipitation observation sequence.

[0112] In step S306, the seasonal precipitation target prediction model is used to predict the seasonal precipitation in the middle and high latitude region of the to-be-predicted area, and a seasonal precipitation prediction result is obtained. For details, please refer to step S106 of the embodiment shown in FIG. 1, which will not be described here.

[0113] The seasonal precipitation prediction method for the middle and high latitude region provided in this embodiment divides the to-be-predicted area by using rich historical precipitation data and a climate factor index set, and the correlation coefficient and the root mean square error of the seasonal precipitation fitting sequence of the to-be-predicted area in the preset time period calculated by the seasonal precipitation observation sequence of the to-be-predicted area in the preset time period and the seasonal precipitation initial prediction model can be used to verify the seasonal precipitation initial prediction model and obtain the seasonal precipitation target prediction model for the middle and high latitude region that meets the conditions, thereby improving the model prediction accuracy and providing a prediction reference for the planning needs of the hydropower industry and the like.

[0114] In an example, taking a certain area A as an example, a physical statistical prediction method for seasonal precipitation in a middle and high latitude region is provided, including the following steps:

[0115] I. Area A division and seasonal precipitation sequence making.

[0116] 1. Using the daily precipitation data from 44 weather observation stations provided by the Meteorological Bureau of Region A, the precipitation of the four seasons is calculated. The four seasons are defined as: spring (March-May), summer (June-August), autumn (September-November), and winter (December-February of the following year).

[0117] 2. According to the above relationship (1), the precipitation of the four seasons in Region A from 1979 to 2021 is calculated. The correlation coefficient (r) between the index (climate factor index) and the precipitation of the four seasons in Region A during the same period is calculated, and the spatial distribution map of the correlation coefficient is drawn. Most of the correlations show a north-south and east-west reverse characteristic, so the region is divided into four areas: the northern part of Region A (5°S-5°N, 70°W-45°W, 9 stations), the eastern part of Region A (20°S-0°N, 45°W-35°W, 18 stations), the southern part of Region A (32°S-20°S, 60°W-40°W, 6 stations), and the western part of Region A (20°S-5°S, 70°W-45°W, 11 stations).

[0118] 3. The average precipitation of the four seasons in each region from 1979 to 2021 is calculated.

[0119] II. Selection of prediction factors. Using the 130 climate factor indices provided by the National Climate Center of the Meteorological Bureau and the four-season precipitation data of Region A from 1979 to 2016, a set of prediction factors for the four-season precipitation of the four regions is established.

[0120] 1. Calculate the R of the precipitation of each season in each region and the climate factor 2 months ahead from 1979 to 2016. Calculate the R of the autumn (September-November) precipitation and the average climate factor from June to July, the R of the spring (March-May) precipitation and the average climate factor from December to January, the R of the summer (June-August) precipitation and the average climate factor from March to April, and the R of the autumn (September-November) precipitation and the average climate factor from June to July.

[0121] 2. Select the climate factors with a confidence level exceeding 95% as prediction factors to establish a set of prediction factors for the four-season precipitation of the four regions.

[0122] III. Construction and verification of prediction model.

[0123] Specifically, the prediction equation for the autumn precipitation in the northern part of Region A is established, as shown in the above relationship (2).

[0124] Optionally, the above relationship (2) is used to calculate the autumn precipitation in the northern part of region A from 1979 to 2023, wherein 1979-2016 is the fitting value, and 2017-2023 is the prediction value of the independent sample. Using the observed value and the fitting value, the r and the root mean square error RMES of the two sequences are further calculated, the prediction model is tested, and the physical statistical prediction model for the seasonal precipitation in the middle and high latitude regions after calibration is obtained.

[0125] Optionally, the model can be used to predict the seasonal precipitation in the middle and high latitude regions.

[0126] The present example proposes a new physical statistical prediction method for seasonal precipitation in the middle and high latitude regions with low prediction skill of dynamic climate models, establishes prediction factor sets and prediction equations for different regions in different seasons, and applies them to improve the prediction results, so as to realize one-month-ahead prediction of seasonal precipitation, and make the fitted precipitation closer to the observed precipitation.

[0127] Further, taking a certain region as an example, the prediction results show that the time correlation coefficient of the prediction model established by the present method for predicting the precipitation in the northern part of region A is increased by 0.20 (40% increase) compared with the CFSv2 model, and the root mean square error is reduced by 13.3 mm (18.8% reduction) compared with the CFSv2 model, so that the demand of hydroelectric power planning can be better met.

[0128] Therefore, the physical statistical prediction method for seasonal precipitation in the middle and high latitude regions provided by the present example has the following effects:

[0129] (1) Reasonably dividing region A overcomes the problem of large spatial difference in precipitation between the north and south and between the east and west, and dividing the region into four regions facilitates statistical modeling;

[0130] (2) The prediction factor selection range is wide, covering 130 climate indices that can represent global climate anomalies in sea, land and air three-dimensional changes, which facilitates the excavation of prediction factor sets in different regions and different seasons;

[0131] (3) The physical statistical modeling is simpler and easier to understand than the dynamic climate model, and the prediction effect is improved obviously. Through comprehensive comparison, the present method has the advantages of simple operation and business application, high efficiency (accurate prediction results).

[0132] Also provided in the embodiment is a device for predicting seasonal precipitation in middle and high latitude areas, which is used to implement the above-mentioned embodiments and optional implementation manners, and details thereof have been described above. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation in hardware or a combination of software and hardware is also possible and contemplated.

[0133] The embodiment provides a device for predicting seasonal precipitation in middle and high latitude areas, as shown in FIG. 4, which comprises:

[0134] The first obtaining module 401 is configured to obtain a historical daily precipitation data set and a climate factor index set.

[0135] The division module 402 is configured to divide the area to be predicted into a plurality of sub-areas by using the historical daily precipitation data set and the climate factor index set.

[0136] The second obtaining module 403 is configured to obtain a plurality of seasonal precipitation history sequences of the plurality of sub-areas in a preset time period.

[0137] The calculation module 404 is configured to obtain a prediction factor set by using the climate factor index set and the plurality of seasonal precipitation history sequences through a first relationship.

[0138] The establishment module 405 is configured to establish a target prediction model for seasonal precipitation in middle and high latitude areas by using the prediction factor set.

[0139] The prediction module 406 is configured to predict the seasonal precipitation in middle and high latitude areas of the area to be predicted by using the target prediction model for seasonal precipitation, to obtain a prediction result of the seasonal precipitation.

[0140] In some optional implementation manners, the division module 402 comprises:

[0141] The first calculation sub-module is configured to calculate a first precipitation of each season in a preset time of the area to be predicted by using the historical daily precipitation data set.

[0142] The first obtaining sub-module is configured to obtain a plurality of climate factor indexes of the area to be predicted in a preset time period based on the climate factor index set.

[0143] The second calculation sub-module is configured to calculate a first correlation coefficient of each climate factor index and each first precipitation in the preset time period by using the first relationship.

[0144] The division sub-module is configured to divide the area to be predicted into a plurality of sub-areas based on each first correlation coefficient.

[0145] In some optional embodiments, the calculating module 404 comprises:

[0146] a third calculating sub-module, configured to calculate a plurality of second correlation coefficients based on the set of climate factor indexes and the plurality of historical sequences of seasonal precipitation amounts.

[0147] a second acquiring sub-module, configured to acquire a plurality of confidence level values of the plurality of second correlation coefficients.

[0148] a determining sub-module, configured to determine a set of prediction factors from the set of climate factor indexes based on the plurality of confidence level values.

[0149] In some optional embodiments, the establishing module 405 comprises:

[0150] a third acquiring sub-module, configured to acquire a sequence of observed seasonal precipitation amounts of the region to be predicted in a preset time period.

[0151] an establishing sub-module, configured to establish an initial prediction model of seasonal precipitation amounts in the mid-high latitude region by using the set of prediction factors.

[0152] a fourth calculating sub-module, configured to calculate a fitted sequence of seasonal precipitation amounts of the region to be predicted in the preset time period by using the initial prediction model of seasonal precipitation amounts.

[0153] a verifying sub-module, configured to verify the initial prediction model of seasonal precipitation amounts by using the sequence of observed seasonal precipitation amounts and the fitted sequence of seasonal precipitation amounts, until a target prediction model of seasonal precipitation amounts in the mid-high latitude region is obtained.

[0154] In some optional embodiments, the verifying sub-module comprises:

[0155] a first calculating unit, configured to calculate a third correlation coefficient of the sequence of observed seasonal precipitation amounts and the fitted sequence of seasonal precipitation amounts by using a first relationship.

[0156] a second calculating unit, configured to calculate a root mean square error of the sequence of observed seasonal precipitation amounts and the fitted sequence of seasonal precipitation amounts by using a second relationship.

[0157] a verifying unit, configured to verify the initial prediction model of seasonal precipitation amounts based on the third correlation coefficient and the root mean square error, until the target prediction model of seasonal precipitation amounts in the mid-high latitude region is obtained.

[0158] Further function descriptions of the above-mentioned modules and units are the same as those of the corresponding embodiments, which will not be repeated here.

[0159] The seasonal precipitation prediction device in the middle and high latitude region in the embodiment is presented in the form of functional units, and the units herein refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0160] The embodiment of the present application further provides a computer device having the seasonal precipitation prediction device in the middle and high latitude region shown in Figure 4.

[0161] Referring to Figure 5, Figure 5 is a structural schematic diagram of a computer device according to an optional embodiment of the present application. As shown in Figure 5, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively connected with each other by using different buses, and can be installed on a common mainboard or in other manners as needed. The processor can process instructions executed in the computer device, including instructions stored in the memory or graphics information of the memory to display a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or buses can be used together with multiple memories and multiple storage devices, if necessary. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). One processor 10 is taken as an example in Figure 5.

[0162] The processor 10 can be a central processor, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a generic array logic, or any combination thereof.

[0163] The memory 20 stores instructions executable by the at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0164] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required for at least one function, etc. The data storage area can store data created by the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory such as at least one disk storage device, a flash memory device, or other non-transitory solid state memory device. In some alternative embodiments, the memory 20 can optionally include memory that is remotely located with respect to the processor 10, and which can be connected to the computer device through a network. Examples of such networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communications network, and combinations thereof.

[0165] The memory 20 can include a volatile memory, such as a random access memory, and / or can include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid state memory device. The memory 20 can also include an array of multi-state flash memory cells, which can be programmed to store one or more bits per cell. For example, multi-state flash memory cells can store two or more bits per cell. In a particular embodiment, the memory 20 can include a three-state flash memory cell, which can be programmed to store one or two bits per cell. In some embodiments, the memory 20 can include a combination of storage devices, such as one or more flash memory devices combined with one or more dynamic random access memory (DRAM) devices.

[0166] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0167] The embodiments of the present application also provide a computer readable storage medium. The above-mentioned method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer code stored in a storage medium or non-transitory machine readable storage medium and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc. Alternatively, the storage medium can also include a combination of the above-mentioned storage devices. It can be understood that the computer, processor, microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code, which is accessed and executed by the computer, processor or hardware when the software or computer code is accessed and executed by the computer, processor or hardware, to implement the method shown in the above embodiments.

[0168] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be called or provided. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file and the like, and accordingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0169] Although the embodiments of the present application are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method for predicting seasonal precipitation in mid-high latitude regions, characterized by, The method comprises: obtaining a historical daily precipitation data set and a climate factor index set; dividing the region to be predicted into a plurality of sub-regions using the historical daily precipitation data set and the climate factor index set; obtaining a plurality of seasonal precipitation history sequences of the plurality of sub-regions within a preset time period; based on the climate factor index set and the plurality of seasonal precipitation history sequences, a first relationship formula is used to calculate a prediction factor set; establishing a seasonal precipitation target prediction model for middle and high latitude regions using the prediction factor set; using the seasonal precipitation target prediction model to predict the seasonal precipitation of middle and high latitude regions in the region to be predicted, and obtaining a seasonal precipitation prediction result.

2. The method of claim 1, wherein, The method comprises: using the historical daily precipitation data set to calculate a first precipitation of each season within the preset time period in the region to be predicted; based on the climate factor index set, obtaining a plurality of climate factor indexes of the region to be predicted within the preset time period; using the first relationship formula to calculate a first correlation coefficient of each climate factor index and each first precipitation within the preset time period; based on each first correlation coefficient, dividing the region to be predicted into a plurality of sub-regions.

3. The method of claim 1, wherein, The method comprises: based on the climate factor index set and the plurality of seasonal precipitation history sequences, a first relationship formula is used to calculate a plurality of second correlation coefficients; obtaining a plurality of confidence level values of the plurality of second correlation coefficients; based on the plurality of confidence level values, determining the prediction factor set from the climate factor index set.

4. The method of claim 1, wherein, The method comprises: obtaining a seasonal precipitation observation sequence of the region to be predicted within the preset time period; establishing a seasonal precipitation initial prediction model for middle and high latitude regions using the prediction factor set; using the seasonal precipitation initial prediction model to calculate a seasonal precipitation fitting sequence of the region to be predicted within the preset time period; verifying the seasonal precipitation initial prediction model using the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence until the seasonal precipitation target prediction model for middle and high latitude regions is obtained.

5. The method of claim 4, wherein, The method comprises: using the first relationship formula to calculate a third correlation coefficient of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence; using a second relationship formula to calculate a root mean square error of the seasonal precipitation observation sequence and the seasonal precipitation fitting sequence; The third correlation coefficient and the root mean square error are used to verify the seasonal precipitation initial prediction model until a seasonal precipitation target prediction model for the middle and high latitude region is obtained.

6. A seasonal precipitation prediction device for mid-to-high latitude regions, characterized in that, The device comprises: A first obtaining module is configured to obtain a historical daily precipitation data set and a climate factor index set. A division module is configured to divide a to-be-predicted region into a plurality of sub-regions based on the historical daily precipitation data set and the climate factor index set. A second obtaining module is configured to obtain a plurality of four-season precipitation historical sequences of the plurality of sub-regions in a preset time period. A calculation module is configured to obtain a prediction factor set based on the climate factor index set and the plurality of four-season precipitation historical sequences. A prediction module is configured to predict a seasonal precipitation of the middle and high latitude region of the to-be-predicted region based on the seasonal precipitation target prediction model to obtain a seasonal precipitation prediction result. The division module comprises: A first calculation submodule is configured to calculate a first precipitation of each season in a preset time period of the to-be-predicted region based on the historical daily precipitation data set.

7. The apparatus of claim 6, wherein, A first obtaining submodule is configured to obtain a plurality of climate factor indexes of the to-be-predicted region in the preset time period based on the climate factor index set. A second calculation submodule is configured to calculate a first correlation coefficient of each climate factor index and each first precipitation in the preset time period based on the first relationship. A division submodule is configured to divide the to-be-predicted region into the plurality of sub-regions based on each first correlation coefficient. The device comprises: A memory and a processor, which are communicatively connected, and the memory stores computer instructions, and the processor executes the computer instructions to perform the seasonal precipitation prediction method for the middle and high latitude region.

8. A computer device, comprising: The computer readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the seasonal precipitation prediction method for the middle and high latitude region. The computer instructions are used to make a computer execute the seasonal precipitation prediction method for the middle and high latitude region.

9. A computer-readable storage medium, characterized in that, ​ 10. A computer program product, characterised in that, ​

Images